commit 34bca063cd8e7721c876e0f06d42978d5ff4d835 Author: Kaleb S. KEITHLEY Date: Mon Nov 12 09:58:02 2012 -0500 NFS is picking up geo-rep's already open (read-only) file descriptor Add anonymous member to fd_t and use it instead of over-loading pid for geo-rep and self heal Change-Id: I4d6b29a044a8ed4b8f69ff6e3f35ee227739b2af Signed-off-by: Kaleb S. KEITHLEY BUG: 874272 Reviewed-on: http://review.gluster.org/4185 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.org/5283 commit 3521020078e822d74eed235074dc978981fb56ed Author: Pranith Kumar K Date: Thu Jun 6 11:25:07 2013 +0530 cluster/afr: detect in-progress creation in lookup and return ENOENT Port of http://review.gluster.org/4625 if any subvol returned ENOENT while parent entrylk lock was held, yield and return ENOENT for the entire lookup. This is how the issue happens: Multiple clients A, B and C are attempting 'mkdir -p /mnt/a/b/c' 1 Client A is in the middle of mkdir(/a). It has acquired lock. It has performed mkdir(/a) on one subvol, and second one is still in progress 2 Client B performs a lookup, sees directory /a on one, ENOENT on the other, succeeds lookup. 3 Client B performs lookup on /a/b on both subvols, both return ENOENT (one subvol because /a/b does not exist, another because /a itself does not exist) 4 Client B proceeds to mkdir /a/b. It obtains entrylk on inode=/a with basename=b on one subvol, but fails on other subvol as /a is yet to be created by Client A. 5 Client A finishes mkdir of /a on other subvol 6 Client C also attempts to create /a/b, lookup returns ENOENT on both subvols. 7 Client C tries to obtain entrylk on on inode=/a with basename=b, obtains on one subvol (where B had failed), and waits for B to unlock on other subvol. 8 Client B finishes mkdir() on one subvol with GFID-1 and completes transaction and unlocks 9 Client C gets the lock on the second subvol, At this stage second subvol already has /a/b created from Client B, but Client C does not check that in the middle of mkdir transaction 10 Client C attempts mkdir /a/b on both subvols. It succeeds on ONLY ONE (where Client B could not get lock because of missing parent /a dir) with GFID-2, and gets EEXIST from ONE subvol. This way we have /a/b in GFID mismatch. One subvol got GFID-1 because Client B performed transaction on only one subvol (because entrylk() could not be obtained on second subvol because of missing parent dir -- caused by premature/speculative succeeding of lookup() on /a when locks are detected). Other subvol gets GFID-2 from Client C because while it was waiting for entrylk() on both subvols, Client B was in the middle of creating mkdir() on only one subvol, and Client C does not "expect" this when it is between lock() and pre-op()/op() phase of the transaction. Change-Id: I40107d4638ffdcb7b1ff4748c8e5ea92e62697e8 BUG: 860210 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/5173 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1a7e6053d3842761f946fbbdd693c72aa3945a97 Author: shishir gowda Date: Thu May 16 19:32:49 2013 +0530 cluster/dht: Linkfiles creation with correct uid/gid If renames are done with different uid/gid (non-owners), then we would end up with incorrect uid/gid. The fix is to create linkfiles, and heal the uid/gid as root:root. This preserves our notion of creation as root:root and heal the uid/gid as root:root in all paths. Additionally, we need to consider uid/gid from only src_cached subvol, and not from linkfiles. rename is also done as root:root if done on linkfile, as setattr of ownership on linkfile is done after the rename BUG: 884597 Change-Id: Ifaacd8dba0f39cb909761ffc8fe7e06cd44ec8de Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.org/5025 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ddc0b45c4d4826e86500740f672892eeb28ab325 Author: shishir gowda Date: Thu May 16 19:25:25 2013 +0530 cluster/dht: Create linkfile with file uid/gid Currently, linkfile creation happens as root. use uid/gid returned from _cbk (link/rename) to set the correct ownership of the link files. Change-Id: I5345cff193d5095442ca446fbe5ea05f2c2d86a3 Signed-off-by: shishir gowda BUG: 884597 Reviewed-on: http://review.gluster.org/5024 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 2ee82710c088461cf4d3769625723346345566f9 Author: Raghavendra Bhat Date: Tue May 14 14:00:08 2013 +0530 libglusterfs/statedump: move options file and statedumps from /tmp Change-Id: I6b107b9a668b0521b955dba8895cbbeaf9e7cb02 BUG: 764890 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.org/5005 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c59166c5a3306231864fe7d99e383259a9385233 Author: Raghavendra Bhat Date: Tue May 14 11:59:20 2013 +0530 glusterfs: add gf_mkostemp api and use it instead of mkostemp of libc Change-Id: Ia3d2f37ae1f7a7d87a75c82bedb4963729d45b6c BUG: 764890 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.org/5004 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3490689f29342116cf78cc57bc90ad1979d9e1bb Author: Csaba Henk Date: Thu Feb 28 04:18:41 2013 +0100 geo-rep: retire old style ssh setup Users are still using geo-rep with the old, deprecated, insecure, unsupported ssh setup. Not their fault -- the implementation of the new method had the following charasteristics: - old method is possible, but with default settings it's not working - it can be made operational by fiddling with "remote-gsyncd" tunable - with default setting, an unhelpful, actually misleading error message is produced - the UI gave no hint to the changes in the ssh setup http://review.gluster.org/4392 tried to fix these; what it accomplished was unrestricted support to the bad practice (by making the default old setup operational). From this on: - we disable the old method by reserving the "remote-gsyncd" tunable - if the old method is attempted, give a hint what to do Change-Id: Icade94725d8d8d2d4c89cab992d4226351637b86 BUG: 895656 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.org/4892 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6113bfe8c9f5528f54b66d31a7bd0f1803ffe092 Author: Csaba Henk Date: Thu Jan 17 13:54:36 2013 -0500 glusterd: replace obsolete /usr/local reference for remote ssh/gsyncd See https://bugzilla.redhat.com/show_bug.cgi?id=895656 https://bugzilla.redhat.com/show_bug.cgi?id=764679 (GLUSTER-2947) https://bugzilla.redhat.com/show_bug.cgi?id=764623 (GLUSTER-2891) The comments in the bzs are a bit obtuse and/or vague. As near as I can make out we had, for a while, a "convenience symlink" to or from /usr/local/libexec/gsyncd, which no longer exists. And, lacking any comments in the code, I gather this is some sort of fallback or failsafe logic: if the first, normal attempt to invoke gsyncd fails then an attempt is made to ssh to the box and invoke it. In any event, there's nothing in /usr/local/... so it's unquestionably wrong to try to invoke anything there. [Backporting Kaleb's patch] BUG: 895656 Change-Id: I3b7ac7a049b91ce101b930599294830147cc60ad Signed-off-by: Kaleb S. KEITHLEY Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.org/4891 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 45a9d1e70e0d3e0ab504643a3cd1bf3f0a3a43fd Author: Kaushal M Date: Fri Apr 26 11:39:15 2013 +0530 distribute: Fix fds being leaked during rebalance This patch is a backport of 2 patches from master branch which fixes the leak of fds during a rebalance process. The patches are, * libglusterfs/syncop: do not hold ref on the fd in cbk (e979c0de9dde14fe18d0ad7298c6da9cc878bbab) * cluster/distribute: Remove suprious fd_unref call (5d29e598665456b2b7250fdca14de7409098877a) Change-Id: Icea1d0b32cb3670f7decc24261996bca3fe816dc BUG: 928631 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.org/4888 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 0ab16bb29a2e242714a76a3bad31921142c7dd35 Author: Varun Shastry Date: Tue Apr 16 12:11:17 2013 +0530 cluster/dht: Correct min_free_disk behaviour Problem: Files were being created in subvol which had less than min_free_disk available even in the cases where other subvols with more space were available. Solution: Changed the logic to look for subvol which has more space available. In cases where all the subvols have lesser than Min_free_disk available , the one with max space and atleast one inode is available. Known Issue: Cannot ensure that first file that is created right after min-free-value is crossed on a brick will get created in other brick because disk usage stat takes some time to update in glusterprocess. Will fix that as part of another bug. Change-Id: Icaba552db053ad8b00be0914b1f4853fb7661bd3 BUG: 874554 Signed-off-by: Raghavendra Talur Signed-off-by: Varun Shastry Reviewed-on: http://review.gluster.org/4839 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 490b791f44135db72cba1d8df9b40a66b457bff2 Author: shishir gowda Date: Wed Apr 10 10:42:25 2013 +0530 dht: improve transform/detransform of d_off (and be ext4 safe) Backporting Avati's fix http://review.gluster.org/4711 The scheme to encode brick d_off and brick id into global d_off has two approaches. Since both brick d_off and global d_off are both 64-bit wide, we need to be careful about how the brick id is encoded. Filesystems like XFS always give a d_off which fits within 32bits. So we have another 32bits (actually 31, in this scheme, as seen ahead) to encode the brick id - which is typically plenty. Filesystems like the recent EXT4 utilize the upto 63 low bits in d_off, as the d_off is calculated based on a hash function value. This leaves us no "unused" bits to encode the brick id. However both these filesystmes (EXT4 more importantly) are "tolerant" in terms of the accuracy of the value presented back in seekdir(). i.e, a seekdir(val) actually seeks to the entry which has the "closest" true offset. This "two-prong" scheme exploits this behavior - which seems to be the best middle ground amongst various approaches and has all the advantages of the old approach: - Works against XFS and EXT4, the two most common filesystems out there. (which wasn't an "advantage" of the old approach as it is borken against EXT4) - Probably works against most of the others as well. The ones which would NOT work are those which return HUGE d_offs _and_ NOT tolerant to seekdir() to "closest" true offset. - Nothing to "remember in memory" or evict "old entries". - Works fine across NFS server reboots and also NFS head failover. - Tolerant to seekdir() to arbitrary locations. Algorithm: Each d_off can be encoded in either of the two schemes. There is no requirement to encode all d_offs of a directory or a reply-set in the same scheme. The topmost bit of the 64 bits is used to specify the "type" of encoding of this particular d_off. If the topmost bit (bit-63) is 1, it indicates that the encoding scheme holds a HUGE d_off. If the topmost bit is is 0, it indicates that the "small" d_off encoding scheme is used. The goal of the "small" d_off encoding is to stay as dense as possible towards the lower bits even in the global d_off. The goal of the HUGE d_off encoding is to stay as accurate (close) as possible to the "true" d_off after a round of encoding and decoding. If DHT has N subvolumes, we need ROOF(Log2(N)) "bits" to encode the brick ID (call it "n"). SMALL d_off =========== Encoding -------- If the top n + 1 bits are free in a brick offset, then we leave the top bit as 0 and set the remaining bits based on the old formula: hi_mask = 0xffffffffffffffff hi_mask = ~(hi_mask >> (n + 1)) if ((hi_mask & d_off_brick) != 0) do_large_d_off_encoding () d_off_global = (d_off_brick * N) + brick_id Decoding -------- If the top bit in the global offset is 0, it indicates that this is the encoding formula used. So decoding such a global offset will be like the old formula: if ((d_off_global & 0x8000000000000000) != 0) do_large_d_off_decoding() d_off_brick = (d_off_global % N) brick_id = d_off_global / N HUGE d_off ========== Encoding -------- If the top n + 1 bits are NOT free in a given brick offset, then we set the top bit as 1 in the global offset. The low n bits are replaced by brick_id. low_mask = 0xffffffffffffffff << n // where n is ROOF(Log2(N)) d_off_global = (0x8000000000000000 | d_off_brick & low_mask) + brick_id if (d_off_global == 0xffffffffffffffff) discard_entry(); Decoding -------- If the top bit in the global offset is set 1, it indicates that the encoding formula used is above. So decoding would look like: hi_mask = (0xffffffffffffffff << n) low_mask = ~(hi_mask) d_off_brick = (global_d_off & hi_mask & 0x7fffffffffffffff) brick_id = global_d_off & low_mask If "losing" the low n bits in this decoding of d_off_brick looks "scary", we need to realize that till recently EXT4 used to only return what can now be expressed as (d_off_global >> 32). The extra 31 bits of hash added by EXT recently, only decreases the probability of a collision, and not eliminate it completely, anyways. In a way, the "lost" n bits are made up by decreasing the probability of collision by sharding the files into N bricks / EXT directories -- call it "hash hedging", if you will :-) Change-Id: I9551c581c3f3d4c9e719764881036d554f60c557 Thanks-to: Zach Brown BUG: 838784 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.org/4799 Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Tested-by: Gluster Build System Reviewed-on: http://review.gluster.org/4822 commit d836002fce7454fabd13f0f9a1fd247bec7e7fc0 Author: Venkatesh Somyajulu Date: Wed Apr 3 17:30:37 2013 +0530 dict: Put "goto out" in dict_unserialize to avoid process crash Problem: In the dictionary serialization function, if the [(buf + vallen) > (orig_buf + size)], then memdup is getting failed. Fix: Put "goto out" whenever this condition is met. Change-Id: Ia10ddc7e1cf551eed0e2c3d0f0364c6961e13025 BUG: 947824 Signed-off-by: Venkatesh Somyajulu Reviewed-on: http://review.gluster.org/4770 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 650708316527346ae47ff129fba55f455f2fcfb4 Author: Pranith Kumar K Date: Mon Mar 18 17:00:23 2013 +0530 cluster/afr: Try for all locks before failing in rename Change-Id: If0e917e5d4914f6807b4a96f81668a467b15d0df BUG: 922809 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/4689 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 26ab9cfeca978cc5459d1638fb1628051143eab9 Author: Pranith Kumar K Date: Fri Mar 8 15:20:22 2013 +0530 cluster/afr: Preserve mtime in self-heal Problem: Data self-heal may choose sink iatt to set mtimes. This happens because after syncing of data is done self-heal does one more xattrops/fstat to determine sources sinks to set the inode-ctx. Since this is done after data syncing and erase of xattrs, old source and old sink are now sources, but the mtimes of them differ. Old code just takes the first source from the list and update mtimes, which could be sink before the self-heal started. Fix: Set mtime from 'sources before syncing'. Change-Id: Id769e1b99aa4f041eaee775f64cbf2c57b799723 BUG: 918437 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/4658 Reviewed-by: Jeff Darcy Tested-by: Gluster Build System Reviewed-on: http://review.gluster.org/4664 Reviewed-by: Vijay Bellur commit f42426512700fc2ff508a889eb5ffe97bd9b9002 Author: Joe Julian Date: Tue Mar 12 15:33:27 2013 -0700 Fix spelling error "temporary" was misspelled s/tempaory/temporary/ BUG: 818884 Change-Id: If033acd4d8d778bde7588d8b4b512d6508e36f22 Signed-off-by: Joe Julian Reviewed-on: http://review.gluster.org/4661 Reviewed-by: Jeff Darcy Tested-by: Anand Avati commit 2c99e868b9f5e77f1c2b441bf548f0ba85faef77 Author: Niels de Vos Date: Mon Mar 4 11:44:40 2013 +0100 rpm: package /var/run/gluster so that statedumps can be created Creating statedumps fail when /var/run/gluster does not exist. This directory should be part of the 'glusterfs' package that is installed on storage servers and native clients. BUG: 917554 Change-Id: I2f6d8dc46f338b33042478d19ed9f00c2c03658c Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/4615 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Shishir Gowda Reviewed-by: Anand Avati commit 23fad84fa8e68db05b8b0bb23fe2baa3dd494e08 Author: Vijay Bellur Date: Mon Feb 18 10:08:05 2013 +0530 libglusterfs: Fix memory leaks in fd_lk_insert_and_merge Change-Id: Id322717b79c5252172811fea259f2073f710a463 BUG: 834465 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.org/4530 Reviewed-by: Anand Avati Tested-by: Anand Avati commit 988460a9f597a489f22d39cd259fdb17fe2e5de6 Author: Kaleb S. KEITHLEY Date: Fri Jun 22 11:25:32 2012 -0400 localtime and ctime are not MT-SAFE There are a number of nit-level issues throughout the source with the use of localtime and ctime. While they apparently aren't causing too many problems, apart from the one in bz 828058, they ought to be fixed. Among the "real" problems that are fixed in this patch: 1) general localtime and ctime not MT-SAFE. There's a non-zero chance that another thread calling localtime (or ctime) will over-write the static data about to be used in another thread 2) localtime(& <64-bit-type>) or ctime(& <64-bit-type>) generally not a problem on 64-bit or little-endian 32-bit. But even though we probably have zero users on big-ending 32-bit platforms, it's still incorrect. 3) multiple nested calls passed as params. Last one wins, i.e. over- writes result of prior calls. 4) Inconsistent error handling. Most of these calls are for logging, tracing, or dumping. I submit that if an error somehow occurs in the call to localtime or ctime, the log/trace/dump still should still occur. 5) Appliances should all have their clocks set to UTC, and all log entries, traces, and dumps should use GMT. 6) fix strtok(), change to strtok_r() Other things this patch fixes/changes (that aren't bugs per se): 1) Change "%Y-%m-%d %H:%M:%S" and similar to their equivalent shorthand, e.g. "%F %T" 2) change sizeof(timestr) to sizeof timestr. sizeof is an operator, not a function. You don't use i +(32), why use sizeof(). (And yes, you do use parens with sizeof().) 3) change 'char timestr[256]' to 'char timestr[32]' where appropriate. Per-thread stack is limited. Time strings are never longer than ~20 characters, so why waste 220+ bytes on the stack? Things this patch doesn't fix: 1) hodgepodge of %Y-%m-%d %H:%M:%S versus %Y/%m/%d-%H%M%S and other variations. It's not clear to me whether this ever matters, not to mention 3rd party log filtering tools may already rely on a particular format. Still it would be nice to have a single manifest constant and have every call to localtime/strftime consistently use the same format. BUG: 832173 Change-Id: Iee9719db4576eacc6c75694d9107954d0912cba8 Signed-off-by: Kaleb S. KEITHLEY Reviewed-on: http://review.gluster.org/3613 Reviewed-by: Anand Avati Tested-by: Anand Avati commit 32fff8967f10efa391815c06093086a9ee276762 Author: Raghavendra G Date: Mon Jan 21 10:54:05 2013 +0530 performance/quick-read: fix race condition in unlink use same lock (inode->lock), while incrementing/decrementing local->open_count. Change-Id: I08cbab5b5dec09b6057f43324fe3152f1564ce46 BUG: 902174 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.org/4396 Reviewed-by: Anand Avati Tested-by: Anand Avati commit 1206f652a08e7d3cb679b565ab73b3eebe28d247 Author: Kaleb S. KEITHLEY Date: Fri Aug 24 09:09:48 2012 -0400 dual license rebase BUG: 820551 Change-Id: Iec1073ee3ed2d9cab25c0882544a18e8ba23c9aa Signed-off-by: Kaleb S. KEITHLEY Reviewed-on: http://review.gluster.org/3857 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 39b1073424aa230b4c814685628c6cc19dfcca83 Author: Niels de Vos Date: Mon Sep 3 12:42:24 2012 +0200 doc: Add the "enable-ino32" native-client mount-option Change-Id: I9568a39c3e3497f94c098cdac0331d0a25122e35 BUG: 850352 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3887 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit fbb9ad5030abf058ce75af1890b7ec1be77d22f9 Author: Niels de Vos Date: Mon Sep 3 13:34:22 2012 +0200 mount/fuse: add mount-option "enable-ino32" for the native client By default the GlusterFS-native client uses 64-bit inodes. Some 32-bit applications can not handle these correctly. Introduce a client-side mount option "enable-ino32" which causes the FUSE-client to squash the 64-bit inodes into a 32-bit value. Change-Id: I7544010a27b7eb2d3b9fadb84ed934e4e7dff21e BUG: 850352 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3886 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 0f4bd1706f9243a0ae3569c47889ba7a784be23a Author: Raghavendra G Date: Wed Jan 16 12:09:05 2013 +0530 rpc-transport/rdma: use 24008 as default listen port. BUG: 849122 Change-Id: Ie76b105096f038b98434952a4eb352984595cecd Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.org/4384 Reviewed-by: Niels de Vos Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 47b2bc274a0f00520b4b930da9034a76903b66b1 Author: Varun Shastry Date: Fri Dec 21 17:25:54 2012 +0530 system/posix-acl: prevent NULL pointer dereference of group_ce Thanks Amar Tumballi. Change-Id: I3ac9b46d4c3fcd12d1eec779317a03c47d267556 BUG: 887098 Signed-off-by: Varun Shastry Reviewed-on: http://review.gluster.org/4395 Reviewed-by: Anand Avati Tested-by: Anand Avati commit 0f433ca0b8fa797466aeb012eb2981341c21def9 Author: xarlos Date: Fri Jan 11 16:34:09 2013 +0000 man: fixed typo in "volume statedump" entry of manpage Patch to simply correct a spelling mistake as reported under: "894355 - spelling mistake?" Change-Id: I2a93b3fc34a8e39e6fe775f3747d91c6fb489f43 Signed-off-by: xarlos Reviewed-on: http://review.gluster.org/4379 Reviewed-by: Jeff Darcy Tested-by: Vijay Bellur commit b34235bfee175be1dcaad8056239e69f76ae3e95 Author: Rajesh Amaravathi Date: Thu Nov 15 12:04:34 2012 +0530 protocol/client: Remember the gfid of opened fd This is needed when the fresh lookup triggers self-heal, gfid won't be present in inode yet. Similar situation happens with Rebalance as it does not perform inode_link. Added similar fix for re-opendir. Removed inode from fdctx and removed some duplication of code. BUG: 826080 Change-Id: I5840b86bf70ef73d40ae899b34a210b2dbcbf91f Signed-off-by: Pranith Kumar K Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.org/4192 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 775626f44f30e38cccd5efcd959b61f4f0f61969 Author: Pranith Kumar K Date: Thu Nov 1 17:19:04 2012 +0530 cluster/afr: Filter O_TRUNC in afr-fix-open RCA: When open was done while a brick is down, afr opens the file after the brick comes backup. If this happens after the self-heal on the file is completed by self-heald etc, the file will end up in truncated state. Fix: Filter O_TRUNC while afr-fix-open because afr_open turns O_TRUNC into truncate transaction, so there will be pending changelog for the subvolume on which open fails. Testing: Had to simulate the race by stopping fix-open until self-heald completes self-heal on the file after brick online. Change-Id: If99eb3eb272dea0ed8c7b754dce675eb6efaf802 BUG: 841840 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/4147 Reviewed-by: Jeff Darcy Tested-by: Gluster Build System commit 251a0056e35ea5d4c1ef4d5eede15e67c7428469 Author: Emmanuel Dreyfus Date: Tue Aug 21 10:55:37 2012 +0200 glusterd-volgen: by default include 'cluster/distribute' in volfile This is a backport of Ie9d559e6b26aafd3d67908ab20a006e4e5e70d73 We need it in order to avoid spurious EINVAL when scaling from 1 brick to more in distributed volumes. BUG: 815227 Change-Id: I9858af03bf6d7724ff997f341faca62e89aecfb0 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/3838 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c2475b94ea0403efff117c70bf6eb70afd31ed3c Author: Niels de Vos Date: Tue Jul 10 16:47:07 2012 +0200 extras: add clear_xattrs.sh to the glusterfs-server sub-package Change-Id: Iba695a6d19389fbc1776da5e939d67318916aadf BUG: 812214 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3900 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 06f60ff9a274d455c6b4fa1125e704ef2b7c6a85 Author: Niels de Vos Date: Mon Jul 16 18:11:17 2012 +0200 build: Create directories and files that get created during runtime This should not be needed for files marged as "ghost", but rpm-4.9 is broken in this respect :-( Building the packages works again: $ make dist $ rpmbuild -ta glusterfs-3git.tar.gz The now created files and directories are not packaged in the RPM, but are marked as belonging to the packages. Here a example for glusterfs-geo-replication: $ rpm -qlp glusterfs-geo-replication-3git-1.fc17.x86_64.rpm \ | grep /var/lib /var/lib/glusterd/geo-replication /var/lib/glusterd/geo-replication/gsyncd.conf $ rpm2cpio < glusterfs-geo-replication-3git-1.fc17.x86_64.rpm \ | cpio -t --quiet '/var/lib/*' $ Change-Id: I32019cfbf40e25d9b7ce875fa92b98bae19dabee BUG: 839668 See-also: https://bugzilla.redhat.com/show_bug.cgi?id=839656 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3899 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 505470cbadc9ffe0eae8642242d02566cf8f44aa Author: Niels de Vos Date: Fri Jun 8 11:59:31 2012 +0200 Mark /var/lib/glusterd as owned by glusterfs, subdirs belong to -server Change-Id: Ib1df8da7e8abdcd3edece45bd39fe238f28838f1 BUG: 829734 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3898 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit d40c345aac5adc3ec429858240953569b0434052 Author: Niels de Vos Date: Thu Jul 12 12:39:33 2012 +0200 extras: install clear_xattrs.sh The script was not installed by default, this breaks building the RPM packages since Change-Id Iba695a6d19389fbc1776da5e939d67318916aadf. Change-Id: I4fb982cb5217dc7b3ec3c7a664dd3997a2e05170 BUG: 812214 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.org/3897 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 53d376d94304e045d81f6b9a8fb6eec68ee557c6 Author: Varun Shastry Date: Thu Oct 11 12:54:15 2012 +0530 glusterfs man page edit Updated man page, * Added some of the options which were not there before. * Updated the default dirs. Change-Id: Ide4db3b7858de86c8bf0f8d773f90b8dd1ef0d87 BUG: 825906 Signed-off-by: Varun Shastry Reviewed-on: http://review.gluster.org/4061 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e1e5326c22b6b64784a7562ce7ef462841f39609 Author: Raghavendra Bhat Date: Wed Oct 10 15:18:06 2012 +0530 storage/posix: return -1 if lstat call returns non zero value apart from -1 * If lstat() call in posix_{pstat, istat} returns non zero return value other than -1, then treat lstat() call to have been failed and return -1 itself. This might happen if there is some bug in the backend filesystem. Change-Id: Ie23787f6c838f14f92edadad71b83471e3d22289 BUG: 864401 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.org/4054 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e7f14ad073956b08b37d7b102afab57a08dfabac Author: Vijay Bellur Date: Thu Oct 11 22:31:13 2012 +0530 build: Add glusterd man page packaging in buildspec Change-Id: Id412a2738b80516bbfc0a9ad7862a45821703c3e BUG: 825906 Reviewed-on: http://review.gluster.org/4064 Tested-by: Gluster Build System Reviewed-by: Sachidananda Urs commit 3e9777a35b481a2c9218c286ced045579b64a731 Author: Kaushal M Date: Tue Sep 25 20:31:12 2012 +0530 doc: Update man page for 'gluster' command. Change-Id: Idb749a4bdde0a07e6919e8007302070fcd6cc67a BUG: 825906 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.org/3977 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit fe3fbdec4250f20a5d8d0e2fccf5c8396c85ed60 Author: Varun Shastry Date: Tue Sep 25 20:25:08 2012 +0530 Fixed some general typing errors. Eg: changed recieved to received Change-Id: I360fcb99c97c8a0222e373fee20ea2fccfb938db BUG: 860543 Signed-off-by: Varun Shastry Reviewed-on: http://review.gluster.org/3999 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 517a9d2450c4de6229d2b699a2ffd9102c3488c9 Author: Kaleb S. KEITHLEY Date: Thu Sep 13 16:21:07 2012 -0400 glusterfs SEGV on Fedora 17 from UFO fallocate(2) call An upload of a file will cause the volume's glusterfs to SEGV when it fields a FUSE_FALLOCATE op. Swift inspects libc to determine if there is a symbol for fallocate(2) and if so will use it. And while the libc in RHEL 6 does have fallocate(2), the version of fuse in RHEL 6 does not support fallocate, and things are handled gracefully elsewhere (the kernel perhaps?) N.B. fallocate was added to version 7.19 of fuse. Fedora 17 and later (and maybe earlier too) has 7.19. RHEL 6 still has 7.13. Glusterfs uses the 7.13 version (in contrib/fuse-include/fuse_kernel.h) Thus on Fedora 17, with both fallocate(2) in libc and fallocate support in fuse, the fallocate invocation is dispatched to glusterfs, but the dispatch table (fuse_std_ops in xlators/mount/fuse/src/fuse-bridge.c) is too short for one thing; the fallocate opcode (43) indexes beyond the end of the table, and even when that doesn't directly cause a SEGV, the NULL pointer at that location does cause a SEGV when attempting to call the function through the pointer. BUG: 856704 Change-Id: Iffe3994dde6ca29444d07d27eb04d6f86773fa03 Signed-off-by: Kaleb S. KEITHLEY Reviewed-on: http://review.gluster.org/3941 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Anand Avati commit 314dd4da976cd329417b43c3ad281fd9990fdcd7 Author: Kaushal M Date: Wed Aug 22 16:53:04 2012 +0530 mount.glusterfs: Add support for {attribute,entry}-timeout options Change-Id: Ib0c9b5be6f05cf9a36271df67e5e5c251c4c4628 BUG: 829279 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.org/3840 Tested-by: Gluster Build System Reviewed-by: Brian Foster Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 948b9a5aa1dccdd0cf00e95e24409ff3dbe25139 Author: Kaushal M Date: Mon Jun 4 10:13:19 2012 +0530 glusterd: nfs.disable fix for "volume set help" Fixes volgen to include "nfs.disable" in output of "volume set help". Change-Id: Idaac2cee04b7b38aad5a77db558808c0eb699fcf BUG: 828027 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.org/3881 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 21ed135a5ab503ba31048a983038d354c0f7a1b2 Author: Krishnan Parthasarathi Date: Thu Sep 13 12:33:31 2012 +0530 cli: Fix double free in cli_add_key_group Change-Id: I3c2f030ac7c53913612a3fbac5e582c47b005621 BUG: 851237 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3944 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2635c4a68d82be731461bb3c31188e5dd0093e7d Author: Krishnan Parthasarathi Date: Sun Sep 2 15:22:34 2012 +0530 storage/posix: Option to set brick(of a volume)'s root dir's uid/gid CLI --- gluster volume set VOLNAME owner-uid uid gluster volume set VOLNAME owner-gid gid where uid,gid are the owner's user id and group id respectively that would be set on the root of all brick (backend) fs. TODO: uid/gid should not be -1. Today we don't validate that in CLI. Change-Id: Ib6a2fb5e404691c5fe105a89faaeff3e1ab72e91 BUG: 853842 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3939 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 80ef34fea4a8850b6f34dc59dcdfaef989d7b9e5 Author: Emmanuel Dreyfus Date: Mon Sep 10 16:07:13 2012 +0200 mount.glusterfs NerBSD portability fix NetBSD stat(1) gets inode using -f %i while Linux uses -c %i This has already been fixed a few lines above, but one test failed to be fixed. This is not based on master, as the code hasbeen reworked a lot, and is already bug-free. BUG: 764655 Change-Id: I5dc1196ddba06ff31f695b7dbb0c6d28df32f324 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/3926 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 700ed44e73fee15d678654830c4cb019ffaeb4af Author: Krishnan Parthasarathi Date: Mon Aug 20 21:34:26 2012 +0530 cli: Added special key "group" for bulk volume set. gluster volume set VOLNAME group group_name - where group_name is a file under /var/lib/glusterd/groups containing one key, value pair per line as below, key1=value1 key2=value2 [...] - the command sets key1 to value1 and so on. Change-Id: Ic4c8dedb98d013b29a74e57f8ee7c1d3573137d2 BUG: 851237 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3896 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b130bcb8c664b7f03fc64414717058b37b039959 Author: Emmanuel Dreyfus Date: Mon Sep 10 03:13:29 2012 +0200 Detect python > 2.5, make sure MKDIR_P is substituted gluster build machine generate configure scripts unable to detect python > 2.5 This change include a more recent python.m4 so that newer python can be correctly detected. Build.gluster.com also produces a configure that fails to subsitute MKDIR_P, leading to bugs at make install. Works this around by introducing mkdirp.m4 from aclocal-1.11, with the autoconf version test removed because build.gluster.com also has an outdated autoconf. And we need a bit from a recent autoconf This is a backport of I3ffac50cc7a10cb9e56dd490dbc2b550bba3fabd BUG: 764655 Change-Id: I5ceeed957f30af4504701d789931f407b501eeb6 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/3923 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 17ddf18ae17679117cee2033b010a72975525ef6 Author: Emmanuel Dreyfus Date: Thu Sep 6 03:11:12 2012 +0200 Honour configure --localstatedir and --sysconfdir Makes sure /etc/glusterd to /var/lib/glusterd migration does nonour configure --localstatedir and --sysconfdir. Backport of I65a5f96424d67531e81e75b084265bd4e6e30f29 BUG: 764655 Change-Id: I71e0d3b7f0d27b490b591dcc92ddfe26fb8e818d Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/3911 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 87e88243e827d7c1dc5b5138ac966b41002564e4 Author: Emmanuel Dreyfus Date: Fri Aug 31 03:23:33 2012 +0200 Add missing contrib/libgen files to distribution This is a backport of I3f49eb4a1a186cb2d178539ada6a05c8c1aa8265 BUG: 764655 Change-Id: I32264acec0f122d045f369a254df17b488962b9f Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.org/3884 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Anand Avati commit 0b60e7252650355f412974bfc840bc2fc81b4157 Author: Krishnan Parthasarathi Date: Sat Sep 8 12:12:48 2012 +0530 glusterd: Expect setmntent(3) to return NULL - Closed the mtab FILE * using endmntent(3) Change-Id: I5e1ebb7f092abda638cfbb5524da693dcac6c872 BUG: 851109 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3922 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit ace4cae71c19004c51fe5116c67492acaf2afc73 Author: Kaushal M Date: Wed Aug 29 18:32:29 2012 +0530 cli: Proper xml output for "gluster peer status" Change-Id: I90952ba2ea606552cf4ad67dd296a440f90592d6 BUG: 847760 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.org/3870 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 50cb2c23e8e7bd1173572a21990dbdf545f09141 Author: Krishnan Parthasarathi Date: Tue Aug 28 17:29:53 2012 +0530 glusterd: Fixed incorrect assumptions in rpcsvc actors of glusterd Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3864 Tested-by: Gluster Build System Reviewed-by: Anand Avati Conflicts: xlators/mgmt/glusterd/src/glusterd-handler.c Change-Id: Iabfcb401de9d658e32433aa1e8c87b329cbd2cf7 BUG: 851109 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3876 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 84298d77060772b91123d9cde9f0e6e4d9efc9ca Author: Krishnan Parthasarathi Date: Tue Aug 28 13:12:31 2012 +0530 glusterfsd: rpcsvc actors must return success after an attempt to submit reply rpcsvc attempts to send "error reply" using the req object. If actor has already performed rpcsvc_submit_generic, then req is destroyed. So if the actor returned -1 (RPCSVC_ACTOR_ERROR) on failing to submit reply, then req would be 'free'd' twice and will result in a crash eventually. Change-Id: I5eae19570202bbe5e154e9cb03390cfeb9b5f223 BUG: 851410 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.org/3863 Tested-by: Gluster Build System Reviewed-by: Anand Avati Reviewed-on: http://review.gluster.org/3875 Reviewed-by: Vijay Bellur commit e908ee20e8a87ba1170f228dd4dd5993f36a0da6 Author: Pranith Kumar K Date: Mon Jun 4 23:23:45 2012 +0530 Self-heald: Fix inode leak RCA: There is an inode-leak because inode_link returns linked inode by taking a reference. That needs to be unreffed. Fix: Added the code to perform unrefs. In addition to that updated the loc inode with the linked-inode because that is the best practice. The code to update the input inode's gfid can be removed later, its already removed in master. Tests: Checked that opendir comes with an loc with valid inode Checked that re-opendir happens successfully. Tested index, full self-heal work fine with the fix. BUG: 826580 Change-Id: I0c68192ff98f76152ed112b393d497b8fee93355 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/3518 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit f382d5c5656301d9b426dc50a95e8c54db42c90e Author: shishir gowda Date: Tue Aug 28 14:45:47 2012 +0530 dht/rebalance: set the correct ownership on the dst file. Currently, the dst file created has root:root ownership, till migration is completed. During this phase, open fails on the dst file if uid/gid is non-root. Setting the dst_file to the correct ownership fixes the issue Change-Id: Icfec89eb10dc866cdee38dab17695fe21174ef99 BUG: 852361 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.org/3862 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 10617e6cbc73329f259b471327d88375352042b0 Author: shishir gowda Date: Thu Aug 23 18:34:09 2012 +0530 storage/posix: implement native linux AIO support Configurable via cli with "storage.linux-aio" settable option Backported Avati's patch http://review.gluster.org/#change,3627 BUG: 837495 Change-Id: Ia7c26f5734d34d341debd422a5c59bba31eef844 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.org/3849 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit d0c52c8064a4097d97180240b36c53bfe98cac22 Author: Varun Shastry Date: Mon Aug 13 15:50:45 2012 +0530 cli/: Displaying the size in human readable format rebalance status displaying the size in bytes. Converted to human readable Change-Id: Id73b6e792c39b85480ddf1dc9c0c22fcaca29530 BUG: 825193 Signed-off-by: Varun Shastry Reviewed-on: http://review.gluster.org/3810 Tested-by: Gluster Build System Reviewed-by: Kaushal M commit 753f8c13245220c4b9ec6364a5e644274a36b1d6 Author: Krishnan Parthasarathi Date: Fri Aug 17 14:19:39 2012 +0530 afr: Avoid excessive logging in self-heal. - (Excessive) Logging has been very useful as 'bread-crumbs' in many a root-cause analyses. This patch aims at avoiding logging when the information could be reconstructed using the xattrs, statedump, and/or "volume heal" CLI commands. Change-Id: I8f646cbee44e98495ea6963f9dfcae95375c8900 BUG: 844804 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3827 Reviewed-by: Pranith Kumar Karampuri Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1df75bc835a75f17fa0fcd3722ef68f05f5f3200 Author: Pranith Kumar K Date: Mon Jul 30 21:01:21 2012 +0530 cluster/afr: Handle child_up & fd not opened case in xaction RCA: When an fd is opened while a brick is down, after the brick comes back up afr issues open on the other brick. It can fail for a number of reasons (enoent etc). While the system is in that state, inode/entrylks pre-op happen only on the brick that is up and fd is opened for fd-fops. post-op should consider only the bricks where both pre-op and fop succeeded as success, rest of them as failures. Code now marks only the children that are down as failures as opposed to child_down & fd-not-opened. This makes change-log appear as success on the subvolume where we did not do any fop leading to no change-log but differences in data/metadata for reg-files. Fix: Mark non-participants of fop as failure. This is tracked in transaction.pre_op[]. Tests: Simulated the scenario using err-gen on top of one of the client xlator which fails all fops always. Performed fops and the changelog represented pending fops on the brick with err-gen loaded. Tested the case of brick down and perform entry/metadata/data operations to confirm they still work as expected. Change-Id: I41905936126b19abba56ca581c0301a894507e1a BUG: 844987 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3776 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 30a9ebd91339f36d092f46bbba116fa4047fb8c5 Author: Kaushal M Date: Fri Aug 17 13:12:33 2012 +0530 rpc: Reduce frame-timeout for glusterd connections Reduce frame-timeout for glusterd connections from 30mins to 10 mins. 30mins is too long when compared to cli timeout of 2mins. Changing to 10mins reduces the disparity between cli and glusterd. Also, fix glusterfs_submit_reply() so that a reply is sent even if serialize failed. BUG: 843003 Change-Id: Ie8d5ec16fbbb54318a5935a47065e66fd3338b87 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3812 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b96e499e9e290547a655072fede969f51854e2d8 Author: Amar Tumballi Date: Sat Jul 14 08:25:56 2012 +0530 core: check for pre-allocated blocks in backend fs, fix it. There is a possibility that the backend FS (like XFS) can allocate blocks beyond EOF for better performance reasons, which results in 'st_blocks' with higher values than what is consumed by the file descriptor. This would break few logic inside GlusterFS, like quota behavior etc, thus we need the exact number of blocks which are consumed by the file to the higher layers inside GlusterFS. Currently, this logic won't work for sparse files (ie, file with holes) Change-Id: Ied216733a8862e84f7da8386ae0a144f3f5cd5f2 BUG: 839589 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/3671 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 502c95bdfb35640fb424b37b080664e9c1639a86 Author: shishir gowda Date: Mon Aug 13 11:20:17 2012 +0530 cluster/dht: Optimize readdirp calls in DHT Bring in option which is supported by posix xlator to filter out directory's entries from being returned. DHT would now request non-first subvols to filter out directory entries. dht xlator-option readdir-optimize will enable this optimization Change-Id: Ibf99f1bef501f285ff44a1cecfbebee9e16063b6 BUG: 838199 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3806 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 28328417bff73b13392e95a07c3d359c881bebc8 Author: Raghavendra Bhat Date: Thu Aug 9 17:47:34 2012 +0530 performance/io-cache: use pthread_mutex_trylock to hold mutex in statedumps Do not use pthread_mutex_lock and gf_log functions while dumping information to statedump, to avoid deadlocks. Change-Id: I6569366856fc2bc0fefb49c8379e2e4337717ce4 BUG: 843787 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3799 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit cb7647f67390920fa2aa25fd0af7c84787c08ed0 Author: Raghavendra Bhat Date: Mon Aug 13 19:16:43 2012 +0530 performance/write-behind: use pthread_mutex_trylock to hold mutex in statedumps Change-Id: I24c83b1b5e83ef3e38a019043c7fbca13b19ff43 BUG: 841543 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3815 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 41d3605fab2f0ce8c8b4c5d976fc1a013c823e3d Author: Shylesh Kumar Date: Mon Aug 13 12:10:38 2012 +0530 cluster/stripe: Filter coalesce xattr from getfattr Change-Id: I1c5740e29699ef464a3d30365396711f03c24974 Signed-off-by: Shylesh Kumar BUG: 801887 Reviewed-on: http://review.gluster.com/3809 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 3e5e736043cdb0f48ce617d71c974912a96acef0 Author: Emmanuel Dreyfus Date: Mon Aug 13 15:00:45 2012 +0200 NetBSD swapcontext() portability fix This is a backport of http://review.gluster.com/#change,3794 Patchset 8d47741d5a041e632d9c74c5936fcfaf6ceaaa78 This has been tested on release-3.3 for a few days. BUG: 764655 Change-Id: I75d990649e9cdfbd7dd327ed1071f6ab7ab49f4a Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3813 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 12aa31278c651f36c2ea1c0698ba789aa3f9262c Author: Pranith Kumar K Date: Wed Jul 18 10:28:18 2012 +0530 cluster/afr: Avoid setting split-brain outside inode locks RCA: The bug is observed because the decision to mark a file in split-brain is taken outside appropriate locks. Lookup gathers xattrs outside any lock. The xattrs being in split-brain in lookup should only be taken as a hint. Appropriate inodelks should be taken before confirming a split-brain. Self-heal confirms this at the moment. Fix: Self-heals are launched to inspect xattrs when the data/metadata self-heal options are turned on. Decision to set/reset split-brain flag is taken inside appropriate locks. Known Issue After fix: If data/metadata self-heal is turned off, inspecting of xattrs could not be performed so split-brain behavior does not work correctly if the self-heal options are turned off. This bug is handled only in upstream. Change-Id: I59a43d5ce7bf9ca35bff54a51bf4cfa55d717a9e BUG: 833727 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3691 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit aa4e7d04ff20e38182a62576595951d59524fff0 Author: Pranith Kumar K Date: Sat Jul 28 12:18:50 2012 +0530 features/locks: Fix statedump code RCA: Taking blocking mutex/spin locks lead to dead locks because of the locking order in statedumps. Also we were asked to remove gf_logs if possible to avoid extra cost in signal handlers. Fix: changed blocking mutes/spin locks to their non-blocking variants. Removed gf_logs in locks xlator statedump code-path. Tests: State-dump success cases are working fine. Triggered try-lock failures by putting statedumps in a while loop. In parallel did chown of the same file in a while loop. BUG: 843781 Change-Id: Iac9b75d79cd5e036cd3eafc1e106074e2c6b5c47 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3752 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d40d5a3a32a515ff29c71467a0f701e91ae99718 Author: Pranith Kumar K Date: Fri Jul 27 10:51:50 2012 +0530 performance/io-threads: Provide option to turn off least-priority RCA: In cases when self-heal is in progress, self-heal fops are starved because of least-priority. This affects other fops with conflicting inode, entry locks with self-heal. Fix: This patch provides configuring enable/disable of least-priority. Additional changes: Moved RCHECKSUM fop to low instead of least because it will still affect the performance of other fops if RCHECKSUM is in LEAST priority. Tests: Tested that the enabling/disabling of fops is working fine. Tested that RCHECKSUM fop priority is assigned LOW when least-priority is disabled. BUG: 843704 Signed-off-by: Pranith Kumar K Change-Id: I892f99d6d0a3e0ae6c0a280f82e2203af0c346f6 Reviewed-on: http://review.gluster.com/3751 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e427d39d629b8f89c25ac7f7a9d1eeca25b9579a Author: Raghavendra Bhat Date: Thu Aug 9 18:25:31 2012 +0530 performance/read-ahead: use pthread_mutex_trylock to hold mutex in statedumps Change-Id: I4de64915a9c6a46e126ef4a5b987e49de558f827 BUG: 843796 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3801 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 92d722fdbeb3ce7316d8bf3a40ae2ac27e06b806 Author: Raghavendra Bhat Date: Thu Aug 9 18:19:09 2012 +0530 performance/quick-read: use pthread_mutex_trylock to hold mutex in statedumps Do not use pthread_mutex_lock and gf_log functions while dumping information to statedump, to avoid deadlocks. Change-Id: Ic77d96bc52f2a2a32629c0ae20bba797317e0a81 BUG: 843789 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3800 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c79690c4cb503a6e6b52998038fd85cdfcf0f7be Author: Raghavendra Bhat Date: Thu Aug 9 18:33:37 2012 +0530 protocol/server: use pthread_mutex_trylock while dumping statedumps Change-Id: I2b04dc35a51d940915197cf8e26e638f32fa4d7b BUG: 843821 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3802 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a1d071374365a10ebef508c38c39f61da0a0f855 Author: Amar Tumballi Date: Thu Jul 26 17:16:00 2012 +0530 acl: enable handling of FMODE_EXEC flag on linux systems, with open(), we can get below flag as per 'linux/fs.h'. /* File is opened for execution with sys_execve / sys_uselib */ '#define FMODE_EXEC ((fmode_t)0x20)' Instead of adding '#include , its better to copy this absolute number into other variable because then we have to deal with declaring fmode_t etc etc.. With the fix, we can handle the file with '0711' permissions in the same way as backend linux filesystems. Change-Id: Ib1097fc0d2502af89c92d561eb4123cba15713f5 Signed-off-by: Amar Tumballi BUG: 843960 Reviewed-on: http://review.gluster.com/3746 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 475efecfba7194c598a94879852bcd37ac2deb5d Author: Brian Foster Date: Wed Jul 25 08:14:38 2012 -0400 cluster: fix crash on link of named pipe in stripe/replicate vol A crash occurs when attempting to link a named pipe on a striped, replicated volume. The cause for this crash is attempting to deref a NULL inode pointer in stripe_link_cbk(). The RCA for this bug uncovered a couple of problems: - AFR ignores the inode pointer it receives on failure (returning NULL). - stripe assumes the inode pointer is valid on failure. Either one of these changes addresses the crash, but this patch includes both changes. AFR is modified to pass along the inode pointer it receives (which could still be NULL). stripe is modified to not assume the inode pointer is valid on fop failure. BUG: 842825 Change-Id: I368849b7cfbb137a08ae5f89d26406814ff5bb09 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3790 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e741983b740a26634b8d371521da2f668ec8e584 Author: Brian Foster Date: Wed Aug 8 07:44:43 2012 -0400 cluster/stripe: don't fail if no fctx on a non-regular file cluster/stripe broke directory rename. Only check for fctx on regular files. BUG: 842652 Change-Id: I29d7b265cbe40921226feb3e1c4e6b97b3a01d95 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3789 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0c1cee625818275dd1b3f6718bd246d2e30dabd1 Author: Kaleb S. KEITHLEY Date: Tue Jul 10 10:19:16 2012 -0400 calls to dict_allocate_and_serialize() are not 64-bit clean All calls to dict_allocate_and_serialize() pass the address of a 32-bit type, but must cast it to the 64-bit pointer type (size_t *). This happens to work on LE machines, but even if it's apparently benign, it's still a bug. On BE machines it is not benign. GF_PROTOCOL_DICT_SERIALIZE() hacks around it by creating a size_t temp var, but that's, well, a hack, IMO when you consider that all the callers are actually passing &; the param should just be a u_int * and eliminate the buggy casts and the temp var in the macro. Nobody apparently uses the Fedora/EPEL PPC RPMs, but they might. People are trying to build gluster.org bits on SPARC and tripping over this. Change-Id: I92ea139f9e3e91ddbbb32a51b96fa582a9515626 Signed-off-by: Kaleb S. KEITHLEY BUG: 838928 Reviewed-on: http://review.gluster.com/3643 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f1a0ec826be94f2d0413dd819fd7033c437843f9 Author: Anand Avati Date: Mon Jun 25 19:37:09 2012 -0700 nfs: make NFS filehandles deterministic The NFS3 file handles now includes just the bare minimum of (ident, exportid, gfid) and removes legacy 'variable' members which are unnecessary since the introduction of GFID backend Change-Id: Iff6e4435d170074b18d208742b48e79b130e2a4d BUG: 835336 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3617 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d451dfeb4643b1894e99dc66454f630d26c459a1 Author: Pranith Kumar K Date: Mon Jun 11 11:38:14 2012 +0530 cli: Change cli output for heal commands BUG: 826406 Change-Id: Ic32c89b92314ee201ec67afc4617e412d4b4c21d Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3636 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1cc71909a619ee9f081ccb0646aeb015fd6f7598 Author: Krishnan Parthasarathi Date: Sat Jun 30 17:04:26 2012 +0530 rpc: Fixed ping timer algo. The purpose of the ping timer is to assert the absence of any evidence the server is possibly alive. The current implementation updates the 'last_sent' timer in the following points in time, - rpc_clnt_submit: when rpc messages are being queued at the transport layer. (wrong!, since we have no way to determine if server actually received the message) - rpc_clnt_notify: when client receives pollout event on sending a message on the 'wire'. (correct, since it indicates ACK from server) The fix removes the 'incorrect' update of 'last_sent'. Change-Id: I56af7b15c3672673696977a7c50ee66eafa4ec55 BUG: 836448 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3624 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 31e81065edc26378eabdd4785f5dd689719cd126 Author: shishir gowda Date: Fri Jun 22 13:28:31 2012 +0530 cluster/dht: Remove dht dependency on glusterfsd-mgmt glusterfs_ctx->notify can be used by any xlator to talk to glusterfsd-mgmt. Note- This is for any rpc communication initiated by the xlator, and not from glusterd. Change-Id: Ic0e4af106fe1e98d797ca621facda8839b87598a BUG: 835757 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3610 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 84d0f889eab947b58a0f6e8d0eda5ae84c15a6c7 Author: Raghavendra G Date: Tue May 29 10:02:52 2012 +0530 rpc-transport/rdma: decode and handle RDMA_ERROR msgs. RDMA_ERROR msgs are resulted as part of failure to decode requests or failure to send reply (for eg., reply being bigger than a msg that can be sent inline, but client has not provided any write-chunks to rdma-write into). Change-Id: I0184cfb5ff8f49ed892767345e32e6c7b01c49e7 BUG: 822337 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3475 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f2b709054d6eec89760bb3513f7b27209c6a6ea7 Author: Kaushal M Date: Tue Jun 5 15:02:49 2012 +0530 glusterd: Set errstr for duplicate add-brick Sets op_errstr when add-brick is given a duplicate brick. BUG: 832293 Change-Id: I2d6d13b2ca29615678902b56e6b394ea05f37923 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3585 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b8d5208f5c8945debe565ae72fea5a3795a44dfe Author: shishir gowda Date: Wed Jul 25 13:08:14 2012 +0530 cluster/distribute: Suppress user xattr mismatch log message Changing the log-level to DEBUG. Xattr mismatch can occur when parallel setxattr's race, or when one of the bricks was down. A subsequent setxattr will fix the condition when all the subvols are up. In this case, the 'user.swift' xattr used by ufo was out of sync, but did not cause any other error. Change-Id: I6fdff78869b8ff72c305bbe122033e6c1d9d3cff BUG: 838197 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3723 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Vijay Bellur commit 98564a3de126658190c7d54873d4ea2adab59bd8 Author: Raghavendra Bhat Date: Wed Jul 11 23:00:27 2012 +0530 storage/posix: handle getxattr failures gracefully Use proper variable types for getting return value of getxattr calls, which otherwise can lead to segfaulting of processes or page allocation failures in the kernel. Change-Id: Idc41b4022401c238d17ba357648234f7c2d56c87 BUG: 838195 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3658 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ed9a37fdf4c110697a3c6201764be7ccbb91573e Author: Kaushal M Date: Wed Jun 27 11:04:48 2012 +0530 glusterd: Fix peer probe when username/password is missing Prevent failure of building volumes dictionary during peer probe, when username/password for a volume is missing. This situation can be caused by migration of gluster from pre-3.3 to 3.3 and above. BUG: 834229 Change-Id: I042ecfcc5024e6b18c4ffb44ea0977ec58e22ef8 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3629 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 01b365d5bba3bea0847bc79fb5dfe82e5c75dc91 Author: Csaba Henk Date: Wed Jun 13 14:15:14 2012 +0530 geo-rep / gsyncd: fixes to communication with child processes due to not using the proper Python keyword, errhandler thread was possible to run into empty select Signed-off-by: Csaba Henk BUG: 764678 Change-Id: I3c39e718e72545c27d50fd73aa6daf54062331b0 Reviewed-on: http://review.gluster.com/3562 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c0a5348af37c634cc61fa72251e029a3a0301eca Author: Rajesh Amaravathi Date: Wed May 23 14:08:37 2012 +0530 nfs/nlm: statedump of locks This change allows statedump of nlm locks giving number of clients, number of locks each client holds and the files on which lock(s) is/are held. Change-Id: I6341c12ec58005ef71b93b316b527e610ff7ee8f BUG: 824804 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3492 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri Reviewed-by: Vijay Bellur commit 1e1a162fa7ea5b6275a0212273ca96b4de410c00 Author: Brian Foster Date: Mon May 7 13:53:31 2012 -0400 cluster/stripe: implement the coalesce stripe file format The coalesce file format for cluster/stripe condenses the striped files to a contiguous layout. The elimination of holes in striped files eliminates space wasted via local filesystem preallocation heuristics and significantly improves read performance. Coalesce mode is implemented with a new 'coalesce' xlator option, which is user-configurable and disabled by default. The format of newly created files is marked with a new 'stripe-coalesce' xattr. Cluster/stripe handles/preserves the format of files regardless of the current mode of operation (i.e., a volume can simultaneously consist of coalesced and non-coalesced files). Files without the stripe-coalesce attribute are assumed to have the traditional format to provide backward compatibility. extras/stripe-merge: support traditional and coalesce stripe formats Update the stripe-merge recovery tool to handle the traditional and coalesced file formats. The format of the file is detected automatically (and verified) via the stripe-coalesce attributes. BUG: 801887 Change-Id: I682f0b4e819f496ddb68c9a01c4de4688280fdf8 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3639 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 1d1639019284f9baaee9d8f4b7d617c6edb52eec Author: Emmanuel Dreyfus Date: Fri Jun 15 09:47:29 2012 +0200 Use inet as default listene This is backport of Change-Id: I172570aa58ea08c4c74cfd28f121d3d4e02a55e0 BUG: 764655 Change-Id: I60232b73c303d296e34871ed317925c9af0d322e Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3575 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 74d7d2d53c539c822cf7b6da44a515f1e326c5bc Author: Emmanuel Dreyfus Date: Fri Jul 6 16:53:35 2012 +0200 NetBSD build fixes This is a backport of Change-Id: Icd7290f1e340675d763665a0d0c5f95bc14e0c55 BUG: 764655 Change-Id: Iaca3dc30e61c0864af673b90d2a7fdea6a3143cc Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3577 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e14095fbbe5c410863ffca865803762dd8cf6e87 Author: Emmanuel Dreyfus Date: Fri Jun 15 09:58:53 2012 +0200 Use linkat(2) for symlink to get portable behavior This is a backport of Change-Id: If7f6f17b48a4ccf8827c3795ec147306df6b5542 BUG: 764655 Change-Id: I374aca5d72d003d67a2bdc9a22b88ce7dd412a0d Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3580 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f626ea8e9121baab4c0447f9aaf273e1141a79ed Author: Emmanuel Dreyfus Date: Fri Jun 15 09:53:34 2012 +0200 Set LD_LIBRARY_PATH before starting glusterfs This is a backport of Change-Id: I13bf0bea043351498b4bc885c5ac45b108229a0a BUG: 764655 Change-Id: I7908352f7a9baae48a7c3bd2c8845980d0dc9b96 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3578 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ca297bc9ba096c64e182872692981a1d7ee250fa Author: Emmanuel Dreyfus Date: Fri Jun 15 09:55:28 2012 +0200 stat(1) flag to specify format is not portable This is a backport of Change-Id: Iae3c40b03118078530c29d14d5f7180c36361c16 BUG: 764655 Change-Id: Ic4e7adbda6b53b248aa93cd20a045cb885fa818e Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3579 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6ee9d105695e4fd8ea86d8c173b234e2df12eb51 Author: Emmanuel Dreyfus Date: Fri Jun 15 09:49:15 2012 +0200 Switch to GNU basename_r() and dirname_r() This is a backport of Change-Id Ic9a159fffdc7bacc9408f8e90854e4c2db81930c and Id874b9c7aacd9aa3a7a4bd6a92a9633f5b2d6ac0 BUG: 764655 Change-Id: I51aac601fb4cc9a0d87afcab2240dc7a1d131c93 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3576 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a091f75386fee1499553546e4e6849dabec77338 Author: Csaba Henk Date: Tue May 22 14:03:32 2012 +0530 geo-rep / gsyncd: sanitize error log of external commands If a command invoked by gsyncd fails, gsyncd makes a log of what comes out on its stderr. So far the log indeterministically broke lines at random places. Now put some effort into reconstructing original lines and having a faithful log. BUG: 764678 Change-Id: I16fcc75d3e0f624c10c71d9b37c937ca677087cc Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3563 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d98068a71b63330180281e09347c02d69213c2aa Author: Emmanuel Dreyfus Date: Fri Jun 15 09:45:23 2012 +0200 NetBSD build fixes. This is a backport of Change-Id: Ib8183d4b585465d05a7adf3a4ceae93ae1bded15 BUG: 764655 Change-Id: I552b87b72c234b3a11af6ffd4a03975879602363 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3574 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d3f1007400735812c88353ed6b0a49d9d4d2c7b2 Author: Kaushal M Date: Mon Jun 4 09:56:33 2012 +0530 libglusterfs: valid_host_name() fix Fix valid_host_name() to allow single character hostnames. BUG: 827403 Change-Id: Ie8df0114cee55b0472b83c077b8ac4fc952f5acd Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3516 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 0c95f6bdb0d934384111aabab0ee2d8980102a50 Author: Raghavendra G Date: Mon May 28 16:55:52 2012 +0530 protocol/client: provide a buffer for storing reply of readlink. since a readlink response can be bigger than size of rdma-msges that can be inlined, we need to provide a buffer where server can do an rdma-write of response. Change-Id: I6ab06c3a94702f810ab0c57b409aaaf35cc93057 BUG: 822337 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3463 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Tested-by: Amar Tumballi commit b8fccb47dd43977150ce4c14a1889b2c82917711 Author: Raghavendra G Date: Fri May 25 16:41:14 2012 +0530 rpc-transport/rdma: logging enhancements Signed-off-by: Raghavendra G Change-Id: I07f00fb768dfdabdc04b43fdb8a0609098cd1838 BUG: 822337 Reviewed-on: http://review.gluster.com/3447 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4f31c4ccd36ed446f705fa7537e81b753de3d85d Author: Amar Tumballi Date: Mon Jun 4 16:05:49 2012 +0530 mount.glusterfs: update the glusterd WORKDIR Change-Id: I70d091611d314598412b5315adcbe1b5147a8773 Signed-off-by: Amar Tumballi BUG: 824231 Reviewed-on: http://review.gluster.com/3512 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8519baae01b64c3d102b2af6e6e8912f17907fb2 Author: Krishna Srinivas Date: Wed May 23 03:37:16 2012 +0530 nfs/nlm: when setting nlmclnt->rpc_clnt, do not overwrite old rpc_clnt Change-Id: I01a1c0c0c8d3402b8fe061258001eea2c0029e83 BUG: 819518 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3433 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a0cf60dc59642b4b4db24173fb9ab1bb81c10a89 Author: Raghavendra Bhat Date: Wed May 30 22:34:25 2012 +0530 cluster/dht: set conf->defrag to NULL after freeing the defrag structure Also no need to free the xlator object after rebalance is over, as the process is about to be killed. Change-Id: I6973e43c0353b5de61c0b39e52a22c618be361f4 BUG: 826584 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3495 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Anand Avati Reviewed-on: http://review.gluster.com/3607 Reviewed-by: Shishir Gowda commit e2f1d73017894f893889b78135331355eb86836e Author: Pranith Kumar K Date: Fri Jun 15 12:21:15 2012 +0530 cluster/afr: split-brain should be reset on data-self-heal If the govinda flag is set in the beginning then missing_entries_done will fail the self-heal before it can come to data_self_heal. Change-Id: I4d5b6a7c3bb26bae78979ee59c7c0997fd3fd84b BUG: 832305 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3583 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 27bc10d67b9502c03668ca851e8330485cb5e2b5 Author: Pranith Kumar K Date: Tue Jun 12 19:39:49 2012 +0530 cluster/afr: Treat EEXIST as success in hardlink Change-Id: I6711fe9230553306eab6012edea8de157a336a78 BUG: 831151 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3549 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a04bbeafa9b96c0f05e6403749d2b8002b6c4f12 Author: Pranith Kumar K Date: Thu Jun 7 14:01:46 2012 +0530 cli: Fix time_t conversions Change-Id: I98eb76e5971ea800a249d21557d5dd4f093fdaaf BUG: 828058 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3534 Reviewed-by: Kaleb KEITHLEY Tested-by: Gluster Build System Reviewed-by: Niels de Vos Tested-by: Joe Julian Reviewed-by: Joe Julian Reviewed-by: Vijay Bellur commit 7ded1a6e11dae194f04d8717125ff5c18066731e Author: Mohammed Junaid Date: Mon Jun 11 16:39:17 2012 +0530 swift: Donot display async_pending container. async_pending container is for internal, should not be exposed to the users on a GET. Change-Id: I460242667ae0cb5e96d4c63296f0bae4bb83b28e BUG: 829137 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3546 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 93e9c02599e710bac112ac19ac4932ac4ad52a25 Author: Vijay Bellur Date: Thu May 31 23:10:01 2012 +0530 doc: Changes in Hadoop to reflect the right RPM Change-Id: Ieb179affe5cb3c7d3ae1ca1e47c1a76ada876ced Reviewed-on: http://review.gluster.com/3499 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit 6d602670ef63e184492e19ed2dea6095db3ec36e Author: Csaba Henk Date: Fri Mar 9 09:11:23 2012 +0100 geo-rep / gsyncd: fix cleanup of temporary mounts [This is a "forward port" of fafd5c17, http://review.gluster.com/2908] The "finally" clause that was meant to cleanup after the temp mount has not covered the case of getting signalled (eg. by monitor, upon worker timing out). So here we "outsource" the cleanup to an ephemeral child process. Child calls setsid(2) so it won't be bothered by internal process management. We use a pipe in between worker and the cleanup child; when child sees the worker end getting closed, it performs the cleanup. Worker end can get closed either because worker closes it (normal case), or because worker has terminated (faulty case) -- thus as bonus, we get a nice uniform handling with no need to differentiate between normal and faulty cases. The faulty case that was seen IRL -- ie., users of maintainance mounts hang in chdir(2) to mount point -- can be simulated for testing purposes by applying the following patch: diff --git a/xlators/mount/fuse/src/fuse-bridge.c b/xlators/mount/fuse/src/fuse-bridge.c index acd3c68..1ce5dc1 100644 --- a/xlators/mount/fuse/src/fuse-bridge.c +++ b/xlators/mount/fuse/src/fuse-bridge.c @@ -2918,7 +2918,7 @@ fuse_init (xlator_t *this, fuse_in_header_t *finh, void *msg) if (fini->minor < 9) *priv->msg0_len_p = sizeof(*finh) + FUSE_COMPAT_WRITE_IN_SIZE; #endif - ret = send_fuse_obj (this, finh, &fino); + ret = priv->client_pid_set ? 0 : send_fuse_obj (this, finh, &fino); if (ret == 0) gf_log ("glusterfs-fuse", GF_LOG_INFO, "FUSE inited with protocol versions:" Change-Id: I14bad56a60a7fa82d0104fa4b9a20f4e42a7186f BUG: 786291 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3542 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 05ad7e460c9f7ab7759313dfcd07ab37f9acd2b2 Author: Mohammed Junaid Date: Thu May 31 22:24:25 2012 +0530 swift: Updated the UFO admin guide for 3.3. Also, added a script to install the new rpm's. Change-Id: I66ba72822046d5930d021073a0cd918aafda6c24 BUG: 811430 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3498 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 281c79c3766ca6a912e419d0cde24d1b8c457cbe Author: Amar Tumballi Date: Fri Jun 1 10:30:34 2012 +0530 doc: added release-notes directory Change-Id: Idd45c0fe6a0615a3204aad216002894746cea03c Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/3501 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f037fe9143706375bea140b61fd87d13e5b2b961 Author: Amar Tumballi Date: Mon May 28 19:32:14 2012 +0530 documentation - Admin-Guide Updates Change-Id: I6e053b6a5f099fb7b1c228668949463c795b4fc7 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/3496 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1b798491193add9cb296ce6817a6cbc2fdb9db34 Author: Anand Avati Date: Sun May 27 16:52:21 2012 -0700 storage/posix: readdirp enhancements - avoid multiple calls to posix_istat(). use cheaper posix_pstat() - code re-org Change-Id: I4a2e32626ade49b7d18158952849c6fe7bd6875c BUG: 816140 Reviewed-on: http://review.gluster.com/3488 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 493ef71222e780cb542c7edc5dfb7d0e3097c55a Author: Anand Avati Date: Tue May 29 22:30:53 2012 -0700 protocol: do not log getxattr/ENODATA as warning When SELinux is enabled, most of the files do not have labels and result is a ton of unnecessary logs Change-Id: I0e781e2fb6bcfb3fb12298175a41f7b981af9c39 BUG: 811217 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3487 Tested-by: Gluster Build System commit f69785a9e3f9ad55e81f1fe8212485b7e4dc11fe Author: Anand Avati Date: Tue May 29 22:01:42 2012 -0700 fuse: make SELinux support configurable Make support for SELinux labels (extended attributes) configurable and disabled by default as it can cause significant performance penalty when enabled (it need not be enabled unless specially crafted policies are set -- which is not by default) Change-Id: I97bc4b1c26cf055fd520e9bf2d49e52b14fe7515 BUG: 811217 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3485 Tested-by: Gluster Build System commit 647f561f6ad16174da700ea6b70f01b6e0ae6d96 Author: Raghavendra Bhat Date: Tue May 29 17:57:54 2012 +0530 glusterd: change working-directory from /etc/glusterd to /var/lib/glusterd as it is changed in RPM based install (using spec file), makes sense to do it everywhere, even in source install Change-Id: Id813104cf017ac575d4ce9bdff76b414c99db999 BUG: 824231 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3479 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Vijay Bellur commit 9b9ede959d70438b1c41aad14ed189c03d16a544 Author: Raghavendra Bhat Date: Tue May 29 18:22:16 2012 +0530 distribute: use global synctask 'env' instead of local creating a local synctask_env can lead to creating of many more syncop threads than required. The current syncop logic can handle the scale-up/scale-down of threads depending on the load. Hence, its neater to use global synctask env. Change-Id: Iff71885ed92eaab67fa2c2cf88c85af3a4a603d9 BUG: 823774 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3480 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 90394b565aa61f9a649233bf6b92fabf32c3af39 Author: Mohammed Junaid Date: Tue May 29 16:33:52 2012 +0530 swift: Fix for multiple mounts on the same mount point. When swift server receives multiple requests on a volume and if the volume is not mounted before hand, for each request swift tries to mount the GlusterFS volume on the mount point. This process is racy and may mount multiple times on the same mount point. Also added a new option object_only in fs.conf which should be enabled only if the user requires ReST interface and will have better performance. By default it is set "off". Change-Id: Ie1718554c5aaf577e823bbd84da8e78d803e954d BUG: 821310 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3478 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 292949eeeef888f87d833bdfcfbc1f4ede8d38ea Author: Rajesh Amaravathi Date: Wed May 23 14:44:26 2012 +0530 nfs/nlm: avoid duplicate replies for nlm procedures The way NLM handles errors and corresponding response messages has been simplified to avoid duplicate replies in case of failures. Also, unlock_cbk and unlock_fd_resume functions are moved in with other unlock functions. Change-Id: I94100aa3c8de95dabebed4598651bbcd49d95782 BUG: 824316 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3462 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c55aad83235d86cfe15a26c760649a91e04f389a Author: Krishnan Parthasarathi Date: Fri May 25 23:41:19 2012 +0530 glusterd: Run post hooks on a different thread This change ensures post hooks can 'wait' if need be and _not_ prevent glusterd from being able to run other operations meanwhile. Also ensures that post hook scripts are 'serialized' between transactions. ie, post hook scripts of txn1 are completed before post hook scripts of txn2 are started, where txn1 happens before txn2. Change-Id: Iaeb676737d8c67e7151127c8d1fd8c2891e10aee BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3476 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c7ed7013e9cc22b1e01d49580d138955034395a3 Author: Pranith Kumar K Date: Mon May 28 15:31:36 2012 +0530 glusterd: regenerate brick vol-files on upgrade If upgrade/downgrade option is set in glusterd it terminates after the volfiles are regenerated. No need for 'sleep 10' hack anymore. Change-Id: I83b1cd83b1cc56c6d221e6f2bbbf58af62cb56b9 BUG: 825872 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3472 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 98c39b1a7b65184db95ae690648765dd64fae8ee Author: Vijay Bellur Date: Tue May 29 00:35:20 2012 +0530 build: Update licensing in buildspec Change-Id: I1d3348a99dad621608eccb08a71c85766e9ae451 BUG: 820551 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3470 Tested-by: Gluster Build System Reviewed-by: Sachidananda Urs commit b278ff4b71f2b779810383ec1bba147cc5b2e07d Author: Amar Tumballi Date: Tue May 29 08:54:45 2012 +0530 doc: changed installation to not install man pages this is temporary fix till man pages are updated to match the release data. Change-Id: I78ce4ee303ebc2aefc9d630d9c72d7b4bfa9a404 Signed-off-by: Amar Tumballi BUG: 825906 Reviewed-on: http://review.gluster.com/3473 Tested-by: Gluster Build System Tested-by: Kaushal M Reviewed-by: Kaushal M Reviewed-by: Vijay Bellur commit 7f52ce36d1a378c0983fb00c06032297033e350d Author: Pranith Kumar K Date: Fri May 25 09:49:58 2012 +0530 cluster/afr: Don't reset split-brain when data-self-heal is off Change-Id: Ie3b2c19e0bee85f64d4c2522beaf7d08e46b8a9e BUG: 804606 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3466 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7224bedd47891e36fb55b8480f5c1f9c0338f70d Author: Vijay Bellur Date: Mon May 28 23:50:01 2012 +0530 libglusterfs: Fix incorrect NULL check Change-Id: I8f9e6452c3ee7038417a9f3bcd9fc5990386af42 BUG: 825197 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3468 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 42491cf4eac02dd3f3ae9ee57e8af16873ca30b8 Author: Pranith Kumar K Date: Thu May 24 20:45:56 2012 +0530 mgmt/glusterd: self-heals should be on in glustershd Change-Id: I804dee79eaba0a1b055ad51a194278c8fec8de8f BUG: 825740 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3461 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit 063679d8fbeaad7034db33f1dc4cb1713754cb3a Author: Krishnan Parthasarathi Date: Wed May 23 15:15:51 2012 +0530 glusterd: Replace-brick should create dst brick path only on 'dst' node. Change-Id: I61e6f8aa44dfef85c7cd98f40b176b796422c4b2 BUG: 824302 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3457 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a1904d84f7a62f0defe195d3c316fbe95adb51e4 Author: Venky Shankar Date: Mon May 28 12:10:04 2012 +0530 glusterd / geo-rep : fix rotating slave log file Attempt to rotate log files for slave that are local. Remote slaves (identified by the 'ssh' scheme) are ignored. Change-Id: Iff46462c388d39433917159c0e89e7ac9e772c0f BUG: 821443 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/3459 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8df11080514f37e61c666c162c774d4bb02016f2 Author: Pranith Kumar K Date: Wed May 23 18:09:48 2012 +0530 cluster/afr: Release inodelk on erase changelog failures Change-Id: I58271e1ac5a116b5bc717d7cad9f03eb7dc8a1a4 BUG: 811551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3416 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d497922a725da0690e5c5c75911e59d30c5d53a1 Author: Krishnan Parthasarathi Date: Fri May 25 15:02:47 2012 +0530 glusterd: Cherry-picked e44ac01b08c3ee from master branch Fix volume create Improve Krishnan Parthasarathi's patch, which fixed situation where a brick mount point did not had EA enabled. This fixes an incorrect assumption that dirname(3) returns the same address it was given as argument. GNU dirname(3) does it, BSD dirname(3) does not. Also makes the code a bit easier to read. Signed-off-by: Emmanuel Dreyfus Change-Id: Ie5106b0ee7bda126666cd0ec9c827c895ec035c9 BUG: 812214 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3441 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3d653908554dc92af6b7414df4083bee2b9e039f Author: Krishnan Parthasarathi Date: Wed Apr 18 14:30:16 2012 +0530 glusterd: Disconnected bricks of 'stale' volume before deleting it. If glusterd_delete_bricks is called before glusterd got the DISCONNECT event from the brick that was stopped, then glusterd_brick_rpc_notify would dereference a free'd brickinfo. This can happen if the brick had not been disconnected before. Change-Id: I6c07ec50f6739422a14478a549edd06c4c0ce913 BUG: 802015 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3442 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c4d4d9d1d3ec4565346efcfe8bdc6c10b8d5ba2d Author: Krishna Srinivas Date: Tue May 8 15:15:31 2012 +0530 nfs/mount: Support MOUNT protocol on UDP. Needed for NLM on solaris clients. Change-Id: I3f5c35d06827fb267a7dae53d949c61567a945d0 BUG: 799287 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3434 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 252bd6b8b6952127ee3462495b1e5063e7a22ad0 Author: Csaba Henk Date: Sat May 26 19:04:25 2012 +0530 glusterd/geo-rep: cleanup and fixes - fix the hilarious fd leak of "geo-rep status" - instead of "corrupt", which can trip up users to think their data is in danger, use the term "defunct" to describe the condition when gsyncd is dead/unresponsive - don't use buffered I/O when unnecessary - stop using PATH_MAX for sizing buffers that don't hold paths - some cleanups wrt. memory management Change-Id: I396aacc45dc06a002318b19c60c44041fa9fa18d BUG: 764268 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3456 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 74c0dd6b7b3f4caaf36a18b37e62cf3338f99cab Author: Csaba Henk Date: Wed May 23 14:54:02 2012 +0530 geo-rep / gsyncd: add "--super" to rsync invocation This forces rsync to perform supposedly privileged operations on unprivileged slaves (like chown(2)). For consistent behavior (with gsyncd's "chown" RPC call that's being used for symlinks and directories), we also pass "--numeric-ids" to rsync. Also took the chance to retire gsyncd's "--rsync-extra" option which was there for debugging purposes (related to a resolved issue). Change-Id: I4ee4d0d3a8c4e0f6746d34d7722c8a567a67491c BUG: 822121 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3426 Tested-by: Gluster Build System Reviewed-by: Anand Avati Reviewed-on: http://review.gluster.com/3453 Reviewed-by: Vijay Bellur commit 4409b22a7a86431631f3fdf5a07d642e32735042 Author: Csaba Henk Date: Mon May 14 17:07:28 2012 +0530 fuse, glusterfsd: mount logic fixes Commit 7d0397c2 introduced two issues: i) broke the libfuse derived mount logic (details below) ii) in case of a daemonized glusterfs client is ran as daemon, parent process can return earlier than the mount is in place, which breaks agents that programmatically do a gluster mount via a direct call to glusterfs (ie. not via mount(8)). This patch fixes these issues by a refactor that merges the approaches sported by commits 7d0397c2 fuse: allow requests during mount (needed for SELinux labels) c5d781e0 upon daemonizing, wait on mtab update to terminate in parent Original daemonized libfuse event flow is as follows: try: fd = open("/dev/fuse") mount("-oopts,fd=%s" % fd ...) mount(8) -f # manipulate mtab except: sp = socketpair() env _FUSE_COMMFD=sp fusermount -oopts fd = receive_fd(sp) where fusermount(1) does: fd = open("/dev/fuse") mount("-oopts,fd=%d" % fd ...) sp = atoi(getenv("_FUSE_COMMFD")) send_fd(sp, fd) daemonize( # in child fuse_loop(fd) ) # in parent exit() As of 013850c9 (instead of adopting FUSE's 47e61004¹), we went for async mtab manipulation, and as of c5d781e0, still wanted keep that in sync with termination of daemon parent, so we changed it to: try: fd = open("/dev/fuse") mount("-oopts,fd=%s" % fd ...) pid = fork( # in child mount(8) -f ) except: sp = socketpair() env _FUSE_COMMFD=sp fusermount -oopts fd = receive_fd(sp) daemonize( fuse_loop(fd) ) waitpid(pid) exit() (Note the new approch came only to direct [privileged] mount, so fusermount based mounting was already partially broken.) As of 7d0397c2, with the purpose of facilitating async mount, the event flow was practically reduced to: fd = open("/dev/fuse") fork( mount("-oopts,fd=%s" % fd ...) fork( mount(8) -n ) ) daemonize( fuse_loop(fd) ) exit() Thus fusermount based mounting become defunct; however, the dead code was still kept around. So, we should either drop it or fix it. Also, the mtab manipulator is forked into yet another child with no purpose, while syncing with it in daemon parent is broken. mount(2) is neither synced with parent. Now we are coming to the following scheme: fd = open("/dev/fuse") pid = fork( try: mount("-oopts,fd=%s" % fd ...) mount(8) -n except: env _FUSE_DEVFD=fd fusermount -oopts ) where fusermount(1) does: fd = getenv("_FUSE_DEVFD") mount("-oopts,fd=%s" % fd ...) daemonize( fuse_loop(fd) ) waitpid(pid) exit() Nb.: - We can't help losing compatibility with upstream fusermount, as it sends back the fd only when mount(2) is completed, thus defeating the async mount approach. The 'getenv("_FUSE_DEVFD")' mechanism is specfic to glusterfs' fusermount (at the moment -- sure we can talk about it with upstream) - fusermount opens /dev/fuse at same privilege level as of original process², so we can bravely go on with doing the open unconditionally in original process - Original mounting code actually tries to mount through fusermount _twice_: if first attempt fails, then, assuming subtype support is missing in kernel, it tries again subtype stripped. However, this is redundant, as fusermount internally also performs the subtype check³. Therefore we simplified the logic to have just a single fusermount call. - we revert the changes to mount.glusterfs as of 7d0397c2, as now there is no issue with glusterfs to work around in that scope ¹ http://fuse.git.sourceforge.net/git/gitweb.cgi?p=fuse/fuse;a=blobdiff;f=ChangeLog;h=47e61004;hb=4c3d9b19;hpb=e61b775a ² http://fuse.git.sourceforge.net/git/gitweb.cgi?p=fuse/fuse;a=blob;f=util/fusermount.c;h=b2e87d95#l1023 ³ http://fuse.git.sourceforge.net/git/gitweb.cgi?p=fuse/fuse;a=blob;f=util/fusermount.c;h=b2e87d95#l839 Change-Id: I0c4ab70e0c5ad7b27337228749b266bcd0ba941d BUG: 811217 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3428 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 507a4ebb6ca3704e1a6ee3d1b6511b58ed9f6ba7 Author: Csaba Henk Date: Thu May 24 12:25:43 2012 +0530 fuse: allow requests during mount (needed for SELinux labels) Resurrecting Jeff's commit: commit 7d0397c2144810c8a396e00187a6617873c94002 Author: Jeff Darcy fuse: allow requests during mount (needed for SELinux labels) that was reverted as of: commit 4ab1c326f3862714b960302f06c6323d6291b695 Author: Vijay Bellur Revert "fuse: allow requests during mount (needed for SELinux labels)" BUG: 811217 Change-Id: Ia1af402897e6a7290acf79617c34fdc804751729 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3452 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 994c56a185d1f3e0f0f40f4051f82cdf2c7905b9 Author: Krishna Srinivas Date: Fri May 18 17:43:49 2012 +0530 nfs/nlm: nlm-unlock call should reply success in case it is not able to find the lock in the list. Change-Id: I84b298702c445320082ef03de90c924931f1a1e1 BUG: 822384 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3451 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 69392d4daa9df0612630813713ae02a99cc068e0 Author: Mohammed Junaid Date: Mon May 21 15:47:28 2012 +0530 swift: Passing account name in container_update. This patch also contains fixes to bugs * 811501 * 812498 * 821310 Also, removed the default set of users in the proxy-server.conf file. Change-Id: Ief83905d10ff7bf7c43685ada4d7f05959cee9d1 BUG: 821310 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3440 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 65275d048bb031f93a690c69cb32bb751298c212 Author: Mohammed Junaid Date: Fri May 11 12:51:38 2012 +0530 protocol/client: Concatenate the graph uuid along with process uuid in setlk_version. Change-Id: Idec06c5ef1d440864e465f008a38c86395b52aba BUG: 820831 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3439 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 0917026a3629cd8bfb9af73f1c8d5a333c2bf569 Author: Mohammed Junaid Date: Wed Apr 25 15:39:20 2012 +0530 mount/fuse: Use state->lk_lock to print lock information on EAGAIN. Change-Id: I24a4a0b1c8dc0b8e08b380a5bc8efc111ccdb2c3 BUG: 808400 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3438 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ed67fbf9d22a8099155795a5482c219f488992c3 Author: Krishnan Parthasarathi Date: Sat May 19 23:40:13 2012 +0530 locks: Fixed opt arg parsing in clear-locks Change-Id: I470fd21d5d53e3c6f0bd2a4f84c6327532e18559 BUG: 823151 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3429 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b86436da7e0de47282c46cd14989e4cbaad0501d Author: Raghavendra G Date: Wed May 23 23:43:44 2012 +0530 protocol/client: use correct xlator object while creating frames during reopening files and reacquiring locks. Change-Id: I29f42fcfa9e782ce9e323e53024e5034029914a7 BUG: 822337 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3421 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 9d4c8b3909b8f572a732b884062b70efa51e4956 Author: Raghavendra G Date: Sat May 19 14:49:21 2012 +0530 performance/quick-read: fix race-conditions in qr_unlink. The list of fds on which open needs to be done as part of unlink, was being modified at different places using different locks. This resulted in a race-condition where open was marked as in-transit, but fdctx was removed from the list of fds on which open was being sent even before open was done. Because of this, open_in_transit would be set forever (as an open was never actually sent, there would be no open_cbk called and hence we could not reset the variable), blocking all the future fd based fops on this fd. Change-Id: Ie84a55bee578869a9a060a094ba28480e7643ae8 BUG: 819490 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3372 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 638a4740cc553c96bc01d1dfe4a2b7acf0b406e6 Author: shishir gowda Date: Tue May 22 11:25:55 2012 +0530 cluster/dht: Handle ENOENT failure in dht_rmdir_opendir_cbk We should not treat ENOENT as a failure in rmdir. BUG: 806761 Change-Id: I847cfd9fb31880b8200cf04aa795fed3c870f71a Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3402 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a87151dc3a34e24d6ba6d3f4b84d2c5feabff587 Author: Raghavendra Bhat Date: Sun May 13 21:56:06 2012 +0530 features/marker: use the gfid from the stat structure instead of inode in fresh lookup, the inode would not have linked to the inode table until the fop reaches back to protocol/server, thus it would not contain the gfid within it (gfid would still be null). So use the stat structure to get the gfid in lookup callback instead of inode's gfid. Change-Id: Id70277f0228f3db64b05d613108cfb4f070197e6 BUG: 791087 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3400 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 065703939125c2c4be88c400cc9c6690acdd5f93 Author: Raghavendra Bhat Date: Mon May 21 13:34:20 2012 +0530 performance/md-cache: use mdc_fsetattr_cbk as the callback if setattr is on a fd Change-Id: I114a16055540e0cd3317b83b329600251ffe03c3 BUG: 823886 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3404 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit cd246b4ce4f5968f80de245adebbf634e3fdf37e Author: shishir gowda Date: Tue May 22 11:39:47 2012 +0530 glusterfs/rebalance: Register cbk for glusterfs_rebalance_event_notify In case of n/w failures, cbk needs to be passed to mgmt_submit_request BUG: 822086 Change-Id: Ie443902b94a09e11a2696b89de44a11fb477ca3e Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3403 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit f5e63d3ebb02898212b11a9a6599f3483a76568d Author: Csaba Henk Date: Mon Apr 16 21:37:31 2012 +0200 glusterd / mountbroker: warn if mountbroker-root permissions are suspected to be too strict At the level of mountbroker, this is a best effort, as "too strict" depends on the purpose it's being used for (thus we just warn, don't err). However, it's a good guess, as it stands for existing use cases of mountbroker. Change-Id: Ic5e7d6cb44ced5509c05e0ee8a9043252470683f BUG: 765214 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3171 Tested-by: Gluster Build System Reviewed-by: Anand Avati Reviewed-on: http://review.gluster.com/3406 Reviewed-by: Vijay Bellur commit 38f3920ae59fc0f0b70ccf79131901cffc493ccd Author: Csaba Henk Date: Mon May 7 16:59:43 2012 +0530 geo-rep / gsyncd: typo fix fix topy. Change-Id: I84df3e850dd24d9e86713dfa401c603a84a81ca6 BUG: 763302 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3375 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3407 commit 80f4d9a0561f7b263c2d9f0e1cc941208b58a468 Author: Csaba Henk Date: Wed Apr 4 03:12:26 2012 +0200 geo-rep / gsyncd: recognize ECONNABORTED as termination of aux glusterfs Don't dump stack, rather log the "glusterfs session went down" message. If the aux glusterfs is already dead when we try to do some file operation, we get a failure with ENOTCONN, which is already handled as above. However, it's also possible that glusterfs dies while we are in a syscall into it -- in that case we get ECONNABORTED, and so far then we end up with an ugly stack strace. From now on we take ECONNABORTAD as well into consideration. Nb. wrt. testing: it's not easy to synthetically force the aux glusterfs to end this way; for that we have to provoke gsyncd into intensive synchronization. I succeeded in that with the following ruby oneliner: ruby -rcgi -e ' Dir.chdir($*[0]) a=[] Thread.new { loop { while a.size >= 100; File.delete a.shift; end; sleep 1 }} loop { a< Reviewed-on: http://review.gluster.com/3078 Tested-by: Gluster Build System Reviewed-by: Venky Shankar Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3408 commit 8e7f28fa1ebc6d7efdc892856884a92191e47040 Author: Kaushal M Date: Mon May 21 11:59:34 2012 +0530 glusterd: On-wire changes required for probe/detach errstr This patch changes the on-wire structures for 'peer probe' and 'peer detach' to include op_errstr. These changes have been backported from patches feb99ca (glusterd, cli: Enable errstr for peer probe) and 3213a4e (glusterd,cli: Enable errstr for peer detach). The remaining changes will be included later on. Change-Id: I6e8e917f5ad928b80862d301c364cd4df56bb4c0 BUG: 816840 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3387 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 7a9a28742a7dffa8cc16866e9e3388f392e0e3b2 Author: Csaba Henk Date: Fri Apr 20 17:21:12 2012 +0200 geo-rep / gsyncd: fixes regarding the command invocation framework Some of the bugs to fix were found by the following stress-test: make "glusterfs --client-pid=-1" exit immediately on slave side. Also fix eintr_wrap which should not "adopt" exceptions generated by the wrapped call, by re-raising them as GsyncdError. Change-Id: Ia0d39e0635975ebbbf98d86e1e26f3122e1ed6ff BUG: 764678 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3258 Tested-by: Gluster Build System Reviewed-by: Venky Shankar Reviewed-on: http://review.gluster.com/3409 Reviewed-by: Vijay Bellur commit 258b0f9b2e73d560774d80bd4724155e550ea31b Author: Csaba Henk Date: Wed May 16 15:40:47 2012 +0530 geo-rep / gsyncd.c: fix coverity fix gsyncd wrapper was segfaulting as coverity fix freed up pointer at wrong place (after it was reused) Instead of the apporach of the original coverity fix that added elaborate control flow to hunt down potential leaks, here we move the code over to static allocations in place of (the not really necessary) dynamic ones. Change-Id: Ida3855ff4a4f4371b350d27f858f129ceed51785 BUG: 789278 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3345 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3405 commit 52f3aac6d80aea5d7c531005cb621463806000af Author: Pranith Kumar K Date: Sun May 20 21:02:55 2012 +0530 cluster/afr: Unlock higher entry locks in rename entrylk failure. Change-Id: I4646809ec86baf4b741a874353dbf27fbffb4791 BUG: 823255 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3381 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 86c8e411143a9ee2bfd81270676ebd2a987cf946 Author: Pranith Kumar K Date: Sat May 19 11:14:25 2012 +0530 protocol/server: del_locker should delete one locker per unlock BUG: 771595 Change-Id: If1c352b2d65938ad07f2e4b70c0e58c2d3be11bc Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3399 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 27960b127ea55f1bd877c1e421c93fea3a2c42af Author: Pranith Kumar K Date: Fri May 18 17:00:07 2012 +0530 features/locks: Don't delete blocked locks in pl_flush BUG: 810502 Change-Id: I68c1c11754e1f4413b457c5f4bb7da3bc1aafc23 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3398 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f742f5e6902af5c984f948c8ef5c38022752a018 Author: Pranith Kumar K Date: Fri May 18 11:06:52 2012 +0530 features/locks: insert_and_merge should not operate on blocked locks BUG: 810502 Change-Id: I1c560dae638ddb66f47ea64b661979b31708731b Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3397 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a289a11b0f7892e62e4b31041c852c4a98fa4c25 Author: Pranith Kumar K Date: Mon Apr 2 21:46:42 2012 +0530 cluster/afr: Perform conservative merge on dir with xattr split-brain BUG: 765587 Change-Id: Ifa7a4eae37b0c887a913c8c59d83a679c96c345b Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3396 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 64156e71bc71d7100b0e81bbe0702740b37c3ffb Author: Pranith Kumar K Date: Tue Mar 13 11:15:36 2012 +0530 cluster/afr: Handle files w.o. xattrs and size mismatch. BUG: 765587 Change-Id: I1c1a739f25c4a798ba8ccaa52bc23d2c1dadd034 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3395 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f5c87c7bedfda7ed80d03918bfc3ce90069378e8 Author: Pranith Kumar K Date: Thu Apr 5 14:26:22 2012 +0530 cluster/afr: Mark zero size file as sink in absense of xattrs. BUG: 765587 Change-Id: I225dbf79ec2d4669333cbb28b3c5319a08fe0600 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3394 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit bdec439fe59c5e3fa9701d9cf4b5b92bd7e8a98f Author: Pranith Kumar K Date: Thu Apr 5 11:31:47 2012 +0530 cluster/afr: Determining sources should do both fxattrop, fstat BUG: 765587 Change-Id: Ibaf719776667595e8e9ea2c6be5a0a390a27b506 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3393 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4da1b231c3333806cec16321efa45cc410359574 Author: Amar Tumballi Date: Mon May 21 14:13:05 2012 +0530 protocol/client: free the 'loc2' variable of client_local in common client_local_wipe(), local->loc2 was not getting freed up, but its used in few functions for logging purpose. Change-Id: I05715843b59aa216a79f5164a152c605dc9ad114 Signed-off-by: Amar Tumballi BUG: 823133 Reviewed-on: http://review.gluster.com/3389 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4746ed1a055c595f08445d5a670e9585f8209183 Author: Amar Tumballi Date: Mon May 21 09:05:23 2012 +0530 protocol/server: fix a crash with NULL dereference in setxattr() and fsetxattr() _cbk functions Change-Id: I9798d182e7f68509e8e37d43cb18e4c2f4bd6fab Signed-off-by: Amar Tumballi BUG: 823244 Reviewed-on: http://review.gluster.com/3385 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1d939fe7adef651b90bb5c4cd5843768417f0138 Author: Raghavendra Bhat Date: Fri May 18 14:58:52 2012 +0530 features/quota: get the top xlator from the active graph outside the list In quota reconfigure we were getting the top of the active graph within the list which contains the limits set on the volume. Suppose the list is empty, then the code inside the list traversal loop is not executed, and thus top will be NULL which might lead to segfault when accessed later. Change-Id: I1648d69256490878339294537e17300399ddbf2c BUG: 822827 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3379 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d54d9e9412a267ed8abaee1c682c7b6f734e8205 Author: Pranith Kumar K Date: Fri May 18 22:00:03 2012 +0530 cluster/afr: Assign gfid path if path is NULL in lookup BUG: 820355 Change-Id: I68bea2b8408e741af5fff9e6588ddb87421dbda4 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3374 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 86e0789a8e3c9e7289857fee59b9dedffc5b5e54 Author: Rajesh Amaravathi Date: Tue May 15 16:00:52 2012 +0530 nfs/mount: avoid duplicate reply on ENOENT Change-Id: I310e525b5bd302c0acadcc077213fbd570bf772d BUG: 820582 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3355 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ef3cd63cc95c26fdf7f7a2d8046b4686b02cb836 Author: Krishnan Parthasarathi Date: Mon May 7 13:31:24 2012 +0530 glusterd: Fixed glusterd_brick_create_path algo. - check if any prefix of the brick path has "trusted.gfid" or "trusted.glusterfs.volume-id" set. - set trusted.glusterfs.volume-id on the bricks as soon as its induction into the volume is settled. Earlier, the setting of "volume-id" used to happen during the first run of the brick process, leaving of window for bricks part of one volume to be (ab)used by another volume inadvertently. - removed creation of brick directory (if missing), during start volume force. This is to avoid directory creation as part 'force'ful starting of volume and leave the responsibility with the user, who understands the 'availability' of the export directory (brick) better. Change-Id: I4237ec4ea7a4e38a7501027e7de7112edd67de8c BUG: 812214 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3280 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3313 commit 0cdb1d147afd644153855f6557bf7e809e5444f0 Author: Raghavendra Bhat Date: Fri May 11 18:11:31 2012 +0530 libglusterfs/fd: while dumping the fd_ctx use fd->xl_count While dumping the fd_ctx when statedump is issued fd->xl_count should be used to determine the number of xlators instead of using latest graph's count, since while creating the fd only those many slots would have been allocated as the number of xlators in the graph at that instant. Then the graph would have changed, thus the xl count. All the above things should happen before any operation is done on fd, otherwise fd_ctx_set will allocate the extra slots for the new xlators present in the graph. Also added the program which can be used to reproduce the bug. Change-Id: I11fe75d71ef5d37e29e2958d53752aa31098c313 BUG: 820887 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3335 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3369 commit 7914df6c6ab6d7d3905b26c1dbc5ac07d79ef10f Author: Rajesh Amaravathi Date: Thu Apr 12 14:49:44 2012 +0530 nfs/nlm: procedures for PC clients * This change introduces four NLMv4 procedures: NM_LOCK, SHARE, UNSHARE and FREE_ALL. These are used by PC clients (windows/dos) to control access to files. 1. NM_LOCK: this lock is not monitored by statd. 2. SHARE: A share reservation is a lock on the whole file that is taken whenever a file is opened on windows clients. This has ACCESS (N, R, W, RW) and DENY MODE (N, R, W, RW). ACCESS: mode of access requested by the client; DENY MODE: what the requesting client wants to deny other clients. 3. UNSHARE: remove a share reservation obtained by SHARE. Called while closing a file. 4. FREE_ALL: remove all share reservations and locks, both monitored and unmonitored, of the calling client. * lock and nm_lock use a common function with only a flag conveying whether or not to monitor a lock. * NOTES: 1. SHARE reservations are not STACK_WIND'd to subsequent xlators. These are maintained in-memory in the nfs xlator. 2. Consequently, for SHARE reservations to work effectively, all PC clients *must* mount from the same gNfs server. Not doing so will result in different servers maintaining separate SHARE reservations which will not be enforced for obvious reasons. Change-Id: Id4f22670a94ed58691a6a7f4c80aa8c11421a277 BUG: 800287 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3356 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 27f4cc44140260516efa5a226b9f49b761b6b559 Author: Pranith Kumar K Date: Fri Apr 20 17:22:43 2012 +0530 Self-heald: Print the time stamp of the event-history BUG: 796579 Change-Id: I4c738d9073b53fc3c4d4797b5f01e841dae1b4e9 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3352 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3e3a687d025918232763488e6c9e102b0b2a0dcc Author: Pranith Kumar K Date: Tue Mar 13 17:33:34 2012 +0530 cluster/afr: Return EIO if read-child < 0 in inode-read fops BUG: 800884 Change-Id: Ia3382d169e96308eaf48fbd717a72d5266e40677 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3351 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit bdd240eca1e7350f4e6ddec047ea8f6db67512d5 Author: Vijay Bellur Date: Thu May 17 09:28:02 2012 -0700 Revert "fuse-resolve: consider cases where an entry should be resolved even" This reverts commit 27fb213be6101bca859502ac87dddc4cd0a6f272. commit 99ac60193a31438258b751e4c99c85d153ddaae5 Author: Kaushal M Date: Tue May 15 16:31:55 2012 +0530 client/protocol : Changes in client3_1_getxattr() Backporting change 1d02db63ae from master. Copy args->loc to local->loc in client3_1_getxattr(). This prevents logs with "(null) (--)" in client3_1_getxattr_cbk(). Also save args->name in local->name and print it in the log as well. Also, fixes crashes caused by above patch in master. (trying to gf_strdup a NULL args->name) BUG: 812199 Change-Id: I5419f6a244de93dd1a96ac8e229be3ecdc9f456e Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3350 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit ab12e305fcd303972c17e8b9e777cc1482aadf37 Author: Vijay Bellur Date: Sat May 12 23:14:13 2012 +0530 configure.ac: Update version to 3.3git Change-Id: I6f42bfe920fff5166d2424e8fc08f1286297e2e1 BUG: 820551 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3318 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 8852f95869139c03d9504887a95a6ca52b5d65e0 Author: Vijay Bellur Date: Fri May 11 11:23:58 2012 +0530 build: Include COPYING-{LGPLV3,GPLV2} and remove COPYING Change-Id: Ib7867a79b3831b24b5f26cfee44b87e72f6be09b BUG: 820551 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3312 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 8707fac1f92415f9fc05dc6484026a66e6e7873b Author: Vijay Bellur Date: Fri May 11 11:32:01 2012 +0530 Update rfc.sh to release-3.3 Change-Id: I9452d9166ae0a441ed1dc09613e836f2262fd1f3 BUG: 820551 Reviewed-on: http://review.gluster.com/3311 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4ab1c326f3862714b960302f06c6323d6291b695 Author: Vijay Bellur Date: Thu May 10 22:18:20 2012 -0700 Revert "fuse: allow requests during mount (needed for SELinux labels)" This reverts commit 7d0397c2144810c8a396e00187a6617873c94002. commit 7319017fae450af1d8988bc3a95eec40d913e701 Author: Kaleb KEITHLEY Date: Tue May 8 07:21:17 2012 -0400 license: dual license under GPLV2 and LGPLV3+ Note that the license was not changed in any of the following: .../argp-standalone/... .../booster/... .../cli/... .../contrib/... .../extras/... .../glusterfsd/... .../glusterfs-hadoop/... .../mod_clusterfs/... .../scheduler/... .../swift/... The license was not changed in any of the non-building xlators. The license was not changed in any of the xlators that seemed — to me — to be clearly server-side only, e.g. protocol/server Note too that copyright was changed along with the license; I did not change the copyright in files where the license did not change. If you find any errors or ommissions please don't hesitate to let me know. The complete list of files with the license change is: libglusterfs/src/byte-order.h libglusterfs/src/call-stub.c libglusterfs/src/call-stub.h libglusterfs/src/checksum.c libglusterfs/src/checksum.h libglusterfs/src/circ-buff.c libglusterfs/src/circ-buff.h libglusterfs/src/common-utils.c libglusterfs/src/common-utils.h libglusterfs/src/compat-errno.c libglusterfs/src/compat-errno.h libglusterfs/src/compat.c libglusterfs/src/compat.h libglusterfs/src/daemon.c libglusterfs/src/daemon.h libglusterfs/src/defaults.c libglusterfs/src/defaults.h libglusterfs/src/dict.c libglusterfs/src/dict.h libglusterfs/src/event-history.c libglusterfs/src/event-history.h libglusterfs/src/event.c libglusterfs/src/event.h libglusterfs/src/fd-lk.c libglusterfs/src/fd-lk.h libglusterfs/src/fd.c libglusterfs/src/fd.h libglusterfs/src/gf-dirent.c libglusterfs/src/gf-dirent.h libglusterfs/src/globals.c libglusterfs/src/globals.h libglusterfs/src/glusterfs.h libglusterfs/src/graph-print.c libglusterfs/src/graph-utils.h libglusterfs/src/graph.c libglusterfs/src/hashfn.c libglusterfs/src/hashfn.h libglusterfs/src/iatt.h libglusterfs/src/inode.c libglusterfs/src/inode.h libglusterfs/src/iobuf.c libglusterfs/src/iobuf.h libglusterfs/src/latency.c libglusterfs/src/latency.h libglusterfs/src/list.h libglusterfs/src/lkowner.h libglusterfs/src/locking.h libglusterfs/src/logging.c libglusterfs/src/logging.h libglusterfs/src/mem-pool.c libglusterfs/src/mem-pool.h libglusterfs/src/mem-types.h libglusterfs/src/options.c libglusterfs/src/options.h libglusterfs/src/rbthash.c libglusterfs/src/rbthash.h libglusterfs/src/run.c libglusterfs/src/run.h libglusterfs/src/scheduler.c libglusterfs/src/scheduler.h libglusterfs/src/stack.c libglusterfs/src/stack.h libglusterfs/src/statedump.c libglusterfs/src/statedump.h libglusterfs/src/syncop.c libglusterfs/src/syncop.h libglusterfs/src/syscall.c libglusterfs/src/syscall.h libglusterfs/src/timer.c libglusterfs/src/timer.h libglusterfs/src/trie.c libglusterfs/src/trie.h libglusterfs/src/xlator.c libglusterfs/src/xlator.h libglusterfsclient/src/libglusterfsclient-dentry.c libglusterfsclient/src/libglusterfsclient-internals.h libglusterfsclient/src/libglusterfsclient.c libglusterfsclient/src/libglusterfsclient.h rpc/rpc-lib/src/auth-glusterfs.c rpc/rpc-lib/src/auth-null.c rpc/rpc-lib/src/auth-unix.c rpc/rpc-lib/src/protocol-common.h rpc/rpc-lib/src/rpc-clnt.c rpc/rpc-lib/src/rpc-clnt.h rpc/rpc-lib/src/rpc-transport.c rpc/rpc-lib/src/rpc-transport.h rpc/rpc-lib/src/rpcsvc-auth.c rpc/rpc-lib/src/rpcsvc-common.h rpc/rpc-lib/src/rpcsvc.c rpc/rpc-lib/src/rpcsvc.h rpc/rpc-lib/src/xdr-common.h rpc/rpc-lib/src/xdr-rpc.c rpc/rpc-lib/src/xdr-rpc.h rpc/rpc-lib/src/xdr-rpcclnt.c rpc/rpc-lib/src/xdr-rpcclnt.h rpc/rpc-transport/rdma/src/name.c rpc/rpc-transport/rdma/src/name.h rpc/rpc-transport/rdma/src/rdma.c rpc/rpc-transport/rdma/src/rdma.h rpc/rpc-transport/socket/src/name.c rpc/rpc-transport/socket/src/name.h rpc/rpc-transport/socket/src/socket.c rpc/rpc-transport/socket/src/socket.h xlators/cluster/afr/src/afr-common.c xlators/cluster/afr/src/afr-dir-read.c xlators/cluster/afr/src/afr-dir-read.h xlators/cluster/afr/src/afr-dir-write.c xlators/cluster/afr/src/afr-dir-write.h xlators/cluster/afr/src/afr-inode-read.c xlators/cluster/afr/src/afr-inode-read.h xlators/cluster/afr/src/afr-inode-write.c xlators/cluster/afr/src/afr-inode-write.h xlators/cluster/afr/src/afr-lk-common.c xlators/cluster/afr/src/afr-mem-types.h xlators/cluster/afr/src/afr-open.c xlators/cluster/afr/src/afr-self-heal-algorithm.c xlators/cluster/afr/src/afr-self-heal-algorithm.h xlators/cluster/afr/src/afr-self-heal-common.c xlators/cluster/afr/src/afr-self-heal-common.h xlators/cluster/afr/src/afr-self-heal-data.c xlators/cluster/afr/src/afr-self-heal-entry.c xlators/cluster/afr/src/afr-self-heal-metadata.c xlators/cluster/afr/src/afr-self-heal.h xlators/cluster/afr/src/afr-self-heald.c xlators/cluster/afr/src/afr-self-heald.h xlators/cluster/afr/src/afr-transaction.c xlators/cluster/afr/src/afr-transaction.h xlators/cluster/afr/src/afr.c xlators/cluster/afr/src/afr.h xlators/cluster/afr/src/pump.c xlators/cluster/afr/src/pump.h xlators/cluster/dht/src/dht-common.c xlators/cluster/dht/src/dht-common.h xlators/cluster/dht/src/dht-diskusage.c xlators/cluster/dht/src/dht-hashfn.c xlators/cluster/dht/src/dht-helper.c xlators/cluster/dht/src/dht-inode-read.c xlators/cluster/dht/src/dht-inode-write.c xlators/cluster/dht/src/dht-layout.c xlators/cluster/dht/src/dht-linkfile.c xlators/cluster/dht/src/dht-mem-types.h xlators/cluster/dht/src/dht-rebalance.c xlators/cluster/dht/src/dht-rename.c xlators/cluster/dht/src/dht-selfheal.c xlators/cluster/dht/src/dht.c xlators/cluster/dht/src/nufa.c xlators/cluster/dht/src/switch.c xlators/cluster/stripe/src/stripe-helpers.c xlators/cluster/stripe/src/stripe-mem-types.h xlators/cluster/stripe/src/stripe.c xlators/cluster/stripe/src/stripe.h xlators/features/index/src/index-mem-types.h ¹ xlators/features/index/src/index.c ¹ xlators/features/index/src/index.h ¹ xlators/performance/io-cache/src/io-cache.c xlators/performance/io-cache/src/io-cache.h xlators/performance/io-cache/src/ioc-inode.c xlators/performance/io-cache/src/ioc-mem-types.h xlators/performance/io-cache/src/page.c xlators/performance/io-threads/src/io-threads.c xlators/performance/io-threads/src/io-threads.h xlators/performance/io-threads/src/iot-mem-types.h xlators/performance/md-cache/src/md-cache-mem-types.h xlators/performance/md-cache/src/md-cache.c xlators/performance/quick-read/src/quick-read-mem-types.h xlators/performance/quick-read/src/quick-read.c xlators/performance/quick-read/src/quick-read.h xlators/performance/read-ahead/src/page.c xlators/performance/read-ahead/src/read-ahead-mem-types.h xlators/performance/read-ahead/src/read-ahead.c xlators/performance/read-ahead/src/read-ahead.h xlators/performance/symlink-cache/src/symlink-cache.c xlators/performance/write-behind/src/write-behind-mem-types.h xlators/performance/write-behind/src/write-behind.c xlators/protocol/auth/addr/src/addr.c ¹ xlators/protocol/auth/login/src/login.c ¹ xlators/protocol/client/src/client-callback.c xlators/protocol/client/src/client-handshake.c xlators/protocol/client/src/client-helpers.c xlators/protocol/client/src/client-lk.c xlators/protocol/client/src/client-mem-types.h xlators/protocol/client/src/client.c xlators/protocol/client/src/client.h xlators/protocol/client/src/client3_1-fops.c ¹ Copyright only, license reverted to original Change-Id: If560e826c61b6b26f8b9af7bed6e4bcbaeba31a8 BUG: 820551 Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3304 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f6694199e637f67051b02ae423a4823a1594ee50 Author: Kaleb KEITHLEY Date: Wed May 9 14:06:58 2012 -0400 glusterfs.spec.in, Add BuildRequires: libxml2-devel so that configure will DTRT on Fedora's Koji build system Change-Id: I14a64d2e562282e4e7d1d37b526c112c9f343454 BUG: 819916 Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3305 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Joe Julian Reviewed-by: Anand Avati commit 72da7808cb0497b4ac6df55c58c9bf34daeee7ac Author: Krishnan Parthasarathi Date: Thu May 10 15:48:22 2012 +0530 locks: Set flock.l_type on successful F_UNLCK to signal last unlock on fd. NLM expects a successful F_UNLCK on an fd to set flock.l_type to F_UNLCK if it were the last unlock else F_RDLCK. Change-Id: Ib304ac6102664abbb13d1fda649b3da63f1ee97e BUG: 800300 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3306 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas Reviewed-by: Anand Avati commit 4789058d916de596720213154cd1e2f73695aa13 Author: Vijay Bellur Date: Thu May 10 22:22:45 2012 +0530 build: Include protocol/server* shared libraries in the glusterfs-server rpm Change-Id: I46354dd8c0e9c9d81366d3e92af4a24a9d2c568a BUG: 764702 Reviewed-on: http://review.gluster.com/3308 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Kaleb KEITHLEY Reviewed-by: Anand Avati commit 17b0814243b4ccd56c0ce570b7f42d5e572e1e71 Author: Amar Tumballi Date: Thu May 3 16:39:55 2012 +0530 geo-replication: coverity resource leak fixes Change-Id: I5739e9c9ae6fe78a6defb640d630e5f918ac1295 Signed-off-by: Amar Tumballi BUG: 789278 Reviewed-on: http://review.gluster.com/3266 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 53a09f49abb291625c96409627cba348f0c35e55 Author: Vijay Bellur Date: Sun Apr 29 23:08:42 2012 +0530 mgmt/glusterd: Avoid re-starting nfs unconditionally. NFS server is restarted unconditionally when a volume option is configured through the set interface. This patch prevents restart of NFS server when operations are performed on translators that are not part of the NFS graph. This does not prevent re-start of a NFS server when an option corresponding to a translator that is part of the NFS graph is re-configured. Change-Id: Ic4b8e48e5e7e80438f230521042c267ec3b96a25 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3247 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Anand Avati commit 8af87a7ff4da6791a339e2bdb159a4b0c4a66c30 Author: shishir gowda Date: Fri Apr 20 18:49:40 2012 +0530 cluster/dht: rmdir should succeed last on the hashed subvol mkdir and rename both first happen on the hashed subvol. Rmdir should succeed, only if all non hashed subvol succeed, and finally removal from hashed_subvol succeeds. if hashed_subvol is unavailable, then rmdir should be sent on all subvols Change-Id: I1bf5d5fc25393d0e2fde13ae403cf867a01f5ec7 BUG: 773187 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3202 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit fc481386d296921d883d1b8678795eb45bb8b8b7 Author: Kaushal M Date: Tue May 8 13:57:31 2012 +0530 glusterfsd: Make sure mountpoint is an absolute path If the mountpoint path given to glusterfs is not an absolute path, convert it to an absolute path by concatenating it with the curren working directory. This prevents cases, where in gluster cannot perform clean unmounts when mount is done with a relative path. Change-Id: Ie25add4e1dc59171e522c4244c79a6c148844ab3 BUG: 819466 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3302 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 27fb213be6101bca859502ac87dddc4cd0a6f272 Author: Raghavendra G Date: Mon Mar 26 18:44:14 2012 +0530 fuse-resolve: consider cases where an entry should be resolved even when parent belongs to active itable. When parent is root, the parent inode returned will always be active_subvol->itable->root and hence there can be cases where we should explicitly resolve the entry in active graph. Change-Id: I4e82df9a351ff6b5304891abc9932495bf7ea79d BUG: 804592 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3007 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d6244e238976e45ccb8c64ab4a0fe443fe44c952 Author: Brian Foster Date: Thu May 3 10:09:27 2012 -0400 quick-read, md-cache: selectively cache xattr data to conserve memory The md-cache translator can cache items for a long period of time and thus is sensitive to memory usage associated with the items it references. This implements two changes to help conserve memory: - quick-read - Migrate the file content data to a local dict and delete from the xdata dict that passes through the stack. - md-cache - Create a local dict to selectively store the xattr data md-cache is interested in. This includes a slight optimization to not allocate an empty dict in the case where we have not received any xattr's of interest. I've tested both changes independently and together by running a readdirp test against several compiled source trees (~340k files). The base test results in a 7.7GB RSS on the client. The quick-read modification cuts RSS down to 4.1GB, which is still large due to md-cache unintelligently caching a large number of empty dictionaries. The combined modification cuts RSS down to 462MB on the same workload. NOTE: Theoretically the md-cache change should supercede the quick-read change, but practically I save an extra 150MB or so with both. I already had the change and consider it an improvement that quick-read clean up after itself. BUG: 812876 Change-Id: Id59734d12dd6476b0e32480939e633448adb6884 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3268 Tested-by: Gluster Build System Reviewed-by: Raghavendra G Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy commit 11a19ce031932640584f8bc207274f4e08d97c5f Author: Pranith Kumar K Date: Fri Apr 27 18:43:23 2012 +0530 Resolve: Assign correct path while resolving Change-Id: Ia17ff38a60225dd2e9115aaa298bed42f9e43f56 BUG: 812277 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3248 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f233e26f99decc0b2552ed10cd81c30c684139ac Author: Pranith Kumar K Date: Fri Apr 27 16:15:12 2012 +0530 mgmt/gluster: Load index xlator on brick always Change-Id: I56e4fce83a6bd557a3d0dc115a7dd0cd699328e0 BUG: 816941 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3239 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 44a1857e544f64e10e8bfb4641bedd841910a6c6 Author: Kaushal M Date: Fri May 4 15:13:03 2012 +0530 protocol/{client,server} : Log improvements Make use of gfid in log messages. Change-Id: I28548be64d19418f99ee9ccdbd3ac4ae67c6c015 BUG: 814666 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3274 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit eb7c8dd03d84d7c3917d18a59d86c379382c8b2d Author: Amar Tumballi Date: Sat May 5 09:54:22 2012 +0530 glusterd: remove-brick: add more error handling with this, we can make sure, all wrong patterns in CLI can be reported with proper message back to user, instead of resulting in an wrong volume type. Change-Id: Ib461956dd7d51f7f81c19c27112d44c2adb3a66d Signed-off-by: Amar Tumballi BUG: 803711 Reviewed-on: http://review.gluster.com/3278 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Vijay Bellur commit c4dadc74fd1d1188f123eae7f2b6d6f5232e2a0f Author: Pranith Kumar K Date: Wed Apr 18 17:30:39 2012 +0530 Self-heald: Dump the event history completely Change-Id: Icf08ef1752795276f88c343d1d74af104095c6cb BUG: 796579 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3276 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ca5861fdf9fdf9c29523893418312bdf1796c28e Author: Pranith Kumar K Date: Wed Apr 25 14:58:31 2012 +0530 cluster/afr: Fix inodelk-trace logs to print lk-owners Change-Id: Icc983effcf1b6283410a162f260755e97d41ee65 BUG: 810502 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3228 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c5d9ac3477d295b5e97166ac655a52463a0d1fb8 Author: Pranith Kumar K Date: Mon Apr 23 19:58:41 2012 +0530 cluster/afr: Perform Flush with lk-owner given by parent xlator. Lk-owner of posix-lk and flush should be same, flush can't clear posix-lks without that lk-owner. Change-Id: If775abb5741a0beb00c419b54d023fbd429e3cb7 BUG: 810502 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3221 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0caffe52b8db6670dfa2b1c825477ede7ba304c6 Author: Raghavendra G Date: Tue May 1 10:50:50 2012 +0530 protocol/client: hold lock when cancelling ping_timer in client_ping_cbk. Change-Id: I2b4e723ef119c62902f8a692a8a1f424da0d08b4 BUG: 816951 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3254 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 9bd1b291e3e107250b38d05702df7cd751382bdc Author: Krishna Srinivas Date: Mon Apr 30 16:43:16 2012 +0530 libglusterfs/inode.c: do not link the inode in the dentry cache for "." and ".." Change-Id: I18c2e090c1ca64f47ce70dc63c9f73ea7def2f86 BUG: 810828 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3220 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 298ff93eab48de51a1bd77e4b12e88a7add1d174 Author: shishir gowda Date: Thu May 3 15:56:15 2012 +0530 glusterd/store: Move remove-brick/rebalance status to node_state.info Hence forth, all node related info, which does not need chksum or versioning can be stored in this file. This data might not be in sync across nodes, as it contains only information related to local node. Change-Id: I88a48c1b7bb7b4c29625550a9ff349442bcc5d09 BUG: 812234 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3141 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4ec3c04a43b89fc76c8919aadfe28fb0b8990cd0 Author: Pranith Kumar K Date: Sat May 5 16:50:18 2012 +0530 mgmt/glusterd: allow volume start force Change-Id: If920bf0bf96b61b39bccbb10e66f5f39a55967f5 BUG: 812214 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3279 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 530a44a7c936dca76bda30bd40abdcc47c21fa7f Author: Mohammed Junaid Date: Wed Apr 11 08:55:46 2012 +0530 swift: Gluster object storage plugin for Openstack Swift. Change-Id: I5e07339064b1f3bb2aa5b04740ed870e114db4f9 BUG: 811430 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3118 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3651c7425ef41eae70d86b67151b62e8b6d5a3fc Author: Kaushal M Date: Fri May 4 12:27:16 2012 +0530 mount.glusterfs: Fix log-level Change-Id: Ia5ad073ba384e1569970ada8763a8bf9bccbc9c4 BUG: 818835 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3272 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 44c152bd8feb089b8b6d7124f88d0d97cd80bdf2 Author: Pranith Kumar K Date: Fri Apr 6 15:19:59 2012 +0530 self-heald: loc should have gfid path for better logging Change-Id: I31e51c8bd68a72ea2216df306a2f5c738c5d155c BUG: 810144 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3099 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 66701832cf2db0fc3fc55bc99d01d4b0f1cb6a2a Author: Pranith Kumar K Date: Fri Apr 6 15:43:31 2012 +0530 self-heald: Don't trigger self-heal always. - If self-heal is disabled, the crawl is always spawned but immediately terminated upon realizing that the self-heal-daemon is disabled. Fixed it. - If for some reason finding child position fails, it should still spawn timer and should keep the timer alive until the position is found to be REMOTE. Change-Id: I20cc6af93a1ff26f2b837bbf063bbe508b5fdc78 BUG: 810144 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3100 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 352f09f8eb5c2487612e6e6afa20742c9b9d6df4 Author: Krishnan Parthasarathi Date: Fri May 4 12:00:14 2012 +0530 extras/hook-scripts: Fixed EXTRA_DIST to explicitly list *.sh files Change-Id: I48785317b42e37a6e7768c89bdb7ca8ac41220fa BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3271 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit cfaf9989e63dda0cc8e4e2c5e42bcd4ad4e43c4b Author: shishir gowda Date: Wed May 2 11:59:35 2012 +0530 stripe: don't send parent pointer in stripe_readdirp_lookup() Change-Id: I53e28f4046c13ad13c9300990a95480a5c62f180 BUG: 808353 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3232 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e4b3c0d90c46e6dde97f57fa93ed215b0d34e0c4 Author: Amar Tumballi Date: Thu Apr 12 17:52:10 2012 +0530 iobuf: option to provide larger size of buffers provide an option to failover to standard allocation if iobuf of required size doesn't exists. this can be achieved by keeping an arena dedicated for all the out of boundary allocations. Change-Id: I41a2bd7d353dc7bcb2e1a6e4b41735afe9865975 Signed-off-by: Amar Tumballi BUG: 812784 Reviewed-on: http://review.gluster.com/3136 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d879951ca9e69632517cf13f8f8773c330c14165 Author: shishir gowda Date: Thu May 3 12:45:25 2012 +0530 glusterd/rebalance: Switch off afr self heal in rebalance process. Self heal if any will be taken care of the self heal daemon. Change-Id: I4f3c270b6fce250cbdf6f986066f64e7c4b2f29f BUG: 808977 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3263 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 3b47032cbec05ebd90a73e362eaf2653789a09bc Author: Amar Tumballi Date: Wed May 2 14:23:27 2012 +0530 cli: fix remove-brick output behavior in failure cases earlier it was dependant on server sending the dict for knowing the command. Now it preserves the dictionary in frame->local, which is used to understand the command. Change-Id: Ica675b497e466f77878f67792ae96b71f0704d6b Signed-off-by: Amar Tumballi BUG: 815745 Reviewed-on: http://review.gluster.com/3235 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 5f48ad266195ec85171db48cf3dba83f98cbe728 Author: Krishnan Parthasarathi Date: Wed May 2 18:38:52 2012 +0530 glusterd: Added glusterd command specific optional args for hooks scripts. start volume: --first=yes if the volume is the first to be started and --first=no otherwise stop volume: --last=yes if the volume is the last to be stopped and --last=no otherwise set volume: -o key=value ... for every key, value supplied in volume set command Change-Id: Ia8530771f8b9d7424fd1c736cb4c3622b5cabec2 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3260 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit d88237faa6982c9f0beca65262a220becaacb096 Author: Raghavendra Bhat Date: Wed May 2 16:29:49 2012 +0530 cluster/pump: Fixed fd leaks in pump directory traversal logic Change-Id: Ie54c8c9b19be6824445ada6bbcd4983e90a7c5c4 BUG: 818593 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3267 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7509afb03da6fe9a0f07e902869f44d4ff545fa7 Author: Amar Tumballi Date: Thu Apr 26 15:41:10 2012 +0530 RPC: change the AUTH_GLUSTERFS_v2 value to private range As per RFC5531, the value we were using with AUTH_GLUSTERFS_v2 (6) is already a standard number for RPCSEC_GSS. Hence having a number from the free pool for now, till IANA approves a standard number for GlusterFS RPC itself. Change-Id: I10ef6f349bccf3cf42fadfa3861c374adae2a808 Signed-off-by: Amar Tumballi BUG: 816148 Reviewed-on: http://review.gluster.com/3230 Tested-by: Gluster Build System Reviewed-by: Niels de Vos Tested-by: Niels de Vos Reviewed-by: Anand Avati commit c204e8c2713678e990b74c98f9eda8f18d714b3d Author: Amar Tumballi Date: Sun Apr 29 09:32:43 2012 +0530 protocol: fix memory leak of lk-owner buffer in *lk() calls Change-Id: I7fb0e1757c5e04b1a2609c9822ac79301808f671 Signed-off-by: Amar Tumballi BUG: 768330 Reviewed-on: http://review.gluster.com/3244 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit a2ca310cd334bc4c3387107a0931f695efac5ba9 Author: Krishnan Parthasarathi Date: Sat Apr 14 11:58:28 2012 +0530 glusterd: Disallow (re)-using bricks that were part of any volume Change-Id: I001a67bed1cc3118174a5ddc2f2011e8e48d8ae8 BUG: 812214 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3147 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit b8cfc761bd7a664a4ed73999e898973c9718ecee Author: Pranith Kumar K Date: Fri May 4 00:29:40 2012 +0530 cluster/afr: Fix race in nonblocking entrylk Change-Id: I6d96c1aed4bf08b90b6918e3694c688eccdc2445 BUG: 818578 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3270 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 9b3def01e4b6c7c3e6899e4ad52ee64440285f54 Author: Pranith Kumar K Date: Mon Apr 30 07:29:16 2012 +0530 libgluster: Fix counting, synctask state errors When a synctask is executed in synctask_switchto, if by the time it goes to check the woken/sleep part a reply already comes and __wake is called, already running task is going to be put in runq this generates a false warning "re-running already running task". If the reply does not come before the woken/sleep check, then the running task is put in waitq which decrements env->runcount even when the task is not in runq, this leads to -ve runcount everytime a task goes from runq->switchto->waitq. This patch fixes both of them by introducing a new state for the task called SYNCTASK_SUSPEND just when the task is suspended before yeild in SYNCOP. Change-Id: Ib82182cf950f9d85b5656f6243541489a104ca3d BUG: 816551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3249 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 170a3a411c88f6ce1662c55440a372f512e901d1 Author: Amar Tumballi Date: Wed May 2 11:38:33 2012 +0530 log cleanup: in setxattr() path * in posix we log occassionally if errno is ENOTSUP, added a suggestion to mount with 'user_xattr' option. * changed server's *etxattr_cbk to log ENOTSUP in debug level. * changed client's *etxattr_cbk to log ENOTSUP in debug level. Change-Id: Icd604050aaa68546011f2c950ecd7883ac6ee820 Signed-off-by: Amar Tumballi BUG: 811957 Reviewed-on: http://review.gluster.com/3140 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 7ee1c22353e3af4153d1716a5f3629615de4510e Author: Krishnan Parthasarathi Date: Wed Apr 18 18:16:30 2012 +0530 extras: Added hook script to help in CTDB setup Change-Id: Ib43cd3583e791aabc8cc25fe4eea43a620f73d01 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3188 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 3d5d5846d86b305955c1f1fcd1f426b5ecb1df6f Author: Raghavendra Bhat Date: Thu Apr 26 20:07:32 2012 +0530 glustershd: allow changing of log-level through cli Change-Id: Ie33ad4f4ffcb025b22801d6beb9b87d8325021a0 BUG: 815903 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3234 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 69a946bfea058bd5f9776343d7ccc1864d4a81b8 Author: Rajesh Amaravathi Date: Wed May 2 10:31:27 2012 +0530 rpcsvc: size check before calloc in rpcsvc_handle_disconnect Change-Id: Ib9e9e28b4fd3d68ebd4b5dcbd0ee4576217b9d4f BUG: 782761 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3257 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 1c825e5f2498ec586c0e9123c472f6d134706e08 Author: Raghavendra Bhat Date: Fri Apr 27 14:34:07 2012 +0530 mgmt/glusterd: take the statedumps of running bricks if one of the bricks is down Till now if one of the bricks of the volume is down, then statedump of that volume (bricks) did not take the statedumps of running bricks. This patch fixes that issue and cli command will take the statedumps of running brick processes. Change-Id: Id9b11905d3d759202e505c2ecfa6ccd5dce6a9ff BUG: 816884 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3237 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 3dd38a4a35885adf6ac2e0c6c4e38d36ab862441 Author: Emmanuel Dreyfus Date: Sun Apr 29 09:51:06 2012 +0200 get rid of ZR_PATH_MAX As suggested by Amar Tumballi Change-Id: Id1cd74fd7530e8c846f3be4a88b1fa301a728cf1 BUG: 764655 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3243 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit d09a5beae2d26803b67ab8f3de6862044a8a758c Author: Raghavendra Bhat Date: Mon Apr 30 16:18:50 2012 +0530 libglusterfs/fd: use reallocated memory for intializing new graphs contexts While setting fd_ctx, if we have to scale the fd contexts, then we get the xl_count of the new graph and reallocate the memory for contexts so that it is suffecient for contexts of xlators of both new as well as old graph, and then initialize the new graph xlator contexts. For that we are considering the old pointer itself, instead of using newly reallocated pointer. Change-Id: I32c18cd69c03c771b4a63e5186c65ae658e54e92 BUG: 817461 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3250 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 67ceb347c83e3b994791feb58fc607475fa1177e Author: Kaleb KEITHLEY Date: Mon Apr 30 09:36:38 2012 -0400 contrib/rbtree: additional license from Richard Fontana BUG: 807724 Change-Id: I1e9a7aac7b535687b9e48bdb0e94c7f52dc6aad7 Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3252 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 99bdbb2ed9697bb93f006d4060d4f1aaeb0850af Author: Krishnan Parthasarathi Date: Wed Apr 18 15:45:44 2012 +0530 glusterd: Fail replace-brick subcmds on bricks other src/dst. Change-Id: I5b55d3e353e70a9d4d8b7948853cbfa5b001a447 BUG: 811956 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3184 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 4c84a4cd5e5e563e1e91656f7462b4c444e5f4e6 Author: Amar Tumballi Date: Fri Apr 27 13:20:21 2012 +0530 storage/posix: fix illegal memory access in fgetxattr() we were not checking for the return value of the fgetxattr(key), and used to continue with the allocation even if size was -1, leading to wrong memory access. Change-Id: Ib5cf2e74fee95bc919b12efe89fed5cd25807efd Signed-off-by: Amar Tumballi BUG: 815346 Reviewed-on: http://review.gluster.com/3236 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit f9ca9f09ce47715573d0ae2b5e174e8b63185b56 Author: shishir gowda Date: Fri Apr 27 16:19:38 2012 +0530 storage/posix: Fix leak of dict in getxattr calls. get_new_dict does not take a ref. Ref was taken only when any data was added to the dict. But in the out tag: we call explicit unref, which would move the ref count to -1, if it was a unsuccessful call. unref destroys the dict only if ref == 0. Change-Id: Ie08c301237c2042daf90a7ef25569e3b06e3e1e9 BUG: 816870 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3240 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit c3a16c32f5bd1924766d5844c100d5aa6ce8c392 Author: Krishna Srinivas Date: Tue Mar 13 20:49:35 2012 +0530 nfs: use hostname without port numbers Change-Id: I7c4cba84723a9ca73f1d1f1e9a2c479a2bfd14fe BUG: 798969 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/2973 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8b6534031ab9b60da293e9c2ffb95141d714f973 Author: Raghavendra G Date: Fri Apr 20 11:41:20 2012 +0530 libglusterfs/fd.c: Dynamically scale fd->_ctx when there are no slots for new keys. Since while migrating fds to new graph we retain the same fd object, we might run out of slots for new keys in fd->_ctx after some graph switches. Change-Id: I1e3865c76f4703768f9b10b0453558877c2f5448 BUG: 811562 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3201 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 4213745eba97ffe1e2bdb13446fe2fd87e7c6fef Author: Raghavendra G Date: Tue Mar 27 15:31:50 2012 +0530 features/quota: update inode ctx in reconfigure. Till this patch, quota was relying on lookups after reconfigure, for new limits to be effective. However, this might be restrictive for users who don't want to change directories after resetting quota limits. Change-Id: I236aa31fdc7dcbc01d40d38c9b5b7b0a28a4d2ea BUG: 802905 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3022 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Jeff Darcy Tested-by: Amar Tumballi Reviewed-by: Vijay Bellur commit ecb818902e4ee7491aaeae21226b62a0ab806370 Author: Kaushal M Date: Thu Apr 26 14:28:05 2012 +0530 cli: Make use of cli_err() Use cli_err() in case of errors instead of cli_out(). Change-Id: Ib0766e59516a1ccd56a2133f33fac3877c4384d6 BUG: 815194 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3229 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 81df001b3efb2313e68745abd84f02e24fba6e67 Author: Krishna Srinivas Date: Thu Apr 26 17:42:11 2012 +0530 nlm: use correct subvolume when opening the file Change-Id: Ia0a482c89f10481184dc8f0f5b27cf6612ac114a BUG: 816476 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3233 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6db7f8f173d30313ab9f1d88e7a6398ac97fdf8d Author: Kaushal M Date: Thu Apr 26 15:57:42 2012 +0530 glusterfsd: Change a free() to GF_FREE() Change-Id: I19bad33864b67e7ac79d8c5e642efa19dbc5bd80 BUG: 816163 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3231 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit bb55a0c967a829a0b5eb5a4883d86540511a9d1c Author: Kaleb KEITHLEY Date: Mon Mar 26 11:16:11 2012 -0400 contrib/rbtree license GPL -> LGPL The latest source of rb.c in the avl-2.0.3 package from GNU/FSF is now licensed under LGPL, a better license for allowing our partners to write translators and applications for gluster. Resubmitting with a BZ. The real question is whether this is okay with LGPL or whether we should go all the way to a BSD-licensed implementation. Change-Id: Ifb9c344c84d960832671a2619d37b925e4dede2d BUG: 807724 Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3008 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 8afd8abd982442155d727aaec82c76706d77b84f Author: Pranith Kumar K Date: Fri Apr 6 12:49:34 2012 +0530 cluster/afr: Log enhancements Change-Id: I12918cb0a4e85310d4463bc3e75e7c89565a3218 BUG: 810144 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3098 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e8f9d42504126f8af6bbb8d160925148ad44c5de Author: Krishnan Parthasarathi Date: Tue Apr 24 19:39:40 2012 +0530 pump: Removed extra dict_unref in pump_command_reply afr_local_cleanup is already performing the dict_unref on local->dict. Change-Id: I07bcb100db0a0b96b3a698c444f43f96065746fb BUG: 804905 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3223 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 8be3e656aa58e790c301c9078afdbd4bd4909d92 Author: shishir gowda Date: Tue Apr 24 10:39:31 2012 +0530 glusterd/rebalance: Remove state dependency on rpc event Status is updated by event_notify handshake by the rebalance process. If there is disconnect, before rebalance process, only then the state is moved to failure. Change-Id: I334055397c3d38688dbef653826bc07ac47a1911 BUG: 813167 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3165 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit bd892b972eb5df5d3f48637cc473f9622684087d Author: shylesh Date: Wed Apr 25 03:00:28 2012 -0400 cli: Show proper remove-brick usage Change-Id: I669736b34f50caa146eea47dcd8c081f6436a585 BUG: 816051 Signed-off-by: shylesh Reviewed-on: http://review.gluster.com/3224 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Shishir Gowda commit 8f2eba00fd315b42aeaa01d683b765fbd2ee111b Author: shishir gowda Date: Tue Apr 24 10:27:18 2012 +0530 rebalance: handshake_event_notify to make fsd talk to glusterd Event_notify can be used by others to communicate with glusterd. A cbk event is also added for future use. req has a op, and dict. rsp has op_ret, op_errno, and dict. With this, rebalance process can update the status before exiting. Signed-off-by: shishir gowda Change-Id: If5c0ec00514eb3a109a790b2ea273317611e4562 BUG: 807126 Reviewed-on: http://review.gluster.com/3013 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 3f35280a364bd35293d3e5804eb2a659a7f174b1 Author: Amar Tumballi Date: Mon Apr 23 11:11:43 2012 +0530 cli: implement a fn 'cli_err()' to send error messages to 'stderr' we were using 'cli_out()' to send all the possible msgs, which is not very friendly with scripts, because if one want to get only valid output with " 2>/error.log 1>/proper-info.log" Change-Id: I008ebcbd90935c41dbfc1bd2adeb094ed21116cb Signed-off-by: Amar Tumballi BUG: 815194 Reviewed-on: http://review.gluster.com/3208 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Vijay Bellur commit 90d5d569b5a2333094ba8741bb29fe040b695b23 Author: Kaushal M Date: Tue Apr 24 10:32:53 2012 +0530 glusterd: glusterd_op_build_payload() fix for geo-rep Change-Id: I9f625022fa6d70ccda70d197e4124fa73be8e776 BUG: 815603 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3215 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 4a0f5e49f85f88912cc9c73b379403ead82e4912 Author: Amar Tumballi Date: Tue Apr 24 16:36:52 2012 +0530 glusterd: command check failure fixes due to the patch 29f2de478cc6a475e6ae760d9cbe7ac847e9d79c (coverity issues fix), geo-replications assumption of anything other than -2 is valid error (ie, expected error), was broken, which resulted in staging failure of all geo-replication commands. now fixed!!! Change-Id: I26c3574e966dd8ba89ef423a3ad17aa863a62c13 Signed-off-by: Amar Tumballi BUG: 815613 Reviewed-on: http://review.gluster.com/3219 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2a59514236630756dc996e08b50f539ccc2d3ff0 Author: Raghavendra Bhat Date: Tue Apr 24 18:40:00 2012 +0530 mount/fuse: unref the fds after they have been migrated to the new graph In fuse upon graph changes fds were being migrated to the new graph. It was done by taking all the fds from the fdtable in a structure and then migrating each fd in the structure to the new graph. But after the fds are migrated the structure which had the fds within it (that is refed fds) was being freed without unrefing the fds, thus leading to a fd leak. Change-Id: I7b25220a48954384a004373d378cee11c6109f7e BUG: 811552 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3222 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 1fc54cf7c5e2a88cf8f59d98f6e0eb7df485ae80 Author: Anand Avati Date: Mon Apr 23 00:39:14 2012 -0700 statedump: fix deadlock during state dump of fds Existing state dump of FD context tries to be extra safe by trying to call the fd dump callback outside the inode lock. It acheives this by taking an fd ref and unreffing it later. This exercise can be harmful at times when the fd unref performed by state dump ends up being the last unref and triggers fd_destroy. fd_destroy in turn triggers inode_unref which blocks on inode table lock, while the inode table lock was already held by the thread before it even attempted fd ctx dump. The fix takes away the dangerous ref/unref of the fd during state dump and instead calls fd_ctx_dump() whiel the inode lock is held. This is not a problem as long as the dump functions do not call any inode function which tries to take an inode lock (none of the existing fd dump ops do) Change-Id: Ia4b27ba5a321285d3e64896a679a00363bb1e822 BUG: 815242 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3210 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit be2cc2f7ce90b97328d933517ce66169ae89baeb Author: shylesh Date: Tue Apr 24 02:32:32 2012 -0400 cli: Return -1 if fix-layout stop is issued Change-Id: If2e4b842029a1a720403cbec0c076f3dbf1fc6df BUG: 803971 Signed-off-by: shylesh Reviewed-on: http://review.gluster.com/3216 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 19c2d6b3d61e2fcf52e1097de4d70ecbb2966ffd Author: shylesh Date: Tue Apr 24 02:49:52 2012 -0400 dht: Log message fix gfid's to gfids Change-Id: I9ad67b6ded05992d1b56ca843f685c4fe2b15b71 BUG: 815186 Signed-off-by: shylesh Reviewed-on: http://review.gluster.com/3217 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 5d3108d182877795eab118a448d1e21f021d7d9c Author: Raghavendra G Date: Tue Mar 27 15:05:15 2012 +0530 libglusterfs/inode.c: add inode_resolve inode_resolve takes an itable and path as arguments and returns either NULL or the inode corresponding to the path Change-Id: Id42d62cce6b04dbfec7d606120b09a1e54ab484e BUG: 802905 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3021 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Mohammed Junaid Reviewed-by: Anand Avati commit 7313b22f10fafe7773a15d8306496d1d56ef5f81 Author: Emmanuel Dreyfus Date: Fri Mar 30 15:58:43 2012 +0200 NetBSD build fixes Signed-off-by: Emmanuel Dreyfus Change-Id: I8f9aabeadd2f842521a82e59594115bd80155d68 BUG: 2923 Signed-off-by: Emmanuel Dreyfus Reviewed-on: http://review.gluster.com/3053 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 92baa61bfe5853fca301eb1e10f063097df24e2e Author: Csaba Henk Date: Wed Apr 18 16:51:35 2012 +0200 geo-rep / glusterd: update list of reserved tunables (keeping up with http://review.gluster.com/399) Change-Id: Iefc095a65efaa722a980315603f9ad027ee16eba BUG: 764557 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3189 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7cc14db79d4579cfa50c30108fdf67ffa61cb94a Author: Kaushal M Date: Thu Apr 19 14:10:44 2012 +0530 glusterd,glusterfsd : Perform proper cleanup of connections and socket files Perform proper disconnections and cleanup in glusterd on stopping nfs-server and self-heal daemon processes to prevent glusterd from opening unneded unix domain socket connections. glusterfsd processes will cleanup the socket files properly in cleanup_and_exit() to prevent junk socket files. Also, fix rpcsvc_program_unregister() to preform the unregistering properly. Change-Id: I1c7302c1166cf43feba1c7a813c3dc10169dc53a BUG: 810089 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3168 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 7c49e18bb58e91698630f95b67bd52e79ad391ca Author: Raghavendra Bhat Date: Sat Apr 21 16:20:17 2012 +0530 glusterfsd: print entire path of functions whenever serializing a reply fails Change-Id: I72c0296e16c90ec09ecb1678b4c78e8ffd834580 BUG: 814926 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3205 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit cbd13c0c1e2abbd04aff616d9767fc7b95365707 Author: Amar Tumballi Date: Mon Apr 23 10:55:22 2012 +0530 cli: fix the output of 'gluster volume list' make it script friendly Change-Id: I5b196cf5cf1744090a1360eef95c9a842d7be996 Signed-off-by: Amar Tumballi BUG: 815190 Reviewed-on: http://review.gluster.com/3207 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Anand Avati commit 853452410adc284faba03c001f0b25188deeeea8 Author: Csaba Henk Date: Mon Apr 16 17:53:06 2012 +0200 gerrit / rfc.sh: further trim of fetch target We _really_ don't need anything to be fetched from anywhere except for origin. We can do away with all other tracked repos (which still can be a nuisance eg. if they are in a VPN that we are not happen to be joined to). Change-Id: I98b375698f999500153e5a000dc8dac5005dfaec BUG: 764966 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3162 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 29f2de478cc6a475e6ae760d9cbe7ac847e9d79c Author: Amar Tumballi Date: Fri Apr 13 17:29:41 2012 +0530 core: coverity issues fixed this is not a complete set of issues getting fixed. Will address other issues in another patch. Change-Id: Ib01c7b11b205078cc4d0b3f11610751e32d14b69 Signed-off-by: Amar Tumballi BUG: 789278 Reviewed-on: http://review.gluster.com/3145 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 4c9e8fad23836d87b0c4327e990c789630fe5b97 Author: Vijay Bellur Date: Mon Apr 23 12:51:50 2012 +0530 doc: Added admin guide Change-Id: Ic60558dee0d20df0c2a1bf41e4bd072ae4774912 BUG: 811311 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3209 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Tested-by: divya M N Reviewed-by: divya M N Reviewed-by: Anand Avati commit 664daecef49d5e497bb5dd867fc1f51b046d4bf2 Author: Csaba Henk Date: Tue Apr 17 00:19:54 2012 +0200 clean up handling of special client pids - no need to name a lower boundary [drop GF_CLIENT_PID_MIN] - drop utility function to decide about pid speciality [gf_pid_client_check()]; when we implement uniform policy for special pids, use just comparison with GF_CLIENT_PID_MAX (currently such uniform policy exists in io-threads, where special clients get lowest priority) - io-threads: drop numeric literal, use GF_CLIENT_PID_MAX - xattr flipping (in fuse): - fuse_xattr_alloc_default() made static - avoid compiler warnings wrt. partial enum traversal in the switch by not casting the original numeric value to gf_client_pid_t (enum) type - trim down the switch to those cases with which there is something to do [GF_CLIENT_PID_GSYNCD, GF_CLIENT_PID_HADOOP] - eliminate the (theoretical) chance of succesfully returning from fuse_flip_xattr_ns() with unallocated nkey [as was the case with pids GF_CLIENT_PID_{MIN,MAX,DEFRAG}] Change-Id: Ic2b83b908d8e3be23a7fba1e5895869828a6194b BUG: 765433 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3170 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 6fbf369d59cf87b903403699666d99232a372fef Author: Jeff Darcy Date: Thu Apr 19 16:53:19 2012 -0400 Make option code quieter to make logs more readable. A lot of this stuff is extremely uninformative, such as messages about default values that can be read from the code. Having them in the logs makes more important messages harder to find, so they're down to GF_DEBUG_TRACE now. Change-Id: I18921b3deac7a01ad94c50670b90342d1130837b Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3198 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Anand Avati commit 7d0397c2144810c8a396e00187a6617873c94002 Author: Jeff Darcy Date: Mon Apr 23 11:51:22 2012 -0400 fuse: allow requests during mount (needed for SELinux labels) Change-Id: Ia1af402897e6a7290acf79617c34fdc804751729 BUG: 811217 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3199 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit eb9003cdca755980da9ed5a3a3fb0fc52c750131 Author: Pranith Kumar K Date: Mon Apr 23 10:49:02 2012 +0530 libglusterfs: Never block syncproc Change-Id: I64cd8a2ef37926173c19a33df0716183530e22bf BUG: 814074 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3194 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit fc024df2b6f9307f23a4a0800103555708036b17 Author: Raghavendra G Date: Mon Apr 2 16:32:18 2012 +0530 cluster/distribute: handle dht_layout_normalize errors differently in dht_lookup_dir_cbk and dht_discover_complete. return value from dht_layout_normalize is interpreted as follows: ret > 0 - number of subvolumes returned ENOENT errors. ret = 0 - no anomalies found. ret < 0 - there are holes/overlaps. We need to handle errors differently in dht_discover_cbk because, if a subvolume is newly added, the directory will not be present on it and we cannot create a directory there since a nameless lookup has resulted execution in this code-path. Hence if directory is guaranteed to be present in atleast one subvolume and there are no holes/overlaps in the layout, lookup can be treated as successful. there is no change in behaviour dht_lookup_dir_cbk caused by this patch. Change-Id: I9b0b510f1c7de187be95a47da6c9ec57b5e38d1d BUG: 802233 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3069 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit fdcbf065a9a4c39f08dfbe9e40695de250829bd8 Author: Krishnan Parthasarathi Date: Mon Apr 23 13:22:42 2012 +0530 glusterfs.spec: Added hook-scripts in server rpm Change-Id: Idd0ed2a72ea9ec947eaf142b889730e8d4be63c1 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3211 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f47b0fa1ccd594be9f0cda7f756973a04c0faed6 Author: Krishna Srinivas Date: Sat Apr 21 17:42:10 2012 +0530 nfs/nlm: remove /var/run/rpc.statd.pid before starting rpc.statd. Sometimes rpc.statd fails to start if rpc.statd.pid exists. Change-Id: Ic6feb375330fceb8dd6c35330757738fb5cbe16f BUG: 814265 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3206 Tested-by: Gluster Build System Tested-by: Saurabh Jain Reviewed-by: Vijay Bellur commit 66fddb979d7f33a86869211c06e4a9ef4a54a080 Author: Anand Avati Date: Sun Apr 15 22:14:38 2012 -0700 storage/posix: prefer absolute path handles over GFID handles Change-Id: I9afefa2f8a39c5f2c77271ea64aff95249c88821 BUG: 791187 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3204 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit e2216fbc37831f76039cae77bf724550827daa0f Author: Kaushal M Date: Thu Apr 19 13:17:49 2012 +0530 cli: Strip whitespace from "volume set" option values Strips the whitespace from options values before sending to glusterd. This prevents options containing whitespace to be written to the volfiles which would cause the volfile parser to fail. Change-Id: I46faee7b0853141fa102d06bb067c7ab499a2f6e BUG: 813937 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3192 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 3a26a7324128aed8181959b995d09ffc19ec2265 Author: Pranith Kumar K Date: Wed Apr 18 16:17:51 2012 +0530 mgmt/glusterd: Make priority threads configurable Change-Id: I7aa4c80fac3269052adb1b5516e9dd774d5f9e0a BUG: 812515 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3187 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2d836326ce8962a734ac099560256fe00e3b2c9c Author: Pranith Kumar K Date: Wed Apr 18 14:33:01 2012 +0530 performance/io-threads: Change the thread scaling logic. Change-Id: Idc0db1cb2c26dcb0b36a58d4d43f2da10cde62c5 BUG: 812515 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3186 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 9083ed64125f17ff04383f32300582d7b33c0be4 Author: Kaushal M Date: Fri Apr 20 11:20:41 2012 +0530 storage/posix: Don't allow mkdir() on HIDDEN_DIRECTORY Change-Id: Iecbd71d13ee8a492a99689674be99b4a451593db BUG: 788150 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3200 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit d10e17bf59966d66ebe4ea5627cf89b10bcd5fe8 Author: Krishna Srinivas Date: Thu Apr 5 18:42:25 2012 +0530 nlm: register client name with statd for blocking, nonblocking and reclaim lock calls Change-Id: If983f7b2f94703442e0745c5cbd2701edb2a972a BUG: 809362 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3097 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 443806fcfa6332163e08a63620e54d2f6be3996e Author: shishir gowda Date: Thu Apr 19 13:18:33 2012 +0530 stripe: make sure we have complete set of subvolumes before making fop Change-Id: Ifc3b05183945a7ce3e25f8c777daaf3fd4aecff3 BUG: 810450 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3190 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 10e8f8e7a9dbcb048fd6991d3c474e3430676859 Author: Krishnan Parthasarathi Date: Thu Apr 19 17:59:21 2012 +0530 glusterd: Enable hooks for volume set. Change-Id: I0cfa83feea719fb98c37418ad7b8dbe613ce7641 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3193 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 857ba84a236bcfb665aa930976106d990e96db77 Author: Vijay Bellur Date: Thu Apr 19 23:51:15 2012 +0530 rpc-transport/socket: Set NODELAY for connect socket This is essentially a re-introduction of setting TCP_NODELAY on the connect socket which was erroneously removed as part of commit 2da18b6 Change-Id: Icc3a8faafce0e63a9dde592a48f22b90a72860d1 BUG: 795635 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3197 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit cbb7a20daf7d59681eb21495361236cf68e9cd3b Author: Krishnan Parthasarathi Date: Fri Apr 13 14:28:05 2012 +0530 glusterd: Moved 'hooks' interface code to glusterd-hooks.* Change-Id: Ia7c0e37154414bddb05516e11b3cc4e6ae83ff38 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3142 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1a46dcecd0cfba549ae54bf61eaea2223b39c10f Author: Amar Tumballi Date: Thu Apr 19 12:18:53 2012 +0530 rpc-clnt: use the correct xdr_size for getting the iobuf earlier we used to get the size of rpc_msg from an empty msg, which was resulting in minimum size allocated for rpc-msg. the correct way is to fill the required fields in rpc_msg structure and then calculate the size, and allocate the iobuf. Change-Id: I3692831b53b8820a36e4562a1fa3d4c3dbdf4f9d BUG: 813787 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/3191 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 3ad81d490f9e822efa34b3ffaf3c527e99af5d40 Author: Pranith Kumar K Date: Wed Apr 18 14:48:35 2012 +0530 cluster/afr: Set errno correctly in find_fresh_parents failures Change-Id: I923103a03c1efe38285cd70842ec91b98a3f6bfd BUG: 765551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3185 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c284511c1ff7639ff674bca9260553680a917aa3 Author: Pranith Kumar K Date: Tue Apr 17 15:45:44 2012 +0530 cluster/afr: Handle transient parent-entry xactions in lookup This patch addresses the case when the lookup on an entry is performed while it is being renamed. The lookup can possibly return 2 different gfids when lookup on one subvol reached before rename and on other after rename. In such cases the conflicting entry self-heal is triggered to resolve the issue, but if there are lot entry transactions going on the parent directory of the entry then the non-blocking locks could fail resulting in EIO. To avoid this, lookup queries locks xlator if there are any parent-entrylk on entry's basename. If afr finds that there are such locks and gfids are differing then it chooses the file with latest ctime as the iatt of the entry. This solution is not foolproof, but it decreases the probability of hitting the EIO. The correct solution is to take blocking locks on the parent-entry to find out the correct source. Taking blocking locks in lookup is not good. One stale entry lock can hang the whole filesystem. So we chose to go with this for now. Change-Id: Ibebb6c3074f56f80a96893b6bf5b77941e30d400 BUG: 765551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3179 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 64177411f7c032eeb2b65635a9ca4e5767a72b40 Author: Krishnan Parthasarathi Date: Wed Apr 4 23:37:58 2012 +0530 extras: Added (hook) scripts to start/stop samba on volume start and stop These are example/helper scripts that demonstrate how one could leverage the recently added hooks interface in glusterd. The scripts are in 'beta'. Change-Id: I7aaf999f3bdfb276ef64e115a57cbdb36c7a896e BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3086 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f8bbf1cef9da21ea55649f5a05a88479853cd8eb Author: Raghavendra Bhat Date: Mon Apr 16 14:50:16 2012 +0530 cli: do not put the frame->local to mempool since its a calloced structure In cli, frame->local is not allocated from the internal mempool, rather its calloced. So while destroying the stack, we have to set frame->local to NULL. Otherwise if frame->local is not NULL, STACK_DESTROY will try to put it back to the mempool and thus segfault. Change-Id: I5bd17d099e16fb8e73f3250cc022008e26e28f50 BUG: 812735 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3167 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 678efee04855f88919904d98176b0d7c44e543d6 Author: shishir gowda Date: Wed Apr 18 10:49:09 2012 +0530 cluster/dht: Remove un-used pathinfo code for link files Currently, we do not return LINK: attributes for a file in pathinfo requests. Change-Id: If8667bd6af06de3d11c37dd0a09726dfe1d2e330 BUG: 795289 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3175 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit 1b8f254daf05f84ebc3170e7b840608fc7baf068 Author: Krishna Srinivas Date: Tue Apr 17 23:58:08 2012 +0530 nfs/nlm: disable NLM if rpc.statd is not found. Change-Id: I571e1f14cefdfabecd8996b6d0ffc928464d2b51 BUG: 813258 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3174 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c9a8da5bb8c78aba4b2477c011e2a4f335351fd8 Author: Kaushal M Date: Mon Apr 16 12:07:15 2012 +0530 glusterd: Properly validate compressed form of IPv6 addresses Properly validate IPv6 compressed notation, when used in volume set. Change-Id: Ia489125a45472fc0971c6b11de073aaeb9b1a123 BUG: 810442 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3152 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6ff8c16cbaa23e209d270d2d559a6072e554e68f Author: Pranith Kumar K Date: Wed Apr 18 11:44:21 2012 +0530 cluster/afr: Build parent loc for expunge Change-Id: Ifd1a4117924a7f9a90eb8e02dd2d655f2156fabd BUG: 765551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3178 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit fb9f485db2b4a92c16c0683cf3d5cfcd07054d71 Author: Pranith Kumar K Date: Tue Apr 17 13:20:43 2012 +0530 features/locks: Find parent-entrylk presence in lookup Change-Id: I8fc85676827f26b07bf578ea1152d3e251adb4af BUG: 765551 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3177 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c0eec503b78949bd1785e5bf2533db211f3d256c Author: shishir gowda Date: Wed Apr 18 12:16:51 2012 +0530 glusterd/rebalance: Start process with xlator option client-pid -3 This would prevent updation of xtime by the marker. Set frame->root->pid while creating sync-task. Removing the command option, as it is in-effective Change-Id: Ifaa587df67a72ec0571c7d0043de8048e2be12a8 BUG: 812287 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3180 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 7522df3b98467c2ddfb9cc12f5c807d4408267cc Author: Amar Tumballi Date: Tue Apr 17 23:30:23 2012 +0530 glusterd (remove-brick): fix data-loss issue * when more than one brick (more than one distribute subvolume) was removed using single command, rebalance process used to get started only on one node, causing data-loss when 'commit' was done, because the brick's data was not migrated at all. Fixed the logic of validating rebalance required in remove- brick case. Change-Id: I3a90ff9f9593e5215110a3a0974bb97e7271f910 Signed-off-by: Amar Tumballi BUG: 812770 Reviewed-on: http://review.gluster.com/3173 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Shishir Gowda commit 7ef32ae76d1c1e4a5ff47899d175be9fdeb73bc8 Author: Raghavendra G Date: Mon Apr 16 11:38:33 2012 +0530 performance/quick-read: disable reading from cache if unlink has happened after fd was opened. If dentry being unlinked is the last one, there is a possibility that later, a new entry with same name being created. After creation of new file, we shouldn't be returning the contents of this new file, when application reads using fd opened before unlink. Change-Id: Ic98aa9cd76d24e8a37ce02a0aae6c66290043192 BUG: 811976 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3151 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 80eeaab2be884f0ebc89704011421541742cd5e6 Author: Krishna Srinivas Date: Thu Apr 5 15:57:47 2012 +0530 nlm: send sm-notify to clients whenever the nfs server is restarted so that clients reclaim the locks. Change-Id: I0a8e291ad0a78e2e68070b1d289d32a786da8da2 BUG: 802885 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/3096 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b69f0110410c670eb6c31b6669d47ec2aaeb92f4 Author: Rajesh Amaravathi Date: Mon Apr 16 12:05:45 2012 +0530 nfs: option to disable NLM Adding support to disable/enable nlm with the following command: # gluster volume set nfs.nlm [on|off] Change-Id: I1ad3e44c5d4349d0f3463bfca0995fd10def39dd BUG: 812869 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3160 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas commit c20f501d0632d6105f0d570ac8dec251974ebe87 Author: shishir gowda Date: Mon Apr 16 14:39:10 2012 +0530 cluster/dht: Handle failures in getxattr_cbk Change-Id: Ifbce2d69f0fdd0c45cba92b6fc2dffe13c60de28 BUG: 810106 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3156 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Venky Shankar commit 0049c2405aa39fe4ef299bd646e7a53e40753039 Author: Kaushal M Date: Mon Apr 16 19:31:44 2012 +0530 glusterd : Fixes for breakages caused by volume-id validation Fixes glusterd_op_build_payload() to, 1. take account of status cmd type when building payload for "volume status" to prevent "volume status all" from failing. 2. take account of volname being "help/help-xml" in volume set to prevent "volume set help/help-xml" from failing 3. obtain volname using key "master" prevent "volume geo-replication" commands from failing Also, fails op and sets correct op_errstr if volume not found during glusterd_dict_set_volid(), to make sure cli displays proper message. Change-Id: I40ded15c50b54a82ee61bf6d6e9d07f571679c8c BUG: 812801 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3157 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 79620e8f63148b1ad7d8180da46176a759435590 Author: Kaushal M Date: Wed Apr 11 17:04:15 2012 +0530 cli: Fix for "volume status all" Fixes output of "volume status all" when some volumes are stopped and some changes to xml output. Change-Id: I77938422c0258bb69e32b54c23df1225474532bc BUG: 811539 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3130 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 4359d00fcb17d22ef487bff34943475c77194692 Author: Rajesh Amaravathi Date: Tue Apr 17 15:37:38 2012 +0530 nlm: unregister nlm v1 when gNfs is stopped NLM v1, registered to communicate with statd is unregistered once gNfs is stopped. Change-Id: I165658488f4971e743736f5f77c7247590e64bd5 BUG: 786345 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3166 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas commit 6b0a44b4df1c1f7d70b2296862d25bf166009ebc Author: shishir gowda Date: Tue Apr 17 11:23:46 2012 +0530 protocol/server: Check if dict arg is NULL in setxattr Change-Id: I44d199ffa5d08115cc0aa7cb0b99298a9907af60 BUG: 808067 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3164 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 41bd7281a5fe4062fabe963d7862117aca50cc3d Author: Amar Tumballi Date: Mon Apr 16 13:26:40 2012 +0530 features/marker: fix possible NULL access in strcmp() for a given setxattr call, loc->path can be NULL now, handle that case properly Change-Id: Ic56ec81aa8eb62aafdb524bf22f6d84390ab1d4b Signed-off-by: Amar Tumballi BUG: 812767 Reviewed-on: http://review.gluster.com/3154 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 754112b7b716c68fb6cf44941ce4f343698d533e Author: Mohammed Junaid Date: Mon Apr 16 12:57:57 2012 +0530 protocol/client,server: Lock self healing off by default. Also, merged the options client.grace-timeout and server.grace-timeout into one option "features.grace-timeout". Change-Id: Icb9f0809f89379de673f8c9f7ca4725bc113797f BUG: 812760 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3153 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 42c06ba048d0bcb7093063bf99dfa3e520a038a5 Author: shishir gowda Date: Fri Apr 13 15:22:57 2012 +0530 glusterd/rebalance: Start process with xlator option client-pid -3 This would prevent updation of xtime by the marker. Signed-off-by: shishir gowda Change-Id: I11e287511026326271c2926e55993e48b32018f6 BUG: 812287 Reviewed-on: http://review.gluster.com/3144 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Csaba Henk Reviewed-by: Vijay Bellur commit c75a5d348f0d30b61bdc45e9e54d623957a6050f Author: Pranith Kumar K Date: Sat Apr 14 18:02:05 2012 +0530 cluster/afr: increment change log with correct byte order Change-Id: Id2af3e61ad659ff6d168161673e5e1e19f36bdb5 BUG: 765194 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3149 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 369873fbeac1c33bf5f2468e475c3a08608e8965 Author: shishir gowda Date: Mon Apr 16 13:31:59 2012 +0530 cluster/dht: Revert to calling ftruncate Additionally, change lookup failure error to DEBUG level. Change-Id: I6eaf8e92a9cd34eba125a1e0e183bc3b6dc71945 BUG: 812769 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3155 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit c6e226751efb4ce98e5c887b955c778b713b77bc Author: Rajesh Amaravathi Date: Fri Apr 13 14:19:11 2012 +0530 nfs/server: hard resolve fh on restart the filehandle passed to hard resolving code was not initialized to it correct value (resovlefh). Change-Id: I0a26c7b90bf3efec7fda26fed0823755c4b9e87b BUG: 802779 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3150 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit dc4c44d51e3eb4b53e78840bf223911e48ce62b5 Author: Pranith Kumar K Date: Fri Apr 13 18:37:55 2012 +0530 libglusterfs: Syncop procs should not exceed SYNCENV_PROC_MAX Change-Id: I0eb2adac06eae31939c8ed6b544b4be43d1a5885 BUG: 810109 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3146 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 77645c35323c30f881ac5e5418c8723642f3845f Author: Jeff Darcy Date: Thu Apr 12 17:32:00 2012 -0400 Fix dangling references to examples. Change-Id: Ic90f332fb6554173a03f7a026fc3677e7cf42eae Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3139 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 5c67b2c99de39c988be7c5fffd504fdbaae74a01 Author: Kaushal M Date: Wed Apr 11 13:40:28 2012 +0530 glusterd: IPv4 auth improvment Check if last character of an IPv4 address is valid to prevent successful validation of addresses with '.' as last character. Change-Id: I0af6c288e12a47986ce3f8b02c317b99767e69e6 BUG: 811458 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3124 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 362c5283ace6f048d0404a8a390faeb014ebe351 Author: Krishnan Parthasarathi Date: Thu Apr 12 12:39:48 2012 +0530 server: Modified logging information to ease log based analysis Change-Id: I1bde6505346b5dda37cf88c66f9af8ff48668ed9 BUG: 811864 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3133 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 28f373d89fba7266473c952d9c2bf6ec5f02628c Author: Kaushal M Date: Mon Apr 9 12:17:16 2012 +0530 xlator/server,xlator/nfs : Fix authentication for address lists Fixes authentication problems when address lists are given for auth.{allow,reject} and nfs.rpc-auth-{allow,reject}. Change-Id: I9959ebfa6820aef52c883372e1085660560e1e73 BUG: 810179 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3104 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit b19a7fee17ddedfc6692deb5a8dc8df927a2cf7b Author: shishir gowda Date: Thu Apr 12 15:32:05 2012 +0530 dht/rebalance: Display migration failure count Change-Id: Ib2f8be2c98eae1b4df5d2090c1f1eec8ab264a35 BUG: 811923 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3135 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit bada6aeb2cabd12a11b0fe17bb01e9f2045b013d Author: shishir gowda Date: Wed Apr 11 15:30:22 2012 +0530 glusterd/remove-brick: Replace ABORT with STOP Remove-brick stop now invokes rebalance stop. This leads to a graceful stop of decommissioning. The volfile is also updated (removal of decommission) Change-Id: I5a8f725c0f54439b810ce32d988c21c02229c703 BUG: 811513 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3126 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d80846bee0621f591a7b519743e4d91a620ccdca Author: shishir gowda Date: Wed Apr 11 11:47:17 2012 +0530 dht/rebalance: Handle ASSERT_ON_CHILD_DOWN gracefully In rebalance process, instead of terminating, send a stop event. The migration in question will either complete or be handled as error. Also, handle few syncop calls as errors, instead of just logging them. Change-Id: If6ed54474cb0f1fe0e28a5765e6d90966740dfde BUG: 811444 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3120 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c2ebd7aa84ed666ac8d1f0e9424cd01f877fb53b Author: shishir gowda Date: Wed Apr 11 12:11:06 2012 +0530 glusterd/remove-brick: Remove support for pause option Decommissioning through rebalance has no pause option. Change-Id: I90f165cdb2eccfaefc99365ae4b48d81320fb753 BUG: 811459 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3123 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit c238e5073a8d60fede1f88e584c14de42885276e Author: Csaba Henk Date: Tue Apr 10 15:34:02 2012 +0200 geo-rep / gsyncd: log sync failures as warnings Syncing of certain files can fail naturally if changes happen on master (eg. file gets deleted). Therefore logging an error is misleading. Change-Id: I7b54904e5ec7c85e4e0fa1e330123d2c44c78ac5 BUG: 764510 Reported-by: Vijaykumar Koppad Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3113 Tested-by: Gluster Build System Reviewed-by: Vijaykumar Reviewed-by: Venky Shankar commit ecfe2d0a94dd6626e2e6c1e7707549adf550a5af Author: shishir gowda Date: Mon Apr 9 17:20:10 2012 +0530 glusterd/rebalance: re-establish conn between rebalance process Signed-off-by: shishir gowda Change-Id: Ib13b4b9beebf18632027e4dd7c68f627c311781c BUG: 810688 Reviewed-on: http://review.gluster.com/3110 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit d2a73be6d94d108673e3427e534c1abbe71ccbff Author: Jeff Darcy Date: Sun Apr 1 14:50:08 2012 +0530 mount.glusterfs: multiple fixes * noticed that the regex to parse the options were not fool proof. for example, 'ro' in a logfilename could have made the mount point read-only. Now fixed. * this issue existed for 'acl', 'worm' options. * log-server/log-server-port options were legacy, and no more needed in codebase. * refactored option processing in general to avoid above issues Change-Id: I172d24c86ece9a34420ba997fa385e304b4924ae BUG: 806978 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3058 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 8a45a0e480f7e8c6ea1195f77ce3810d4817dc37 Author: Krishnan Parthasarathi Date: Tue Apr 3 15:37:25 2012 +0530 glusterd: Added volume-id to 'op' dictionary Volume-id passed in op dictionary would help detect possible split brains among peers in a cluster. The idea is to check if the volume's id and the vol-id that was passed are equal. ie, same volume name, but different volume id indicate that glusterd 'metadata' of one of the participating peers is stale or there is a split brain. This is over and above the existing checksum based validation of peer supplied cluster 'metadata' (ie, volume info file). Change-Id: I1049ef249e417e540ccb4243e450f92fcd0f46f9 BUG: 797734 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3083 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit b337b755325f75a6fcf65616eaf4467b70b8b245 Author: Krishnan Parthasarathi Date: Mon Apr 9 18:21:43 2012 +0530 glusterd: Removed 'unprotected' concurrent access of priv->volumes on glusterd restart This must have been removed as part of afe542eca18888463798747d2a95e5a9d239a4a0 (reverting to non-synctask behaviour). Change-Id: Ic23c8bbf8f90f4c9af6e68349de63e22d7f25606 BUG: 810829 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3109 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit e46a57fda716c00b7c490be74485863c80d6f7b4 Author: Raghavendra G Date: Sun Apr 8 11:40:48 2012 +0530 features/quota: don't adjust statfs buffer if size used is already greater than available limit. members f_bfree and f_bavail of struct statfs are unsigned types. A negative value assigned to them is interpreted as some positive number and resulting in incorrect output of df output. Signed-off-by: Raghavendra G Change-Id: I4d3d38b9bb6f675958ee38ad4d6c71ebcf4bb9a1 BUG: 773530 Reviewed-on: http://review.gluster.com/3102 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit ea8378299e4d9ae5a8d296feb1d16950d07173de Author: shishir gowda Date: Mon Apr 9 16:29:45 2012 +0530 glusterd/rebalance: Provide option start rebalance with valgrind Change-Id: Ia7a836425f5dbfe07b2e46563e49aaeaaaaa4e14 BUG: 810836 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3108 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 122da53bd1a82eaaf4aeb2ce6443fe8d0fe3ab46 Author: Pranith Kumar K Date: Wed Apr 11 16:14:31 2012 +0530 cluster/afr: Perform gfid-less lookup in afr Change-Id: I78d9f0563e25047f392675ae32db38d2c94f6651 BUG: 795355 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3129 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7edec07b139626bb64ea34e143a02dbfd28a6d9f Author: Pranith Kumar K Date: Wed Apr 11 16:14:16 2012 +0530 storage/posix: Handle gfid-less lookup Change-Id: I4605dbb1dd8bf8e26de7f253e54a7f4840c8a8be BUG: 795355 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3128 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit a3c61c6aea4045a6adafcc7350bd14f1e9c68ca1 Author: Pranith Kumar K Date: Thu Apr 12 22:03:49 2012 +0530 libglusterfs: loc_copy should set name only if src->name is set Change-Id: If06d97dd1ff1293730e0cd4933f6ab3283f0475e BUG: 788051 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3137 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 918678dc8e5a8cac1ec2dea7f8d2b11a186f38eb Author: Brian Foster Date: Thu Apr 12 15:46:37 2012 -0400 md-cache: fix dict memory leak in mdc_inode_xatt_update We currently either dict_ref() or dict_copy() into mdc->xattr. The double dict_ref() call path is obvious. Alternatively, dict_copy() does not ref the dict in the situation where it creates a new dict, but we only call dict_copy() in this context when we already have a dict, which should mean the extra ref is unnecessary. BUG: 801582 Change-Id: I72e3f1a16f942f04752c033812d13d50ee7c2c2c Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3138 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 6a995ab3300a5ee0ee79a4d7d75281a79deec96e Author: Kaleb KEITHLEY Date: Thu Apr 5 10:29:18 2012 -0400 contrib/md5: prune contrib/md5/* from tree Previous change set did not delete contrib/md5 from the tree. BUG: 807718 Change-Id: I74eee1897fac24b83b379f2433de5e4648eb5f4c Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3095 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit f2921551424a97dcc3914cc79a241dca42675b97 Author: Amar Tumballi Date: Wed Apr 11 23:55:58 2012 +0530 glusterfsd: mem-pool count of dict_t is adjusted increased dict_t pool count based on test results. Change-Id: Ia5b24940b79a1489b00cca2993241c32be94bbec Signed-off-by: Amar Tumballi BUG: 809034 Reviewed-on: http://review.gluster.com/3131 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 472b55a6db996ca3058fec3aa6ab9a8745cbd5cb Author: Anush Shetty Date: Wed Apr 11 11:49:46 2012 +0530 Error-gen: declare the structure for cbks Change-Id: Iaa2e367ad225a2b24dd56c3941163f90be74e6ee BUG: 811445 Signed-off-by: Anush Shetty Reviewed-on: http://review.gluster.com/3121 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 076830c068fb39bbc3e863c89a4253cbea36357e Author: Vijay Bellur Date: Mon Apr 9 23:11:52 2012 +0530 doc: Move outdated documentation to legacy Change-Id: I0ceba9a993e8b1cdef4ff6a784bfd69c08107d88 BUG: 811311 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3116 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit df8e2f53b70f4f49af70df308010dddfe5ca35ec Author: shishir gowda Date: Wed Apr 11 16:07:43 2012 +0530 dht/rebalance: Correct log messages Change-Id: Ica73707922c1bf1a0975a8057d39c1441b987b0a BUG: 808376 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3127 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Anand Avati commit dde9cfcaf3016968fade7591ddfc1c95851e9e59 Author: Amar Tumballi Date: Wed Apr 11 11:51:31 2012 +0530 protocol/client: in link_cbk() try to print valid information in case of error currently there is a chance we don't have a source 'loc_t' path information instead we would have gfid. Need to print destination information too. Change-Id: I7a5edbdc9abe18fdb330fc7ed49c9946cf7fe382 Signed-off-by: Amar Tumballi BUG: 810146 Reviewed-on: http://review.gluster.com/3122 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Raghavendra Bhat Reviewed-by: Anand Avati commit 0bfadb56d0ce0ffaa410eccb2a9d9eaaf6f3ab7c Author: Amar Tumballi Date: Wed Apr 11 14:40:44 2012 +0530 protocol/server: validate connection object before dereferencing in 'release()' and 'releasedir()' fops the check for 'connection object' was not done before dereferencing it. the check was in place for all other fops. handling the missing cases now. also removed some warnings related to 'set-but-unused' Change-Id: I47b95318e8f2f28233179be509ce090b2fb7276d Signed-off-by: Amar Tumballi BUG: 801411 Reviewed-on: http://review.gluster.com/3125 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f56404a3358c799f907f36aecedf774b1875a56c Author: Anand Avati Date: Fri Apr 6 11:17:34 2012 -0700 fuse-bridge: generate GFID as gfid-req in fresh lookup This is necessary for self-heal to assign fresh GFID when performing lookup on files/dirs without GFID (migration from old version, etc.) Change-Id: I6f070255dc6e85bf6625b704cb5fb7f831ee58e6 BUG: 795355 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/3101 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit 7f5c1e5777d77570be0f9698de39d2f1905c509f Author: Jeff Darcy Date: Tue Apr 10 17:12:05 2012 -0400 Fix compiler warnings and typos from Debian build. Mostly to do with "-Werror=format-security" being buggy, but while we're here we might as well fix some typos and such. Credit goes to Patrick Matthäi for pointing these out. Change-Id: Ia32d1111d7c10b1f213df85d86b17a1326248ffd BUG: 811387 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3117 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4bb82b2c779bb984a980e371c3119254cf1cb0f8 Author: Mohammed Junaid Date: Mon Apr 9 12:14:59 2012 +0530 storage/posix: Avoid excessive logging in posix. When quota or gsyncd is enabled, the marker translator performs setxattr on files/directories. If the file/directory is deleted before setxattr, posix gets an error when it does setxattr and logs it. But its not an error for marker and it handles the case gracefully. Hence, avoid logging for these keys. Change-Id: Ic614777399497be92ed1c2b4718d46adfb639d96 BUG: 765498 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3105 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 05a9780c9111396f4e2c3ebdae77cf8a257f1a54 Author: Krishnan Parthasarathi Date: Mon Apr 9 21:27:40 2012 +0530 glusterd: Modified algo for creating hooks directories. - This change will ensure that hooks directories are created when glusterd is upgraded from a version that doesn't have the hooks feature or the 'current' hooks version. Change-Id: I8a0ea64eda52a15b1605b98588b9b19df209a73e BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3111 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 79b3e4111a1a64dc74046571845b3ed83b8ede24 Author: shishir gowda Date: Mon Apr 9 17:22:16 2012 +0530 rebalance: revert sending PARENT_DOWN event to xlators reverting patch 1043dedfb54c80bdbb6e050920ced204515b226e Change-Id: I2e919c8a5e43f3cce74a8eaf58554830fa708364 BUG: 808402 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3107 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1222e2ae2d42cf12569a0cf00bb1f1504ef4e7b7 Author: shishir gowda Date: Wed Apr 4 16:04:10 2012 +0530 remove-brick: Abort should revert volume changes Also, enhanced gluster cli output. Signed-off-by: shishir gowda Change-Id: I520ccfb63b3568a2e6654d8a5fbf265b9b903af1 BUG: 788524 Reviewed-on: http://review.gluster.com/3082 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7768d700a18f5bdb1e4640070ec5dd380384c7a9 Author: Venky Shankar Date: Mon Apr 2 12:47:55 2012 +0530 hadoop-glusterfs: Fix IndexOutOfBounds Exception Fix IndexOutOfBounds Exception which is hit when one of the replica pair is down. Problematic code existed in assuming a uniform size for each replica in pathinfo string. Change-Id: I85377ba5549e0603fe86e8d787115004f50e0c6a BUG: 808009 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/3087 Tested-by: Gluster Build System Tested-by: M S Vishwanath Bhat Reviewed-by: M S Vishwanath Bhat Reviewed-by: Vijay Bellur commit f132cc666ba4aa5e804de1c4529674618ca0d875 Author: Vijay Bellur Date: Thu Apr 5 19:00:08 2012 +0530 cluster/afr: Fix a compilation warning Change-Id: I36dc1b53fd4a7d824fe8506a4ad83ad652f95ce5 BUG: 807718 Reviewed-on: http://review.gluster.com/3094 Reviewed-by: Kaleb KEITHLEY Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 8b892fff8be9adca22c180a62d1dd01d83559330 Author: Pranith Kumar K Date: Tue Apr 3 15:36:55 2012 +0530 self-heald: succeed heal info always Succeeding the mgmt op enabled the rsp_dict to be used to get the reason for the failures. Change-Id: I781ded31afa5aafd717543a5339dee3f316aade8 BUG: 807556 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3076 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 6424f5a6cce467751fdfe991addc922a498d44fc Author: Pranith Kumar K Date: Tue Apr 3 15:20:44 2012 +0530 mgmt/glusterd: Use the correct status string for filtering Change-Id: Id62bec56aeda0cede19369708242f0b92f800125 BUG: 807556 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3075 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3e27f277951e9369517bdd16170639f587d3fb9d Author: Pranith Kumar K Date: Tue Apr 3 11:13:09 2012 +0530 self-heald: Add node-uuid option for determining brick position Change-Id: Ia60981da7473d74682d86286e4d540568c8de25b BUG: 807556 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3074 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 73e2c0dec5b432c788cd80c4210b887517188f3d Author: Csaba Henk Date: Wed Apr 4 03:42:31 2012 +0200 geo-rep / gsyncd: shuffle directory entries in crawl In order to randomize the walk of the file tree. Change-Id: I9fc3b83d5804914a50faae8df7dbcfed2ba6f4b4 BUG: 809675 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3079 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit bd83e10deec2e7dcd289ca30d2a3de19e0d59c30 Author: Rajesh Amaravathi Date: Mon Apr 2 11:56:21 2012 +0530 nfs/nlm: dummy actor for FREE_ALL procedure NLM4_FREE_ALL rpc procedure has been provided nlm's null procedure as actor to facilitate windows Nfs mounts. NOTE: windows Nfs needs several other NLM procedures to work. As a result, this patch only makes it possible to do a working mount of a volume with "nolock" option in windows. *Windows mount WITHOUT "nolock" option does NOT work as expected* Change-Id: Ie163982497871312c5bb15f8c141fef460cadc34 BUG: 800287 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3063 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas commit 7d62749f14663ea6c0000a4aab2c32041cbb4e75 Author: Pranith Kumar K Date: Tue Apr 3 08:12:34 2012 +0530 self-heald: Find self-heal failures, split-brain Change-Id: Ib967f0fe0b537fe60e51d7d05462b58a7f16596e BUG: 806745 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3077 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 1f3a0dd4742a2fcd3215aee4a5e22125d7ea4f4d Author: Raghavendra G Date: Wed Apr 4 18:04:52 2012 +0530 fuse-bridge/fd-migration: document migration failures in fdctx. Change-Id: Ib85871e586f89f88dd7bf738fbb284b5d7b70a86 BUG: 809919 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3085 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 42a0889d93450e6f1f3472ec0818e678412346c2 Author: Pranith Kumar K Date: Sun Apr 1 15:48:26 2012 +0530 cluster/afr: Handle self-heal of files with holes Change-Id: I6c04fe3022f234455d52620f42b9add80fc6abe4 BUG: 765424 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3065 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 69f70038171862daedcbbccf0eaba3d1f8d885f5 Author: Kaleb KEITHLEY Date: Tue Mar 27 11:14:23 2012 -0400 Replace GPLV3 MD5 with OpenSSL MD5 Ric asked me to look at replacing the GPL licensed MD5 code with something better, i.e. perhaps faster, and with a less restrictive license, etc. So I took a couple hour holiday from working on wrapping up the client_t and did this. OpenSSL (nee SSLeay) is released under the OpenSSL license, a BSD/MIT style license. OpenSSL (libcrypto.so) is used on Linux, OS X and *BSD, Open Solaris, etc. IOW it's universally available on the platforms we care about. It's written by Eric Young (eay), now at EMC/RSA, and I can say from experience that the OpenSSL implementation of MD5 (at least) is every bit as fast as RSA's proprietary implementation (primarily because the implementations are very, very similar.) The last time I surveyed MD5 implementations I found they're all pretty much the same speed. I changed the APIs (and ABIs) for the strong and weak checksums. Strictly speaking I didn't need to do that. They're only called on short strings of data, i.e. pathnames, so using int32_t and uint32_t is ostensibly okay. My change is arguably a better, more general API for this sort of thing. It's also what bit me when gerrit/jenkins validation failed due to glusterfs segv-ing. (I didn't pay close enough attention to the implementation of the weak checksum. But it forced me to learn what gerrit/jenkins are doing and going forward I can do better testing before submitting to gerrit.) Now resubmitting with a BZ Change-Id: I545fade1604e74fc68399894550229bd57a5e0df BUG: 807718 Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/3019 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 3c5aed7d8226e50296c6a7106e0d59682732e9b5 Author: Raghavendra Bhat Date: Tue Apr 3 15:22:45 2012 +0530 locks, stripe: check if dict is NULL before refing it Change-Id: Ifab58504280ed92e4435f7805052745e56bef5ef BUG: 808003 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3073 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0e4c74861f762d4af7b7d8ffce5384920a6aa335 Author: Raghavendra G Date: Tue Apr 3 13:17:28 2012 +0530 quota: log msgs indicating NULL parent inode in DEBUG level. with name-less lookups its common to hit situations where parent inode is NULL. Signed-off-by: Raghavendra G Change-Id: I980b14c3d4691e850ae15768f73cf1b7d867e930 BUG: 809032 Reviewed-on: http://review.gluster.com/3071 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e5b5bb4de46a2a37c8ff392c456c306026517269 Author: Csaba Henk Date: Tue Apr 3 01:57:23 2012 +0200 libglusterfs/run: POSIX compatible closing of child fds on non-Linux It just occurred to me that I realized there are POSIX features that let this be done cleanly. However, For Linux we keep the proc based approach to get more graceful strace logs. Change-Id: I6b473271b2adfd85cef6612eb65d88e5d00f5943 BUG: 764294 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3068 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1043dedfb54c80bdbb6e050920ced204515b226e Author: shishir gowda Date: Mon Apr 2 16:52:10 2012 +0530 dht/rebalance: Send PARENT_DOWN event before cleanup in rebalance To prevent any crashes, due to backend ops (e.g: afr self heal), sending GF_EVENT_PARENT_DOWN before calling cleanup_and_exit. Change-Id: I58c87c114bf259a69a8d081d291ca908b30ec407 BUG: 808402 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3062 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 943ca064ec6ab2f009f12b3d5f1e90a5402f04d6 Author: Csaba Henk Date: Sat Mar 31 00:15:02 2012 +0200 libglusterfs/run: clean up properly also if program could not be spawned Change-Id: Ie81a6e1a99c1cb002653c0175bb3c5fcff9c8a4a BUG: 808427 Reported-by: Krishnan Parthasarathi Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3055 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 22cc617902794f4136fe6ba7b631ebe9f7bd4563 Author: Csaba Henk Date: Sat Mar 31 00:15:02 2012 +0200 libglusterfs/run: test suite refinement If run is compiled as a standalone self-test program (-DRUN_STANDALONE -DRUN_DO_TESTS) add the possibility to pass an integer which makes the program sleep that many seconds before exit (0 forever). This makes it possible to investigate post-test state (eg. if there are leftover zombies). Change-Id: Ia8d80a74eb83615ad50db2e17bb2701dc0d69070 BUG: 808427 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/3067 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit b283a09b05606b953339ea419d16cb1ec40326c3 Author: Kaushal M Date: Mon Apr 2 11:08:24 2012 +0530 cli: Limit value of bs * count in "volume top" The maximum value of bs * count is limited to 10GB. This prevents gluster from returning 0 throughput with large values of bs * count. If throughput for values larger than 10GB is required, use dd. Change-Id: Ia4ea70cb20f3f32b6cb81fd451ad56933f438452 BUG: 803322 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3059 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7bcf48a73f6313a0cffbc37288041f1dc8bba71e Author: shishir gowda Date: Mon Apr 2 18:32:05 2012 +0530 cli/rebalance: Fix parse error for volume rebalance cmd gluster volume rebalance force was handled as a success. Signed-off-by: shishir gowda Change-Id: I4f73aa5935c7e62673d457b52a6dfea6c7197dcc BUG: 808991 Reviewed-on: http://review.gluster.com/3064 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit dcfd0f4ee8c3c405f768cbb79219c0c5fa071a56 Author: Brian Foster Date: Mon Apr 2 09:56:42 2012 -0400 md-cache: fix time comparison to support 0 timeout The time comparison currently causes caching when the current time matches the timeout. This causes caching to occur even when the timeout parameter is set to 0. Fix the condition to support the no caching scenario. A longer term approach is to use gettimeofday() for more accurate granularity, but this apparently fixes a known bug. Change-Id: I6552c5961743edb22a1aec2e6a3a6e041d0647b2 BUG: 809193 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/3066 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit b0bb1a2c979078efa3ab024e14119df6087c4320 Author: Amar Tumballi Date: Tue Mar 27 18:22:15 2012 +0530 cli: do the proper STACK_DESTORY of created frames * fixes memory leaks * fixes some random local mem-pool empty messages Change-Id: Ic79f279f2acfe4722fa54d52397d0267b3918928 Signed-off-by: Amar Tumballi BUG: 803638 Reviewed-on: http://review.gluster.com/3018 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit dc2a52fa0d83ba2e807a175655fc0362b707a22d Author: Raghavendra Bhat Date: Mon Apr 2 14:57:20 2012 +0530 nlm: print the reason of failure when clnt_create fails to create the client object Change-Id: Icc271e2166dbccc2cc12029e26c674fdb79fe975 BUG: 808390 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3061 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e51f690d7c5eda400316ba97ab2f4ce448b51e7d Author: Kaushal M Date: Mon Apr 2 13:00:47 2012 +0530 glusterd: Include port in nfs status Change-Id: I679e491e801b694e8a0f93dd87cf540441dae927 BUG: 806877 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3060 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0f3b55be4376c1c59131d999469d3b3c6aaddd87 Author: Raghavendra G Date: Fri Mar 30 10:04:45 2012 +0530 performance/quick-read: open shouldn't be worried about checking whether it is being done on a deleted dentry. lookup would've taken care of sending ENOENT, in case the entry was already deleted. Change-Id: I79c51e34ae3a202eb04123a2a58d0e819b6e94fa BUG: 808017 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3044 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 67450da471307d1c09bd21694a76fb12b2fcd405 Author: Rajesh Amaravathi Date: Fri Mar 30 17:18:07 2012 +0530 mgmt/glusterd: unregister NLM service from portmapper Native NLM v4 service is unregistered from portmapper when Nfs is stopped. Change-Id: Id74cf9a31f6b00450504a1271bb47617aa5ec1fc BUG: 786345 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/3052 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ca4d7c9dfc1d7f8c09994a862868f55b8320eb95 Author: shishir gowda Date: Tue Mar 27 12:50:59 2012 +0530 performance/io-cache: Enhance state-dump output Along with weight, print uuid and path. If only the inode is cached, only weight, path and uuid will be printed. Change-Id: Ie7567832915319f26c6bab8a34576f6c43be7998 BUG: 806900 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3014 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c2dd1510e18e4c91d54ce4de91ecd47b408524dd Author: Vijay Bellur Date: Sat Mar 31 20:43:12 2012 +0530 mgmt/glusterd: Improvements for volume heal CLI. 1) Brought in a CLI improvement for volume heal cmd when it fails before initiating a transaction. 2) Minor improvements in UI messages related to self-heal-daemon. Change-Id: I983c1e54b48f2efe8793fa5b00fa50df2067683b BUG: 807261 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/3057 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit 778c8d616ba2e9b47cafbbe95dbec7f2eb788302 Author: Pranith Kumar K Date: Sat Mar 31 13:30:22 2012 +0530 cluster/afr: Fix frame leak in hardlink self-heal Change-Id: I8560fc2ba0d989eeb33226f8eb8c7fbad46dfe32 BUG: 765391 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3056 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 06226c19a2b6a8840c0fd88837164f1e2150ba5b Author: Amar Tumballi Date: Fri Mar 30 15:42:21 2012 +0530 glusterd: remove-brick validation behavior fix earlier one of the major validation case was missed if user provided a 'replica N' option for remove-brick where N is already existing replica count of the volume. This would have left the volume in inconsistent state, eventually crashing glusterd. Now fixed. Change-Id: I418f3bbb983d36aa51214c616a887e5a3ee98e74 Signed-off-by: Amar Tumballi BUG: 803711 Reviewed-on: http://review.gluster.com/3050 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 96e68adc348e96c1b9d70f6a621f607591f052c2 Author: Pranith Kumar K Date: Fri Mar 30 12:03:32 2012 +0530 features/locks: INIT the list before insert_merge Change-Id: I1612565e2bbf1811a85341016b86571bdf6e5062 BUG: 805994 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3047 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit c078b9df8d8f44ca90e61566f83f83809ce5ac0f Author: Pranith Kumar K Date: Thu Mar 29 19:45:29 2012 +0530 cluster/afr: Handle invalid inode in open_fd_fix Change-Id: Ie009fb4b8b7745ebd5b76f7a40287998be35eef3 BUG: 804914 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3045 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 66d430da4e3788aeb41eea46455ca25a2d19a626 Author: Krishnan Parthasarathi Date: Mon Mar 26 16:11:29 2012 +0530 glusterd: Added init scripts like interface for gluster commands Directories to hold the scripts mentioned above would be created for each gluster command under glusterd's 'working dir' as follows: (eg.) /hooks/version/create/pre /hooks/version/create/post where, version corresponds to the version of hook scripts. The scripts beginning with 'S' under the above directories would be run before (pre) and after (post) the volume created. The scripts would receive a command line argument as below: --volname= This can be optionally used by the script. Change-Id: Ia81b4ff9dd4477d99dd59b39c805aa645521edb0 BUG: 806996 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3010 Tested-by: Gluster Build System Reviewed-by: Csaba Henk Reviewed-by: Vijay Bellur commit 3f81c44a03e9ab78be2b4a69e3e36d41a4de324a Author: Krishnan Parthasarathi Date: Thu Mar 29 14:00:50 2012 +0530 glusterd: Used runner's RUN_PIPE to get inode size in xfs/ext3/ext4 Change-Id: I8057fd04baf36db86fe679a1beb86f76a1085b7c BUG: 786367 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/3033 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit 73c789cd9c530ded113905ef7efb47e1ac3251d6 Author: Raghavendra Bhat Date: Fri Mar 30 13:33:10 2012 +0530 nlm: do not destroy the NULL client object Change-Id: Ie1946b33353a91a266d2b21727d0c8eaa06af7f9 BUG: 808341 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3046 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 6f10f48a6a1632cd62206fd84634ab0e5db1c361 Author: shylesh kumar Date: Wed Mar 28 14:13:00 2012 +0530 cluster/stripe: minimum blk size log message Change-Id: I16ba2e17796cd91e89a6216d4981c09f1bcdc5cb BUG: 807637 Signed-off-by: shylesh kumar Reviewed-on: http://review.gluster.com/3026 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit cc2e9ad0751da55dfdcd86fea2d5b312a1cbd1b5 Author: Pranith Kumar K Date: Thu Mar 29 22:43:29 2012 +0530 cluster/afr: Fix split-brain log Change-Id: Id6869fb83bb083809a2a69227e233458e0b9e0bf BUG: 787653 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3041 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 80d0c49125c67fcc0aab48cce7ef895dabf1d006 Author: Pranith Kumar K Date: Thu Mar 29 21:07:06 2012 +0530 cluster/afr: Fix the split-brain log Change-Id: Ia4937dee009af7c945ec590a827c982b0e6ad307 BUG: 787653 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3039 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 630e272a89fde08315b6159b83fcbbd6711a6046 Author: Amar Tumballi Date: Thu Mar 29 13:02:32 2012 +0530 glusterd: add-brick: give proper reason in few error cases had missed few 'else' cases, which were needed to send the right error message to the user regarding the reason for failure. Change-Id: I42d92782f4dec6f6bdffd42df254b7f38a715e36 Signed-off-by: Amar Tumballi BUG: 772544 Reviewed-on: http://review.gluster.com/3032 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 33bbab6ff9b34b1e623a53cc0c3483563f2aeace Author: Kaushal M Date: Thu Mar 29 18:18:50 2012 +0530 cli, glusterd : "volume status detail" fixes Use _PATH_MOUNTED, which refers to /etc/mtab, in glusterd_add_brick_mount_details(), instead of _PATH_MNTTAB, which refers to /etc/fstab. More changes to cli to show available information. Change-Id: I9da97c0fec14b3372f281efc0be37b2799bc2d0d BUG: 808044 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3037 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 7cc52b98a54ef29844a302f2d4f129adcaefcbf3 Author: Amar Tumballi Date: Wed Mar 28 00:14:29 2012 +0530 cli: give warning to user in add-brick if stripe count given * as it is currently not so well tested, user should get notification about possibility of problems with the volume type changes. * added warning instead of removing the feature because with keeping an option we can enhance what is there already. Change-Id: I6cf3491870ac2e50e85c5dbe15c61622a47c18cb Signed-off-by: Amar Tumballi BUG: 787967 Reviewed-on: http://review.gluster.com/3034 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit db501c73701b620be67b4c33ea16cac983dcd9b1 Author: Amar Tumballi Date: Sun Mar 25 22:48:09 2012 +0530 core: fix all the iobuf related refs and unrefs reviewed the code against all the possible places where iobuf/iobref ref unref are present, and hopefully fixed most of the issues around memory leaks with respect to iobuf Change-Id: I9aa30326962991f8e23acedd389a0e962e097885 Signed-off-by: Amar Tumballi BUG: 797875 Reviewed-on: http://review.gluster.com/2994 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 2dea3b34755d9af1d1c1ffe517c6a087cf44512a Author: Kaushal M Date: Tue Mar 27 15:52:47 2012 +0530 cli,glusterd: more volume status improvements The major changes are, * "volume status" now supports getting details of the self-heal daemon processes for replica volumes. A new cli options "shd", similar to "nfs", has been introduced for this. "detail", "fd" and "clients" status ops are not supported for self-heal daemons. * The default/normal ouput of "volume status" has been enhanced to contain information about nfs-server and self-heal daemon processes as well. Some tweaks have been done to the cli output to show appropriate output. Also, changes have been done to rebalance/remove-brick status, so that hostnames are displayed instead of uuids. Change-Id: I3972396dcf72d45e14837fa5f9c7d62410901df8 BUG: 803676 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3016 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 735714edca08e2de16c0e447f8c3256913186ce6 Author: Raghavendra Bhat Date: Thu Mar 29 16:31:24 2012 +0530 features/locks: check whether dict is NULL before refing it Change-Id: I8906b80e584466aceb5a7402e3cee6ac2a552fab BUG: 808003 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/3036 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 3fb9ee6caa3325423ac221b5f24e980c24edafde Author: Jeff Darcy Date: Mon Mar 26 12:27:12 2012 -0400 Save old volfiles in the RPM standard way. I just got bitten by this again. It appears that the previously merged fix was inadvertently reverted by a subsequent change. Change-Id: I3a2067ee891fd5b8be0cd6cee58dcbc8cb6005e9 BUG: 764702 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3009 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d1c8d296a23244a351bc2274e78c315b0870aeeb Author: Kaushal M Date: Thu Mar 29 12:41:22 2012 +0530 glusterd: Increase output_string size in glusterd_get_volopt_content The number of volume options with docs has increased, which causes the output_string to overflow and causes glusterd to crash. This change prevents glusterd from crashing. Change-Id: I79f8931f92ad55245aa547e7df15c9826537b615 BUG: 807914 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3030 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 9d884d7139e9c5b3edca2ecb89f7824ac207ad98 Author: shishir gowda Date: Thu Mar 29 15:17:14 2012 +0530 cluster/dht: send dict with linkto key for lookup in rmdir_readdirp Without this, if there are any stale link files, rmdir fails with ENOEMPTY error. Change-Id: I7056b272122eb5540c22412856f46f638774c119 BUG: 807246 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/3035 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit 834408a49f204e8c256dad4b46d0f19053bf4b0e Author: Pranith Kumar K Date: Thu Mar 29 12:17:12 2012 +0530 cluster/afr: handle fstat failure in data-self-heal The final fstat which makes the call_count 0 could be a failure. In that case the buf could either be NULL or buf is all zeros. If buf is NULL then it will crash, if it is all zeros buf->ia_type will be IA_INVAL and it proceeds to special file fix. sh->type is assigned with the ia_type of the file to be healed. I modified the code to depend on that instead. Change-Id: Icf7e19ff5908207128f2a1ee2963ad6b791c1ac5 BUG: 804645 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/3031 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit fbfb4d48491b160436e6ac986057a8fe5e320502 Author: Raghavendra G Date: Thu Mar 29 11:21:07 2012 +0530 performance/quick-read: fix build errors. Change-Id: I8c4781bdd6c3cfd50cff95c31ecd6d653b916ac3 BUG: 765363 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3028 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 864c9b612a5965a0934dcbdc51f84018d27c2c80 Author: M S Vishwanath Bhat Date: Tue Mar 27 17:59:15 2012 +0530 build-deploy-jar.py: Print usage message when hadoop home directory is missing. Change-Id: I0b55b33a36a4a5e4f1b71547629d20ae6b5eba5a BUG: 807155 Signed-off-by: M S Vishwanath Bhat Reviewed-on: http://review.gluster.com/3017 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit 3360fca3f3abf4dd6b1025063610f5c8c880a747 Author: Kaushal M Date: Wed Mar 28 16:18:17 2012 +0530 cli, glusterd: "volume set help" additions "auth.allow/reject" and "server.statedump" options are included in "volume set help" now. Change-Id: I7f9ba89d1782c26792347ffd2cd4042c3c396934 BUG: 783390 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/3025 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1f7692fecd1b5eaab60a01b64e9e4a67f0630804 Author: Pranith Kumar K Date: Thu Jan 19 12:40:34 2012 +0530 cluster/afr: Handle afr data self-heal failures gracefully Change-Id: I5f91098111a8ca29982f3b4292e2109e4a36cce1 BUG: 765373 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2662 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 243f02a5ef77d69fa91c18092d5da8578bb8f042 Author: Raghavendra G Date: Tue Sep 27 01:20:21 2011 +0530 performance/quick-read: make unlink aware of open-behind behaviour of quick-read. quick-read should do an open of all the fds that are waiting for to be opened behind before doing an unlink on a path. Change-Id: I4c8d65c0511e8a37765ff57e30d99dd89b56c4fc BUG: 765363 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/506 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Vijay Bellur commit bfb6366bd2a6de4cb5322dda72fbc1e6ad1edc41 Author: shylesh kumar Date: Wed Mar 28 10:50:06 2012 +0530 cluster/stripe- do not ref if dict is null Change-Id: Ifa4a5253482d837e2583de078e908b8c442f9dca BUG: 807214 Signed-off-by: shylesh kumar Reviewed-on: http://review.gluster.com/3024 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit b8c4da2ce0326d5c1a3303d4c3931e60b40e9bdc Author: Mohammed Junaid Date: Wed Mar 28 06:31:56 2012 +0530 protocol/client: Set grace_timer_needed flag to false on a disconnect. A grace timer is registered on a disconnect, but a reconnect timer sends a connect request after every 3sec and if the server is down, the client protocol receives disconnect and a grace timer will be registered which on timeout will increase the lk-version value. Its enough to register the grace timer once after the first disconnect and later just ignore other psuedo disconnects until the next successful reconnect. Change-Id: I7f34a98a79fdc25370ef15a6712bfa316a9b7c7c BUG: 807271 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/3020 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit af0eb165f624c6a76e84e5a0c78881715ceae7c3 Author: Raghavendra G Date: Tue Mar 27 08:47:35 2012 +0530 performance/write-behind: queue setattr fop with writes always. stat returned in setattr_cbk can be cached by the kernel. Hence it is always necessary that we return correct stat, which implies that setattr should not be out of order with respect to write fops. Change-Id: I305feeb4802f8a41ffaf032100832cbd65dfc5c1 BUG: 765443 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3011 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c3c4ee24a64a2447f77788cb84559f1e07a21e04 Author: Krishnan Parthasarathi Date: Mon Feb 13 19:15:17 2012 +0530 glusterd: Fixed replace-brick commit_force algo. - commit force subcommand of replace-brick (rb) should be allowed even if source brick is (irrecoverably) offline. - modified rb_timer to be active only for start subcommand. This is important since, the rb timer event relies on src_brick and dst_brick objects to be 'alive' when it 'happens'. In the case of abort/commit/commit force it is very likely that src_brick and/or dst_brick objects could have been destroyed. Change-Id: Ib8b8a4d690fbdd6f99b8aff306490eb59c54a437 BUG: 772845 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2620 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 3184ad0f88255fdec5a33b29790f677848c422e3 Author: Kaushal M Date: Tue Nov 15 18:26:44 2011 +0530 cluster/dht : Acl fix for distribute directory selfheal Send acl xattrs, if present in the xattrs returned during lookup, during directory self-heal. Change-Id: I5337bbd3f3963aeed500a8a552e5f6713089b53e BUG: 764787 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/737 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 98b98d6cd7d94bfae5b4a7b54b04b59bf9381df9 Author: Raghavendra G Date: Mon Mar 26 18:36:29 2012 +0530 libglusterfs/fd: ref fds while copying the fdentries. Change-Id: I8973ec5d9858adfbdd6efc7cd596cf5d5af0e3cb BUG: 767862 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/3006 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 78e5e52c51ceb2255ac28ab86a91ed887d334cf6 Author: Rajesh Amaravathi Date: Wed Mar 7 14:04:07 2012 +0530 mgmt/glusterd: native sort of info files dependence on sort(1) has been removed, sorting of the files is now done using qsort(3). Change-Id: I90e162ba626506d01323ddfbfa594cf64b2e43c3 BUG: 790337 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2990 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c1f8af00eaa03f1c2a7ea145ff627ca749e330cb Author: Jeff Darcy Date: Fri Mar 23 13:13:09 2012 -0400 Fix build problem with "trash" being semi-removed. With "trash" removed from xlators/features/Makefile.am but not from configure.ac, configure fails trying to create .../features/Makefile from .../features/Makefile.in which was itself never created. Change-Id: Idcba2c282c09821ae620e59748952e8d26117fdc Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/3003 Reviewed-by: Kaleb KEITHLEY Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 9d3af972f516b6ba38d2736ce2016e34a452d569 Author: Amar Tumballi Date: Tue Mar 20 17:22:24 2012 +0530 core: adding extra data for fops with this change, the xlator APIs will have a dictionary as extra argument, which is passed between all the layers. This can be utilized for overloading in some of the operations. Change-Id: I58a8186b3ef647650280e63f3e5e9b9de7827b40 Signed-off-by: Amar Tumballi BUG: 782265 Reviewed-on: http://review.gluster.com/2960 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit afe542eca18888463798747d2a95e5a9d239a4a0 Author: Amar Tumballi Date: Thu Mar 22 16:37:42 2012 +0530 glusterd: bring back the 'non-synctask' behavior revert back to non synctask behavior Change-Id: Icfc9cbdeaf8dd6735df8366a6121c6598c56fade Signed-off-by: Amar Tumballi BUG: 805802 Reviewed-on: http://review.gluster.com/3002 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit dc174a4d60ebca6a67e32c1834c2f0dcbff2c3c0 Author: Amar Tumballi Date: Thu Mar 22 04:11:38 2012 -0700 Revert "core: enable process to return the appropriate error code" This reverts commit 16717f4df7b0fbd3c255f5faf8a2744444231bb7 Change-Id: I65624db4d31e11e1bec66b07b352ce823ef069b9 Reviewed-on: http://review.gluster.com/3001 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2db6b286d091346b4386fd6091eb22bd9d3ea7a0 Author: Amar Tumballi Date: Thu Mar 22 13:51:23 2012 +0530 glusterd: fix bugs of syncop for operations * free the stack created for synctask * use different key than 'operation' in dictionary as thats being used already by other glusterd operations * send proper frame to 'rpc_clnt_submit()' API, as it gets used internally * also make sure to destroy the above frame in all _cbk() * move everything specific to synctask into one file, so it is easy to maintain Change-Id: Ia1a4414fffec6f9e51700295947eea4a2104a8c2 Signed-off-by: Amar Tumballi BUG: 805802 Reviewed-on: http://review.gluster.com/3000 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 1522ac5c15516156bb33f8d47b0c0e7de6cd411f Author: Kaushal M Date: Tue Mar 20 18:05:18 2012 +0530 cli: Display available information in "volume status detail" Display the available information in "volume status detail", without failing and erroring out if some information is missing. Change-Id: If8edc268fe91ca9c681f25135738a75eec43b8c3 BUG: 765464 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2989 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f7842792de7661dd72c40fb950102e5dfcf0e487 Author: Rahul C S Date: Wed Mar 21 12:15:52 2012 +0530 Add space for heal vol req log message. Change-Id: Iadf1d6304bcae8f666f2435ffa2d71c50dd1395a BUG: 764658 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2991 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Raghavendra Bhat commit 11be645bb84ade2c5c9f42baec5ca6c6d1dc1d2c Author: Amar Tumballi Date: Wed Mar 14 15:10:48 2012 +0530 dict: add a dict_dump() function to dump the dictionary contents helps for debugging some functionalities where we have to understand what we send from one end point to another is properly received on the other endpoint without any errors. Change-Id: I9b802f12ae542e499161a1f3b9a5602f7b93b0ee Signed-off-by: Amar Tumballi BUG: 782265 Reviewed-on: http://review.gluster.com/2959 Reviewed-by: Jeff Darcy Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System Reviewed-by: Anand Avati commit ebb5c6cc1e0d47513edb851128e424e747bb9166 Author: Krishnan Parthasarathi Date: Wed Mar 21 12:39:13 2012 +0530 glusterd: Disabled self-heal on clear-locks internal mount - Also, changed afr_get_xattr_clrlk_cbk to use dict_set_dynstr for clear-lock summary. Earlier, it was relying on 'str' passed from xlators below. Change-Id: I175f4542e6ef2c859c4811eecb9d8c5a7d25a283 BUG: 800779 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2992 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit abae8a2086e71aaf193b12df90ae3fe687117c28 Author: Amar Tumballi Date: Thu Oct 13 15:23:39 2011 +0530 core: enable process to return the appropriate error code Credit of this patch goes to Avati as I just did a rebase to the lastest master. Change-Id: I53b2adf90fd9808433bdc35b57dad0682bc90860 BUG: 762935 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/579 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit c3bdb1d4c6c4491afdf1ba26bb0d6204270cc058 Author: Amar Tumballi Date: Tue Dec 20 14:54:35 2011 +0530 glusterd: bring in feature to use syncop for mgmt ops * new sycnop routines added to mgmt program * one should not use 'glusterd_op_begin()', instead can use the synctask framework, 'glusterd_op_begin_synctask()' * currently using for below operations: 'volume start', 'volume rebalance', 'volume quota', 'volume replace-brick' and 'volume add-brick' Change-Id: I0bee76d06790d5c5bb5db15d443b44af0e21f1c0 BUG: 762935 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/479 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 8217148c97a474a9eab4a309589ceb8ff281f5c6 Author: Pranith Kumar K Date: Wed Mar 21 21:57:37 2012 +0530 features/locks: Avoid race in pl_inode_get Change-Id: I6c7b878fb43863137aac6552ee66f091534a6296 BUG: 770080 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2998 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b1f1d57ca547cfa7644914bf7ff2d731b4a49134 Author: Pranith Kumar K Date: Wed Mar 21 15:41:26 2012 +0530 features/locks: Avoid race in creating domains Thread:1 | Thread:2 ----------------------------------------- 1) Does inodelk on inode1| 1) Does inodelk on inode1 2) It tries to get the | 2) It tries to get the dom object for the volume| dom object for the volume volname-replicate-0. But | volname-replicate-0. But the domain list is empty.| the domain list is empty. 3) Create the new domain | dom1 and add it to head | of the list of domains. | 4) inodelk happens on | 3) Create the new domain dom1 on range r1. | dom2 and add it to head | of the list of domains. | 4) inodelk happens on dom2 on range r2 5) unlock for r1 comes | 5) Unlock on r2 succeeds. on inode1. | 6) It tries to get the | domain, of the inodelk | for volume | volname-replicate-0, gets| dom2 but the lock on | range r1 is not present | so it fails. | subsequent inode lock, unlocks will keep happening on the domain dom2. The stale lock present in the dom1 on range r1 will live on. It wont cause any hangs, but the statedump will always be scary. Change-Id: I9adc120d33febf685b30859cc307768c2fc63ae5 BUG: 770080 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2993 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit c40b9975d0bb3fdffdab281ad4f5e222d63d8674 Author: Raghavendra G Date: Wed Mar 21 10:58:03 2012 +0530 protocol/client: memory leak fixes. Signed-off-by: Raghavendra G Change-Id: I804c934d79ed13ded9d1b741cef6597bc238e476 BUG: 803675 Reviewed-on: http://review.gluster.com/2987 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit b8e98e8d6fa1a783f9dac4eb17609f799fde4b2b Author: Raghavendra G Date: Tue Mar 20 17:11:04 2012 +0530 performance/read-ahead: destroy pages which survived from being flushed in flush_region because of frames waiting on them, after those frames are served. Change-Id: Ic8402f3da32058a1a11e62124b598b0ec3befeff BUG: 767948 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2982 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit dbae3d58d7dbfb404211866a17da1559cdde3387 Author: Raghavendra G Date: Tue Mar 20 16:48:18 2012 +0530 performance/io-cache: destroy the pages which survived in __ioc_page_destroy because of non NULL waitq in ioc_fault_cbk. Change-Id: I00b83f8bf0a654b3a3a23cf0b25657fbfda17804 BUG: 767948 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2981 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit e8f9aabb782d4e97b1c2a6df379128c3f3962401 Author: Raghavendra Bhat Date: Tue Mar 20 16:00:41 2012 +0530 protocol/server: remove the transport from the list irrespective of lock-heal is on/off Upon getting disconnect, remove the transport from the list of transports that protocol server maintains irrespective of whether lock-heal is on or off, since upon reconnect a new transport would be created. Change-Id: I18a269a93487d6e2cb11c345b6dde813d089809c BUG: 803815 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2980 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit a2291931d550cbbc19983bccb93dbf31a9993db4 Author: Mohammed Junaid Date: Mon Mar 19 12:05:09 2012 +0530 features/marker: Replacing -1 with GF_CLIENT_PID_GSYNCD as part of code cleanup. Change-Id: Ia665060bff636b372904a726aba5249de9ade124 BUG: 769494 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2971 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit c816d16288d3089d9e986c3155cb5ca9265b6210 Author: Jeff Darcy Date: Mon Mar 12 09:32:40 2012 -0400 replicate: fix a glitch in up_count/down_count updates. Change-Id: I4919a98191bf7fe5edad9a149a129bcd177cd4a8 BUG: 802522 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/2927 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2ffefd720a54fb815b1efa11e9de766fe1518831 Author: Mohammed Junaid Date: Mon Mar 19 21:26:56 2012 +0530 protocol/client: Handle failures in lock self healing gracefully (part2). During reopening of fd's and reacquiring of locks on the fd (after a reconnect), a release on a fd on which reacquiring of locks is in progress will free up fdctx. This patch will keep fdctx valid until the reacquiring of locks is in progress. Change-Id: I0fae27544a7f8ddaa26def4ee4d41a8a2b322521 BUG: 795386 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2819 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d98c3e19342be3b8b3e2c7e3d7e544de34143bdf Author: Amar Tumballi Date: Mon Mar 19 18:10:34 2012 +0530 rpc-clnt: separate out connection_cleanup() from destroy() noticed that there are possibilities where one would like to do a connection_cleanup() before destroying a RPC connection itself, also current code is such that, rpc_clnt_connection_cleanup() does rpc_clnt_ref() and unref(), creating a race window/double unref possibilities in the code. by separating out the functions, this race window/double fault can be prevented. Change-Id: I7ebd3392efa891232857b6db9108b0b19e40fc12 Signed-off-by: Amar Tumballi BUG: 802403 Reviewed-on: http://review.gluster.com/2979 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 55c22fbfae259bff3b0e0cca192f709b74d8bee5 Author: Mohammed Junaid Date: Mon Mar 19 21:07:33 2012 +0530 protocol/client: Handle failures in lock self healing gracefully (part 1). During reopening of fd's and reacquiring of locks on the fd (after a reconnect), a release on a fd on which reacquiring of locks is in progress will free up fdctx. This patch will keep fdctx valid until the reacquiring of locks is in progress. Change-Id: I0464c751a5aa986abac0b72b48b261fceeba24e8 BUG: 795386 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2937 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 83277598bda524f44b76feed6adc7b19fc49d49a Author: Mohammed Junaid Date: Mon Mar 19 19:56:21 2012 +0530 protocol/server: Handle server send reply failure gracefully. Server send reply failure should not call server connection cleanup because if a reconnection happens with in the grace-timeout the connection object is reused. We must cleanup only on grace-timeout. Change-Id: I7d171a863382646ff392031c2b845fe4f0d3d5dc BUG: 803365 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2947 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f076c23f381d9013d4fa2145c329033a51194597 Author: Vijay Bellur Date: Mon Mar 19 18:02:57 2012 +0530 protocol/client: Avoid STACK_DESTROYing more than once in RELEASE fops. Change-Id: I435327c6133aa6739731dabddde860b0b43c1497 BUG: 804607 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2978 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit b315c42344f808bd9e2cba06bade0e5da58b0381 Author: Rahul C S Date: Mon Mar 19 15:03:09 2012 +0530 print bound_xl only once in server statedump since, currently there is only one bound_xl for all connection objects, it does not make sense to print the bound_xl for every conn object. Change-Id: Iaf4a170fe63fb7e80133c449a20f298f0e86364c BUG: 765495 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2975 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a77c4a7954df0f0e3d075895039e66eb4361562b Author: Kaushal M Date: Mon Mar 19 15:13:14 2012 +0530 features/quota : Fix timeout min value Change timeout min value to 0, so that default value of 0 successfully validates and mounts happen properly. Change-Id: I579c6192b97ffe2678fa95c912679b514fa7d8c0 BUG: 804509 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2976 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 028936e2dc544158011eb32ad1629eeed75a42e9 Author: shishir gowda Date: Mon Mar 19 11:56:20 2012 +0530 cluster/dht: Prevent crash in dir xattr selfheal Change-Id: I2ca4ab2f8e8611e7b2ac9ed2edc2e304727259dc BUG: 804280 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2970 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit def3dd7f37150657e1b41a2df8a563a93394a518 Author: Raghavendra G Date: Mon Mar 19 14:07:14 2012 +0530 libglusterfs/call-stub: ref dict while storing it in readdirp stub Change-Id: I11224f7afa2e87dc242cc2e9e865c7ab2bb88c7e BUG: 765785 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2974 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 65c6e3706f5290947179922c9e3b8f05ea6ae91c Author: Harshavardhana Date: Fri Jan 6 16:00:25 2012 -0800 libglusterfs/dict: Add boundary conditions Functions modified: 1. data_to_int16() 2. data_to_uint16() Change-Id: I6775ca5d39f519c24ca3a07ce41018472e238cdf BUG: 769692 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2599 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 5f59fbd81830a5f2157b3206d8413ba862aa5253 Author: Venky Shankar Date: Wed Mar 14 16:45:21 2012 +0530 cluster/stripe: fix {set/get}xattr query for dirs/symlink This patch fixes the following problems: * ENOENT returned for getxattr (xtime) on symlinks Non-data entities are created only on the first subvolume but getxattr fop winds to all subvols. This results in all subvols except the first one to return ENOENT which is propogated down the stack. * ENODATA returned for getxattr (xtime) on directory setxattr calls always wind to the first stripe subvolume. xtime getxattr invocation winds to all subvolumes but the xattr is present in only the first one, resulting in all subvols except the first one to return ENODATA. Fix For symlinks getxattr now always winds to the first subvol and for directories setxattr sets the xattr on all subvols. NOTE For directories the all-subvol-wind in setxattr is done only when request is from a special client (client-pid == -1) Change-Id: I9236345ef319506770d2034b840ee4ac04704b21 BUG: 801394 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2948 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Anand Avati commit 1477fe376ae51ae077430aea25aa6a7a34596768 Author: Pranith Kumar K Date: Sun Mar 18 14:10:08 2012 +0530 Logs: Improved logs in lock/unlock execution path Statedump will now start showing the lk-owner of the stack. Change-Id: I9f650ce9a8b528cd626c8bb595c1bd1050462c86 BUG: 803209 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2968 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit dfc481bf2dfe9a26d8c311de578ca82b347810d0 Author: Raghavendra G Date: Thu Mar 8 14:13:56 2012 +0530 protocol/client: replace STACK_UNWIND_STRICT macro with CLIENT_STACK_UNWIND, which does appropraite cleanup before unwinding. Signed-off-by: Raghavendra G Change-Id: Ic49d6e21c5fc56e747afec35be2bebbbbd2a6583 BUG: 767359 Reviewed-on: http://review.gluster.com/2897 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 4d4a1e0801d1a7b2b3ec226309809c5fddd84319 Author: Raghavendra G Date: Thu Mar 8 10:59:43 2012 +0530 rpc: don't unwind the fop in caller if client_submit_request fails client_submit_request guarantees that the cbkfn - which we pass to it as argument - is called whenever there is a failure. Change-Id: I0e8ce5a6b320246dc13ce4318b04739d38d183a3 BUG: 767359 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2896 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 968c6ba70cbcc058823947cc925072e03cbb0ac8 Author: M S Vishwanath Bhat Date: Fri Mar 16 17:02:46 2012 +0530 Using correct path to build and find jar file in build_deploy_jar. Change-Id: Ifeadd60370b36ab7b345c336a40a17091698ffe5 BUG: 803879 Signed-off-by: M S Vishwanath Bhat Reviewed-on: http://review.gluster.com/2955 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit e6753927338a12175f3a87fd4349d41847b8d2aa Author: Pranith Kumar K Date: Sun Mar 18 13:49:07 2012 +0530 rpc: cancel reconnect timer in rpc_clnt_disable When the graph is considered no longer needed, rpc_clnt_disable is called, which disconnects the connection to server but the reconnect timer is not cancelled in that function, so it is reconnecting to the server before the grace-time-period. The locks of the disabled graph are still there on the server which are leading to hangs. Change-Id: I8d37f1296370e37117005137a0a430e636da4d2e BUG: 803209 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2967 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7fdd830431614231e0372faaff33359932b9631a Author: Amar Tumballi Date: Wed Mar 7 08:11:57 2012 +0530 volgen: by default don't include performance xlators in nfs volfile Change-Id: I183ff00b0c0d23cec1123c320b7444eec0f71765 BUG: 790333 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2883 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas Reviewed-by: Anand Avati commit 9fd44bd90ecb60760919bda85308132341f857f9 Author: Pranith Kumar K Date: Sun Mar 18 13:07:30 2012 +0530 protocol/server: Clear internal locks on disconnect If there is a disconnect observed on the client when the inode/entry unlock is issued, but the reconnection to server happens with in the grace-time period the inode/entry lk will live and the unlock will never come from that client. The internal locks should be cleared on disconnect. Change-Id: Ib45b1035cfe3b1de381ef3b331c930011e7403be BUG: 803209 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2966 Reviewed-by: Anand Avati Tested-by: Gluster Build System commit f20d895a8ed2a3ee032bd0f85d5bfaf645575fd7 Author: Amar Tumballi Date: Mon Mar 12 17:50:34 2012 +0530 mgmt/glusterd: don't create the brick path in 'volume start' create the missing brick directory only on a 'gluster volume start force' command Change-Id: Ica4fab9cefe953d73de9a30843d48f94e6ab735c Signed-off-by: Amar Tumballi BUG: 801610 Reviewed-on: http://review.gluster.com/2921 Tested-by: Gluster Build System Reviewed-by: Rajesh Amaravathi Reviewed-by: Anand Avati commit 6bf0a809c99ec33fee73e6ebebb58baa2614f977 Author: Raghavendra Bhat Date: Tue Mar 6 14:35:45 2012 +0530 protocol/server: send forget on the renamed inode If rename is given on a file "a" to "b" ("b" is already existing file), then after rename, the inode for "b" would still be in the inode table and would not get forget (for fuse client, the fuse kernel module would send, but on server forget will not come on that inode), thus leading to inode leak even when the mount point is empty. To avoid that before doing inode rename, unlink the previous inode that "b" is pointing to and send forget on that, if "b" is the last dentry for that inode. Change-Id: Ie4dcc39ea190ee8f28029b4d7661df576d9cf319 BUG: 799833 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2874 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 93022c0cc6c22b3a30ded3e109a3fe0a0dce8ca0 Author: Kaushal M Date: Wed Mar 7 13:06:38 2012 +0530 mgmt/glusterd : volume set validation fixes This is the new version of the patch by Kaushik at review.gluster.com/699 The following new option types have been introduced: * GF_OPTION_TYPE_INTERNET_ADDRESS_LIST * GF_OPTION_TYPE_PRIORITY_LIST * GF_OPTION_TYPE_SIZE_LIST and option types of several options in translators have been updated to use the new types. valid_internet_address(), valid_ipv4_address() & valid_ipv6_address() functions has been updated for * wildcard matching. Previously used standalone wildcard address checking functions have been removed. Changes have been done to stripe translator to correctly set, update and use stripe-blocksize. Also minimum value for block-size has been set to 16KB. Change-Id: I2aa484ff695f6a915a8fc9a9f965cf0344f41d59 BUG: 765248 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2899 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Anand Avati commit c3bbf6aa6c090fd066ab0079aa1c8ae332309d2a Author: Louis Zuckerman Date: Tue Feb 7 11:16:10 2012 -0500 Updated the Ubuntu upstart jobs for glusterd in extras/Ubuntu. Using upstart jobs, instead of an initscript, solves Bug 765014. See also: https://bugs.launchpad.net/ubuntu/+source/glusterfs/+bug/876648 The new upstart jobs split the work of starting glusterd & mounting glusterfs volumes into two parts: a glusterd service runner and a glusterfs volume moung blocker which waits for the service runner. This is the method preferred by Ubuntu developers to block a mounting event until a required service is available. These changes will be included in the Ubuntu glusterfs-server package starting with release 12.04, Precise Pangolin. Tested on Ubuntu 12.04 Change-Id: I9bb4e8cb05a1da0997c23f2ef7fea8737f6a2eb9 BUG: 765014 Signed-off-by: Louis Zuckerman Reviewed-on: http://review.gluster.com/2727 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 598ab12c30b44c4c5f5922f3b76eec2ed8872790 Author: Raghavendra G Date: Wed Mar 14 16:13:17 2012 +0530 mount/fuse-bridge: don't pass flags O_CREAT | O_EXCL during open as part of fd-migration during graph-switch Change-Id: Ia1494941d3e3d5bebdba3483b0ea7b32c9704b8c BUG: 802710 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2943 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 642343cc55e6ea2b0d463d77334c34790c30080f Author: Pranith Kumar K Date: Fri Mar 16 16:09:42 2012 +0530 Self-heald: Handle errors gracefully and show errors to users Change-Id: I5424ebfadb5b2773ee6f7370cc2867a555aa48dd BUG: 800352 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2962 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f159e2247b58441449ad8da13ddf5cc5d3887b93 Author: Pranith Kumar K Date: Fri Mar 16 22:10:02 2012 +0530 cluster/afr: set_read_child when xactions in progress in fresh lookup Change-Id: I33e0268635ae7a1f247b0052994e027f990083da BUG: 800755 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2963 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7cc412c7a2d2e4a6c7709b84bed75c10e5476244 Author: Amar Tumballi Date: Thu Mar 15 16:04:10 2012 +0530 mem-pool: more debug friendly logs by using gf_log_callingfn() Change-Id: I4d6e53ad8660314315f2ff3aa92ffbe707d6efe9 Signed-off-by: Amar Tumballi BUG: 803638 Reviewed-on: http://review.gluster.com/2951 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit e3a3912f890a73a13020acba86394125bb501b95 Author: Krishnan Parthasarathi Date: Thu Mar 15 11:52:07 2012 +0530 afr: Copy loc->gfid independent of lookup being fresh or otherwise This change ensures that entry self-heal following a lookup on that entry would have loc->gfid 'filled'. Change-Id: If723c71ca43e1f062dcb99cbe5488342514dace0 BUG: 786087 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2950 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit bf818f9a9e299475b09b85e28f3bca57f4a00624 Author: Rahul C S Date: Sat Mar 17 18:32:04 2012 +0530 Change option brick-with-valgrind to run-with-valgrind brick-with-valgrind does not make much sense because all the glusterfs/glusterfsd server processes are run with valgrind. So changing the option from brick-with-valgrind to run-with-valgrind. Also fix misspelt 'valgrnd' for valgrind log file namenames. Change-Id: I87aad6d65ffc37d8f8679be215709a9174385ecd BUG: 804293 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2965 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit a3c8c7be83a4be1cb3d89a187da05d9247cc4f07 Author: shishir gowda Date: Thu Mar 15 10:51:12 2012 +0530 cli/remove-brick: Enhance remove-brick status to display Rebalance status now contains info from all nodes. Signed-off-by: shishir gowda Change-Id: I6208c9879927fb6ddc0713c1480feadcf4f3fd75 BUG: 797887 Reviewed-on: http://review.gluster.com/2949 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Kaushal M Reviewed-by: Anand Avati commit 3823d7ee14fca54e513d45374e882c6de64fd2a7 Author: Raghavendra G Date: Fri Mar 16 09:11:58 2012 +0530 protocol/server: memory leak fixes. Change-Id: I203832d9d52373f068f90e30dc7672329d65bbea BUG: 803675 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2954 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit ca15758018b4da68da40c34f240de75b44cb49e9 Author: Pranith Kumar K Date: Thu Feb 23 15:43:58 2012 +0530 cluster/afr: Enable eager-lock Eager-lock is disabled by default. Use cluster.eager-lock on/off to change the config. write-behind on and eager-lock off is not supported configuration. In afr, when eager-lock is enabled the inode lock on fd is taken using the fd address as the lk-owner. So the lock is interchangableale between the inode-locks on the same fd. Change-Id: I7eef1ecd510f8028f5395dee882782da53c0de3f BUG: 802515 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2925 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit cba2f84cd084fdf005977690dce3c54fa9f8b133 Author: Rajesh Amaravathi Date: Fri Mar 16 16:59:45 2012 +0530 rpc-lib: memleak fix in rpcsvc_volume_allowed Change-Id: Iaa6baa4a3e036b2b5c808ea5e79017fffeb80a24 BUG: 801754 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2956 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit fb406f942befbe48eec75043d89ecd0824f91dd6 Author: Raghavendra Bhat Date: Fri Mar 16 16:25:07 2012 +0530 protocol/server: add and remove the transports from the list, inside the lock Till now for graph changes, glusterfs client used to remember the old graph also. Hence the transport object on the server corresponding the old graph never received disconnect. But now since the graph cleanup is happening, transport on the server side gets disconnect for the cleaned up graph. Server maintains, all the transports in a list. But addition of the new transport to the list, or removal of the transport from the list is not happening within the lock. Thus if a thread is accessing a transport (in cases of statedump, where each transprt's information is dumped), and the server gets a disconnect on that transport, then it leads to segfault of the process. To avoid it do the list (of transports) manipulation inside the lock. Change-Id: I50e8389d5ec8f1c52b8d401ef8c8ddd262e82548 BUG: 803815 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2958 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 178652106c5d731b24ddc9bb9bc1d8aae3952e2d Author: Pranith Kumar K Date: Fri Mar 16 11:35:36 2012 +0530 glusterfsd: Handle errors in response send Change-Id: I2d0a136fdfc4c86fb89cff5565efbf4af80e1edf BUG: 799265 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2961 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 6aab9d9602dc1ef62a2d1d63aa1764a062bf9d9f Author: Pranith Kumar K Date: Sat Mar 3 17:28:17 2012 +0530 protocol/server: Avoid race in add/del locker, connection_cleanup conn->ltable address keeps changing in server_connection_cleanup every time it is called. i.e. New ltable is created every time it is called. Here is the race that happened: --------------------------------------------------- thread-1 | thread-2 add_locker is called with | conn->ltable. lets call the | ltable address lt1 | | connection cleanup is called | and do_lock_table_cleanup is | triggered for lt1. locker | lists are splice_inited under | the lt1->lock lt1 adds the locker under | lt1->lock (lets call this l1) | | GF_FREE(lt1) happens in | do_lock_table_cleanup The locker l1 that is added just before lt1 is freed will never be cleared in the subsequent server_connection_cleanups as there does not exist a reference to the locker. The stale lock remains in the locks xlator even though the transport on which it was issued is destroyed. Change-Id: I0a02f16c703d1e7598b083aa1057cda9624eb3fe BUG: 787601 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2957 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 5e50175f56d05ab6c1295b0e0f0c11695e49c277 Author: Amar Tumballi Date: Thu Mar 15 14:00:13 2012 +0530 core: bring a cmdline option to set memory-accounting currently this is implemented as a command line option, and not as an easier translator option. this is because as of now, before even the volume files are parsed, we would need memory accounting enabled. there is scope for improving this behavior, but for now, this approach solves the problem. Also, this feature's major consumers are the testers who are looking for leaks, hence option is hidden from usage output. Change-Id: I09a5b13743ae43ff42c251989f921319e94cabe3 Signed-off-by: Amar Tumballi BUG: 799199 Reviewed-on: http://review.gluster.com/2856 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit eb8a9aae19755bc21afe2d8ed4893b788c4e84ff Author: Amar Tumballi Date: Thu Mar 1 17:25:12 2012 +0530 core: dict allocations through mem-pool Change-Id: I7401639060957d437808779745a1e46c3f9f4585 Signed-off-by: Amar Tumballi BUG: 798503 Reviewed-on: http://review.gluster.com/2851 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d05708d7976a8340ae7647fd26f38f22f1863b6a Author: shishir gowda Date: Wed Mar 14 15:35:51 2012 +0530 dht: Rebalance status should display status from each process Change-Id: Id128417219bdb7146253618a5f8f31ef35013894 BUG: 801322 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2942 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 212d739886cde04ca79f58915a84b6ed09eec00b Author: krishna Date: Tue Feb 28 13:28:31 2012 +0530 remove code that was part of hard resolution which is not needed anymore. Change-Id: I9321745a40765eff048a656a7885f12847a0a318 BUG: 781318 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2830 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 6826e046157a6ea1a07ba2a38a1825b05eb0b666 Author: Csaba Henk Date: Mon Feb 27 05:41:17 2012 +0100 glusterd/mountbroker: enhance mountbroker-geo-replication.* option to take multiple volumes Comma can be used in the value of a "mountbroker-geo-replication.*" option with semantics as of these examples: option mountbroker-geo-replication.foolabel vol1,vol2,vol3:geouser and option mountbroker-geo-replication.geouser vol1,vol2,vol3 will allow geouser to mount any of the volumes vol{1,2,3} with params of a geo-rep aux mount under label foolabel, resp. geouser Also fix memleak in parsing of this option. Change-Id: I5311388812f503a078a52a14f2679f5ddb33b248 BUG: 765214 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2818 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Venky Shankar commit 48adf93423ba52f2a0e6d9d59060e6f2f1aa203c Author: Krishnan Parthasarathi Date: Mon Mar 12 17:34:32 2012 +0530 afr: Corrected getxattr 'key' matching in case of clrlk cmd - Added local->dict cleanup into afr_local_cleanup Change-Id: Ie1b96615735a9d2a2be1757cd016dbe225aae31c BUG: 800412 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2922 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit bf65ae4fef113d78b7555db8520cd9f64817eda2 Author: Kaushal M Date: Wed Mar 14 18:28:09 2012 +0530 glusterd: Fix brick op to prevent glusterd crashing Was building payload only for node types GD_NODE_BRICK & GD_NODE_NFS. Payload wasn't being built for nodes GD_NODE_SHD & GD_NODE_REBALANCE, which made glusterd crash when those operations were performed. Also fix a compile warning. Change-Id: Id33e21c84901d4d112c54514b7f16add31aeb950 BUG: 803313 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2946 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 160ff641157359dc60d1a37652ef449b3c21ebad Author: krishna Date: Thu Mar 8 17:11:42 2012 +0530 rpc: log in DEBUG when nfs clients try to see if ACL requests are accepted by nfs server Change-Id: I897b48a02ce2150d268a1a8b45163e9e1aee6cff BUG: 801338 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2901 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 152bf376b51a896f65470a65d8e9410f19d8689b Author: Amar Tumballi Date: Tue Mar 13 16:58:04 2012 +0530 rpm spec file: update the 'logrotate' config file during rpm install so there is no need for admin to worry about logrotate configs. Change-Id: Iec6def870d0c3550f2642ade023c03de52d6d530 Signed-off-by: Amar Tumballi BUG: 801372 Reviewed-on: http://review.gluster.com/2935 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit aa0f68aa8ec38808a83553abde8d8211047e7b4e Author: Raghavendra Bhat Date: Mon Mar 12 21:06:45 2012 +0530 nfs: do not call inode_path on the newly created inode While resolving, for building the path into the loc, inode_find is called with gfid as argument to get the inode from the inode table. If the inode is not found, then a new inode is created. Then the path is build using inode_path. But if the inode is not linked to inode table (newly created inode), then gfid will be null and inode_path returns null gfid as the path. Suppose the lookup operation on that gfid fails, then we print the null gfid in the log message. To avoid it, build the path using the gfid only if inode_path fails. Change-Id: I2506fa8675761ddb0bc02980cd3583d9d068fc85 BUG: 802424 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2930 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 7bd561996d5a32071942b598739b130e020f89ee Author: Krishnan Parthasarathi Date: Mon Mar 12 13:15:14 2012 +0530 locks: Fixed incorrect list ptr manipulation in clearing entrylks Avoided unwinding blocked entry lock frames inside pl_inode->mutex. Change-Id: I424c4a1762c889c1a567c588d4ca383a6c338886 BUG: 800412 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2878 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 84ef0ec98763c1ce92d0cc24d29d9953bb6bd3f1 Author: Raghavendra G Date: Wed Dec 14 16:01:20 2011 +0530 performance/io-cache: cleanup the xlator private data completely in fini. Change-Id: Ib8859c57e89248ccaad94662f88944e79ec28d5a BUG: 767862 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/791 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 1e5653165a97999288cbf40e670d6c84a31ad3f6 Author: Raghavendra G Date: Mon Mar 5 15:15:04 2012 +0530 fuse-bridge/graph-cleanup: don't provide a cbk for cleanup syncop task without a cbk, syntask_new returns only after the task is complete. Hence we don't have to wait on a conditional variable in the caller. Change-Id: Ie83894aa6fc02cc3a973930e67ae2b35de3b7647 BUG: 767862 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2870 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a059bc30561a3046e255ba1e6ad54b09f0b03636 Author: Raghavendra Bhat Date: Thu Mar 8 01:26:29 2012 +0530 cluster/afr: handle sending NULL dentry name for inode link in self-heal-daemon * Without the dentry name, dentry cannot be created in inode_link, which leads to trying to access the null dentry to check if it is cyclic and thus segfault. So send the parent inode also NULL, which just returns the proper inode after assigning the gfid and type to the inode without trying to create dentry. * Handle failures such as dentry_create returning NULL, in inode_link properly and return NULL in such cases. * Increase the lru limit of inode table of self-heal-daemon to 2048 Change-Id: I7ae0e0e9be279d1694b6aafb5e054585e43f03ff BUG: 801149 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2893 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f9be1e7c665be0507e431cb42cd55032807bd3ea Author: Raghavendra G Date: Wed Dec 14 16:06:21 2011 +0530 performance/read-ahead: cleanup xlator private data completely in fini. Change-Id: I3bb143036557d7d3844dc825f6870140e414f85a BUG: 767862 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/792 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 7161d0995c937c1712d29a04356a11ca51e9ce07 Author: Raghavendra G Date: Wed Dec 14 15:47:01 2011 +0530 performance/quick-read: implement fini Change-Id: I92d4e7ded470b0e97b699656a890bab8c113bf4f BUG: 767862 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/790 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 29a3dc028d2847bd8421b23b7c7ee5419bd30392 Author: Amar Tumballi Date: Mon Mar 12 12:53:01 2012 +0530 mgmt/glusterd: provide an option to make a volume read-only this can be triggered by "gluster volume set read-only on", which adds read-only translator on server graph, thus making the volume read-only. Change-Id: Iee32e6b2f3022d16016534914a5198d1cd327e25 Signed-off-by: Amar Tumballi BUG: 798877 Reviewed-on: http://review.gluster.com/2915 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit eae8a469e7172380dd9c820405e7528a0ec33bad Author: Raghavendra G Date: Wed Mar 14 10:14:18 2012 +0530 performance/io-cache: store op_errno in page. This will enable us to pass appropriate op_errno indicating EOF even during cache-hits. Signed-off-by: Raghavendra G Change-Id: Ib239b5de9b8fca2bd8eb5ec87c93f2cb1c11a99c BUG: 795789 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2939 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c0b3ba9b3b65de88628a36cc51d2864ec72de0d0 Author: Krishnan Parthasarathi Date: Wed Mar 14 14:16:08 2012 +0530 glusterd: Checked if peer is connected and 'handshaked' before sending updates Change-Id: Ia57378d5c81b263d6fcbc9d54ccc7fb138d83d8e BUG: 801731 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2941 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 404e8f27d3a9e950173e02151eccbb792615e535 Author: Amar Tumballi Date: Tue Mar 13 13:54:11 2012 +0530 distribute-rebalance: fix the logic of ENOENT handling due to this, we were missing the entries from the last subvolume of distribute for all the rebalance or remove-brick operations Change-Id: I486f15c1d3d17cbf6f353f6179b2623af61f4868 Signed-off-by: Amar Tumballi BUG: 770346 Reviewed-on: http://review.gluster.com/2933 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 90333660ce4dd1fc94aa8f6b30c085d354f6693e Author: Amar Tumballi Date: Tue Mar 13 17:26:13 2012 +0530 storage/posix: don't allow rmdir()/lookup() on HIDDEN_DIRECTORY so that we won't even have a GFID set on the GFID dir itself. Change-Id: I65be7d675a308f51f4c62a86499341412b20c47f Signed-off-by: Amar Tumballi BUG: 802726 Reviewed-on: http://review.gluster.com/2936 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 718a8ab91f6b9bd84da52c2029707f48e9fecaa4 Author: Rajesh Amaravathi Date: Tue Mar 13 13:13:11 2012 +0530 rpc-lib/rpcsvc: nfs auth corrections in comparing ip addresses during authentication, we need to take only the ip address of the client instead of the transport endpoint (ip:port). Change-Id: If48eca37edea1d69deb150720fbaea0ea2443a00 BUG: 771845 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2929 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 91b4c34805f69c30c4730352eee873cee0dc17ee Author: Amar Tumballi Date: Mon Mar 12 18:07:09 2012 +0530 nfs: no need to recalculate the 'ino' from gfid it is guaranteed to be sent properly from posix layer itself now Change-Id: Ifbbf558f3bcfa609bf107a75c692003ca261ac0a Signed-off-by: Amar Tumballi BUG: 800831 Reviewed-on: http://review.gluster.com/2923 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit daa7cb945027e6564068310a9b857d0eb4ec1779 Author: Rajesh Amaravathi Date: Wed Mar 14 12:15:05 2012 +0530 glusterd: file perm change for glusterd.info this is need for the vdsm gluster plugin, changing glusterd.info file's permission to 644 from 600. Change-Id: I9de39f1b8b31a6c2f448e2ff6601eb270d042343 BUG: 802217 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2940 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit b61103d7ea35a2ea190465c836fe0d22f9f6f8c1 Author: Kaushal M Date: Fri Mar 9 09:38:36 2012 +0530 core, cli : Changes to statedump This patch, * Enables missing inodectx, fdctx dumpops for cli statedump command. * Reintroduce changes introduced in statedump.c by 489a7a10 which were overwritten by db20a0f8. * Change strncasecmp() in gf_proc_dump_parse_set_option() to strcasecmp() to properly parse similar options like fd-fdctx, inode-inodectx Change-Id: I85ad854dce73048617b933d29cf360af9d0ed90a BUG: 797788 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2914 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 84da099ed321621928f11fe9cd164a4b0cfe1883 Author: Raghavendra G Date: Wed Mar 14 09:58:05 2012 +0530 features/marker: Nameless lookup related fixes while filling a loc structure, marker should not error out if loc->name is NULL or loc->path is just a gfid. Change-Id: Ie3a9cffde2d17da0377f1e41de93b099a9133abe BUG: 801364 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2938 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit a476aba5b0368c3bc649db319ee748ae410144d9 Author: Kaushal M Date: Mon Feb 27 12:41:24 2012 +0530 cli, glusterd, nfs: "volume status|profile|top" for nfs servers Enables usage of volume monitoring operations "volume status", "volume top" and "volume profile" for nfs servers. These operations can be performed on nfs-servers by passing "nfs" as an option in cli. The output is similar to the normal brick outputs for these commands. The new syntaxes for the changed commands are as below, #gluster volume profile {start|info|stop} [nfs] #gluster volume top {[open|read|write|opendir|readdir [nfs]] |[read-perf|write-perf [nfs|{bs count }]]} [brick ] [list-cnt ] #gluster volume status [all | [nfs|]] [detail|clients|mem|inode|fd|callpool] Change-Id: Ia6eb50c60aecacf9b413d3ea993f4cdd90ec0e07 BUG: 795267 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2820 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit fcb5ebde1e84da871a7f43df9ecbce7d1d1de435 Author: Brian Foster Date: Thu Mar 8 16:11:58 2012 -0500 system/posix-acl: fix reference counting in posix_acl_readdirp_cbk unref. the acl pointers from posix_acl_get() Change-Id: I1247f64ceded17bfa204d1b899ec56a27bef0cdb Signed-off-by: Brian Foster BUG: 801183 Reviewed-on: http://review.gluster.com/2904 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit 61a550b77b776145d45025467f3fa6e9040bc2e0 Author: Brian Foster Date: Wed Mar 7 14:56:19 2012 -0500 system/posix-acl: fix acl inode assignment in posix_acl_readdirp_cbk If an entry includes no ACL returned via dictionary, it is possible to skip down to acl_set without updating acl_access and/or acl_default. If either are set from the previous iteration, the unrelated ACLs are set to the current entry. Use a single set of pointers to ensure that valid ACLs are always set. Change-Id: Ia94887ded91845bc39d4d5e95ef00d190681e517 BUG: 801183 Signed-off-by: Brian Foster Reviewed-on: http://review.gluster.com/2903 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit fa5b0347193f8d1a4b917a2edb338423cb175e66 Author: Pranith Kumar K Date: Sat Mar 10 00:54:12 2012 +0530 protocol/server: Remove connection from conf->conns w.o. race 1) Adding the connection to conf->conns used to happen in conf->mutex, but removing happened under conn->lock. Fixed that as below. When the connection object is created conn's ref, bind_ref count is set to '1'. For bind_ref ref/unref happens under conf->mutex whenever server_connection_get, put is called. When bind_ref goes to '0' connection object is removed from conf->conns under conf->mutex. After it is removed from the list, conn_unref is called outside the conf->mutex. conn_ref/unref still happens under conn->lock. 2) Fixed races in server_connection_cleaup in grace_timer_handler and server_setvolume. Change-Id: Ie7b63b10f658af909a11c3327066667f5b7bd114 BUG: 801675 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2911 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 4a37d78da3fef69f0074cab3ff71182a68876358 Author: Krishnan Parthasarathi Date: Tue Mar 13 16:48:58 2012 +0530 glusterd: Updates on members of cluster must include peer to-be friended Updates about members of cluster must be sent to the peer to-be friended. Change-Id: I56745885d75af7c609227ba8582da1bb07c1b894 BUG: 801731 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2934 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8c7549f9094d99d679de447230edaa5040db3e92 Author: Kaushal M Date: Mon Mar 5 19:04:49 2012 +0530 cli: More xml output changes * Added xml output for "volume quota" which was missing. * Fixed xml output for "volume info all" so that it contains only one xml document * Fixed no xml output for normal "volume status" * Fixed normal output for "volume set" Change-Id: I3d85b6800e428226f2970d669e38e4331c99a218 BUG: 799957 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2868 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 6a8fcff3fb6955162dc4eeaeaa627bb31311627e Author: Raghavendra G Date: Mon Mar 12 14:22:01 2012 +0530 features/quota: store quota context even for the cases where loc.name is NULL with name-less lookups, loc.name is NULL. Signed-off-by: Raghavendra G Change-Id: Ie3914924896c90a7fb7251cb0184c8e561ef7f4f BUG: 801364 Reviewed-on: http://review.gluster.com/2917 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 2056df6f5e9ae7ccc6bb1b8f0b036f206b218999 Author: Krishnan Parthasarathi Date: Fri Mar 9 12:36:49 2012 +0530 core: Made lkowner_unparse use 'type-safe' format-specifier Change-Id: Ibd39edb5fccef525f7f0929401f7329508c59ced BUG: 767229 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2907 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 05318789c5dbc92634a03e355acddbffb122b64e Author: Amar Tumballi Date: Mon Mar 12 18:28:31 2012 +0530 glusterfsd: handle a case of NULL dereference during rebalance Change-Id: I9dbe1235f9b5eb7dd43c92bd46830ed9e5734768 Signed-off-by: Amar Tumballi BUG: 801787 Reviewed-on: http://review.gluster.com/2924 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 58776c0800ab146b1dd9a8461a98ca719afff6ef Author: Amar Tumballi Date: Sat Mar 10 19:59:07 2012 +0530 iobuf: add a counter to keep track of request misses requests can be denied if the size of the request is higher than the available sizes. Change-Id: Id1bf2a56de799ccb94f3791899f2e33f68cd1e2b Signed-off-by: Amar Tumballi BUG: 802047 Reviewed-on: http://review.gluster.com/2913 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 08cc17a5528d0194bdb835e05e3950d5516274c3 Author: Amar Tumballi Date: Mon Mar 12 17:24:33 2012 +0530 glusterd: minor log fix in handle probe query now prints the destination hostname instead of self. Change-Id: If73158c36780d597a67ec9185d99083764966c04 Signed-off-by: Amar Tumballi BUG: 802265 Reviewed-on: http://review.gluster.com/2920 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c8e7ec5e24613d8a20cd06d9e1b70e9386a889c4 Author: Amar Tumballi Date: Mon Mar 12 13:00:45 2012 +0530 protocol/client: remove unused variables from 'priv/conf' 'last_sent', and 'last_recieved' variables were not used anymore after having RPC layer. Hence removed it from the code. Change-Id: I1ba74d47f909406ebde43476ccfed724e6c7e77f Signed-off-by: Amar Tumballi BUG: 801721 Reviewed-on: http://review.gluster.com/2916 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit afae9366d220d79fb8b0b1ab96f0e95d25dc4a90 Author: Raghavendra Bhat Date: Fri Feb 24 15:23:08 2012 +0530 cluster/afr: save the xattr obtained in the {f}xattrop_cbk in local If the {f}xattrop operation succeeds on one of the subvolumes and fails on another (thus the xattr dict obtained from the failed subvolume in the callback will be NULL), then afr would be unwinding with op_ret = 0 (since the operation was successful on one subvolume), but the xattr dict would be NULL (afr is not saving the xattr it has received in the callback in its local structure and will send the xattr it has received in the last callback). xlators above afr might segfault when they access the xattr since they would have assumed that xattr would be present as op_ret is 0. Change-Id: I50761a302150285f31dfdaa397f890c9370a989a BUG: 797119 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2813 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c9322f64cc4b8c661cf282bf1a2b08e0d6567b16 Author: Krishnan Parthasarathi Date: Mon Mar 12 14:26:36 2012 +0530 glusterd: Peer(s) mustn't send updates about members not yet in cluster Also, peerinfo is added to peers list synchoronous with the request triggering it. This ensures that atmost one request sees that the peer (in question) is not in peers list. Earlier, 'concurrent' handle_friend_update requests would see that a particular peer is not in the peers list yet, as the addition of the 'peer' into the list happened asynchronously, on the 'connect' event of the 'peer'. Change-Id: I6f017fb43079862fbe5ae7db8f9f4e4fefaa091d BUG: 801731 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2918 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit e7d9f599ee52408819be649ef41ffc00c77e785e Author: shishir gowda Date: Wed Feb 29 12:41:55 2012 +0530 cluster/stripe: Readdirp - send aggregated block_size in stat Change-Id: Iee83a355ab767acac89b11d0a5add8527fc387a7 BUG: 797308 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2833 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 152a0194e736e073d96fedd980b976cc1f1d4df8 Author: Vijay Bellur Date: Sat Mar 10 17:22:55 2012 +0530 Print non-zero timestamps in statedump Change-Id: I686842bc0934128b825828066f613c2a6280ceb9 BUG: 801689 Reviewed-on: http://review.gluster.com/2912 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 7157a2cf42c4cf7c2ec2805e0732b49ebabd975e Author: M S Vishwanath Bhat Date: Sat Mar 10 15:51:22 2012 +0530 posix_fill_readdir: Using strcmp to compare GF_HIDDEN_PATH with entry->d_name instead of strncmp. Change-Id: I29b6fc81213e52a697ed96559c3216c5512799ed BUG: 802005 Signed-off-by: M S Vishwanath Bhat Reviewed-on: http://review.gluster.com/2910 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b596986ca43b2acd83debe3c77607cc4e8ff1dc6 Author: krishna Date: Thu Mar 8 16:38:36 2012 +0530 nfs/nlm: logging NFS client IP address when FH->volume mapping fails or when resolve_and_resume fails. Change-Id: Ia89113f46c1d7c9ed629e9dc0ff0779c41ed947f BUG: 765259 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2900 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ef108d4fa77fd9aba48a7b9475c9b72352c16e6a Author: Mohammed Junaid Date: Fri Mar 9 12:44:05 2012 +0530 protocol/client: Register a timer(grace-timer) conditionally. A grace timer is registered on a disconnect, but a reconnect timer sends a connect request after every 3sec and if the server is down, the client protocol receives disconnect and a grace timer will be registered which on timeout will increase the lk-version value. Its enough to register the grace timer once after the disconnect and later just ignore other psuedo disconnects. Change-Id: I36a153aa86b350d87fe50d014ee0297f558a7fb6 BUG: 795386 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2906 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 56ec59a465c4a4a34bac3a785964c2517570898b Author: Amar Tumballi Date: Wed Feb 22 08:11:57 2012 +0530 glusterfsd: fix some option definitions VOLUME_NAME used earlier in option definitions are confusing with glusterd specific volumes. It should be translator name in volume file. Change-Id: Id4d86c8def65aa6ff1346ef49f8b20ea428de615 BUG: 788437 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2789 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f75277b12af4c7e72c448480feec0d0e2e6582cd Author: Pranith Kumar K Date: Wed Mar 7 17:48:12 2012 +0530 features/locks: Make inodelk ref-counted Ref when the object is allocated. Unref after the response is submitted to that inodelk. Ref when the lock is granted. Unref when the lock is unlocked. Change-Id: I2bfe9182b67bea7dc7b9d0ed9f99f1c7fa0b8a3c BUG: 783449 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2891 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7afa2747234778be3f2cffb860a8c48286dde566 Author: Rajesh Amaravathi Date: Tue Mar 6 11:26:17 2012 +0530 nfs/server: allow deletion of files by default this is needed for Micrsoft Windows-based Nfs clients which do not ignore ACCESS3_DELETE permission not being granted, while linux/unix systems ignore the same. behaviour on linux/unix systems remains unchanged Change-Id: I67f5f66a7486b93163aebedec5fbaa303173964e BUG: 790781 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2875 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas Reviewed-by: Vijay Bellur commit 3193c56b7e3d0be9713138784b1a6477136add9e Author: krishna Date: Fri Mar 9 09:43:18 2012 +0530 nlm: support ipv4 only Change-Id: I0d8381b7d4da0e961677cca63d6d2c82836c1632 BUG: 800735 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2909 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 17111383828b44bf8f437aef76870c2c01fdd946 Author: shishir gowda Date: Fri Mar 9 10:05:48 2012 +0530 cluster/dht: Replace ftruncate call with truncate in rebalance ftruncate call seems to be broken as of now (marker). Signed-off-by: shishir gowda Change-Id: Ib49ced0471e1b8e9ee411eb5a9ff1b83c4d82bec BUG: 801658 Reviewed-on: http://review.gluster.com/2905 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 5b290bc6e3df76bea04c11cb15643173c33455bd Author: Pranith Kumar K Date: Thu Mar 8 22:17:46 2012 +0530 syncop: Make syntask scalable At the moment, synctask uses task->frame to perform all the syncops, this will lead to high-memory usage if the task crawls millions of directories. i.e millions of STACK_WINDS/UNWINDS. To prevent this, in each task a new stack is created to perform the fops which is reset after every syncop. Change-Id: I53c262ec348be9b1d91af73da01f1c217f31ce6e BUG: 798907 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2850 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit bc10ade1cff9d6cd3b3528ec6c845efadc722481 Author: Raghavendra G Date: Wed Mar 7 21:02:16 2012 +0530 performance/io-cache: pass appropriate op_errno even during successful reads. An op_errno equal to ENOENT with op_ret equal to zero is used by storage/posix xlator to indicate EOF. NFS relies on this protocol for correct functioning. Change-Id: I136fbf429a829bd7bd75ce8ce236f9557a418a5d BUG: 795789 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2894 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 204ab142977163f634cbf4ec92be58754225504a Author: Raghavendra G Date: Thu Mar 8 07:45:15 2012 +0530 performance/io-cache: move mem-pool initialisation to init. mem-pool is global structure which is stored in ioc-inode-table and hence can be initialised in init. Change-Id: I4bc88fe3e8c729312e41f62c98f665af5fb26a62 BUG: 765340 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2895 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 9ae2f79879b295639b55411c5339eba04e627345 Author: Venky Shankar Date: Thu Mar 8 14:51:02 2012 +0530 xlator/lib: fix spurious STACK_UNWIND Change-Id: If37eba97710fc79713f70c4117015d49f93ad137 BUG: 801285 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2898 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5fdd65f5f4f5df1d28b0fb4f7efed226d5db1b3c Author: M S Vishwanath Bhat Date: Fri Feb 24 13:18:56 2012 +0530 renaming hdfs -> glusterfs-hadoop Change-Id: Ibb937af1231f6bbed9a2d4eaeabc6e9d4000887f BUG: 797064 Signed-off-by: M S Vishwanath Bhat Reviewed-on: http://review.gluster.com/2811 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e1ab347720f25ed2e7db633a7202f7b873f4b90a Author: Csaba Henk Date: Wed Mar 7 05:29:41 2012 +0100 cleanup and fix xattr namespace flip - function of actual flipping made static - clean out references to particular namespaces from flipping logic - namespaces involved in flipping defined at single location - fix fnmatch(3) invocation with reversed pattern and string arguments - instead of "user", use "system" to flip from, because latter is free from supervision of the VFS layer (cf. attr(5)) Change-Id: I3cc5836fadcad5b237fd5c67d0dcaea63aee9164 BUG: 798716 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2890 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit 33e9f9da8546dc57ecf6b3705f6b6474150ec78c Author: shishirng Date: Tue Mar 6 18:55:37 2012 +0530 glusterd/rebalance: Bring in support for parallel rebalance This patch, enables rebalance processes to be started on all nodes where the volume is spread across (1 process per node) node-uuid xattr identifies which node takes ownership of the task to migrate the file. The model employed is push (src pushes to dst) Change-Id: Ieacd46a6216cf6ded841bbaebd10cfaea51c16d6 BUG: 763844 Signed-off-by: shishirng Reviewed-on: http://review.gluster.com/2873 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f6a779ffc5b515163995dc2d240c3271cc6bceeb Author: Raghavendra G Date: Wed Mar 7 17:34:37 2012 +0530 features/marker: GFID file handle based backend related fixes * make sure loc->gfid is filled. Change-Id: I5304e650d9fc181ee1f3b65be7f2ff3847d9722e BUG: 790389 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/2888 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit 57a51c734408e9439640d215795f7d2188f2383b Author: Krishnan Parthasarathi Date: Sun Mar 4 00:01:17 2012 +0530 glusterd: Append internal mount logs of clear-locks command to a single file To ensure logs of all clear-locks commands executed from a 'peer' (glusterd) are in one place. Change-Id: I9f531a1e24d4502769740010da73b3d4adb5c5c9 BUG: 799267 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2861 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit fe7d9a874d50fe51e26f6ac9293026534b8f22a1 Author: Amar Tumballi Date: Wed Mar 7 15:13:04 2012 +0530 cluster/distribute: fix log level of few messages Change-Id: Ibdeeb705e75a94bb96a1ae259be32ddd2ca5fec8 Signed-off-by: Amar Tumballi BUG: 797715 Reviewed-on: http://review.gluster.com/2885 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8e29fe73b96f1feb3cc4093eb2e71c7c92be4a31 Author: Amar Tumballi Date: Wed Mar 7 23:45:47 2012 +0530 libglusterfs/fd: fixed fd_anonymous() leak fd was getting leaked whenever there was a overlapping operations, which caused memory leak, and process fd leaks, which made most of the operations on NFS mount of a replicate volume not work. With the fix, things are back to normal. Change-Id: I2d2158b2972ba5dae270d6ff7b1a827403653c04 Signed-off-by: Amar Tumballi BUG: 787368 Reviewed-on: http://review.gluster.com/2892 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 63281d7eeb5b8ac44e3630ccfbc61774eedf2ae2 Author: Krishnan Parthasarathi Date: Wed Mar 7 00:19:29 2012 +0530 protocol/client: Added lk_ctx info in fdctx dump - Added a brief explanation as to why we can't use gf_log when in statedump. - Removed gf_log messages from client_priv_dump since it can cause a 'deadlock' - See statedump.c for explanation - Added try-lock based accessors for fd_lk_list for dump purposes. Change-Id: I1d755a4ef2c568acf22fb8c4ab0a33a4f5fd07b4 BUG: 789858 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2882 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit ac568d561ba15a148d8de6a3d4431714bce230f6 Author: Amar Tumballi Date: Mon Mar 5 23:54:51 2012 +0530 cluster/distribute: send proper 'dict' in readdirp() if we do the STACK_WIND from readdirp_cbk(), we were not sending the right dictionary which made our linkfile determination a failure. Change-Id: Ie3f26748608f1a81123fe475d8a42bf2717475c3 Signed-off-by: Amar Tumballi BUG: 799887 Reviewed-on: http://review.gluster.com/2869 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit ebbc6e802bbffc9c0fd03db1cafefcaaca3a0f05 Author: Pranith Kumar K Date: Wed Mar 7 16:03:32 2012 +0530 protocol/client: Free readdirp xdr leak Change-Id: I5e46deedd93e852a483693de42e4bec0082bc08b BUG: 796186 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2886 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 1e22ab9d218405f5081a30e90c4541e43243a216 Author: Mohammed Junaid Date: Wed Mar 7 14:16:07 2012 +0530 nfs: fcntl lock self healing. Change-Id: Ic3e00e8ea3b873acbc3abb5155aecdaac848a3e5 BUG: 795386 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2884 Tested-by: Gluster Build System Reviewed-by: Krishna Srinivas commit 0d99aa113d42d96b35e5bc477349b28ef161c4af Author: krishna Date: Tue Mar 6 15:52:34 2012 +0530 nlm: call nlm4_cancel_fd_resume instead of nlm4_unlock_fd_resume when CANCEL proc is called. Change-Id: Id4c74165f24cccb46ca5de406dd7e47e4a8b99e1 BUG: 798222 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2877 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 293aa0b9a08da1c4703ddd992a2e03d53ec84cc5 Author: Vijay Bellur Date: Wed Mar 7 00:30:17 2012 +0530 xlator/lib: Drain out sent requests to avoid multiple STACK_UNWINDs Change-Id: If28e4b6e157ac0cb9e1f325bbba39f6c3f1c2b45 BUG: 789078 Reviewed-on: http://review.gluster.com/2881 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 228d01916c57d5a5716e1097e39e7aa06f31f3e4 Author: Pranith Kumar K Date: Mon Mar 5 16:05:12 2012 +0530 glusterfsd: Don't reconfigure if process does not know volfile server Change-Id: I09e5527bb1496e0029d73f08dd7892d74df93084 BUG: 799882 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2865 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit e435faeae8bdedbfcdeae6a37e51b913b7c7ff00 Author: Pranith Kumar K Date: Fri Mar 2 13:26:36 2012 +0530 cluster/afr: handle node failures in lookup When a transaction is in progress lookup depends on inode ctx for read-child. If the lookup fails on the read-child while another transaction is in progress, it should select the read-child as the next success_child which is in fresh_children. Change-Id: I33a04b102966b63a64bacf8d2e29f0d0119fdac6 BUG: 773225 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2858 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 347b4d48cba3cc1e00d40ec50e62497d65a27c84 Author: Rahul C S Date: Thu Feb 23 16:51:59 2012 +0530 cli: Fix volume statedump cli output typo Change-Id: I1363123d13fa4364e917344fdd928ac48b85326c BUG: 796617 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2807 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b7dc6b4df748d890d6b76c613f4911c4bd5947eb Author: Kaushal M Date: Mon Feb 27 16:08:56 2012 +0530 glusterd: Rename nodes in "volume set help-xml" output Change-Id: I44bbfb6e78a459783d7d5bbccda6bbbd3ec1e391 BUG: 791054 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2823 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 0783ca994d9ea95fd9ab3dd95d6407918f19f255 Author: Pranith Kumar K Date: Thu Mar 1 12:34:56 2012 +0530 cluster/afr: Reset re-usable sh args in sh_*_done The bug is observed due to stale value of active_sink count set in metadata self-heal. Change-Id: I41996999213c323c0f4d4db575d87b2d0b4b3fec BUG: 798874 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2849 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5d813bb5fa005d15de47ba0cde0af7bda6bd9995 Author: Amar Tumballi Date: Mon Mar 5 14:17:57 2012 +0530 rpc-clnt: print xid of the saved frames getting unwind so that one can match the corresponding submit failed errors in brick logs Change-Id: I4422805a20c251aeffb51d63572c251176b2620c Signed-off-by: Amar Tumballi BUG: 799337 Reviewed-on: http://review.gluster.com/2864 Tested-by: Gluster Build System Reviewed-by: M S Vishwanath Bhat Reviewed-by: Vijay Bellur commit 6756245b1514374712136c8dc1f4ac2a19a6da21 Author: Rajesh Amaravathi Date: Wed Feb 29 15:16:53 2012 +0530 fops/removexattr: prevent users from removing glusterfs xattrs * Each xlator prevents the user from removing xlator-specific xattrs like trusted.gfid by handling it in respective removexattr functions. * For xlators which did not define remove and fremovexattr, the functions have been implemented with appropriate checks. xlator | fops-added _______________|__________________________ | 1. stripe | removexattr and fremovexattr 2. quota | removexattr and fremovexattr Change-Id: I98e22109717978134378bc75b2eca83fefb2abba BUG: 783525 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2836 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy commit 33b9f156e6b6137e33bd9becfe640166986ecc55 Author: Csaba Henk Date: Wed Feb 29 10:20:54 2012 +0100 glusterd: mountbroker-geo-replication.* fix mountbroker-geo-replication.* option's value was always discarded due to bogus control flow Change-Id: I5ec57dd0db9502ba088c42e07e32ac3e15317ce5 BUG: 797702 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2835 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit 5b9d47a3a39fac39e3fbccd4083f2f45c9ce5b49 Author: Csaba Henk Date: Wed Feb 29 10:21:03 2012 +0100 geo-rep / syncdaemon: determine suitable xattr namespace based on privilege Change-Id: I91fe16d7e5e4c21f138eab4ee0b9334aec40e41b BUG: 765433 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2838 Tested-by: Gluster Build System Reviewed-by: Venky Shankar commit eb3bab1c6d391131cdff48a458fbfec2f53d7c6c Author: Pranith Kumar K Date: Sun Mar 4 23:45:26 2012 +0530 glusterfsd: Unref iobuf after using it Change-Id: Ieefc08d9af2125fabc2a86e5ff3a933aec539da0 BUG: 799882 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2866 Reviewed-by: Raghavendra G Tested-by: Gluster Build System commit 7fec9b41d8e1befa8d58a76d98207debddd60b65 Author: Vijay Bellur Date: Sat Mar 3 00:01:23 2012 -0800 Revert "afr: [Un]Set the 'right' lkowner for [f]{inode|entry}_lk and the 'enclosed' fop." This reverts commit 2e80fdbeb6abbb23ff6789c2b98c82704883af0a. Change-Id: I417fd43e4195d63e5b8b83dd3beb712887130e1e Reviewed-on: http://review.gluster.com/2860 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit aaac9cf176b407f89a1e8015140916b3f9d3cddb Author: Vijay Bellur Date: Thu Mar 1 00:17:21 2012 +0530 Refactor xlator/lib for better readability & maintainability. Change-Id: I6468462ae2bbc05c1dd6c2aea66b440aa7cfdd09 BUG: 789078 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2845 Tested-by: Gluster Build System commit f822d76d5a247ea6ba7375a35cb72b63fa413005 Author: Raghavendra Bhat Date: Fri Mar 2 15:34:51 2012 +0530 cluster/afr: copy the parent's gfid from child loc while building parent loc Suppose the process is not a fuse or nfs mounted client, and some other process such as rebalance, then after lookups inode would not be linked to the inode table (since the inode was created for rebalance purpose only), thus keeping inode's gfid NULL. And afr while building the parent loc using child loc, does not copy the pargfid present in child'd loc structure. protocol/client will search for the gfid either in loc or in loc->inode and assert if it cannot find the gfid in either of them. Change-Id: I882e449fb8b79d5c69e4a942abcd844dc4d5d30c BUG: 799262 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2857 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Pranith Kumar Karampuri commit 71cffc0b66b849306778515d385083b9f78857f5 Author: Vijay Bellur Date: Fri Mar 2 00:54:12 2012 +0530 Fix memory leaks found in readdir Change-Id: I0e221e4de9ee12586b09cd8bf7f394e9d4b88a11 BUG: 765785 Reviewed-on: http://review.gluster.com/2853 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Krishnan Parthasarathi Reviewed-by: Pranith Kumar Karampuri Reviewed-by: Vijay Bellur commit 0d62b3e4cd9de73b0cb7e54f904eefe27581cf4d Author: Mohammed Junaid Date: Thu Mar 1 22:34:59 2012 +0530 protocol/client: Calling GF_FREE on memory allocated via GF_CALLOC. This is a temporary fix. A clean fix would be to allocate memory using mem_get0 and free via mem_put. Change-Id: I6351ab22c2f05ba8fa4aaad67f375027df873807 BUG: 796656 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2852 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 316e694d53f20a76ee36654a9a865a493800dc3c Author: Csaba Henk Date: Wed Feb 29 10:21:09 2012 +0100 geo-rep / syncdaemon: make the timeout for establishing the connection to slave configurable It can be set through the connection-timeout tunable but we keep it hidden, intended as a workaround for some special scenarios not for general use. Change-Id: I31f9fa3873afa7babc2106ee34484123a01bdc57 BUG: 789078 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2839 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 326a7d04260c15f1b6e201621438844f8747b963 Author: Pranith Kumar K Date: Tue Feb 21 22:06:29 2012 +0530 cluster/afr: Add new option to know which process it is in Afr xl needs to maintain inode-table inside the xl if it is in self-heal-daemon. The code was depending on the option self-heal-daemon to do this. This is wrong as the option can be reconfigured to on/off. Added a new option which can't be reconfigured for this purpose. Change-Id: Idc42c403c4bd9b73d1f328427ae4158ff1420b3a BUG: 795741 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2787 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 86f631f4283cba7185e5b1d5a3be4b9a614ed985 Author: Pranith Kumar K Date: Thu Feb 23 14:46:04 2012 +0530 protocol/server: Make conn object ref-counted Change-Id: I992a7f8a75edfe7d75afaa1abe0ad45e8f351c8b BUG: 796581 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2806 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f93045296870cb6938d9b4356a4f3198cbebe3ba Author: Venky Shankar Date: Wed Feb 29 19:25:30 2012 +0530 hdfs/plugin: Fix regex for parsing pathinfo string Change-Id: I3a5d78f39a15c8029cd40225013e9ac40beb9373 BUG: 797116 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2844 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0978b5a36d379839ff543fd54612fde476deede7 Author: Pranith Kumar K Date: Mon Feb 27 11:15:51 2012 +0530 cluster/afr: Handle errors in build_parent_loc BUG: 787671 Change-Id: I0b01b0f9e14a26d757748413dd71909e915c7573 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2826 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit bcfd365c10d20bde920a3c6cdd1f95b7da5ffe84 Author: Krishnan Parthasarathi Date: Tue Feb 14 21:27:10 2012 +0530 afr: [Un]Set the 'right' lkowner for [f]{inode|entry}_lk and the 'enclosed' fop. afr 'mangles' the lkowner inorder to ensure [f]inodelk/[f]entrylk fops from the same application contend. But other fops that are 'visible' to the application should operate with the lkowner provided by fuse for correct functioning of posix-locks xlator. Change-Id: I7e71f35ae7df2a070f1f46d4fc77eed26a717673 BUG: 790743 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2752 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1936e29c3ac3d6466d391545d761ad8e60ae2e03 Author: Pranith Kumar K Date: Wed Feb 29 16:31:18 2012 +0530 cluster/afr: Hardlink Self-heal Change-Id: Iea0b38011edbc7fc9d75a95d1775139a5234e514 BUG: 765391 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2841 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 6e9a8f61b7d7371fa749c168162c716c2b0be70b Author: Krishnan Parthasarathi Date: Thu Mar 1 12:18:48 2012 +0530 glusterd: Changed clear-locks cmd to use trusted-volfile for its internal mount Change-Id: Iba8add1802832d4fa7082bc6a68eee966ddc508b BUG: 798127 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2846 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 8747925fb0847364be98afc2c2d59b42b2f8514c Author: shishir gowda Date: Thu Mar 1 12:20:08 2012 +0530 cluster/rebalance: Fix expression in check_free_space Migration should fail if available space in dst < src The expression was evaluating otherwise Change-Id: Ief64ad8797e405d0cdc787eef49bfbf4051dffac BUG: 798864 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2847 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 6c4b8d02db7b47d67a306a71a72bcc016fbdf183 Author: Raghavendra Bhat Date: Wed Feb 29 23:23:54 2012 +0530 mgmt/glusterd: do not close the same fd twice In volfile generation part, if the close on the file stream for the volfile fails, then we should not again close the same file stream which may lead to undefined behavior. Change-Id: Idec00955eea11d5b2ea74574f8d4e53fa80c220a BUG: 798599 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2843 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 70fb696abd6144199bc08b05d403daaca314c7b4 Author: Amar Tumballi Date: Thu Mar 1 00:35:36 2012 +0530 perf/md-cache: hold lock on modification of md_cache structure as it is possible that multiple fops can alter the content of md-cache structure from inode-ctx, we need to safe-guard the issue of corruption due to race conditions. Change-Id: Iea051f8f6adff7690d6d60f3cf82eda75150b449 Signed-off-by: Amar Tumballi BUG: 798179 Reviewed-on: http://review.gluster.com/2834 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 49a0c12e490f72d94acd6169a33f3f0f855000db Author: shishir gowda Date: Wed Feb 29 16:06:25 2012 +0530 cluster/stripe: Send xattr request in lookup even when type is INVAL Change-Id: I6f66b5aa39eaa5eadca2a91b1d4e948490f0aa06 BUG: 798161 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2837 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 0054807e5288727599bc264e64f83e9fb526732f Author: Rajesh Amaravathi Date: Wed Feb 29 16:16:12 2012 +0530 nfs: prevent crash during cthon lock test When cthon was invoked to test nlm, the mount point would hang, and crash nfs server, and all the brick processes. This path fixes the crashes. Change-Id: Ide88adb7e25ea722b143bfd62e23361ff7be4b67 BUG: 798194 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2842 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 72eda6a45b52e98458e4efa3e9819a8a3a25faef Author: Pranith Kumar K Date: Tue Feb 28 09:27:32 2012 +0530 libglusterfs: Handle loc_copy for nameless loc BUG: 787671 Change-Id: I7601f482ae753ead83be16d1df33c2187e76dc5c Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2825 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 15141a7660b1e4430513c8a96a498da652023894 Author: Amar Tumballi Date: Tue Feb 28 15:27:24 2012 +0530 protocol/client: send unique key to server during handshake utilize the graph->id for making the key unique. Change-Id: I0c1b355aa901af88e65fd12cb9e0535318856867 BUG: 783982 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2831 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Mohammed Junaid commit ca8e61069b4fec42efa76da2070d362607770bc7 Author: Rajesh Amaravathi Date: Tue Feb 28 12:57:26 2012 +0530 nfs/doc: corrections corrections in nfs configuration helpers displayed with "gluster volume set help". Change-Id: Iffc0d10eacbaea647270cd875d4cbd5f80333671 BUG: 771876 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2829 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2da18b6724b7daf7c3a973515fc3d59e7d2c4622 Author: Rajesh Amaravathi Date: Wed Feb 22 14:51:53 2012 +0530 transport/socket: configuring tcp window-size Till now, send and recieve buffer window sizes for sockets were set to a default glusterfs-specific value. Linux's default window sizes have been found to be better w.r.t performance, and hence, no more setting it to any default value. However, if one wishes, there's the new configuration option: network.tcp-window-size which takes a size value (int or human readable) and will set the window size of sockets for both clients and servers. Nfs clients will also be updated with the same. Change-Id: I841479bbaea791b01086c42f58401ed297ff16ea BUG: 795635 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2821 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 5ad1c2caed743fc10a0645055a825252dfbf77ba Author: shishir gowda Date: Tue Feb 28 18:03:29 2012 +0530 storage/posix: In lookup check for buf->gfid being NULL There are few cases where create and lookup race. Lookup ends up getting a valid struct iatt, but with no gfid set. We need to check for gfid being 0, and handle it as an error. Signed-off-by: shishir gowda Change-Id: I36ae1978b325aff964cbc3b24730c1e993666267 BUG: 797167 Reviewed-on: http://review.gluster.com/2832 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c2c82c360fda20533093c27c82ce0725cf40cab5 Author: Csaba Henk Date: Mon Feb 27 05:41:11 2012 +0100 glusterd/mountbroker: fix handling of MEET mountbroker keyword Change-Id: I5331a17a772e9ef15e132b9f335e5ff9d70735b7 BUG: 765214 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2817 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c1e3d3b963a46fb92d309ac3d0a11adfad8ce745 Author: Krishnan Parthasarathi Date: Fri Feb 24 14:59:43 2012 +0530 locks/glusterd: Fixed clearing of posix locks from failing always. Change-Id: Ieaf636c6f0d2aa1d001143a2d1433fce85dc8c7a BUG: 797042 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2812 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 19dd4b7f0080a1924099ace7e3d7fcd9f0314f2d Author: shishir gowda Date: Fri Feb 24 15:25:06 2012 +0530 mgmt/glusterd: pass defrag_cmd in rsp dict for volume info glusterd_import_volinfo used to error out as it was not able to find the rebalance key in the dict Change-Id: Ife35a041072a8a978d7595e8381f68e624bd8da3 BUG: 797105 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2814 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a3f6b0c4f231ccdb727227c9c35816b4823cef90 Author: Amar Tumballi Date: Thu Feb 23 12:53:19 2012 +0530 mempool: add more counters to understand the usage scenarios properly current design of mempool is to fallback to standard calloc/free if all the buffers in pool are exhausted. Understanding more about those numbers will help us to tune mempool parameters properly over time. Change-Id: I2c94373186f7c6a486caff2611c2d9df2c37db3c Signed-off-by: Amar Tumballi BUG: 797730 Reviewed-on: http://review.gluster.com/2804 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Vijay Bellur commit 85471322df9676cc344cc2b03627c02ed90da3cd Author: Raghavendra Bhat Date: Thu Feb 23 22:58:44 2012 +0530 glusterfsd: unref the dict and free the memory to avoid memleak Change-Id: Ib7a1f8cbab039fefb73dc35560a035d5688b0e32 BUG: 796186 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2808 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit bd94f6a1cc26fbcf8811e04dab0c90257b44d89a Author: Kaushal M Date: Mon Feb 27 15:34:11 2012 +0530 cli: Fix broken "volume set help/help-xml" Change-Id: I4e71e67f32ff37cfe23bc77c0e27645ac495a247 BUG: 796040 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2822 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3cad6558b030bc3b0ebb662ec7d0346ab9a32cc2 Author: Vijay Bellur Date: Sun Feb 26 22:16:59 2012 +0530 cli: Add 'exit' command. Based on request at: http://community.gluster.org/i/make-cli-understand-command-exit/ Change-Id: I9116236a8c2f7767c88672b8d3d6565906bfc61f BUG: 797551 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2815 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Amar Tumballi commit 20b50008c710c973ebb0a84506b55e6aea044fad Author: Csaba Henk Date: Mon Feb 27 05:40:58 2012 +0100 libglusterfs: fix GF_FREE Argument-taking macros should be possible to use with same syntax that of C functions. In particular (assuming FOO is a single-argument macro), FOO(bar) should break and if (cond) FOO(bar); else baz(); should compile. Change-Id: If852c128a7317dc0dda1c669be7c6af40501e48d BUG: 762061 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2816 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 728de5be7ce2975efb59bb5928fd7261d5ec7760 Author: Krishnan Parthasarathi Date: Thu Dec 15 17:38:05 2011 +0530 locks: Made dump locks formatting more 'readable'. Also, Added inode's path to dump locks. Added basename to entrylk dump output. Added whence field of range locks to dump output. Change-Id: Ifd3f8b585a52de7ff68cd54506619ac3eaedeecc BUG: 789858 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/798 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 88c6c11813cbd60a6b8e5ec4e2edd40e326ac311 Author: Shylesh Kumar Date: Thu Feb 23 14:59:36 2012 +0530 Change rebalance log file name Log file name for the rebalance process should be -rebalance.log Change-Id: I1ed169cdc92b11058b80360086b3c1f7618064ef BUG: 795714 Signed-off-by: Shylesh Kumar Reviewed-on: http://review.gluster.com/2805 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit d4ff4103e09ba076653aa6f0774269c47cc931f2 Author: Krishnan Parthasarathi Date: Wed Feb 22 19:38:14 2012 +0530 glusterd: Modified server graph to have index xl above pump Index xlator needs a resolved inode in the incoming xattrop request to perform its indexing. In the case of replace-brick pump xlator doesn't resolve the inode in the (fop) requests it sends 'downwards', leading to null gfid sent to index xlator. Change-Id: I6b6e7af4354670616bf342292df1a25c219dd9e9 BUG: 796171 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2801 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit 5842656feba99a239b922f8099fb336c66b61929 Author: Venky Shankar Date: Tue Feb 21 14:23:13 2012 +0530 Introduce new extended attribute: node-uuid Request for trusted.glusterfs.node-uuid returns pathinfo like string but containing the UUID of glusterd instead of the backend path for the requested file. This info is benificial for tasks like parallel rebalance that will make use of the UUID for data locality. Change-Id: I766a09cc4a5f63aebd11c73107924a1b29242dcf BUG: 772610 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2614 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Vijay Bellur commit 7820f7563aff8e1a5e73eb75adc387635a301b6e Author: shishir gowda Date: Thu Feb 23 12:24:08 2012 +0530 protocol/client: Pass correct dict in client_readdirp Also, alloc entry->dict before calling unserialize to it. Change-Id: I8a9db93afd6e95e75307467cd654805780d7b467 BUG: 796534 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2803 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 52904f0d416aedf61fcebe2e5051bfa92999c6e4 Author: Vijay Bellur Date: Wed Feb 22 16:08:26 2012 +0530 build: Changes to specfile for correctness and package relevance. - Removes a stale dependency of glusterfs-client on glusterfs-core - Server specific shared libraries included in glusterfs-server package. Change-Id: I852304e6351a9a7864b2049f603e11f6a5601ffb BUG: 764702 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2797 Tested-by: Gluster Build System commit 4ac06a16999bde2f9860f6a8713e7f2544b44f9a Author: Vijay Bellur Date: Thu Feb 23 01:25:47 2012 +0530 features/marker: Use loc.inode to obtain parent if loc.parent isn't set. Change-Id: I89dddb19168a3ffb269afc9f6bcb2d7e7c9a69cd BUG: 790389 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2802 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat commit 72187f8e02e7d3aa17636ade033482e4de41657a Author: Amar Tumballi Date: Wed Feb 22 08:30:47 2012 +0530 glusterfsd: give out the error on screen when cmd is given without options 'glusterfs' cmd would take default options when no option is given, but sometimes default option may not work, in that case, we need to provide usage output Change-Id: I2ebd342890da11d2afaa0a23ee3a01d87694ff28 BUG: 791198 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2790 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 683ce1bca3b6c541e565eec014fa7cc3308957d8 Author: Raghavendra Bhat Date: Wed Feb 22 18:27:15 2012 +0530 glusterfsd: unref the dict and use dict_set_dynstr to avoid memleak Unref the new dict and use proper dict api (dict_set_dynstr) to save data for displaying volume status information, which otherwise leads to memory leak in the process. Change-Id: Icb9ceb1a867c5b9759211a67027d983ab9b7e1c2 BUG: 796186 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2799 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ca502ca780202c71623a34349c88d114ad58ec12 Author: Raghavendra Bhat Date: Wed Feb 22 14:38:42 2012 +0530 cli: print the type of the inode in gluster volume status inode output Instead of a number print the type of the inode in the output of gluster volume status inode. This is what the output symbols indicate. R -----> Regular file D -----> Directory L -----> symbolic Link B -----> Block special device C -----> Character special device F -----> FIFO S -----> Socket I -----> Invalid inode type Also supress a warning message displayed at the time of build. Change-Id: I5a2adfe044ce21d9da159652d4b6e25cd0a2fdca BUG: 796078 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2794 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1350aecc7e600e73b810522c7727be20bdd3ae40 Author: Pranith Kumar K Date: Wed Feb 22 18:35:07 2012 +0530 protocol/client: Print correct error message Change-Id: Ic68626c4a205cd78b60831aa7bd838b6d8824fa1 BUG: 796195 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2800 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 67104b716a93520d66c6e572b5f94aa808645e56 Author: Amar Tumballi Date: Tue Feb 21 16:55:28 2012 +0530 mempool: adjustments in pool sizes * while creating 'rpc_clnt', the caller knows what would be the ideal load on it, so an extra argument to set some pool sizes * while creating 'rpcsvc', the caller knows what would be the ideal load of it, so an extra argument to set request pool size * cli memory footprint is reduced Change-Id: Ie245216525b450e3373ef55b654b4cd30741347f Signed-off-by: Amar Tumballi BUG: 765336 Reviewed-on: http://review.gluster.com/2784 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f37fcaab9eb0601898f4ba6fb747d5c8d3fe4195 Author: Amar Tumballi Date: Wed Feb 22 17:27:59 2012 +0530 mount.glusterfs: multiple fixes * fix return value in case of proper 'backup-volfile-server' option, and actual default server based mount failed. * fix a syntax error (bug: 796050) Change-Id: I6a530c9b9431e46f45ec9eeb99f6103386dd10dc Signed-off-by: Amar Tumballi BUG: 796101 Reviewed-on: http://review.gluster.com/2798 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a423cf80d17285de69594401559b7a255281c26c Author: shishir gowda Date: Wed Feb 22 15:06:23 2012 +0530 cluster/stripe: Readdirp should call lookup on entries We were calling stat on each entry. Also, the inode ctx needs to be populated with the stripe_fd_ctx_t. Signed-off-by: shishir gowda Change-Id: Ibaafa360f22b551d1609041f13a4339e22c95645 BUG: 795669 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2795 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 064bd0f25a02bd65e32a1c03bfb124340dd60651 Author: Pranith Kumar K Date: Thu Feb 2 19:17:12 2012 +0530 cluster/afr: Don't trust the fd returned in open_cbk Change-Id: Id7d85a38875e3675904fc134e54e723c6a0c4de2 BUG: 786766 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2792 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2b52b096a7db3124fdd97554e63792f36e889af9 Author: Pranith Kumar K Date: Wed Feb 22 13:46:37 2012 +0530 features/locks: Don't access free'd memory Change-Id: I4e22ede84622f2c9c46cc0bc9f17bef73afa815c BUG: 796069 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2791 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f3b2305009b98de42c84e5b86668cf8b5f41e01f Author: Krishnan Parthasarathi Date: Wed Feb 22 15:07:03 2012 +0530 pump: Fixed undefined reference to fill_loc_info fn. Changed function to pump_fill_loc_info since its use is relevant only in pump's context. Change-Id: I5be1a908f88328f732dacfd7eac18f0c62f49eb8 BUG: 796066 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2796 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri Reviewed-by: Vijay Bellur commit 2d470cd910b49976befea664ae5cc7ea6aa10020 Author: Harshavardhana Date: Tue Feb 21 10:45:32 2012 -0800 libglusterfs/options: Cleanup xlator percent_sizet code. Change-Id: I1a39252d6c26f7e30b77ef682b8b3cdcde8a4a51 BUG: 769691 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2619 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 311de6f96c4fabf30f734e62996ec18817447e2f Author: Pranith Kumar K Date: Tue Feb 21 18:12:41 2012 +0530 features/index: Set correct ret value in index_add Change-Id: I6314ea25ef26920593a3113eb2951d18255db34f BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2786 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 42cc043875621a02444f3324b2f9629ac68ab5aa Author: Vijay Bellur Date: Tue Feb 21 23:35:05 2012 +0530 build: More rpmbuild friendly changes Change-Id: I7dcd5c6461bbddde3bcc3d2519777e4c8889fe52 BUG: 764702 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2788 Reviewed-by: Venky Shankar Tested-by: Gluster Build System commit f2eb8e4a17219e6a75b8673181f4bb0b85697d66 Author: Vijay Bellur Date: Tue Feb 21 17:35:31 2012 +0530 build: rpmbuild friendly changes Change-Id: Ia1299d4404da0bd6787516924ebadcf9d6e021d1 BUG: 764702 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2785 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 0344a8a12e7675bee24c770d71eff52db6b2d128 Author: Rajesh Amaravathi Date: Tue Feb 21 13:39:29 2012 +0530 glusterd/auth: 3.2.x compatibility volumes created with GlusterFS 3.2.x will be compatible with GlusterFS 3.3 w.r.t auth.allow enhancements Change-Id: I615e46d648e1270a7b856cd71fab24cfe791ddb8 BUG: 795634 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2779 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 6a6abb5367f46bab4a7363db9e181c845a334cdb Author: Pranith Kumar K Date: Tue Feb 21 14:46:05 2012 +0530 features/index: Fix fd leak Change-Id: Ib01d03999b099369674495ce500f48d492758f91 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2781 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 709de8c86a2947c98d59a5b32bcf258c196bab4b Author: Pranith Kumar K Date: Tue Feb 21 11:25:07 2012 +0530 libglusterfs: Warn on missing _cbk calls in xlator Change-Id: I44684b5eeca3674ed8d5b7b0120699bb3767e38d BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2782 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit e311a30f845255b44f3abc56215f584a3c245136 Author: Kaushal M Date: Fri Feb 17 12:32:18 2012 +0530 cli, glusterfsd: Fixes for "volume top {read,write}-perf" Changed variables to use unsigned types, to support larger comninations of block_size * block_count Also increases cli time out for "volume top" ops to 600, to allow more time for glusterd to return the results to cli. Change-Id: I4b953799c78a5a184311f6f8c4a7a99dc9e87a07 BUG: 783980 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2761 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 0ef7e763c85c045ef7937d0ca02d8c5f0333e6e8 Author: Amar Tumballi Date: Tue Feb 21 14:47:48 2012 +0530 core: utilize mempool for frame->local allocations in each translator, which uses 'frame->local', we are using GF_CALLOC/GF_FREE, which would be costly considering the number of allocation happening in a lifetime of 'fop'. It would be good to utilize the mem pool framework for xlator's local structures, so there is no allocation overhead. Change-Id: Ida6e65039a24d9c219b380aa1c3559f36046dc94 Signed-off-by: Amar Tumballi BUG: 765336 Reviewed-on: http://review.gluster.com/2772 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 1f296b84e6c7bf55fc81d0c1dade7ccda75229a6 Author: Amar Tumballi Date: Fri Feb 17 17:22:59 2012 +0530 cluster/distribute: send the right 'dict' for check_is_linkfile() earlier we were using 'check_is_linkfile_wo_dict()' for readdirp_cbk(), which is no more required now. Change-Id: I52295e08f8c494b7a081cfc684164a7f72562d0d Signed-off-by: Amar Tumballi BUG: 794641 Reviewed-on: http://review.gluster.com/2763 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 1979cee4716fdb95909654148eebb8b0b973f484 Author: Pranith Kumar K Date: Tue Feb 21 11:18:32 2012 +0530 features/index: Add release, releasedir cbks Change-Id: Ice45a0b4e953e270273aa4155a895d6ec033fda8 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2780 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 39fb5051ffdf6a978537e8c50f05b7a0135f7075 Author: Vijay Bellur Date: Tue Feb 21 15:50:35 2012 +0530 features/md-cache: Change strdup to gf_strdup Change-Id: Ic96e7d38b988efab49f723c9d1d46f65037a84ed BUG: 795682 Reviewed-on: http://review.gluster.com/2783 Reviewed-by: Anand Avati Tested-by: Gluster Build System commit 490d8805f0d9b4e58258505d678f0e75e089aa26 Author: Jeff Darcy Date: Tue Jan 10 17:42:24 2012 -0500 Honor O_SYNC etc. properly. Change-Id: I3dd90fe230386ad5571c5e639f27460e3d003f0e BUG: 773100 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/2626 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit bca46fd46b1a1a28daeb9ea3f47cef9bbacecd6d Author: Amar Tumballi Date: Tue Feb 21 15:02:39 2012 +0530 rpc/clnt: handle PARENT_DOWN event appropriately Change-Id: I4644e944bad4d240d16de47786b9fa277333dba4 BUG: 767862 Signed-off-by: Raghavendra G Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2735 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7197111677619da96c80572a09331d6e28c1015b Author: Raghavendra G Date: Wed Feb 8 15:06:30 2012 +0530 fuse-bridge: Handle graph-switch. The purpose of this patch is to let protocol/client know when its transports can be disconnected, without application running on gluster mount noticing any effects of graph switch. In order to do this, we migrate all fds and blocked locks to new graph. Once this migration is complete and there are no in-transit frames as viewed by fuse-bridge, we send a PARENT_DOWN event to its children. protocol/client on receiving this event, can disconnect up its transports. Change-Id: Idcea4bc43e23fb077ac16538b61335ebad84ba16 BUG: 767862 Reviewed-on: http://review.gluster.com/2734 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6d19136de7af9135dd23662f18c3ee544a2888da Author: Pranith Kumar K Date: Tue Feb 21 12:45:24 2012 +0530 performance/md-cache: Add mem_acct_init Change-Id: I1b91ee0bde160762548c39646ceb96c3c778e06c BUG: 795651 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2778 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 81ab6622d403558cd6f31efeb535fe886d3beeaa Author: Pranith Kumar K Date: Thu Feb 16 21:30:47 2012 +0530 cluster/afr: Add commands to see self-heald ops Change-Id: Id92d3276e65a6c0fe61ab328b58b3954ae116c74 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2775 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5f117a4a1fca3ec2d163fe77615cf6859c0450e4 Author: Pranith Kumar K Date: Tue Feb 14 22:40:34 2012 +0530 cluster/afr: Self-heald, Index integration Change-Id: Ic68eb00b356a6ee3cb88fe2bde50374be7a64ba3 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2749 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8456c28af75a4083286fc6ceadc03f2703f4c9b6 Author: Anand Avati Date: Fri Feb 3 00:16:30 2012 +0530 md-cache: replace stat-prefetch with md-cache in a backward compatible way - preserve CLI set option key as "performance.stat-prefetch" - create a symlink stat-prefetch.so to point to md-cache.so Change-Id: Ib95e7c30073f13ae04c39e9466967ba1db5a0614 BUG: 765785 Reviewed-on: http://review.gluster.com/2714 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c41a9d1c3fe4002bdf8849c4e8ae7c2e10841c69 Author: Anand Avati Date: Sat Sep 24 16:14:11 2011 +0530 md-cache: meta-data caching translator This is a metadata caching translator which is well integrated with glusterfs core framework and leverages some of the recent protocol changes to do a better job at caching. - It uses the attributes returned along callbacks of all calls to update its attribute cache as frequently as possible without issuing calls on its own (i.e, very low overhead) - It caches attributes returned via readdirp into the inode contexts corresponding to those entries (i.e, well integrated) - It caches and updates xattrs and not just inode attributes (i.e, eliminates the need for a separate xattr-prefetch translator) In its current form it has a timeout based consistency model Change-Id: I891f6225c1a4c08bb111e287571d5f6d326dbe97 BUG: 765785 Reviewed-on: http://review.gluster.com/2713 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 1206437fcfc1f3e1bd4a6faec3341c240bae5cf2 Author: Anand Avati Date: Tue Feb 21 09:25:14 2012 +0530 syncop: Multi-processor support in syncenv This patch introduces: - multithreading of syncop processors permitting synctasks to be executed concurrently if the runqueue has many tasks. - Auto scaling of syncop processors based on runqueue length. - Execute a synctask (synctask_new) in a blocking way if callback function is set NULL. The return value of the syncfn will be the return value of synctask_new() Change-Id: Iff369709af9adfd07be3386842876a24e1a5a9b5 BUG: 763820 Reviewed-on: http://review.gluster.com/443 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit dfc88bf3727fb33e2fc273bd7f24401e0209f39e Author: Pranith Kumar K Date: Mon Feb 20 19:48:07 2012 +0530 storage/posix: Add xattr for gfid2path Change-Id: I1fe987d255bf50e8433043749b482b67554a0ac3 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2774 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d349334fc0b3b069875b2724a5a46dfeb84289e4 Author: Vijay Bellur Date: Mon Feb 20 22:27:31 2012 +0530 nfs/server: Fix compilation warnings Change-Id: If5c2375adb3769827cf5099cb6b2d19ba75bf238 BUG: 795421 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2776 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 12480df27becfc5aef5ff0f1d712d4d73c894c7a Author: Pranith Kumar K Date: Thu Feb 2 19:14:28 2012 +0530 features/index: Index translator implementation Change-Id: If8a11ecbdd010f64fb4409add5751080f4b59086 BUG: 763820 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2722 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit ed2036979499cb272336187c06955aa5e484023d Author: Krishna Srinivas Date: Mon Feb 20 14:34:39 2012 +0530 NLM - Network Lock Manger V4 Change-Id: Ic31b8bb10a28408da2a623f4ecc0c60af01c64af BUG: 795421 Signed-off-by: Krishna Srinivas Reviewed-on: http://review.gluster.com/2711 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit db20a0f8a99f715a77366e518720612f043d5c9e Author: Raghavendra Bhat Date: Mon Feb 20 18:42:37 2012 +0530 libglusterfs: Implement circular buffer and event history Implement circular buffer framework, so that it can be used by other components such as event history management. And event history is implemented which can be used by xlator to dump some information to a file (such as information of some structure etc). Through statedump, history of each xlator can be dumped. An option called history should be given to the statedump command. Change-Id: I7c5e8f6bd1018584eaee856e933e7c4b94c6709c BUG: 795419 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2769 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f764516c2e526624ce0088963924ff2d88304553 Author: Mohammed Junaid Date: Wed Feb 8 18:06:39 2012 +0530 protocol/client,server: fcntl lock self healing. Currently(with out this patch), on a disconnect the server cleans up the transport which inturn closes the fd's and releases the locks acquired on those fd's by that client. On a reconnect, client just reopens the fd's but doesn't reacquire the locks. The application that had previously acquired the locks still is under the assumption that it is the owner of those locks which might have been granted to other clients(if they request) by the server leading to data corruption. This patch allows the client to reacquire the fcntl locks (held on the fd's) during client-server handshake. * The server identifies the client via process-uuid-xl (which is a combination of uuid and client-protocol name, it is assumed to be unique) and lk-version number. * The client maintains a list of process-uuid-xl, lk-version pair for each accepted connection. On a connect, the server traverses the list for a matching pair, if a matching pair is not found the the server returns lk-version with value 0, else it returns the lk-version it has in store. * On a disconnect, the server and client enter grace period, and on the completion of the grace period, the client bumps up its lk-version number (which means, it will reacquire the locks the next time) and the server will distroy the connection. If reconnection happens within the grace period, the server will find the matching (process-uuid-xl, lk-version) pair in its list which guarantees that the fd's and there corresponding locks are still valid for this client. Configurable options: To set grace-timeout, the following options are option server.grace-timeout value option client.grace-timeout value To enable or disable the lk-heal, option lk-heal [on|off] gluster volume set command can be used to configurable options Change-Id: Id677ef1087b300d649f278b8b2aa0d94eae85ed2 BUG: 795386 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2766 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4d1b040f00e7ec8de997d151b35fa035bba9cb25 Author: Amar Tumballi Date: Mon Feb 20 14:34:39 2012 +0530 volgen: give an option to insert trace/error-gen currently, these translators can be plugged in on the server volfile. Need to enhance on client side too. Change-Id: I8c3696f62f1de646a736d68c4c427c6fffd6bbf4 Signed-off-by: Amar Tumballi BUG: 782262 Reviewed-on: http://review.gluster.com/776 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 6827f56dfcde4546e5adb3af65e7f21bef7fd58a Author: Rajesh Amaravathi Date: Wed Feb 15 14:33:19 2012 +0530 protocol/client: delete locks only for non-anonymous fds delete_granted_lock_owners () is not called for anonymous fds since they are not involved in locking Change-Id: Icdc7818f98f5371232ba276ed442704ef69e6b0e BUG: 787365 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2754 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c0b8e886cac4ef0f16d5f93adab02229bb1414cd Author: Amar Tumballi Date: Tue Feb 14 15:05:19 2012 +0530 iobuf: use 'iobuf_get2()' to get variable sized buffers added 'TODO' in places where it is missing. Change-Id: Ia802c94e3bb76930f7c88c990f078525be5459f5 Signed-off-by: Amar Tumballi BUG: 765264 Reviewed-on: http://review.gluster.com/388 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 975933a25d14cbac861e809b40c6edd01acaa28d Author: Rajesh Amaravathi Date: Mon Feb 20 12:31:10 2012 +0530 glusterd: auth allow enhancements * PROBLEM: When address-based authentication is enabled on a volume, the gNfs server, self-heal daemon (shd), and other operations such as quota, rebalance, replace-brick and geo-replication either stop working or the services are not started if all the peers' ipv{4,6} addresses or hostnames are not added in the "set auth.allow" operation, breaking the functionality of several operations. E.g: volume vol in a cluster of two peers: /mnt/brick1 in 192.168.1.4 /mnt/brick2 in 192.168.1.5 option auth.allow 192.168.1.6 (allow connection requests only from 192.168.1.6) This will disrupt the nfs servers on 192.168.1.{4,5}. brick server processes reject connection requests from both nfs servers (on 4,5), because the peer addresses are not in the auth.allow list. Same holds true for local mounts (on peer machines), self-heal daemon, and other operations which perform a glusterfs mount on one of the peers. * SOLUTION: Login-based authentication (username/password pairs, henceforth referred to as "keys") for gluster services and operations. These *per-volume* keys can be used to by-pass the addr-based authentication, provided none of the peers' addresses are put in the auth.reject list, to enable gluster services like gNfs, self-heal daemon and internal operations on volumes when auth.allow option is exercised. * IMPLEMENTATION: 1. Glusterd generates keys for each volume and stores it in memory as well as in respective volfiles. A new TRUSTED-FUSE volfile is generated which is fuse volfile + keys in protocol/client, and is named trusted--fuse.vol. This is used by all local mounts. ANY local mount (on any peer) is granted the trusted-fuse volfile instead of fuse volfile via getspec. non-local mounts are NOT granted the trusted fuse volfile. 2. The keys generated for the volume is written to each server volfile telling servers to allow users with these keys. 3. NFS, self-heal daemon and replace-brick volfiles are updated with the volume's authentication keys. 4. The keys are NOT written to fuse volfiles for obvious reasons. 5. The ownership of volfiles and logfiles is restricted to root users. 6. Merging two identical definitions of peer_info_t in auth/addr and rpc-lib, throwing away the one in auth/addr. 7. Code cleanup in numerous places as appropriate. * IMPORTANT NOTES: 1. One SHOULD NOT put any of the peer addresses in the auth.reject list if one wants any of the glusterd services and features such as gNfs, self-heal, rebalance, geo-rep and quota. 2. If one wants to use username/password based authentication to volumes, one shall append to the server, nfs and shd volfiles, the keys one wants to use for authentication, *while_retaining those_generated_by_glusterd*. See doc/authentication.txt file for details. Change-Id: Ie0331d625ad000d63090e2d622fe1728fbfcc453 BUG: 789942 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2733 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 27e51951bc53f36b2286c70eb2263173b29d7a85 Author: Venky Shankar Date: Wed Feb 15 12:04:24 2012 +0530 GlusterFS Hadoop Plugin Apache Hadoop plugin to run Map/Reduce (MR) jobs on data stored on GlusterFS. This is a drop in replacement for HDFS requiring the plugin jar and modification to a single conf file to enable MR jobs to process data on GlusterFS. Change-Id: I8862efec30708849fa7c544fed88b8e50e622fed BUG: 790671 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2751 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 4a65356275cda45f665dfa99d3712f6fb9087aff Author: shishir gowda Date: Fri Feb 17 19:21:07 2012 +0530 cluster/dht: Support for hardlink rebalance when decommissioning The support for hardlink rebalance is only available for decommissioning of a node. this can be triggered in two ways 1. remove-brick start 2. if decommission node value is set in vol file, then a normal rebalance command The way we handle it is- if (nlink > 1) do * if src file doesnt have linkto xattr * mark src's linkto to the dst * else * perform a link on the dst * do a look up * if nlinks = dst.nlinks * migrate data * else * continue crawling done Signed-off-by: shishir gowda Change-Id: If43b5524b872fd1413e9f7aa7f436cb244e30d8d BUG: 763844 Reviewed-on: http://review.gluster.com/2737 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 6123265556e54891369cc79a72b670a4b23a8a41 Author: shishir gowda Date: Thu Feb 16 14:47:27 2012 +0530 cluster/dht: Handle get cached/hashed subvol failures gracefully Change-Id: I7a41c2876be04acd166b2004d9aa66af078d32ea BUG: 790328 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2757 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit be0fdd8363fd3683c782d9fef86a1b9ffb38983a Author: Vijay Bellur Date: Fri Jan 20 00:01:53 2012 +0530 cluster/dht: Exit clean when assert_no_child_down is enabled Change-Id: If90b1080edcf3792f8590492b585a6dd48fac18e BUG: 783249 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2664 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 82da7e9acf6c6091599835117439260f0505d528 Author: Amar Tumballi Date: Sat Feb 18 12:12:10 2012 +0530 cluster/distribute: send the proper 'loc_t' for statfs() in dht-diskusage.c, which was getting used for getting free disk space of all subvolumes Change-Id: Ieb2bb5f2479fac1803b9af4ef1948954a026c2ee Signed-off-by: Amar Tumballi BUG: 290282 Reviewed-on: http://review.gluster.com/2767 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e8b6dad4dea4535a179a03824aa44628f9adaa17 Author: Joe Julian Date: Wed Nov 9 18:27:25 2011 -0800 Merged in the fedora spec file to bring glusterfs into compliance with FSH and Redhat/Fedora requirements. Created a single spec that works for both 3.1 and 3.2 versions. Releases will now require changing the source url in configure.ac at the same time the release version is set. OLDBUG: 2970 BUG: 764702 Change-Id: I1ec9d10fce6dbd72c329d04c7ad61df2ad117adb Signed-off-by: Joe Julian Reviewed-on: http://review.gluster.com/701 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7ba1e1ed45cee56ef51b9c04df99c976546d5d04 Author: shishirng Date: Wed Jan 18 15:29:15 2012 +0530 cluster/dht: Rebalance will be a new glusterfs process rebalance will not use any maintainance clients. It is replaced by syncops, with the volfile. Brickop (communication between glusterd<->glusterfs process) is used for status and stop commands. Dept-first traversal of dir is maintained, but data is migrated as and when encounterd. fix-layout (dir) do Complete migrate-data of dir fix-layout (subdir) done Rebalance state is saved in the vol file, for restart-ability. A disconnect event and pidfile state determine the defrag-status Signed-off-by: shishirng Change-Id: Iec6c80c84bbb2142d840242c28db3d5f5be94d01 BUG: 763844 Reviewed-on: http://review.gluster.com/2540 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 061d70e8195d082043b071118333b7e3173fa3ec Author: Amar Tumballi Date: Sat Feb 18 12:58:39 2012 +0530 extras/rpc-coverage.sh : behavior fix don't treat getfattr after 'setfattr -x' (ie, removexattr()) as an error. ignore the output so the script runs for completion Change-Id: Id7089b91e7259a39be7cb6fce627828774c4acbc Signed-off-by: Amar Tumballi BUG: 787956 Reviewed-on: http://review.gluster.com/2768 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit df12073c4cc8340eb85b5d25c2da84fc21ec1f38 Author: Rajesh Amaravathi Date: Tue Jan 31 17:04:37 2012 +0530 cli/glusterd: volume status modification * Method of getting mount details of brick has been changed from direct reading of /etc/mtab to using libc's , providing a fairly portable version independent of different linux distributions. It is only supported on Linux though. * Wrong fs type (rootfs for /) in fedora-based distributions has been fixed. * Allows options (detail, mem, fd, et al) to "all" volumes. * Use of the fnmatch's GNU extension flag, FNM_LEADING_DIR is restricted to Linux hosts only. In case of non-Linux hosts, partial match functionality is absent. Change-Id: I102ce808c192ef635c2536a2167101be0aa0fc50 BUG: 786367 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2705 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit acb691f8908049e651fc12ff1cf01e9cf4ddde65 Author: Krishnan Parthasarathi Date: Sat Dec 24 13:49:52 2011 +0530 cli, glusterd : Added support for clear-locks command. Change-Id: I8e7cd51d6e3dd968cced1ec4115b6811f2ab5c1b BUG: 789858 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2552 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b016fe67b6c8957eebc9736b9af9406326800b6d Author: Raghavendra Bhat Date: Fri Feb 17 12:15:48 2012 +0530 mount/fuse: unref the fd from resolve to avoid fd leak Change-Id: I162e07219b98669bc6e09784830ca9407518fd8b BUG: 794618 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2760 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 489a7a10fe2e00d00d86f0304145a4910bb94070 Author: Kaushal M Date: Wed Feb 1 14:44:07 2012 +0530 cli: Fix for statedump crashing gluster processes 1. Fixes the bug in statedump causing the gluster process to crash when an unknown option was given in the 'glusterdump.*.options' file. 2. Also fixes cli, making it send full statedump option strings even when only partial option strings are given in 'volume statedump' command. 3. Minor change to order of operations during statedump to allow option parsing errors to be written to the dump file. Change-Id: Ic878cbca4dbf46b83fba0fd88fcb3c03f05ae46d BUG: 772586 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2706 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7fa06c4ce1a44bbd89d3798193f173c057533bb6 Author: Amar Tumballi Date: Wed Feb 15 19:48:50 2012 +0530 protocol: remove the 'path<>' from rename() and link() missed it in the previous round of cleanup, path is completely useless in resolve function. Change-Id: I1aef0f5276afb77dfacfcc0c337ac80b4fcacc55 Signed-off-by: Amar Tumballi BUG: 790298 Reviewed-on: http://review.gluster.com/2756 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 47e748fe60c46d543c87f3228eb59d6580db8cf1 Author: Amar Tumballi Date: Wed Feb 15 17:20:40 2012 +0530 posix: handle some internal behavior in posix_mknod() assume a case of link() systemcall, which is handled in distribute by creating a 'linkfile' in hashed subvolume, if the 'oldloc' is present in different subvolume. we have same 'gfid' for the linkfile as that of file for consistency. Now, a file with multiple hardlinks, we may end up with 'hardlinked' linkfiles. dht create linkfile using 'mknod()' fop, and as now posix_mknod() is not equipped to handle this situation. this patch fixes the situation by looking at the 'internal' key set in the dictionary to differentiate the call which originates from inside with regular system calls. Change-Id: Ibff7c31f8e0c8bdae035c705c93a295f080ff985 BUG: 763844 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2755 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4cc4e47f6cad1127ad425cc0ab10bc42ab1411c8 Author: shishir gowda Date: Thu Feb 16 17:48:44 2012 +0530 storage/posix: reset op_ret to -1 after call to MAKE_INODE_HANDLE MAKE_INODE_HANDLE uses op_ret. We do not reset it to -1, and in few instances we jump to label out, where we unwind with op_ret. Change-Id: Iac4d9f250f5253b3ce0cd91cc385168247efd4a8 BUG: 788998 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2759 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b19719d037f32a5af109bc474afda2230a0a2403 Author: Shylesh Kumar Date: Thu Feb 16 11:06:08 2012 +0530 filter stripe internal xattrs from getxattr call Change-Id: Ia0e9662644494c61033e7a7853353294598984af BUG: 787964 Signed-off-by: Shylesh Kumar Reviewed-on: http://review.gluster.com/2758 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 26800453aacd76e6edc36c078aaacbe7c16aa75e Author: Kaushal M Date: Wed Feb 15 16:18:25 2012 +0530 cli: Enable output in XML This patch enables gluster cli to output data in xml format. XML output can be obtained by passing "--xml" as an argument. A new "volume list" command, which lists the volumes present in a cluster, has been added. This can be used for obtaining a quick list of volumes. Several commands, including "volume top", "volume profile", "volume status" and "volume info", "volume list", have custom XML output routines. Other commands use either one of the 2 generic output routines, cli_xml_output_str() & cli_xml_output_dict(). NOTE: When using "all" for "volume status" and "volume info" the XML output will have multiple roots. Change-Id: I6117baa02ec06fda116177dbd401f66521263ac6 BUG: 790713 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2753 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c8d47f056ef69d2a644646fd24e8f58de4c0e70e Author: Raghavendra Bhat Date: Wed Feb 15 11:22:00 2012 +0530 features/marker: copy the gfid to loc from oplocal->loc.inode Change-Id: I8cfb70c163a3c4a0bd682678f71b38b5bae20ab4 BUG: 790393 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2750 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 69dad8baff6b0461fde1edbcb1418d0ba3beaa6c Author: Raghavendra Bhat Date: Thu Jan 12 12:53:48 2012 +0530 mgmt/glusterd: changes to run nfs server and self-heal daemon with valgrind Currently glusterd can start only the brick processes in the valgrind mode. This patch ensures that nfs server and self-heal daemon are also started with valgrind along with the bricks. Change-Id: I3136deb58d54075627cdd204002eb26fdfdde462 BUG: 773600 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2638 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 1fbed11ead209a8bcd1fd65846e0dfac6d5e1f2d Author: Rajesh Amaravathi Date: Tue Feb 14 16:28:44 2012 +0530 nfs: avoid logging invalid fdctx in case of anonymous fds if get_fd_ctx fails (as in case of anonymous fds), overwhelming amount of entries are seen in the nfs log, causing dd and other heavy i/o operations to become unresponsive. this patch logs an invalid fdctx only if it is not an anonymous fd. Change-Id: I4e917d150d6a053af77d47a94a2f1c2633acadb5 BUG: 787365 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2747 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 22d2abe742a67f1700f0f8f2a6449f3640826b27 Author: Rahul C S Date: Tue Feb 14 17:09:21 2012 +0530 Allows Successful log rotation when no bricks are specified. log rotate must happen for all the bricks if no specific brick path is given as an argument for the command. Change-Id: I39e55883fd301bedffae996384a8284119011951 BUG: 765578 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2748 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 38d73bdfc659dde4a2632da2da01c785b642c728 Author: Krishnan Parthasarathi Date: Mon Feb 13 16:33:32 2012 +0530 glusterd: Fail volume 'modify' operations when rb is ongoing * add-brick, stop-volume, remove-brick are the operations that are explicitly 'failed' when attempted while replace-brick is in progress. * we attach the volume-id to the dst_brick volfile ensuring that the replace-brick operation holds 'claim' on it. Change-Id: If60b2af566ca940b2add600b473c99730e06ab47 BUG: 765470 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2740 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 5f002b5418b557fd03ce59fbfd5d41272bdf491a Author: Amar Tumballi Date: Tue Feb 14 15:27:49 2012 +0530 protocol xdr: remove 'path<>' client was sending 'path' on wire, which gets ignored on server side, and also doesn't get freed up, which causes memory leak. also with not having path on wire, the xdr size on wire most of the time can remain constant, which helps in allocating RDMA buffers. Change-Id: Ie0d36a670be60b02fd1e925c6f977b1a71def5cd BUG: 790298 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2744 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 69a7f2fea23880fbdc776b657dd6aa32c643c6c4 Author: Amar Tumballi Date: Tue Feb 14 15:50:40 2012 +0530 rpc : fix the leak with glusterfs v2 auth structure conversion both 'groups' and 'lkowner' were getting leaked after the conversion Change-Id: Iab7cc1cf5afdad18ead9f33e6ccf98e0a934a09a BUG: 790298 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2746 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b27512e006ae55777f481937d321f60fa195c48d Author: Krishnan Parthasarathi Date: Wed Nov 16 16:23:48 2011 +0530 locks: Added a getxattr interface to clear locks on a given inode. getxattr returns a summary of no. of inodelks/entrylks cleared. cmd_structure: trusted.glusterfs.clrlk.t.k[.{range|basename}] where, type = "inode"| "entry"| "posix" kind = "granted"| "blocked" | "all" range = off,a-b, where a, b = 'start', 'len' from offset 'off' Change-Id: I8a771530531030a9d4268643bc6823786ccb51f2 BUG: 789858 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2551 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 58a538e99806ae84ec4d4bf03aa726302e16d07b Author: Amar Tumballi Date: Tue Feb 14 12:26:29 2012 +0530 features/quota: fix a crash in fgetxattr() by checking for NULL arg 'name' can be NULL in getxattr() as it is overloaded in glusterfs code to support listxattr() too. Change-Id: I70ccee027828e9b2b08da770f513c4edc5c7a46b BUG: 772601 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2743 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit caa5db96282186333e294d93571eb49a3ed63f18 Author: shishir gowda Date: Sat Feb 11 18:46:10 2012 +0530 cluster/stripe: Support for NFS anonymous fd's Moving storing of all ctx info to inode ctx. anonymous fd's do not have the ctx stored in them, hence readv/writev can fail. Open call does not need the additional lookup calls, as all the required fctx info will be available in the inode ctx populated any one of the following create/mknod/lookup Change-Id: I94ca69ff821d46ac8ed3ba1b87b97a3d1c736566 BUG: 786095 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2726 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b0e28fe22293b6b9811094f4048c84a8383e8c8d Author: Vijay Bellur Date: Sat Feb 11 22:25:09 2012 +0530 features/marker: set loc->gfid in setxattr initiated from marker. Change-Id: I7abb62272b7c8bb25ad37cbc13da7b4713924b7a BUG: 787151 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2736 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 0e6df0100e13123fe38f28c5a090777e894d8f52 Author: Amar Tumballi Date: Mon Feb 6 17:49:14 2012 +0530 core: add an extra flag to readv()/writev() API needed to implement a proper handling of open flag alterations using fcntl() on fd. Change-Id: Ic280d5db6f1dc0418d5c439abb8db1d3ac21ced0 Signed-off-by: Amar Tumballi BUG: 782265 Reviewed-on: http://review.gluster.com/2723 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e17ac220e4bff53fb89f5bea636acb61e347cf50 Author: Amar Tumballi Date: Mon Feb 13 13:00:26 2012 +0530 protocol: code cleanup make dict serialize and unserialization code a macro Change-Id: I459c77c6c1f54118c6c94390162670f4159b9690 BUG: 764890 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2742 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 635f3bc0f8a05ad1280f8ab7d55181502bcad700 Author: Jeff Darcy Date: Thu Feb 9 15:57:51 2012 -0500 Fix case where we free a definitely-NULL iobuf Change-Id: I7097386b41c8881f875c9cc3e41354df5c904dea BUG: 789118 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/2732 Tested-by: Gluster Build System Reviewed-by: Harshavardhana Reviewed-by: Amar Tumballi commit 18a5e19b62ff675aaa187fe53bd5cfa6d5945ef4 Author: Rajesh Amaravathi Date: Mon Jan 16 14:04:10 2012 +0530 core: log xlator options in init * The options (default as well as explicitly set) for each xlator are logged at DEBUG log-level Change-Id: I757e206bf06ef5dc60a3255e2377a821c284b6f1 BUG: 767087 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2647 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b71c572df106f33cda0e4b90f174f6426f598741 Author: krishna Date: Thu Feb 9 12:08:07 2012 +0530 support for nano second resolution for mtime,ctime,atime attributes. Change-Id: Id5078f270d0fec280b53d4aa7b16bbaf42a2df05 BUG: 784095 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/2730 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f47558fc72bcb6d786b117061add384f9f6aa6d5 Author: Jeff Darcy Date: Wed Feb 8 16:36:22 2012 -0500 Use /dev/zero instead of /dev/urandom to get realistic numbers. Change-Id: I460a03759b3e450765758e456f0b4f514ca934ae BUG: 788716 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/2728 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Anand Avati commit 8e81cbacc53adc77bc4eabb5a26d6d13012f5f86 Author: Anand Avati Date: Mon Jan 30 15:03:56 2012 +0530 fuse: fix resolver to handle graph switches properly perform resolution on the latest graph by caching it in state->itable and use fuse_nodeid as just a hint to the possible final resolved inode (in case it was resolved off the latest graph). GFID is the primary key for resolving inodes on the latest graph. Change-Id: I3921c6f59c9ff80e4ff076bec3bd334423fc36cc BUG: 785675 Reviewed-on: http://review.gluster.com/2703 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit aec6d5d89249868dc99d8fb432d8ab120bb38ef1 Author: Csaba Henk Date: Thu Jan 5 02:01:00 2012 +0100 geo-rep: gsyncd: fix up fallback xtime for orphans on master side Change-Id: I2fa543b4bd317e06ea621ae968300ffb7223a68a BUG: 771787 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2580 Tested-by: Gluster Build System Reviewed-by: Kaushik BV Reviewed-by: Vijay Bellur commit f4db9775655b24b9896ad697c534caec8868562d Author: Kaushik BV Date: Fri Jan 20 11:47:54 2012 +0530 nfs: export-dir option changed to type GF_OPTION_TYPE_PATH Change-Id: Ica47482cfed794d6923047db859191462919d6fe BUG: 782424 Signed-off-by: Kaushik BV Reviewed-on: http://review.gluster.com/2667 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a4818cef9838ed3b1a270f395b4cce9551532927 Author: Krishnan Parthasarathi Date: Mon Feb 6 15:12:51 2012 +0530 glusterd: Initialised op_sm/friend_sm before cluster restore. Cleaned up peerinfo/rpc association. Change-Id: I11bcaa3ea1f2b86c6b4e235873a60bb5bf76a892 BUG: 786006 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2725 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 0272f7de41fa529f51bc69fdaf694c77b47250f2 Author: Amar Tumballi Date: Fri Feb 3 13:54:02 2012 +0530 protocol/client: assign the right value to 'conf' before de-refing it variable assignment was done after it was actually getting de-referenced. moved the assignment few lines up. Change-Id: Id65e3e2d3dfe071e1c5b14c32488647070398ae4 BUG: 787117 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2712 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 1969ef17591342af2148d3a740b368f8cc6f8d5d Author: Rajesh Amaravathi Date: Wed Feb 1 15:52:36 2012 +0530 mount/fuse: check for existence of volfiles If glusterd is not running in the client host and/or if there are no volume created yet, this patch ensures that appropriate error message is displayed Change-Id: I15d23a45d70aa27bbdd42f435fe705b14c779e3f BUG: 786077 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2708 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit b708b18b833d1f2ba4da394884bc762a821ff56b Author: Kaushal M Date: Tue Aug 23 12:23:53 2011 +0530 cli, protocol/server : improve validation for the option auth.(allow/reject) cli now checks validity of address list given for 'volume set auth.*' Server xlator checks addresses supplied to auth.(allow/reject) option including wildcards for correctness in case volfile is manually edited. Original patch done by shylesh@gluster.com Original patch is at http://patches.gluster.com/patch/7566/ Change-Id: Icf52d6eeef64d6632b15aa90a379fadacdf74fef BUG: 764197 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/306 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 1d77fe2458be6dc567435dc59bb94870cd0fe529 Author: Raghavendra Bhat Date: Mon Jan 9 15:43:10 2012 +0530 glusterd/quota: inform the user if some quota command is executed without enabling it Change-Id: I676e52b0e0a9a6868eaa56d0309faa264e6e73be BUG: 771639 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2609 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5ebc522717ef891c138307d02dcbc0bc1e9017f8 Author: Kaushik BV Date: Mon Jan 30 19:17:12 2012 +0530 read-ahead: add performance.read-ahead--page-count option to 'volume set' framework Change-Id: I727be1ae2e3da1816afa52fc9555269aa07c39c1 BUG: 783379 Signed-off-by: Kaushik BV Reviewed-on: http://review.gluster.com/2700 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 9636f5b16c1847bc94d42ca6ac948c680bd55f2e Author: Kaushik BV Date: Fri Jan 20 11:54:21 2012 +0530 extras: create PID file for glusterd when started from init scripts thanks to Jaroslav Pulchart (jaroslav.pulchart@centrum.cz) for the patch Change-Id: Id07bf50536c8638f790f06e6e5994f85555c3978 BUG: 771221 Signed-off-by: Kaushik BV Reviewed-on: http://review.gluster.com/2668 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Vijay Bellur commit 7d81a11e661654394e116af52f0cab3d400ee2cf Author: Amar Tumballi Date: Sat Jan 21 20:05:55 2012 +0530 extras/test: add a test file to test 'f-fops'. mainly to test f*xattr(), fchown()/fchmod()/ftruncate() on fuse mounts. Change-Id: I59edbe172f307a2ba94f11c650ac0176fd35564f Signed-off-by: Amar Tumballi BUG: 766571 Reviewed-on: http://review.gluster.com/2692 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 08041c321229bdfb2cbe1b638fb4fabb0b9da013 Author: Kaushal M Date: Mon Sep 12 15:14:26 2011 +0530 protocol/client : prevent client from reconnecting when server authentication fails This prevents the client from trying to reconnect on server authentication failure. Reconnecting on authentcation failure causes hung mounts on unauthorised clients. This patch fixes this problem. Also, mount.glusterfs script unmounts mount-point on mount failure to prevent hung mounts. Change-Id: I5615074d27948077bad491a38cecae1b7f5159fb BUG: 765240 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/398 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 3ec7680a70bcace6b195ae412362b7e1b072eaeb Author: Krishnan Parthasarathi Date: Wed Jan 11 15:39:38 2012 +0530 glusterd: Changed op_sm_queue locking mechanism to accomodate nested calls to op_sm Today if an rpc call made inside an op_sm can fail due to a disconnected peer, resulting in the rpc callback to be called in the same stack with appropriate status set. All glusterd rpc cbks move the state machine based on the status returned by the rpc layer, which would result in a nested call to op_sm. With the current scheme of locking, glusterd would end up in a deadlock situation The new scheme will fail the nested glusterd_op_sm (). This prevents the deadlock. It would work without any change in overall behaviour, as the current op_sm () call in execution wouldn't return until all events in the queue are processed. Change-Id: I6a7ba16d3810b699bcd06dc28a5ff3205a25476f BUG: 772142 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2625 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 2313600f0749094f1246e663a0db15da3c2812db Author: Krishnan Parthasarathi Date: Fri Jan 6 12:18:35 2012 +0530 glusterd: Improved err msgs for add_brick Change-Id: I4b97d7e26b8c81ed52657467981be0c4adc291ae BUG: 772145 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2589 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 83a3daf7c205f119169eb2d7091432de05b1861c Author: Amar Tumballi Date: Fri Dec 16 18:27:52 2011 +0530 distribute: utilize new 'fremovexattr()' fop for rebalance instead of existing 'syncop_removexattr()' which is not rename proof for now. Change-Id: Ib171710645a6ee35c86d851a057b68461ecbab27 Signed-off-by: Amar Tumballi BUG: 766571 Reviewed-on: http://review.gluster.com/2691 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 3c0c468640ccd020a585c9f19366f857ee78d013 Author: M S Vishwanath Bhat Date: Tue Jan 31 01:32:50 2012 +0530 removing the dead code in cli-rpc-ops.c Change-Id: Ie80b7938944a5984e4d9cd0a5f52b7976030ea73 BUG: 783972 Signed-off-by: M S Vishwanath Bhat Reviewed-on: http://review.gluster.com/2701 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 698c0750e5b93fb9aa842a1d70def9ecfa6da41c Author: Raghavendra Bhat Date: Wed Feb 1 22:35:55 2012 +0530 performanc/stat-prefetch: check if loc->gfid is present before checking loc->name After gfid based backend changes loc will either contain the gfid of the inode or it will contain the parent gfid and the name of the entry. So before unwinding when loc->name is not there we have to check if loc->gfid is present or not. If loc->gfid is null and loc->name is also NULL, then unwind with the error. Change-Id: If88b9462bde09a80e79f27899c995605697ce453 BUG: 785675 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2710 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 52c13660eec1dd38f71e7119b319209f8cfd84e8 Author: Csaba Henk Date: Tue Jan 24 18:28:22 2012 +0100 Revert "mgmt/glusterd: Allow insecure ports by default" This reverts commit f6e0e614fbd07a57de44f0d16c304d01d1a5b269. Conflicts: xlators/mgmt/glusterd/src/glusterd.c Change-Id: I1da429e4b8c3f8c67367b173aa11dbe2b0435046 BUG: 781256 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2695 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b1a884aae98927d847085c9794f8b4aa8bebf838 Author: Raghavendra Bhat Date: Mon Jan 30 19:34:03 2012 +0530 features/marker,quota: Incorporate changes to support nameless lookup Change-Id: Ic5f00a9891bd835ebee5a3e103ef0f75d0b7fc25 BUG: 783925 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2702 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Jeff Darcy commit c3aa99d907591f72b6302287b9b8899514fb52f1 Author: Jeff Darcy Date: Thu Jan 19 17:49:42 2012 -0500 Fix race between read-ahead and write. Change-Id: I0ed1aca585733302b5e3840f392849e12f0b0f0d BUG: 783313 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/2666 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 20d74c540879d3994d56b9baf7044c79ae5df5e3 Author: Pranith Kumar K Date: Sun Jan 29 16:17:21 2012 +0530 storage/posix: Fix rename gfid handle unset Change-Id: I365ef264056691914ad5bd620d8150f8b71ec887 BUG: 785524 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2698 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 21bad6eb3a3c48ad3edc37927aeabcd3de8b9d64 Author: Pranith Kumar K Date: Sun Jan 29 16:09:29 2012 +0530 storage/posix: janitor should unset gfid handles Change-Id: I449b6a55122dfc27035569e6eb1d74ddcea68a69 Signed-off-by: Pranith Kumar K BUG: 785522 Reviewed-on: http://review.gluster.com/2697 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e2303e774e1e37cd9becb672a67278502724b369 Author: Mohammed Junaid Date: Tue Jan 24 17:12:59 2012 +0530 features/quota: Check for error in statfs fop call back. Change-Id: Ia73d2b77dcb0507a7b8362c336c71301526aaf82 BUG: 783927 Signed-off-by: Mohammed Junaid Reviewed-on: http://review.gluster.com/2685 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit e99cb60af1e153efd616014da6a54d2f95c119d1 Author: Raghavendra Bhat Date: Wed Jan 4 00:08:14 2012 +0530 glusterd: provide option to take statedump of the nfs server Currently the cli command for taking statedump is for glusterfs servers only. Statedump of nfs server cannot be taken. With this patch if one gives nfs as an option to the statedump command, then the nfs-server's statedump is taken. Change-Id: I4ef7a68e608da4aa2f17541d7b42cd78ce2624b6 BUG: 771587 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2579 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 5a8c58cf6e6c993c8665a31e6f108744ca27ccf4 Author: Krishnan Parthasarathi Date: Thu Nov 3 15:16:18 2011 +0530 glusterd: Refactored rb subcmds code and fixed some minor issues. Change-Id: I680a1c8f01883433d4cd1ed51723acebd8fe9245 BUG: 765441 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2689 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 623919a78a7faac30d1f0df5793681da2c449e32 Author: Kaushal M Date: Sun Jan 1 15:59:28 2012 +0530 cli: Extend "volume status" with statedump info This patch enhances and extends the "volume status" command with information obtained from the statedump of the bricks of volumes. Adds new status types : clients, inode, fd, mem, callpool The new syntax of "volume status" is, #gluster volume status [all|{ [] [misc-details|clients|inode|fd|mem|callpool]}] Change-Id: I8d019718465bbc3de727653a839de7238f45da5c BUG: 765495 Signed-off-by: Kaushal M Reviewed-on: http://review.gluster.com/2637 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit a078235dbede380ca695251e86a1502ca131d816 Author: Pranith Kumar K Date: Tue Nov 29 18:30:39 2011 +0530 cluster/afr: Perform xattrop with all afr-keys Self-heal does not happen if the file has change log xattr only for one of the subvol keys. This patch makes sure that xattrop is done for all the afr subvol keys after a new entry is created in entry-self-heal. 1) Added matrix create/cleanup functions 2) Impunging a new file does multiple xattrops on the source subvol, one per sink. The code can do a single xattrop after the entry is created on all the sinks. 3) Missing entry self-heal uses one frame per sink to heal the file. This leads to multiple xattrops on the source subvol. That code is changed now to use one frame which will create the file on all subvols. Change-Id: I65a42f9779b03f7efae283479f8653fb2cb8046b BUG: 762680 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2503 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Krishnan Parthasarathi commit d04a781d9acf328bf5f7a45d67c0d2b4cdd35311 Author: Pranith Kumar K Date: Tue Jan 24 18:47:35 2012 +0530 cluster/afr: Stack wind with correct frame *) Found possible races in _cbk fixed them as well. Change-Id: Id9a9f3cbf71f55827addb24ba2cbddecb8326b5b BUG: 784279 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2687 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit c13e3e090cc4d97dbf87a21b9de77e0b37ee5dd9 Author: Jeff Darcy Date: Wed Dec 14 13:37:36 2011 -0500 Make volfile-save scriptlet follow .rpmsave convention. Change-Id: I7a106defcc441679cf7c48f78eea2c04feb2853e BUG: 764702 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/788 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Vijay Bellur commit 6b0cd9fc8450029449f7c320a2e5d766e87ac8d4 Author: Vijay Bellur Date: Thu Jan 26 16:11:02 2012 +0530 protocol/client: Pass the right arguments to CLIENT_GET_REMOTE_FD Change-Id: I04f984f20964650a38009bba7711d2757151ade5 BUG: 762935 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2694 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit cf57b7b517af68c56fb8d4c229e2988c306384c4 Author: Harshavardhana Date: Mon Jan 9 17:15:23 2012 -0800 common-utils: Add support for solaris, bsd and mac os/x get_mem_size() is more standardized now. Change-Id: I8e3dc29df0a64a5eb8eea4fd3965b268cb1a85c2 BUG: 772808 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2618 Tested-by: Gluster Build System Reviewed-by: Kaleb KEITHLEY Reviewed-by: Vijay Bellur commit e8c722ba2832e4d0cae6ba3d043e5f06aaadbacd Author: Kaleb KEITHLEY Date: Wed Jan 25 07:01:48 2012 -0500 Add format/printf/attribute to log decls This enables compile-time checking of printf-style format checking Reason for doing it this way: N/A Description of test cases: N/A Change-Id: I9e26a5dceef5b545b9434b1d418c3d1193b4ef9a Signed-off-by: Kaleb KEITHLEY Reviewed-on: http://review.gluster.com/2693 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit ef1f9cfbaeb62fbabfcc175dc643baa125b393bb Author: Venky Shankar Date: Tue Jan 24 10:52:00 2012 +0530 geo-rep: gsyncd: Python3 compat fixes Change-Id: I2eef82faab3eed1189e3786a5dca296773e1caa0 BUG: 784498 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2690 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Csaba Henk commit fd61cd598b70fbc9442350483a3777d77990d257 Author: Raghavendra Bhat Date: Tue Jan 24 15:53:52 2012 +0530 protocol/client: if the remote_fd is -1, then unwind instead of sending the call to server For calls with remote_fd set to -1, client xlator is sending the call to the server which results in server not resolving it and thus fd being NULL. Locks xlator when tries to get the inode context using the fd it segfaults. To avoid it unwind the call in the client xlator if the remote_fd is -1. Change-Id: Ic34a49fdf1012dd371f4b194703c0be74f29bda2 BUG: 784187 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2684 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Krishnan Parthasarathi Reviewed-by: Anand Avati commit e98752525706fd6d9989367eb84f1a7fc1b81fa4 Author: Amar Tumballi Date: Fri Dec 23 10:00:28 2011 +0530 protocol: allow extra data in all the 'fops' over wire Change-Id: I3920c68b5b317fc4a4acfd26d64d900bf7bd59d1 BUG: 782265 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/2511 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 49c325d949b2df06572df7dd3825735fb9c8cd6f Author: Amar Tumballi Date: Sat Jan 21 20:05:55 2012 +0530 complete the implementation of missing 'f**xattr()' fops in debug/* and cluster/* translators and a syncop_fsetxattr() added a test case for testing the working of 'f-fop()' on fuse mount. Change-Id: I0c2aeeb30a0fb382ef2495cca1e66b00abaffd35 Signed-off-by: Amar Tumballi BUG: 766571 Reviewed-on: http://review.gluster.com/802 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d7ecaaa1ed0f88869812ea17cb64a102a74c8c1c Author: Amar Tumballi Date: Tue Jan 17 05:57:24 2012 +0530 core: add 'fremovexattr()' fop so operations can be done on fd for extended attribute removal Change-Id: Ie026f1b53793aeb4ae33e96ea5408c7a97f34bf6 Signed-off-by: Amar Tumballi BUG: 766571 Reviewed-on: http://review.gluster.com/778 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 6c54022f1b1c7f5f458f6a7e783203d11e7f89b5 Author: shishir gowda Date: Thu Jan 5 15:38:32 2012 +0530 cluster/dht: handle ENOENT err in rename fop A ENOENT should not be a error propogated for rename failures. As, ENOENT can arise only due to internal unlink call of rename. Change-Id: I925622da8ef370d0385bc5b30cf8dc9b8e852beb BUG: 768879 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/2583 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit cf8486cbef329ef66868f658fa35f470f97db462 Author: Amar Tumballi Date: Wed Jan 18 18:06:44 2012 +0530 core: get xattrs also as part of readdirp readdirp_req() call sends a dict_t * as an argument, which contains all the xattr keys for which the entries got in readdirp_rsp() are having xattr value filled dictionary. Change-Id: I8b7e1290740ea3e884e67d19156ce849227167c0 Signed-off-by: Amar Tumballi BUG: 765785 Reviewed-on: http://review.gluster.com/771 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b02afc6d008f9959db28244eb2b9dd3b9ef92393 Author: Amar Tumballi Date: Tue Jan 17 05:28:51 2012 +0530 core: change lk-owner as a 1k buffer so, NLM can send the lk-owner field directly to the locks translators, while doing the same effort, also enabled sending maximum of 500 aux gid over protocol. Change-Id: I87c2514392748416f7ffe21d5154faad2e413969 Signed-off-by: Amar Tumballi BUG: 767229 Reviewed-on: http://review.gluster.com/779 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 0694749c3e5039be327110a64dd66619b5d9121c Author: Shylesh Kumar Date: Tue Jan 24 12:14:36 2012 +0530 cluster/afr: set loc->gfid for building root loc Change-Id: Icb902846d243df0502f664bfd187280cecd4397c BUG: 784176 Signed-off-by: Shylesh Kumar Reviewed-on: http://review.gluster.com/2681 Reviewed-by: Pranith Kumar Karampuri Tested-by: Gluster Build System commit e04d45facc722d944d51439f4ae57b2af2a03d3e Author: Rajesh Amaravathi Date: Tue Jan 24 12:03:56 2012 +0530 glusterd: fix transpose of memset arguments a fix for transposed arguments to memset in glusterd_get_all_volnames function introduced in volume status enhancement. Change-Id: Iaea60c7d19b23992684f91b016b0841e2153b0a9 BUG: 765464 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2680 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit aecc9f52647e0ebc89cc5ca56a9f5182b7feb594 Author: Harshavardhana Date: Mon Jan 23 13:20:04 2012 -0800 Revert "distribute: utilize new 'fremovexattr()' fop for rebalance" This reverts commit c4e4be31ec2783b984e7dbb9ecbc1eea84044ad0 .. There is a problem here. syncop_fremovexattr doesn't exist in the codebase yet. Have a dependency merge for this. No other patches can be uploaded without a build failure now. Change-Id: Ic2c6194d905ffcfa7cbdc29c9bc8739f628d404e Reviewed-on: http://review.gluster.com/2679 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 54b8d503dd23e72ed3076988c52e689f3554ebc8 Author: Rajesh Amaravathi Date: Thu Jan 19 18:09:34 2012 +0530 pump: move internal pump xattrs out of trusted domain * the trusted.glusterfs.pump.{start|pause|commit|status|abort} xattrs have been moved out of trusted domain. This enables separation of xattrs used as gluster-internal commands (handled by pump) for replace-brick, which are not set in the back-end, from xattrs set on the replace-brick source and destinations bricks. * macros definitions from pump.h and glusterd.h, #defining these xattrs have been merged and put into libglusterfs/src/glusterfs.h Change-Id: I87b8bfbf045aa140f5d3f0c9baa9b2e79f87b67b BUG: 783049 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2663 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 4e2a26eb285de9e0a5836ad5e2edbc14eb9adc80 Author: Amar Tumballi Date: Fri Dec 16 18:27:52 2011 +0530 distribute: utilize new 'fremovexattr()' fop for rebalance instead of existing 'syncop_removexattr()' which is not rename proof for now. Change-Id: I3b2afbe58ce90658100cc56b01e23bed672854e8 Signed-off-by: Amar Tumballi BUG: 766571 Reviewed-on: http://review.gluster.com/803 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Shishir Gowda commit 366c98afe6d8ec1e69d33baad5e914fa3229f2a1 Author: root Date: Mon Jan 23 14:32:31 2012 +0530 storage/posix: Pass correct size to sys_lgetxattr We were passing op_ret (0), instead of size variable obtained by previous sys_lgetxattr to determine the size Signed-off-by: root Change-Id: I886dedc2ab752ac1feabe7a79725ea5f069d6865 BUG: 783916 Reviewed-on: http://review.gluster.com/2676 Tested-by: Gluster Build System Reviewed-by: Rahul C S Reviewed-by: Amar Tumballi commit 4e92c58d27b5cea9d7346d6dd88be9b3479c9e3b Author: Csaba Henk Date: Fri Jan 13 06:12:11 2012 +0100 rpc: extend actors with flag signing if privilege is required Currently we allow the following RPC messages for unprivileged users: GLUSTER_CLI_GETWD, GLUSTER_CLI_MOUNT, GLUSTER_CLI_UMOUNT Change-Id: I05414f3ca7cbe47de45c5e5cfba1537efc774e6c BUG: 781256 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2641 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d3ca9f05ec3a9881b5aeadb7b61cfcb97dbdb718 Author: Csaba Henk Date: Fri Jan 13 06:05:34 2012 +0100 cli: exit with error if connection problem occurs Change-Id: I97fc4d0a260120810b71dd5d9957a269d4550a3b BUG: 781256 Signed-off-by: Csaba Henk Reviewed-on: http://review.gluster.com/2640 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit bb1e07b7f42e7db415527852e98fcc1cbf2e1285 Author: Anand Avati Date: Fri Jan 13 23:17:07 2012 +0530 nfs: changes for using nameless lookup and anonymous FDs - Use gfid to create filehandle instead of encoding path components - Utilize nameless lookups of GFID for deep resolution instead of crawling the namespace with component hints - Use anonymous FDs for file based operations - Do away with fdcaching code for files and dirs Change-Id: Ic48fb23370b25d183f7e1fc1cc5dffa9d5bab3fb BUG: 781318 Reviewed-on: http://review.gluster.com/2645 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7e1f8e3bac201f88e2d9ef62fc69a044716dfced Author: Anand Avati Date: Fri Jan 13 13:27:15 2012 +0530 core: GFID filehandle based backend and anonymous FDs 1. What -------- This change introduces an infrastructure change in the filesystem which lets filesystem operation address objects (inodes) just by its GFID. Thus far GFID has been a unique identifier of a user-visible inode. But in terms of addressability the only mechanism thus far has been the backend filesystem path, which could be derived from the GFID only if it was cached in the inode table along with the entire set of dentry ancestry leading up to the root. This change essentially decouples addressability from the namespace. It is no more necessary to be aware of the parent directory to address a file or directory. 2. Why ------- The biggest use case for such a feature is NFS for generating persistent filehandles. So far the technique for generating filehandles in NFS has been to encode path components so that the appropriate inode_t can be repopulated into the inode table by means of a recursive lookup of each component top-down. Another use case is the ability to perform more intelligent self-healing and rebalancing of inodes with hardlinks and also to detect renames. A derived feature from GFID filehandles is anonymous FDs. An anonymous FD is an internal USABLE "fd_t" which does not map to a user opened file descriptor or to an internal ->open()'d fd. The ability to address a file by the GFID eliminates the need to have a persistent ->open()'d fd for the purpose of avoiding the namespace. This improves NFS read/write performance significantly eliminating open/close calls and also fixes some of today's limitations (like keeping an FD open longer than necessary resulting in disk space leakage) 3. How ------- At each storage/posix translator level, every file is hardlinked inside a hidden .glusterfs directory (under the top level export) with the name as the ascii-encoded standard UUID format string. For reasons of performance and scalability there is a two-tier classification of those hardlinks under directories with the initial parts of the UUID string as the directory names. For directories (which cannot be hardlinked), the approach is to use a symlink which dereferences the parent GFID path along with basename of the directory. The parent GFID dereference will in turn be a dereference of the grandparent with the parent's basename, and so on recursively up to the root export. 4. Development --------------- 4a. To leverage the ability to address an inode by its GFID, the technique is to perform a "nameless lookup". This means, to populate a loc_t structure as: loc_t { pargfid: NULL parent: NULL name: NULL path: NULL gfid: GFID to be looked up [out parameter] inode: inode_new () result [in parameter] } and performing such lookup will return in its callback an inode_t populated with the right contexts and a struct iatt which can be used to perform an inode_link () on the inode (without a parent and basename). The inode will now be hashed and linked in the inode table and findable via inode_find(). A fundamental change moving forward is that the primary fields in a loc_t structure are now going to be (pargfid, name) and (gfid) depending on the kind of FOP. So far path had been the primary field for operations. The remaining fields only serve as hints/helpers. 4b. If read/write is to be performed on an inode_t, the approach so far has been to: fd_create(), STACK_WIND(open, fd), fd_bind (in callback) and then perform STACK_WIND(read, fd) etc. With anonymous fds now you can do fd_anonymous (inode), STACK_WIND (read, fd). This results in great boost in performance in the inbuilt NFS server. 5. Misc ------- The inode_ctx_put[2] has been renamed to inode_ctx_set[2] to be consistent with the rest of the codebase. Change-Id: Ie4629edf6bd32a595f4d7f01e90c0a01f16fb12f BUG: 781318 Reviewed-on: http://review.gluster.com/669 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 33c568ce1a28c1739f095611b40b7acf40e4e6df Author: Krishnan Parthasarathi Date: Wed Jan 18 13:59:32 2012 +0530 glusterd: Fixed crash in stop volume found using efence. Change-Id: I84d38b8af248920a1559d05f0e4f43d3eda0f43e BUG: 782710 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2651 Reviewed-by: Pranith Kumar Karampuri Tested-by: Gluster Build System commit 9b389a3f76bc858f95e498c1539317c7a8bc6188 Author: Raghavendra Bhat Date: Thu Jan 19 11:41:55 2012 +0530 cluster/afr: do not unlock without holding the lock on the fd In afr_open_fd_fix we were unlocking the local->fd->lock, without holding the lock on it if we were not able to get the fd context. Now we are directly going to out and returning, instead of going to unlock without holding the lock. Change-Id: I0da638bbd2c269127cf111b3aac707e4a95d20c6 BUG: 783036 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2658 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 6481f062b8ad0f47fa7715f78b7bf61623d1dc9a Author: Rajesh Amaravathi Date: Tue Jan 17 11:54:20 2012 +0530 cli: trivial changes in cli-rpc-ops.c * the get_volume_cbk has been cleaned up(w.r.t whitespace) and a memset used where appropriate. some other functions have been affected(in a good way) by the whitespace-dealing commands in emacs. Change-Id: Iba473290e87747f8bb06d335db06c872a241d7cd BUG: 781333 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2653 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 3169891538331a8a0e954010c5dac8360997da12 Author: Krishnan Parthasarathi Date: Wed Jan 18 15:16:48 2012 +0530 glusterd: Fixed crash in peer probe found using efence Change-Id: Ie09d1e4eb9a8d338f8e5cf6360b398b196141a81 BUG: 782718 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2655 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri Reviewed-by: Jeff Darcy commit 36cedb338ec1d021e189379f30100f0d983e3e01 Author: Rajesh Amaravathi Date: Tue Dec 6 11:35:33 2011 +0530 core/setxattr: prevent users from setting glusterfs xattrs * Each xlator prevents the user from setting glusterfs-internal xattrs like trusted.gfid by handling it in respective setxattr functions. The speacial case of trusted.gfid is handled in fuse (Not in posix because posix_setxattr is used to set gfid). * For xlators which did not define setxattr and/or fsetxattr, the functions have been implemented with appropriate checks. xlator | fops-added _______________|__________________________ | 1. afr | fsetxattr 2. stripe | setxatrr and fsetxattr 3. quota | setxattr and fsetxattr Change-Id: Ib62abb7067415b23a708002f884d30e8866fbf48 BUG: 765487 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/685 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 4e76cea78b11e9290b16c2faa85cf81b8e32b7ea Author: Niels de Vos Date: Sat Jan 7 16:10:06 2012 +0000 trivial: gluster_pmap_actors should only use GF_PMAP_* procedures GF_HNDSK_NULL is not suitable for gluster_pmap_actors, instead use GF_PMAP_NULL. The actual value (0) is not different for these, so there is no fuctional change. Change-Id: Ibb998ebae88b457c57a42ce63dad095d2d4a22c5 BUG: 772468 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.com/2603 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 3007bdddb1cae3d2b036ebddfc76ca6f6e06a184 Author: Kaleb KEITHLEY Date: Mon Jan 9 12:32:46 2012 -0500 don't try to get ngroups from /proc on non-Linux systems Emmanual Dreyfus abandoned his changes, seemingly because he couldn't get rfc.sh to correctly generate his changed patch set. Since Mac OS is an important port, I suggest we keep this change alive. (This change also works on the other BSDs too) Now with added Solaris support BUG: 764655 Change-Id: I6a9ab7383777f9a09ab5c9a6914f45eee43461fb Signed-off-by: Kaleb S. KEITHLEY Reviewed-on: http://review.gluster.com/2617 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 0e1679aee746040cdd509c5cd4004a4641c4c203 Author: Vijay Bellur Date: Fri Jan 13 18:21:39 2012 +0530 cli,glusterd: Display volume UUID in the output of 'volume info' Cleaned up some leaks along the way. Change-Id: Ibc76c539eee935c0630f9580d0d914814b1a6fe1 BUG: 781445 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2643 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit faf9099bb50d4d2c1a9fe8d3232d541b3f68bc58 Author: Harshavardhana Date: Tue Jan 3 16:05:51 2012 -0800 cluster/distribute: dht_aggregate() fix a logic error before xattr comparisons Change-Id: I20f015263bed9851225005d5f41a5d518bd22592 BUG: 769691 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2557 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 718a2744076ff21d19c0e9b2cadac5b975a3f6a9 Author: Niels de Vos Date: Sat Jan 7 22:05:11 2012 +0000 trivial: correctly document that GLUSTER_CLI_VERSION=2 matches version 0.0.2 Change-Id: I0d7eb0ac67ad83e5f21b60cc2acc514ac602ea42 BUG: 772469 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.com/2604 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit cf944c8ad5da87bce15b08d0bbb2ecd62e553d86 Author: Rajesh Amaravathi Date: Fri Jan 6 16:02:55 2012 +0530 glusterd: prevent adding bricks already in use The add-brick command now checks if the brick provided for add-brick is used in any volumes, even if the volume was never started by looping through the brick lists of all volumes. Change-Id: I15035d41d91386448a3e3d4063d909b880288681 BUG: 771831 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2607 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Amar Tumballi commit bfd429e583f50a4f4712de88dc0a15baadebbf9b Author: Harshavardhana Date: Wed Jan 11 12:24:38 2012 -0800 common-utils: Cleanup old stuff and standardize Change-Id: If15058c3a1cc4070d1ebbabe37e012a70353310e BUG: 769691 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2635 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 3207a33ef67ed0d065935360adb309a7ae046317 Author: Rajesh Amaravathi Date: Tue Dec 27 15:09:39 2011 +0530 glusterd: improve replace brick status message when replace-brick status is invoked without starting replace brick on the specified bricks, appropriate error message is displayed Change-Id: I57230db84314caf807f1ff54f74307d85bdc1633 BUG: 769926 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2531 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit 919e3424849db2276e003dcd919a470838bf084f Author: Lubomir Rintel Date: Mon Dec 19 23:40:11 2011 +0100 posix-acl: properly process umask in case client sent it FUSE used to interpret the umask itself. That was a bad idea, since there are cases where umask is not applied, such as when extended POSIX ACLs are present and default ACLs are set on parent directory. The FUSE bridge was changed to send original mode with umask (alongside masked mode, for compatibility). If that is the case, we decide whether to apply the umask or not in the posix-acl translator depending on whether a default umask is set, or not. The original, broken, behavior is preserved in following cases: * Unpatched client (not sending umask with original mode) * Unpatched server (not understanding umask with original mode) * Old FUSE on client side (FUSE < 7.12 or linux < 2.6.31) (can not find out the umask and original mode) Change-Id: I2e3bfc4c7c9611bc51119ca5c8e28f6582677516 Signed-off-by: Lubomir Rintel Tested-by: Lubomir Rintel BUG: 765508 Reviewed-on: http://review.gluster.com/668 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 8a78d969ee8b7c284751364d72496eec84c7290b Author: Lubomir Rintel Date: Thu Nov 3 08:51:50 2011 +0100 fuse-bridge: preserve original mode and umask FUSE used to interpret the umask itself. That was a bad idea, since there are cases where umask is not applied, such as when extended POSIX ACLs are present and default ACLs are set on parent directory. Thus, FUSE was changed to pass umask to operation handler itself in case the fuse server is initialized with FUSE_DONT_MASK. In case FUSE supports it, gluster client sends mode unmasked and umask separately ( masked mode is still sent, for compatibility with old servers). the mode as-is for compatibility with older clients. Change-Id: I55862b39a25261446f18ba0b3c03f85b41c4d722 Signed-off-by: Lubomir Rintel Tested-by: Lubomir Rintel BUG: 765508 Reviewed-on: http://review.gluster.com/667 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 169c73f28dae61236de54889edcaa8236d91da59 Author: Rajesh Amaravathi Date: Wed Dec 7 20:51:03 2011 +0530 cli: volume status enhancement * Support "gluster volume status (all)" option to display all volumes' status. * On option "detail" appended to "gluster volume status *", amount of storage free, total storage, and backend filesystem details like inode size, inode count, free inodes, fs type, device name of each brick is displayed. * One can also obtain [detailed]status of only one brick. * Format of the enhanced volume status command is: "gluster volume status [all|] [] [detail]" * Some generic functions have been added to common-utils: skipword get_nth_word These functions enable parsing and fetching of words in a sentence. glusterd_get_brick_root (in glusterd) These are self explanatory. Change-Id: I6f40c1e19810f8504cd3b1786207364053d82e28 BUG: 765464 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/777 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 4e40a7e48757feedc959c7982acf05c73f739a15 Author: Pranith Kumar K Date: Wed Jan 11 10:38:45 2012 +0530 mount/fuse: Fix memory leaks Change-Id: Iff10650dc8234f9d8ca0472f2e1ea9c60fbd6d4e BUG: 773211 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2630 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 984de558a959854ddb4042f2fb3d47508883b788 Author: Anand Avati Date: Thu Dec 8 11:08:48 2011 +0530 core/stack: perform locked winds In configurations like pump, where there is a cluster translator on top of io-threads, there are situations where two concurrent stack-winds can be performed on the same call stack in multiple threads. This patch holds locks during the call frame list manipulation Change-Id: I51539210dc8101f7a80cf9bc103b5eff0c86dc9f BUG: 765522 Reviewed-on: http://review.gluster.com/774 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 836c5f0075e83816d00003da440d5c728aefb93e Author: Krishnan Parthasarathi Date: Mon Jan 9 17:03:21 2012 +0530 cli: Corrected replace-brick error messages and usage string. Change-Id: I2739529ca572fd762fbbed27de9e433e8c5b1f81 BUG: 772583 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2613 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 979e12f16b57cbb848fb9096d673dc58ed9b67a4 Author: Pranith Kumar K Date: Mon Jan 9 19:48:44 2012 +0530 cluster/afr: Remove dead code Change-Id: I239128c51b728fbb7814fd6a41020b76c88fbd93 Signed-off-by: Pranith Kumar K BUG: 772876 Reviewed-on: http://review.gluster.com/2623 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 5303f98f674ab5cb600dde0394ff7ddd5ba3c98a Author: Rajesh Amaravathi Date: Mon Dec 26 14:39:24 2011 +0530 extras: add check for brick path existence Adding a couple of checks to validate brick path(s) Change-Id: I2d8538add21407d9457542373b528c2a02cd7eb6 BUG: 765572 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2514 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 22282b4fb82b83621c15773c4c44ff3d28a82e3c Author: Rajesh Amaravathi Date: Wed Jan 4 13:06:29 2012 +0530 lib/mount-broker: move utility functions to common-utils functions skipwhite and nwstrtail have been moved from mount-broker to common-utils library for general use. Change-Id: I9cfefb28bbfcf5d0bd37e35865ff3f3b7923fc53 BUG: 765464 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/2560 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-by: Csaba Henk commit ea275f8cfe8abf5877f67b21afb2c1e6e08f06b7 Author: Krishnan Parthasarathi Date: Thu Jan 5 11:21:25 2012 +0530 glusterd: Fixed add-brick error message. Change-Id: I9260d5a0203ae2990d37b30bcc7c94c81c1e168e BUG: 770678 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2581 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit c66ced7d876c8c96561724901be52a0a8afd4baa Author: Junaid Date: Wed Jan 4 12:46:53 2012 +0530 features/marker: xtime should not be updated for modifications done by special client. Change-Id: Ia577422dedb94a1febeceb2a50cabf61d48cb714 BUG: 769494 Signed-off-by: Junaid Reviewed-on: http://review.gluster.com/2559 Tested-by: Gluster Build System Reviewed-by: Kaushik BV Reviewed-by: Jeff Darcy Reviewed-by: Csaba Henk commit 0a4ac033095c0675c90abc353736f388873291c0 Author: Krishnan Parthasarathi Date: Wed Jan 4 19:05:18 2012 +0530 glusterd: Added checks for remove-brick handler. Removing bricks in a plain stripe-replicate is failed if replica count is not reduced explicitly. Change-Id: I6d0de4862595744d1d1998b9a287c34c53d7fe5f BUG: 770561 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2577 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 60862f5916dff99c91dd6d6319c958d02cb535d8 Author: Harshavardhana Date: Tue Jan 3 11:07:00 2012 -0800 libglusterfs: Add boundary conditions to data_to_int8() function. Change-Id: Iff50d44568895a75fc8743a10346990f764cf8fa BUG: 769692 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2556 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit a6777636fbb94a34a37cadd7840429f72fc5b747 Author: Rahul C S Date: Tue Jan 3 22:24:22 2012 +0530 Avoid setting dict when size is -1 when lgetxattr fails and returns size as -1, we still try to set the dict. Instead it should set proper errno & exit. Change-Id: I282dc0765e562bd9bbcf852453cd3b72d918b269 BUG: 771313 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2555 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit fb825bccca8348cbff64edb239ee0cd66942984e Author: Venky Shankar Date: Sun Jan 1 23:48:15 2012 +0530 cluster/stripe: Fix block size reported in pathinfo xattr Block size (or stripe size) is reported when request is made for pathinfo xattr (trusted.glusterfs.pathinfo) for a striped volume. When the block size is changed, the new block size is reported for files created with older block size. This can be confusing ( or even erroneous ) for applications relying on pathinfo xattr to find chunks in backend. Change-Id: I79cb6721bbd33f44c3fada4dd52e459d2c128e24 BUG: 766530 Signed-off-by: Venky Shankar Reviewed-on: http://review.gluster.com/2545 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 29b9b0c72809456b1ba334a40adc1ed9929eca91 Author: Krishnan Parthasarathi Date: Mon Jan 2 18:40:31 2012 +0530 glusterd: Fixed add-brick handler algorithm. In the fix for 765774, setting the op dictionary with modified stripe and replica count was (accidentally) removed affecting the correctness. The stage and op functions of add-brick rely on the fact that stripe/replica count are zero if there is no change in them during the add-brick operation. Change-Id: I55a23878e618b355009ffd0fce8c4904dbb70691 BUG: 770914 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/2548 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit be003fbb3ac7a1f1021774ecb75a4929f1ba85d4 Author: Pranith Kumar K Date: Thu Dec 15 16:51:02 2011 +0530 cluster/afr: Handle fini for afr,pump Change-Id: Idc0a05a8a25f278a7ab05e242263e0a5001bde18 Signed-off-by: Pranith Kumar K BUG: 767862 Reviewed-on: http://review.gluster.com/800 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c8c0942d1c890fd9b74c8e2fb3897bc96f9b9b82 Author: Pranith Kumar K Date: Thu Dec 29 11:58:21 2011 +0530 cluster/afr: EIO should overwrite ENOENT in lookup In case if lookup decides there is a gfid-mismatch, some enoents and self-heal cant remove the stale entry, it tells lookup to unwind with EIO but since ENOENT has more priority it is not over-written, this patch fixes that case. Change-Id: Icd68c4a5cf05dd97c568964ab647a34fdb6e26f4 BUG: 765528 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2541 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8de9cad2234109913cf090b93e77980603424e85 Author: Raghavendra Bhat Date: Fri Dec 23 14:57:37 2011 +0530 mgmt/glusterd: log the rebalance command received properly in the log file Change-Id: If18d9a49f5a3442755440e08ee7a63f6c6e54c5d BUG: 770058 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/2500 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 145b0f5a45c600c4f84f0d85adf36035a0abce5e Author: shishir gowda Date: Fri Dec 23 11:49:02 2011 +0530 debug/io-stats: Handle fini for io-stats xlator Signed-off-by: shishir gowda Change-Id: I0b36a2f4836fa84ced7414fdba4d68e0cb6cac7b BUG: 767862 Reviewed-on: http://review.gluster.com/2499 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 1c4098a05e8e035c4e155aebb410fe2c811ccd50 Author: Rahul C S Date: Fri Dec 23 03:28:13 2011 +0530 Added/Removed white spaces wherever necessary in replace-brick Change-Id: Ic11d04813109bc6252e4dfe754c7b4c5c74014cd BUG: 769985 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2498 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit d2b6d69023c954eed1031c03e0b6750bb81f52ac Author: Harshavardhana Date: Fri Dec 2 16:57:22 2011 -0800 mount/fuse: Cleanup / remove unnecessary comments Change-Id: If236e82c2e89d2ab4a0e3278319976aeb9fc05a6 BUG: 769691 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/2491 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit e9659b4103680eb82e7004b411d2db18c5fbb9bd Author: Pranith Kumar K Date: Wed Dec 28 12:09:08 2011 +0530 cluster/afr: Handle error cases in local init - Fop should unwind with appropriate errno - Local is de-allocated on errors Signed-off-by: Pranith Kumar K Change-Id: I4db40342ae184fe1cc29e51072e8fea72ef2cb15 BUG: 770513 Reviewed-on: http://review.gluster.com/2539 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e1f6ebc1a41d1759c2c4ec1d81a9b8a777b7a25d Author: Rajesh Amaravathi Date: Wed Nov 23 12:52:04 2011 +0530 rebalance: remove the *.fix.layout xattr from trusted domain. moving trusted.distribute.fix.layout from trusted domain. Change-Id: If4317e4320998bbd739a8472b8814d75c425d341 BUG: 765487 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/747 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 8be9b0502843b755adad7badfc4e144cf7c410f6 Author: Vijay Bellur Date: Sun Dec 25 22:17:08 2011 +0530 build: Change dependency of rsync version for geo-replication Change-Id: Iaf49121ef04bb02114f74cdc2fd2985a564d5407 BUG: 764476 Signed-off-by: Vijay Bellur Reviewed-on: http://review.gluster.com/2505 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit 8543529f381d16349662269342d55ab67a1a4582 Author: Pranith Kumar K Date: Mon Dec 26 10:10:13 2011 +0530 cluster/afr: Handle split-brain/all-fool xattrs for directory In case of split-brain/all-fool xattrs perform conservative merge. Don't treat ignorant subvol as fool. Change-Id: I6ddf89949cd5793c2abbead7c47f091e8461f1d4 BUG: 765528 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2521 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a0c5efcf2cb2be5c9736c75af7a6d8754a101bf5 Author: shishir gowda Date: Wed Dec 21 10:43:28 2011 +0530 features/posix-acl: handle fini for features/posix-acl Signed-off-by: shishir gowda Change-Id: I6cd3a9c3a513cc2a998b82610613bbfa0622eec4 BUG: 767862 Reviewed-on: http://review.gluster.com/811 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 4511ed196f94f639846b899e6b58f5f6af3fa668 Author: Rajesh Amaravathi Date: Tue Dec 13 12:58:25 2011 +0530 extras: clean up a brick's gfid xattr * extras/clear_xattrs.sh: This script enables a brick from a deleted volume(stale brick) to be used in a new volume by clearing all the trusted.gfid xattr from the brick tree. * One should run this script on all machines which have stale bricks if one wants to re-use the same bricks for a new volume. NOTE: This script *SHOULD BE RUN ONLY AFTER STOPPING A VOLUME*, thereby ensuring that no replace-brick or rebalance operations are on-going. Change-Id: I35a4a2784fe502749184b87299b1a043b8e48e90 BUG: 765572 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/781 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 31fa06932952f0cb706653aa7d0450646009eb07 Author: Rahul C S Date: Thu Dec 22 13:17:21 2011 +0530 Improve cli output of gluster volume heal command. Improving cli outputs according to the type of the volume, the "heal" action can be performed on the volume. Also checks if the volume is started & then if the "self-heal" daemon is not started, prints appropriate message. Change-Id: I25b0822e4d518c50e2f1173aa8c7c11ae6b76d3f BUG: 769774 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/2496 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit d7d9f3d4002d31ceefed6ce80ec7567eca9ba6d3 Author: Pranith Kumar K Date: Tue Dec 20 10:05:12 2011 +0530 cluster/afr: Set pargfid when missing client asserts for missing pargfid in case of unlink. So Afr needs to make sure it is present in that fop. Change-Id: Iea0ad65e1e7254c8df412942c52d5870e853aa51 BUG: 769055 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/2495 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5ccbfdd87bebbc4c65a76c72191ac564ff844df8 Author: Pranith Kumar K Date: Mon Dec 19 22:10:38 2011 +0530 libglusterfs: set inode path to be NULL in case of errors Some of the functions calling inode_path, __inode_path are assuming the path to be set to NULL in case of errors. Instead of fixing it in the calling functions, fixing it in the __inode_path function. Change-Id: I77736a2700d3c2c9732a536bcf2a398fe626d54e BUG: 765430 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/810 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit bddb3a014af22133d958da96ad32a02f8ff66805 Author: Pranith Kumar K Date: Mon Dec 19 18:35:19 2011 +0530 protocol/server: Do connection cleanup if reply fails We observed that after the first connection cleanup happens on DISCONNECT the lock calls in transit are granted or added in blocked locks queue. These locks were never cleaned up after that because no unlock would come up on that connection. This would leave references on that transport so it would never be destroyed. Now, the connection cleanup happens whenever the reply submission fails. Also cleaned up the old code which is not used any more. Change-Id: Ie4fe6f388ed18d9c907cf8ae06b0b7fd0601a660 BUG: 765430 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/809 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 23495efe35515891cc56b49ef967d5b1ba195e3e Author: Pranith Kumar K Date: Mon Dec 19 12:45:34 2011 +0530 features/locks: Fix release of locks on disconnect When a disconnect comes on a transport, all the locks on that transport should be cleared irrespective of entry presence. Change-Id: I1c432ec1ddc8fe3f7bf236992f47437d0dacd6ae BUG: 765430 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/808 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 941edee5dc38328fb46dd8b284956357ca67dec9 Author: Pranith Kumar K Date: Fri Dec 16 21:47:14 2011 +0530 cluster/afr: Fix meta data lock range Change-Id: I7615f31309c6c8f5373e1ff0535d84396dfa1455 BUG: 765430 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/807 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 7eed1d5ba51b65e865f79a392aff70048c702bf0 Author: Harshavardhana Date: Fri Dec 2 16:58:14 2011 -0800 transport/rdma: Add attr_timeout, attr_retry_cnt, attr_rnr_retry as configurable options Change-Id: Ifc4710f149be35979746ddfbfb4181638601bc64 BUG: 766040 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/766 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 0074f208448d131a25721d8cd4ed408c5c57c72a Author: Krishnan Parthasarathi Date: Mon Dec 19 12:42:31 2011 +0530 glusterd: Fixed spurious checks in add_brick. Previous algo, - didn't allow volume type change from plain distribute to distribute-[stripe][-][replicate]. - performed 'add-brick' on temporary volinfo without correct initialisations. This was superflous. Change-Id: If5d5d78e59bd04685df9c27974f715df5f0b43f3 BUG: 765774 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/804 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 2a3e74e7a68aac1ad6d89122bbc4d64cd304986b Author: Jeff Darcy Date: Tue Dec 13 17:13:59 2011 -0500 Fix local==NULL crash in wb_sync_cbk during disconnect. Change-Id: I26dc48a85756e189b1ef5cfef1658f9c2aed2157 BUG: 767359 Signed-off-by: Jeff Darcy Reviewed-on: http://review.gluster.com/784 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 255fed3b0d5b9d210d1da47dbd647dd6497cd550 Author: Raghavendra Bhat Date: Thu Dec 15 22:16:13 2011 +0530 cli: validate the volume set command properly For volume set command if after the volume name the key and the value of the option are not given, then gracefully exit by showing the proper usage of volume set, instead of sending the request to glusterd, which makes glusterd crash. Signed-off-by: Raghavendra Bhat Change-Id: I2f0d189a55663c7f47dddff35d4dc68fae16b755 BUG: 767591 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/797 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Jeff Darcy commit 4debbfe7f629626fd2e77a2d98f37f4e808e9f95 Author: Raghavendra Bhat Date: Mon Dec 19 16:36:33 2011 +0530 cluster/stripe: copy the gfid from the dentry structure to loc In stripe_readdirp_cbk we used to send stat call on each of the entry we have got from readdirp, by creating a new inode (but without setting the gfid in loc). Protocol/client asserts if it cannot find gfid in either loc or loc->inode. This patch copies the gfid of the entry from the stat structure to loc. Change-Id: I35228227e943f3b01fac720d6c587764c47e6869 BUG: 768840 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/806 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 3853f4ccaf1f0446af9a3f523008c64834a63df6 Author: shishir gowda Date: Thu Dec 15 15:13:14 2011 +0530 rpc-transport/socket: Donot fail reconnect if error is ENOENT A AF_UNIX family socket should retry connect if error is ENOENT. Signed-off-by: shishir gowda Change-Id: I23b1da12faadc8043d370862bfe29c0c5c223364 BUG: 767932 Reviewed-on: http://review.gluster.com/795 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a6098362f93e321ce25424d2f95cc1d61783f6b9 Author: Rahul C S Date: Thu Dec 15 18:16:29 2011 +0530 Default option to be set to "all" if no option is given to volume statedump cli command. Change-Id: Ia167e9d0fd1f9a50f79554d40e6fa7d292896aa4 BUG: 767545 Signed-off-by: Rahul C S Reviewed-on: http://review.gluster.com/799 Tested-by: Gluster Build System Reviewed-by: Kaushal M Reviewed-by: Amar Tumballi commit 3a0fe71cebd59c1204c60a7d20b2fe2b94f07665 Author: Krishnan Parthasarathi Date: Wed Dec 14 14:46:09 2011 +0530 glusterd: Fail 'requests' from non-peers. glusterd should not honour "volume op requests" from peers who are not part of the cluster. Change-Id: I6cb6d630a9da02ab060650f21edb46db8deb70e8 BUG: 767559 Signed-off-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/787 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit cd24be007c64bd10d8c28e8e9b1c988478a32c8c Author: Raghavendra Bhat Date: Wed Dec 14 10:36:27 2011 +0530 debug/error-gen: add option to generate errors at random percentage Currently error-gen has a option where the percentage of the errors generated can be specified. This patch adds a new option, which if given errors are generated at random percentage. If both the random failure option and the specific percentage of the errors are provided, then random error generation is given preference. Change-Id: I43fffcd7da8935761ed7d30e2a9677895d6a31fb BUG: 767192 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/786 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit ebe0cedb072baf4c1f4bd81f22745c428ab6b911 Author: Pranith Kumar K Date: Tue Dec 6 14:00:40 2011 +0530 protocol/client: Be strict about gfids in fop req Change-Id: I7508ab3a93329bb6a679801fddfcd0e5b0c7c134 BUG: 765198 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/770 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 7235e5b1af090ffc9d87ac59daadf7926433b495 Author: Rajesh Amaravathi Date: Tue Dec 13 15:26:55 2011 +0530 mount/fuse: export PATH for which in mount script exporting PATH environment variable for mount.glusterfs.in to correct the "which: no getfattr in ((null))" error during fuse mount. Change-Id: Id7d024c0d1cf3d265489557897e9e1f8e7ce4ce4 BUG: 765561 Signed-off-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/782 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 91c7ad753884c81b46f05f200b9d9dc00eec5132 Author: Pranith Kumar K Date: Tue Dec 13 15:54:49 2011 +0530 cluster/afr: Double the call count if transaction is for rename In rename the changelog modification needs to happen both on old parent-dir and new parent-dir, so 2 stack winds are done per brick. Change-Id: I43f34661e397c4288162213944529e18b7724b1d BUG: 766603 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.com/783 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1d38ec6ce40279d7e8ef2b5a9bd59a2d289eca23 Author: Amar Tumballi Date: Thu Nov 24 15:42:55 2011 +0530 fuse: bring in the reverse invalidation Thanks to Csaba Henk for the patch Currently one can invalidate the inodes using 'setxattr()' with key 'inode-invalidate' (and any value). This can be further extended to do a purge of inode table itself. Change-Id: I165d5d585ed808b9e463ac0aad859ec64568c7a2 BUG: 762277 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/324 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 289c2902d6a81f7a5b6da04c24cc955bd5427178 Author: Raghavendra Bhat Date: Thu Dec 8 11:42:50 2011 +0530 iobuf: fix a crash in iobuf when statedump is taken With the previous patch this change was missed. Change-Id: If536cef3fa423415eaa4104e6c3e5e72c5d0a22d BUG: 3854 Signed-off-by: Raghavendra Bhat Reviewed-on: http://review.gluster.com/775 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 017344be59fbbd4cf6d29d3f5a6581b468dc29c9 Author: Amar Tumballi Date: Tue Sep 27 18:01:29 2011 +0530 libglusterfs/iobuf: have fixed number of arenas * so overall memory usage will be in limit. * the array is hard-coded, need to improve upon this. * need more benchmarking to tune the proper values to the array * fixed the issue of pruning of arenas. Change-Id: I38a8ffab37378c25d78f77a2d412b1b8935c67d3 BUG: 3474 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/543 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 254fbfd92d4088c97ddde79a37b4e08e80c8eff3 Author: Harshavardhana Date: Mon Nov 21 16:28:47 2011 -0800 cluster/distribute: Assert checks at known locations and new function dict_get_ptr_and_len(). Change-Id: I653a1cc8123baa36d750250d02721aa98b196f38 BUG: 3158 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/744 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2b64c93c9f7f69fab506bdfca163a2805a2ea46c Author: Anand Avati Date: Mon Dec 5 14:18:22 2011 +0530 CONTRIBUTING: add a DCO The new CONTRIBUTING file has a Developer Certificate of Origin with instructions for contributors to ensure 'Signed-off-by:' line in the commit log (git commit -s). Corresponding changes also done in Gerrit to reject patches which do not have Signed-off-by: line. Change-Id: Ia3e1e8d3cfd4b32e4cfd4d2df91c6dbd57e2f60e BUG: 3234 Signed-off-by: Anand Avati Reviewed-on: http://review.gluster.com/767 Tested-by: Gluster Build System commit 99d606e810286eef6f19e39d24dd63cb602a0bb1 Author: Rahul C S Date: Fri Nov 25 17:21:46 2011 +0530 Changes all parent values for quota_check_limit and quota_update_size from 0x0 to NULL to make sure uuid_copy happens between pointers Change-Id: I73ef5f9054f972fce00b8f42125dc49c9d86c3f2 BUG: 3830 Reviewed-on: http://review.gluster.com/756 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Amar Tumballi commit 430f76a6c1c9af06b433a9d6080168b92b30e034 Author: Kaleb KEITHLEY Date: Thu Dec 1 12:44:38 2011 -0500 bz 3826, fix for parallel make in fedora build system builds of glusterfs in the fedora build system often fail due to a race condition between running yacc and starting to compile the y.tab.c produced by yacc We found that the previous fix would still occasionally trip the race condition. This revised patch changes the automake Makefile.am to generate the parser files without incurring the race condition. An extra dimension of the problem is that the tarball from http://download.gluster.com/pub/gluster/glusterfs/3.2/3.2.5/glusterfs-3.2.5.tar.gz contains files that you don't get when you clone from the git repo (e.g. libgluster/src/{graph.lex.c,y.tab.c}, and all the Makefile.in files) so build issues on fedora build systems do not manifest themselves on jenkins and vice versa. This works on jenkins, the fedora build system, and my f16 vm/guest machines. (Finding the right combination that works on all three was an exercise to say the least. I'm open to other suggestions for avoiding the race condition.) Run autogen.sh to (re)generate the Makefile.ins. Then run configure to produce all Makefiles, followed by `make -j X` where X>1 see also https://bugzilla.redhat.com/show_bug.cgi?id=756510 BUG: 3826 Change-Id: Iaeecb59c61a77bf3927da18253c83cf5ffed4254 Reviewed-on: http://review.gluster.com/765 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit f5d5e8012a3762d0ffb95a0ca624a3fce3c262cd Author: Raghavendra G Date: Thu Nov 24 13:50:23 2011 +0530 mount/fuse: Inherit direct-io-mode values from fds already opened, for a new fd being opened. When an fd is being opened, it inherits direct-io-mode characterstics (either enabled or disabled) from the fds already opened on inode. If none are opened and user has not specified the mode through cmdline options, default mode is used. Change-Id: I0c9e959100e9130e46bbd16d63eca278260635b4 BUG: 801 Reviewed-on: http://review.gluster.com/55 Tested-by: Gluster Build System Reviewed-by: Csaba Henk Reviewed-by: Anand Avati commit 5d194403e96d97f82681b5e7d96ddf8e48858cb7 Author: Harshavardhana Date: Tue Nov 29 15:20:48 2011 -0800 contrib/uuid: Make sure that uuid_types.h are generated per system specific. Just the same way e2fsprogs maintains. This avoids unnecessary problems for different architectures. Change-Id: I3911998373756707996afb7b926ec0780ea18b81 BUG: 3833 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/764 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit fbf6ce560dd6e72fc9d404e32d313732077a250f Author: Kaleb KEITHLEY Date: Tue Nov 29 09:36:50 2011 -0500 bz 3826, fix for parallel make in fedora build system builds of glusterfs in the fedora build system often fail due to a race condition between running yacc and starting to compile the y.tab.c produced by yacc This patch changes the automake Makefile.am to generate the parser files without incurring the race condition This works on jenkins, the fedora build system, and my f16 vm/guest machines. (Finding the right combination that works on all three was an exercise to say the least. I'm open to other suggestions for avoiding the race condition.) Run autogen.sh to (re)generate the Makefile.ins. Then run configure to produce all Makefiles, followed by `make -j X` where X>1 see also https://bugzilla.redhat.com/show_bug.cgi?id=756510 BUG: 3826 Change-Id: I06ba0d0a1d59f0f44c0dd2cd9d227ca08d99e205 Reviewed-on: http://review.gluster.com/763 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 1b3571d38fc789100e2c053750eca1109494596b Author: Jeff Darcy Date: Mon Nov 21 12:35:34 2011 -0500 Add command-line support (but no doc) for enforce-quorum option. Change-Id: Ia52ddb551e24c27969f7f5fa0f94c1044789731f BUG: 3823 Reviewed-on: http://review.gluster.com/743 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f52dd9bf2005449f49acd5666a02594fb4c5ac6f Author: Pranith Kumar K Date: Sun Nov 20 09:13:14 2011 +0530 cluster/afr: Update read-child if it becomes stale Change-Id: I00c714a89575023f6dbdd3430dcbf191e5d08019 BUG: 3650 Reviewed-on: http://review.gluster.com/740 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7ae082e9c519ea91540c4d49f9df44c4e6e9f39a Author: Raghavendra G Date: Tue Nov 15 12:14:56 2011 +0530 rpc-transport/rdma: add gf_ prefix to all procedure, variable names Change-Id: I251be23d2c60b88589f71e7a8c3b1f2b7e3eb3e6 BUG: 3319 Reviewed-on: http://review.gluster.com/148 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit f4297a0eec29b7eba2f1ddfde0d273d5f6660723 Author: Emmanuel Dreyfus Date: Fri Aug 12 16:29:28 2011 +0200 NetBSD build tweak to use linkat(2) linkat()é is guarded by -D_INCOMPLETE_XOPEN_C063 for now since support for OpenGroup extended API set 2 is not yet complete. Change-Id: If1038dac61b6945c73a208c6e05f1154ff913098 BUG: 2923 Reviewed-on: http://review.gluster.com/232 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 26fd1cecc985d3cd4d84c7fa061b371757c34a6e Author: Emmanuel Dreyfus Date: Thu Nov 24 09:15:29 2011 +0100 case to uint64_t when convering gfid to inode, otherwise it can get garbled on 32 bit machines. Change-Id: Id2acc1f9ae98194d541f5468616be441896c4239 BUG: 2923 Reviewed-on: http://review.gluster.com/753 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit ad2d5765d955899f56fec5c05ba9e0e55ccac395 Author: Emmanuel Dreyfus Date: Fri Aug 12 16:23:23 2011 +0200 Let NetBSD use its recently added Linux xattr API Change-Id: Ibd365e8d83c6faf631df7cb99ec62440496fcbdf BUG: 2923 Reviewed-on: http://review.gluster.com/230 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 86ed5d68596e577b4d923750a619a6921f2cfe18 Author: Jeff Darcy Date: Mon Oct 3 13:56:23 2011 -0400 Add volfile-generation hook facility. Change-Id: I958c393ce5cfffcde8d120499a43dbe6105a082c BUG: 3688 Reviewed-on: http://review.gluster.com/558 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 3f1092c1a79adefd4400bfb6fd20029a22b0f827 Author: Emmanuel Dreyfus Date: Sun Oct 16 08:06:18 2011 +0200 We must #include for sigprocmask(2). Failure to do so will break on NetBSD kernel without COMPAT_13 option. Change-Id: Ia710bbe31ed48e4df4cd47f99e335d7226b99173 BUG: 2923 Reviewed-on: http://review.gluster.com/594 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 79c379c70ced3fd8a487cf007ba6c82b0773fb9a Author: Emmanuel Dreyfus Date: Sun Oct 16 08:09:11 2011 +0200 usleep(3) shall not be called with argument higher than 1s Change-Id: Ied0a2fedb3b7604f6abbf0a4aa7f71e43a5ea568 BUG: 2923 Reviewed-on: http://review.gluster.com/595 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Anand Avati commit 8b8459b5ee5d3bd2dbbf416e12a1be0cd90c270f Author: Emmanuel Dreyfus Date: Thu Nov 24 06:32:36 2011 +0100 Use /bin/mount on Linux, /sbin/mount on other systems Change-Id: I8d2e518d29cedb1fbfa77d0189a2d4a24957e662 BUG: 2923 Reviewed-on: http://review.gluster.com/752 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit b21d430729c45990492703145c075940e6b1c681 Author: Krishnan Parthasarathi Date: Thu Nov 10 11:09:56 2011 +0530 afr: Fixed backgroundness detection in self-heal algo. Change-Id: I9888d8a0b86fdaf6589885766f2de7222d8c8ba2 BUG: 3802 Reviewed-on: http://review.gluster.com/705 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri Reviewed-on: http://review.gluster.com/745 Reviewed-by: Anand Avati commit 3b2febc1c4b1b0f8d473e4e2503ffdff54236c9b Author: Niels de Vos Date: Sun Nov 13 17:45:54 2011 +0000 rpc-transport: fix some indentions Some lines are indented with spaces, others with tabs. When Tabs are not disaplayd as 8 spaces, the indention is completely messed-up. Change-Id: I31ddf44c5b7f5fe1c5493adca98e95514f2920bd BUG: 3822 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.com/742 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 41e99d3686f3a63b4c6afa9addc93472971e9570 Author: Harshavardhana Date: Tue Nov 15 13:49:18 2011 -0800 rpm: rpmbuild fix for opensuse Change-Id: I4ccf75288aad6d5f210bd7c51c0ce9924bb0efad BUG: 2925 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/729 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 5aed416a5f61b18a7eb105fde0752d1f66c37a88 Author: Sachidananda Urs Date: Wed Nov 23 00:02:33 2011 +0530 Change the start/stop order of glusterd script at boot time. In cases of client and server sharing the same machine, mounting GlusterFS at boot time failed due to the start and stop order we use for glusterd. And people had to resort to the idea of adding mount command in rc.local. Currently the start and stop order at the boot time were 90 and 12, and netfs started before `glusterd' and failed to mount GlusterFS. By changing the rc order to 20 80 glusterd is started earlier than netfs, thus enabling netfs to mount GlusterFS during boot process. Thanks to: alex@net13.info for the suggestion in bug 2484. Change-Id: I482f4dac5e5dd8bc5b8f5034c394f5dbe6c1fd3e BUG: 2484 Reviewed-on: http://review.gluster.com/746 Tested-by: Gluster Build System Reviewed-by: Harshavardhana Tested-by: Harshavardhana Reviewed-by: Kaleb KEITHLEY Reviewed-by: Anand Avati commit 9ac21b5a3e1b0d4afba1afb04ec62ce75e302a5e Author: Pranith Kumar K Date: Wed Oct 26 12:30:29 2011 +0530 cluster/afr: Remove treating sh_frame as special loop_frame Change-Id: I0d87f06f989b2d4b971967c52d4898331693a801 BUG: 3675 Reviewed-on: http://review.gluster.com/735 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0413d46873d082bbd3ee41aced3db01e444422d9 Author: Anand Avati Date: Wed Nov 23 18:10:51 2011 +0530 gerrit: auto-rebase test Change-Id: I4bd0c2ad1ef5880e2de94d3bcc17158f18e114ab BUG: 3234 Reviewed-on: http://review.gluster.com/750 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 74a2eebd9ed68fe5d8785af47c4dede9051e2ae4 Author: Vijay Bellur Date: Wed Nov 23 17:49:59 2011 +0530 Whitespace cleanup Change-Id: Ifd560492f93b1a35b36bb663c62b3c427e066caa BUG: 3158 Reviewed-on: http://review.gluster.com/749 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 7a91ea707ca0f0fec8c63f97eedec04c6a16c50e Author: Vijay Bellur Date: Wed Nov 23 17:49:59 2011 +0530 Whitespace cleanup Change-Id: I6126e22694c177d3e2b0b4e98551a9038d5cdacd BUG: 3158 Reviewed-on: http://review.gluster.com/748 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 3cf35466424046e85dff9f4de2cd6a1c0f9d781b Author: Pranith Kumar K Date: Mon Nov 14 10:10:27 2011 +0530 cluster/afr: Open fd fix should perform opendir for dirs Change-Id: Iee12828ca515d44ed71d9cf97dcb8627c85f0593 BUG: 3740 Reviewed-on: http://review.gluster.com/725 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 896fc241850aaa021f6f8958da4e37e37679c0cd Author: Harshavardhana Date: Tue Nov 15 13:44:43 2011 -0800 cluster/distribute: Add support for 'min-free-inodes' on each distribute subvolume. This change is required as increasingly large number of small files would cause inodes to run out before they run out on available disk space. It is highly necessary to support algorithmic checking of inodes too just as we do for disk space. Change-Id: I9b87405328d443825e239ee80ab664aceb50ee68 BUG: 3799 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/730 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit af7d85074fc05afdee3ff48f62b0ec5c057a3e6b Author: Amar Tumballi Date: Fri Nov 18 17:53:53 2011 +0530 cli: remove reference to 'RAID01' for stripe-replicate volume Change-Id: I3a9b3059fd9b918cb32bbe724ae1125fb1f5642a BUG: 3158 Reviewed-on: http://review.gluster.com/738 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 89a6dc3c2b31299ac10de449d318ecf341e8b840 Author: Niels de Vos Date: Sat Nov 12 17:58:44 2011 -0500 cli-cmd: call cli_cmd_unlock in the same function as cli_cmd_lock cli_cmd_submit calls cli_cmd_lock, but cli_cmd_unlock is done in cli_cmd_await_response. It is clearer to do the locking and unlocking in the same function. Only cli_cmd_submit seems to call cli_cmd_await_response, therefore moving the cli_cmd_unlock to cli_cmd_submit should be safe. Change-Id: I015ae0e2a404005c43606ef5258e3cfad41a88d4 BUG: 3821 Signed-off-by: Niels de Vos Reviewed-on: http://review.gluster.com/721 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 829f2b90fba8f66287e2e3b89aed9c971c2d828b Author: Pranith Kumar K Date: Sun Nov 13 11:56:46 2011 +0530 cluster/afr: Fix memory leaks Change-Id: I79a1c70c47649fbcf236191f174d766d5806545c BUG: 3805 Reviewed-on: http://review.gluster.com/719 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c9fbd4c309552f7f845e73c92315abe3b6d7081b Author: Pranith Kumar K Date: Wed Nov 2 13:09:41 2011 +0530 cluster/dht: set gfid in lookup loc Change-Id: I59599cc88be1d973c955600fdd54e6c49c77b4a2 BUG: 3770 Reviewed-on: http://review.gluster.com/681 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 119289fa51cd6e6ceb149dd3a9596478a85adff4 Author: Pranith Kumar K Date: Sat Nov 5 14:54:28 2011 +0530 cluster/afr: Handle absence of gfid in lookup Change-Id: I6295245a7f40ba4f786f1f9f35b337f3f711128d BUG: 3783 Reviewed-on: http://review.gluster.com/739 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 33477a140fb4e891a05dd9261013e83035155350 Author: Kaushal M Date: Wed Nov 2 11:27:30 2011 +0530 fuse: enable kernel read-only mode Enables kernel read-only mode on mounting with '-oro' and disables the gluster read-only translator from being loaded. As a result, '-oro' is reported correctly in the mount options. Change-Id: If94d97836b13668974cfac61b6e5d52e19880e10 BUG: 3742 Reviewed-on: http://review.gluster.com/655 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Csaba Henk commit e1de01c3fdde2497cc4a24491b75579624467456 Author: Csaba Henk Date: Wed Oct 5 11:47:14 2011 +0200 log to stderr if "-" is given as log-file This works around broken /dev/stderr on some systems. Change-Id: I017b03082ff630c4a713ae74990e88b3fa20d0e1 BUG: 3686 Reviewed-on: http://review.gluster.com/560 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 76d5e5d5b51eb2ffe5a0608bf8869650bb76585f Author: Jeff Darcy Date: Tue Sep 20 09:49:57 2011 -0400 Add quorum checks to avoid split-brain. Change-Id: I2f123ef93989862aa796903a45682981d5d7fc3c BUG: 3533 Reviewed-on: http://review.gluster.com/473 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e6a3902410aaa8756e9c07302d88399fb99641c7 Author: shishir gowda Date: Thu Nov 17 15:12:32 2011 +0530 mgmt/glusterd volume delete - Unref dict only in case of an error Change-Id: I6edee785c69864bf42d869ed9cccb52cabc1523d BUG: 3817 Reviewed-on: http://review.gluster.com/736 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 88ee850e68838df34d0a57307299e07dac7d9771 Author: Krishnan Parthasarathi Date: Tue Sep 27 18:16:12 2011 +0530 rpc: Need to update conn->last_recieved. This is important for protocol/client's ping_timer to function correctly. Change-Id: I9f45d701126bb739535d9c5ec280833362bef9ed BUG: 3816 Reviewed-on: http://review.gluster.com/512 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Jeff Darcy commit 9b391694eb53b73a5284bd5294ee66a690e7398d Author: Krishnan Parthasarathi Date: Mon Oct 31 18:05:23 2011 +0530 glusterd:replace-brick subcmds should detect src_brick offline. Change-Id: I686494c9c2d01fd027d333b267334842cb1dc875 BUG: 3043 Reviewed-on: http://review.gluster.com/651 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 1e652740f74298637577e9861cb5092091404d29 Author: Krishnan Parthasarathi Date: Mon Oct 31 15:54:52 2011 +0530 glusterd: Extended glusterd_is_service_running to get svcs's pid. Also, volume status cmd would print "N/A" if pid couldn't be retrieved from pidfile. Change-Id: Ie83d228b1cf86397d181885b325e337a403e6ed2 BUG: 3043 Reviewed-on: http://review.gluster.com/650 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit c5be0df9149155f9e23a8e9f24d0becb0543efe1 Author: Pranith Kumar K Date: Mon Nov 7 16:13:42 2011 +0530 cluster/afr: lookup should honor gfid present in loc Change-Id: I2319258743e478cc3a932d8ff0b2204a97cd4f8e BUG: 3760 Reviewed-on: http://review.gluster.com/680 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3bc27345bf3aaf911960793ef4d48909f585bd84 Author: Pranith Kumar K Date: Fri Nov 4 19:10:11 2011 +0530 dht,afr: Fixed gfid problems *) removed uuid_generate usage in pump and afr, self-heald *) filled the gfids for the fops which were sending no gfid in loc Change-Id: I85da3c10f5ee2006248b0123155a60867870d202 BUG: 3760 Reviewed-on: http://review.gluster.com/679 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7e085ebc9ca0d34e6251611fdc42dadc243ce276 Author: Krishnan Parthasarathi Date: Thu Nov 17 14:17:46 2011 +0530 glusterd: Fixed volume profile's "are all bricks down?" algo. "count" key is not set if no brick in the volume (located across peers) is running. Sending "count" even when zero bricks are running from originator glusterd to client, simplifies "are all bricks down?" algo. Change-Id: I2b1da13ed4b1b9276917908223c9b2c45ca024b3 BUG: 3553 Reviewed-on: http://review.gluster.com/642 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 5aadd0765ba4c21b5ef626f7f8ca8ccff530dd2f Author: Amar Tumballi Date: Mon Oct 31 12:23:21 2011 +0530 xlator: prevent a crash in xlator_destroy due to uninitialized list was happening when any of the dlopen() fails for xlator loading, and xlator_destroy() was called as it was using a uninitialized list for traversal. now, the list gets initialized at the begining of the xl-init(), so xlator_destroy() works smoothly. Change-Id: I320f6fe922e6d351e6d7c0a3e8da1f6b414d3c47 BUG: 3731 Reviewed-on: http://review.gluster.com/606 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Vijay Bellur commit 43a36decf24b126936bffda273c79e23f547004d Author: Harshavardhana Date: Tue Nov 15 18:58:59 2011 -0800 cluster/dht: Fix a typo Change-Id: I6bcdc7d600ebb9ef68c60319f96cd9e28d12c861 BUG: 3809 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/732 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit ebc497ddb9d362b9f6390b4a8176afe9f2b5def0 Author: Pranith Kumar K Date: Mon Nov 7 14:42:37 2011 +0530 libglusterfs: copy the stat structure in entry_copy Change-Id: I7a8bd3b3f9600ced4a945f07447698876933ade0 BUG: 3760 Reviewed-on: http://review.gluster.com/678 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit 51a78ad316975763d45c11affa571892e03643e8 Author: Harshavardhana Date: Tue Nov 15 14:44:24 2011 -0800 glusterfs: An effort to fix all the spell mistakes and typo in the entire glusterfs codebase. This patch fixes many of spell mistakes and typo in the entire glusterfs codebase and all supported modules. Change-Id: I83238a41aa08118df3cf4d1d605505dd3cda35a1 BUG: 3809 Signed-off-by: Harshavardhana Reviewed-on: http://review.gluster.com/731 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 8c182c6bf700cdc8a7e2d4b75109ad0acee2e70d Author: Amar Tumballi Date: Wed Sep 28 15:41:47 2011 +0530 core: remove 'ino' variable from 'loc_t' structure Change-Id: I53b007fbdb42313d207d5d63fbfaaa6aaf033f95 BUG: 3518 Reviewed-on: http://review.gluster.com/523 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 14f4e023822a22e0a4902acfd28c8f5ea8c94ccd Author: Amar Tumballi Date: Wed Nov 16 15:39:29 2011 +0530 core: remove 'ino' variable from 'inode_t' structure Change-Id: I0f078d1753db65d2f2e0380d1b0450c114cf40dd BUG: 3518 Reviewed-on: http://review.gluster.com/522 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 217842180858afff79d06c24389752299c5ed716 Author: Amar Tumballi Date: Wed Nov 16 12:25:28 2011 +0530 mgmt/glusterd: more cleanup * 'GD_OP_RENAME_VOLUME' removed * unused handler function for rebalance is removed. Change-Id: Id081cb02a6445c09347bacc0fdf9cd600ff94e5d BUG: 3158 Reviewed-on: http://review.gluster.com/734 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7e3faaf682bf8f35fea9e2b4d930cbb68dae213e Author: shishir gowda Date: Fri Nov 11 13:41:01 2011 +0530 cluster/distribute: Trigger selfheal only if rmdir succeeded once A EACCES error also should not trigger a selfheal. Only if rmdir succeeded on any subvol, a selfheal should be triggered Change-Id: Ifebb980f0ebd1548adfd3be975ca52ca44c3f3ab BUG: 3786 Reviewed-on: http://review.gluster.com/716 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit d4ff78d02d049335d827f9293a4e931261b5c2bb Author: Gaurav Date: Tue Oct 11 11:15:30 2011 +0530 NFS: logging enhancement. Change-Id: Ie1731a6b2b63e07bc49a84c2f9dd87c5b50a9f53 BUG: 3527 Reviewed-on: http://review.gluster.com/573 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f97897c394a7f3e9d5e870ba9814ff2ebfc4cc01 Author: shishir gowda Date: Mon Nov 14 15:53:27 2011 +0530 Cluster/stripe setattr: Wind only to first_child for special files Change-Id: Ib055578477461a24562d5da139809cf0965b931e BUG: 3807 Reviewed-on: http://review.gluster.com/724 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 3440b6d68a5e787a6a1baba2073ee0c44a9b1632 Author: shishir gowda Date: Thu Nov 10 16:39:31 2011 +0530 cluster/distribute: Use local call_cnt while winding layout->cnt might be modified in cbk's or different threads, which will lead to corruptions Change-Id: Icfdab01ac583cb3d27d62f878b79e0098b597952 BUG: 3730 Reviewed-on: http://review.gluster.com/694 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit a3c49bb260263dce98d44c28e7106da2a2173ed9 Author: Amar Tumballi Date: Mon Nov 14 15:57:49 2011 +0530 glusterd: remove some of the stale 'log ' functions Change-Id: Ibda7e9d7425ecea8c7c673b42bc9fd3489a3a042 BUG: 3158 Reviewed-on: http://review.gluster.com/726 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit deac165b27d09e762743b180044c33ce90bbeaef Author: Amar Tumballi Date: Sat Nov 12 22:02:37 2011 +0530 mgmt/glusterd: delete volume to have dictionary as context earlier only DELETE_VOLUME was having volume name as context, where as all other OPs used to have dictionary Change-Id: I5bfcc458bff3295374eb4f0b0a31f6134745debd BUG: 3158 Reviewed-on: http://review.gluster.com/718 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit a29ab15988f46fbe98151c37676185de970fb187 Author: Amar Tumballi Date: Sun Nov 13 00:18:32 2011 +0530 glusterd/cli: rpc cleanup no more backward compatibility between glusterd <-> glusterd Change-Id: Ibfcca1c7e315a90b2639c4cba8da19b11875051a BUG: 3158 Reviewed-on: http://review.gluster.com/610 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 7a97478dd1a343fcc5d9d4eab963882191a3de69 Author: shishir gowda Date: Wed Nov 2 18:38:50 2011 +0530 XDR: cli-glusterd xdr consolidation By using only 1 xdr struct for request and 1 xdr struct for response, we will be able scale better and also be able to parse the o/p better For request use- gf1_cli_req - contains dict For response use- gf1_cli_rsp - conains op_ret, op_errno, op_errstr, dict Change-Id: I94b034e1d8fa82dfd0cf96e7602d4039bc43fef3 BUG: 3720 Reviewed-on: http://review.gluster.com/662 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 913b21621e2dad9146366f24048ff07a8046e5c5 Author: Jeff Darcy Date: Fri Nov 4 21:46:08 2011 -0400 Reflect quota-adjusted values in statfs. Change-Id: I7a2a0b1ad0aa2a972aad9712658083c61052bef2 BUG: 3813 Reviewed-on: http://review.gluster.com/675 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid commit be406a1845e84a659ca5c5834b19c094e88cbaaf Author: Junaid Date: Fri Nov 11 17:05:43 2011 +0530 features/marker-quota: Use stack_wind_cookie in place of stack_wind to preserve the cookie value. In marker_rename, some of the call back functions make use of cookies sent by the calling functions. In case of stack_wind the frame->cookie is over written with the address of new frame. Change-Id: I8ec98f3305700e2c3295a10dff159ca6a19a380a BUG: 3808 Reviewed-on: http://review.gluster.com/722 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 01de95f41429967fffaa0e9de4badb101839c3ea Author: Pranith Kumar K Date: Mon Nov 7 14:09:36 2011 +0530 storage/posix: assign ino as -1 if gfid is missing Change-Id: I422c87f977b5da083f9fcfaf20f0ca9a872da0a4 BUG: 3767 Reviewed-on: http://review.gluster.com/677 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit a1fd4c9916cc56c10f83b2a1aa7ecee4d563f82a Author: shishir gowda Date: Wed Nov 9 14:20:10 2011 +0530 cluster/distribute lookup: send revalidate calls to all subvols for directories If mkdir fails on a subvolume, layout is set taking into account only the subvols where it was successful. stat does not trigger selfheal, as its layout based. Revalidate on directories needs to be sent to all subvols, to fix the error, and not just on the layout. Change-Id: If17055508ffcf268806258ed49e7d7500a89d0f2 BUG: 3793 Reviewed-on: http://review.gluster.com/693 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 62088ee6a8d2413c828409dec09e31d600987110 Author: Raghavendra G Date: Wed Nov 9 14:40:02 2011 +0530 rpc-transport/rdma: send correct vector count when both rpc-header and program-header are received through rdma-reads. Change-Id: I1b0b91eb7216f32a5748325d6dda37f3998302c7 BUG: 3754 Reviewed-on: http://review.gluster.com/697 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 5e14417b478520620bb5990eda41e3ad3e9af09c Author: Sachidananda Urs Date: Sat Oct 29 14:20:02 2011 +0530 Move some of the messages to log level `TRACE'. Change-Id: I46133b5e2218b9d810251b3dadadd8f157ab07d7 BUG: 3761 Reviewed-on: http://review.gluster.com/643 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 78f3ee4fb1687db948ad5d07d1ed9e6177cc54bc Author: Raghavendra Bhat Date: Mon Oct 17 11:04:35 2011 +0530 rdd: create the file and do rdd if the file does not exist. rdd takes input file and copies the its data to the specified output file ( by creating it) by selecting random offset. If the input file does not exist it will not work. This patch will create the input file if it does not exist and then does the copy. File size is given as an argument. If the file exists it truncates the file and then does the copy. Change-Id: Ia09451e9e80e13f27320f1edc12c73c0dcf663a9 BUG: 3724 Reviewed-on: http://review.gluster.com/596 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 34795adcc93497d97f1cd258102f4fa4b540464b Author: krishna Date: Thu Sep 29 17:44:55 2011 +0530 Fix memleaks in NFS Change-Id: I522d4bad71d1e914fa88367f70f5e8c28d64fbbe BUG: 3542 Reviewed-on: http://review.gluster.com/533 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Shehjar Tikoo commit bb67817cf582678685ce1207f2a1d41fb4c3649b Author: Rajesh Amaravathi Date: Wed Nov 2 15:26:53 2011 +0530 debug/io-stats: prevent setfattr crash when no value given Check for whether the dump file is given, and proceed on success. If dump file is not given, unwind with ENOENT. Change-Id: If524a2b20d643e0e75d81daebe59560a78000524 BUG: 3716 Reviewed-on: http://review.gluster.com/663 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit cb9ffbe767b8e5edb30bee95e33ebe9945101250 Author: Rajesh Date: Wed Aug 24 12:47:24 2011 +0530 mount/fuse: check for recursive mounts Adding check_recursive_mount() in mount.glusterfs.in to check if mount point is in the lineage of any brick path. Gracefully fails if mount point leads to recursive mount. Change-Id: Iedc4cd767d241c8e256181e472c0815f3831a316 BUG: 2003 Reviewed-on: http://review.gluster.com/314 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 359eee148b2be5aaf9677f61f98b89a50d0f1b88 Author: Harshavardhana Date: Tue Nov 8 16:58:44 2011 -0800 fusermount: Build problem fixed with new glibc Change-Id: Id25e688d3dbecb74d820388faec5ee5041f21630 BUG: 3797 Reviewed-on: http://review.gluster.com/714 Reviewed-by: Anand Avati Tested-by: Gluster Build System commit fc9fbbc35efaa84e68e108895ad64b062feed280 Author: shishir gowda Date: Thu Nov 3 14:47:01 2011 +0530 stripe readv_cbk: Fix stat return values Workaround - If the read request, does not fall to the subvolume with the largest file size set, then we never return the correct size. This leads to clients seeing a truncated file error. The work around is to wipe stat being returned as part of read call. Problem - We were passing the stbuf returned by the first child/index, which can be different to the size/blocks returned by stat. This led to applications viewing the file as being truncated. The stbuf size needs to be the largest of all results, and blocks the aggregation from all subvolumes. (similar to stat) BUG: 3774 Change-Id: I46c53c18b2b42b1f5b86b05555bbab73bf993476 Reviewed-on: http://review.gluster.com/666 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 3200a2be434c462b43bf3ffe0343ddc8900c5d88 Author: Kaushal M Date: Mon Oct 31 10:02:16 2011 +0530 cli : Modify "top read-perf/write-perf" output Improves alignment and width of columns in the output of "top read-perf/write-perf". Change-Id: I9a4ec3a121f40e099c96952e2388b27ed90b6fe6 BUG: 3719 Reviewed-on: http://review.gluster.com/645 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 32173e1c70dcb53470b0738ed4d0022388193113 Author: Kaushal M Date: Thu Oct 20 10:53:58 2011 +0530 cluster/afr : Fix self-heal of special files Fixes self-heal of special files like device files, fifo files, socket files etc. Does it by doing the following: * Prevent setting of pending data xattr on a special file during entry self-heal when a new fils is created. * Allow data self-heal to be started on all file types other than directories. During data self-heal, for special files just erase pending xattrs, if those xattrs were set by previous releases of glusterfs. Change-Id: I34d8121e23ad00e85371ae2a36ef30cf3bd5db7a BUG: 3525 Reviewed-on: http://review.gluster.com/618 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit a29f1a0e36bde5ca7b8f3762f10b210b5e12a875 Author: Venky Shankar Date: Wed Oct 5 16:56:30 2011 +0530 fuse: flip xattr key from user to trusted namespace for certain clients. This is needed for gsyncd/hadoop-plugin running as non-super user to be able to request extended attributes under trusted namespace. Request for a key is made under 'user.' namespace and is flipped by fuse xlator for specific xattr name to the corresponding 'trusted.' extended attribute. Both applications set a identifier (client-pid) while doing a FUSE mount, which is checked by get/set/remove interfaces in FUSE translator. Change-Id: I72f77a5dd1ee1d69c8b0e09209449348dbcf879a BUG: 3701 Reviewed-on: http://review.gluster.com/563 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit af708e9fc2eb2104b9e8e3b5a3eaf99201664324 Author: Pranith Kumar K Date: Tue Oct 25 11:45:10 2011 +0530 cluster/afr: Remove unused 'ino' code Change-Id: I425e2d23e9e45f10ddeff2eacf918dd90f8baee7 BUG: 3744 Reviewed-on: http://review.gluster.com/639 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c770722983f73aa838b5985755999050c746550a Author: Amar Tumballi Date: Tue Oct 11 16:33:24 2011 +0530 changing of the volume types after volume is created. with this patch, one can do all the below operations: on a simple distribute volume 'test' with bricks A,B, add bricks C and D: bash# gluster volume add-brick test replica 2 C D now the volume 'test' becomes distribute-replicate, with pairs A-C, B-D. same holds good for stripe. and now, one can change the replica count 2 on volume 'test' to 4 like below: bash# gluster volume add-brick test replica 4 E F G H now, volume has 'replica' count 4, with pairs being 'A-C-E-F' and 'B-D-G-H'. after this, if user wants to reduce the replica count, he can do bash# gluster volume remove-brick test replica 3 C H # (one from each pair) This should work to reduce the replica count Change-Id: I4f109141a9ba7be4a92a5f5810a4163baeb92973 BUG: 3305 Reviewed-on: http://review.gluster.com/158 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit fb653259265cbef00117e89451689dcea6c356b5 Author: Junaid Date: Mon Oct 17 12:38:14 2011 +0530 features/marker-quota: Donot log when inode or inode-ctx is NULL. When running rm -rf from mount point, quota-updation process may endup in a state where the inode is already removed from the gluster inode table, but the updation has process is still in progress. This is not a error condition because the updation is done asynchronously. Change-Id: I739bff466d23f55f842c16dd4fa2808df188ddf8 BUG: 3609 Reviewed-on: http://review.gluster.com/597 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit dbf7aa864d8f0515fe4d742fc520a4d1134dbbd4 Author: Rajesh Amaravathi Date: Tue Oct 11 16:09:52 2011 +0530 io-stats: improve io-stats dump output * Cumulative statistics' output has been formatted to match #gluster volume profile info * Fop count, latency measurements have been tabulated for better readability. * Minor formatting of individual fop call counts and throughput info dumps. Change-Id: I0fa524f773018be2f73077d107e34170d19fc420 BUG: 3544 Reviewed-on: http://review.gluster.com/581 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 1252cc90da6156945c3636c1a2b5f702bc14fb2d Author: Kaushal M Date: Fri Oct 14 10:33:18 2011 +0530 glusterd: fix '.cmd_log_history'file handle leak on SIGHUP Closes the .cmd_log_history file and reopens it to prevent leakage of file handles. Change-Id: I1c846ccf9a0c1c90c9209f26a1c5332d3dd94ffd BUG: 3678 Reviewed-on: http://review.gluster.com/584 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 1e6780efd7320250a213eca25ee85bbf217825c4 Author: Rajesh Amaravathi Date: Fri Sep 30 18:05:38 2011 +0530 glusterd: allow non-related directories with same prefix Earlier, using two directories with names like /test and /test1 failed volume creation. This patch sees that the next character is checked to be '/' to conclude that they are recursive. Eg: /test and /test2 succeed, while /test and /test/alpha does not. BUG: 3645 Change-Id: Idc90211a7a572200ed983c87c4344271f53b0132 Reviewed-on: http://review.gluster.com/544 Tested-by: Gluster Build System Reviewed-by: Jeff Darcy Reviewed-by: Amar Tumballi commit 90d820d193c06efdae0a7e513faaadffb2bfdafd Author: Anand Avati Date: Sat Oct 22 09:48:17 2011 +0530 locks: perform inode_ref of pl_update_refkeeper outside locked region Performing inode_ref inside the critical section of pl_update_refkeeper (around pl_inode_t->mutex) causes a deadlock with inode_table_t->lock. The other thread (process state dump) holds the inode_table_t->lock first to loop over inodes and then while dumping an inode's lock context, tries to acquire pl_inode_t->mutex thereby completing the deadlock. The fix is to perform inode_ref outside the critical section in pl_update_refkeeper Change-Id: I689ab4a9b46b36287740279fdec6159182c86119 BUG: 3753 Reviewed-on: http://review.gluster.com/628 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit ea4cd6ff18bb811b053b8fc6bcef7d6377dac30b Author: Pranith Kumar K Date: Mon Oct 24 08:27:40 2011 +0530 pump: Change crawl to accommodate afr_lookup changes Change-Id: I600120252445c06d9cc3e7aa24022c2559b6abe2 BUG: 3747 Reviewed-on: http://review.gluster.com/638 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2712393ba21dbfdc7b3443ed019d35ab60628b2a Author: Pranith Kumar K Date: Fri Oct 21 14:45:08 2011 +0530 cluster/afr: Take gfid-req from xattr_req only if inode->gfid is null Change-Id: Iddf5b59d3534c517dcd3c0d7b819e3768f6e915a BUG: 3747 Reviewed-on: http://review.gluster.com/637 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ae78820311fc95047195735b1519fa4d626de208 Author: Pranith Kumar K Date: Sat Oct 22 11:32:40 2011 +0530 mount/fuse: set gfid in lookup after a failed revalidate lookup Change-Id: I1904aa63d9365ebda3e979449454ac08db85d93d BUG: 3747 Reviewed-on: http://review.gluster.com/636 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b3d696f78b16f246bd34f87aafb52317033408cc Author: shishir gowda Date: Fri Oct 21 12:17:04 2011 +0530 Stripe mknod: Always call mknod if REGULAR file on first child. This prevents a possible race between mknod(REGULUAR files) and remove. mknod first creates on the first_child, and only if successful, on other subvolumes. Change-Id: I0ddaeb92c1884c771c966bb151db052ab5735367 BUG: 3727 Reviewed-on: http://review.gluster.com/608 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit bdf20a205a4d67d5f6d3ac6010a34291c2822a80 Author: Venky Shankar Date: Wed Sep 28 16:38:00 2011 +0530 cli: add geo-replication log-rotate command Rotating geo-replication master/monitor log files from cli. On invocation, the log file for a given master-slave session is backed up with the current timestamp suffixed to the file name and signal is sent to gsyncd to start logging to a new log file. Sample commands: * Rotate log file for this : session: gluster volume geo-replication log-rotate * Rotate log files for all session for master volume gluster volume geo-replication log-rotate * Rotate log files for all sessions: gluster volume geo-replication log-rotate Change-Id: I75f641b4e082a04d5373c18583ca4a1d9651d27a BUG: 3519 Reviewed-on: http://review.gluster.com/529 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit 84ebee8c20ce667a5ec5fddc0aa47f8b5bef39f8 Author: Amar Tumballi Date: Tue Oct 18 10:30:42 2011 +0530 build: warning suppression (round n) with this patch, there are no more warnings with gcc (GCC) 4.6.1 20110908 Change-Id: Ice0d52d304b9846395f8a4a191c98eb53125f792 BUG: 2550 Reviewed-on: http://review.gluster.com/607 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 26a51e5e6ec1639a7601c0fc373fd9f6493b014a Author: Amar Tumballi Date: Sun Oct 2 11:34:41 2011 +0530 libglusterfs/syncop: fix minor memory leaks * most of the leaks can happen in syncop_lookup(), if rsp_dict is not provided by user Change-Id: I5a887c45f1a46a91502147e44f7ed9d41f50dbc6 BUG: 3715 Reviewed-on: http://review.gluster.com/550 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 429550b75d2b97f24a102cc648bf9d8240965f93 Author: Amar Tumballi Date: Thu Oct 13 12:59:41 2011 +0530 distribute: handle migration of symlink and special files TODO: currently, wrt. rebalance/decommissioning, only pending thing is hardlink migration. Change-Id: I30cd06802e84c95601a5a081198f1f09c6d6bc01 BUG: 3714 Reviewed-on: http://review.gluster.com/578 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Vijay Bellur commit 54b44736b1558cd7e3adf75a8ecfe1a5c236dc20 Author: Kaushal M Date: Wed Oct 19 13:44:32 2011 +0530 Remove EXCEPTIONS file. Change-Id: I79fe05102a954ee1c831ceca229f6dbc1997113d BUG: 3737 Reviewed-on: http://review.gluster.com/617 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e1fda0971decffeddbaa0a4491270d991d83359c Author: Krishnan Parthasarathi Date: Thu Oct 13 17:52:44 2011 +0530 pump: status shouldn't be cleared until migration is complete during commit. Clearing pump status on migration complete is futile because we would be 'replacing' src brick with destination brick in the volume anyway. Change-Id: Ib12fee84bd5445c4a20dac1cf10555331d7b8ebd BUG: 3653 Reviewed-on: http://review.gluster.com/585 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c59dd30a13993b1988132de168f4f152757ff420 Author: Pete Zaitcev Date: Tue Aug 16 14:42:49 2011 -0600 Print microseconds as a fraction. Change-Id: I35cdf2c771974b9c51db47f24cd044ae014e52ce BUG: 3426 Reviewed-on: http://review.gluster.com/244 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit fed29e0ae382ef24f4d3dff3623daefc57dab6ce Author: Pranith Kumar K Date: Fri Oct 14 18:28:27 2011 +0530 cluster/afr: Prevent truncation of mask uint64_t->gf_boolean_t Change-Id: If67f726f21b713fa9312dc499a1aca4cb00f71de BUG: 3682 Reviewed-on: http://review.gluster.com/589 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3edfb0c492d73b349d83f904c42e6edfb9678965 Author: Krishnan Parthasarathi Date: Mon Oct 10 18:44:41 2011 +0530 glusterd: Removing delayed moving of op sm for stop vol/remove brick op. Earlier we waited for brick disconnect or 5s whichever is smaller, before we move op sm from brick op stage to commit stage. This involves a race where both the above mentioned events can happen 'concurrently' and result in double free. Change-Id: I8b1524afded84c20d55e29cfe2579ca872d2ac26 BUG: 3700 Reviewed-on: http://review.gluster.com/575 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 513cd0d12e3b72e9a3714deeee251414e651213f Author: Amar Tumballi Date: Sun Oct 2 13:20:25 2011 +0530 glusterd: take off 'auto-commit' behavior of decommissioning currently if 'remove-brick start' is given, after all the data is migrated, in the _cbk() function from rebalance complete we used to re-write the volume file without the bricks. But the flaw of this method is that, currently the _cbk() function is called on only the node on which rebalance actually happens, hence other nodes are not aware of this behavior. So, had to remove the 'auto-commit', instead we want the user to issue a command 'remove-brick commit' (or 'force') explicitely to remove the bricks Change-Id: Ifdac1292095029429da502aa6e4c0cf4ee124990 BUG: 1952 Reviewed-on: http://review.gluster.com/551 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Vijay Bellur commit 18071a240bd4c0d92f583632a7cdef1cd32bbe62 Author: Amar Tumballi Date: Mon Oct 3 15:41:04 2011 +0530 libglusterfs/iobuf: increase the iobref's iobuf array size earlier it was hardcoded to 8, now increased the size to 16. also return the exact error code in client_submit_vec_request(), so there will be no missing frames in case of errors. Change-Id: I82a6ee681a543b673a7cf1a0b9c5ade2a7175ebe BUG: 3679 Reviewed-on: http://review.gluster.com/555 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 33ac0c6b48ccbaf357644710c804e55bdfdb12da Author: Vijay Bellur Date: Fri Oct 7 12:29:29 2011 +0530 smoke.sh: Avoid running extended attribute tests with dbench Change-Id: I6d58e387e2bf9d5616ec3950abdb0680801523db BUG: 3234 Reviewed-on: http://review.gluster.com/564 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat commit 3e7d8614cdb4bd77d31b7e10cdd56ab212291568 Author: Sachidananda Urs Date: Thu Oct 6 23:34:50 2011 +0530 Fix a typo in log message. Change-Id: I5c2b170977f21c9a83d36f60d9a145c6cc221358 BUG: 2346 Reviewed-on: http://review.gluster.com/562 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ea3df58fd3fffcfe6f6e703ff3358a6cf1bc0619 Author: Junaid Date: Fri Sep 30 15:41:33 2011 +0530 cluster/dht: Handle 'user.ufo-test' sent by ufo in dht setxattr. In this case, send setxattr to all the bricks to test user xattr support and return error if setxattr fails on even one of the bricks. Change-Id: I9a9b27312a650d25bbc1f57e1ab8899d63d0593d BUG: 3185 Reviewed-on: http://review.gluster.com/542 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f8959749d26de4b13774e04ba4d01d799dc1c725 Author: Junaid Date: Fri Sep 30 12:15:17 2011 +0530 features/marker-quota: Return error when inode-contribution is not present in inode_ctx. Also, create the inode_contribution node even before checking for dirty and xattr not present in mq_inspect_directory_xattr function. Change-Id: Ie5b6e6ba8d5abcfc6aeb9b192720ac10aac1319e BUG: 3624 Reviewed-on: http://review.gluster.com/539 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 78dd69c4c732d3d74070118f0b6b708264d8fc0c Author: Krishnan Parthasarathi Date: Fri Sep 30 17:40:26 2011 +0530 locks: Avoid printing blocked times for locks that were never blocked. Change-Id: Ieedbfbe3ce2d4a87a8fe0e1a4322a1bb0549a2bf BUG: 3662 Reviewed-on: http://review.gluster.com/545 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 9d062a1359994e4c035a413fc9c5aec28fa5e7ae Author: Krishnan Parthasarathi Date: Thu Oct 6 10:33:52 2011 +0530 glusterd: pending_node type missed in profile volume op. Change-Id: Ib3c73a8432fdd2559422577a2f0c91d50b5a098c BUG: 3704 Reviewed-on: http://review.gluster.com/561 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1b2164ec8cfea7ab99fc4a0cb86fa3d41e4fb7e5 Author: shishir gowda Date: Mon Oct 3 17:21:19 2011 +0530 Stripe: Prevent dir gfid mismatch and ENOTEMPTY errors gfid mismatch issue- rmdir- first remove from non first child (FC), and then last from FC. If one fails, FC entry is not removed and op is failed. mkdir- first create dir from FC, followed by other childs. If FC is success then, we succeed, banking on entry self heal ENOTEMPTY issue- unlink: remove from non FC and then on success remove from FC. If non FC remove fails, fail unlink create- Create first on FC, and on success create on non FC. Change-Id: Ia8b9e92cd2aba891d249d1995e383fea0581ffca BUG: 3663 Reviewed-on: http://review.gluster.com/557 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit e397772955f10f22fcb920f34a32efd859fb727d Author: Krishnan Parthasarathi Date: Mon Oct 3 15:25:12 2011 +0530 glusterd: Handle restoring of volumes created in older versions. Change-Id: Idd9cb9d05122750ac78410b8f5a080104d6c1e0a BUG: 3685 Reviewed-on: http://review.gluster.com/554 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 72f80b87c40a899a5c6f838d368a80e6f9846f69 Author: Krishnan Parthasarathi Date: Mon Oct 3 14:53:04 2011 +0530 glusterd: Shouldn't inject COMMIT_ACC event before receiving ACC from all peers. Change-Id: I88b9935f93d9a06e46c3351c2fd37c969396bb0a BUG: 3683 Reviewed-on: http://review.gluster.com/553 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4235f7a74e0c4c637f1db2f49624a972d72b12fb Author: Raghavendra Bhat Date: Mon Oct 3 16:01:25 2011 +0530 cluster/afr: set the read child ctx only if the self-heal source is valid Change-Id: Ifdf0db71594ce526ad85c21103726798d9aceef4 BUG: 3639 Reviewed-on: http://review.gluster.com/556 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b6eee04da4a699c7cd850bf2121825cc67f14707 Author: Amar Tumballi Date: Sun Oct 2 08:46:46 2011 +0530 core: made changes to return value of __is_root_gfid() now returns 'true(1)' is gfid is root, 'false(0)' if not. earlier it was the inverse, which was bit confusing Change-Id: Id103f444ace048cbb0fccdc72c6646da06631584 BUG: 3518 Reviewed-on: http://review.gluster.com/549 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0db88567b916dc0dbfb0dfe2ed8a47f8d50fb317 Author: Raghavendra Bhat Date: Sat Oct 1 19:20:28 2011 +0530 libglusterfs/syncop: do not rely on synctask set in makecontext Across glibc implementations, interpretation of argc/argv passed to makecontext() is different. This patch does away with dependence on such arguments passed to makecontext(). Instead,synctask reference is retrieved from pthread_getspecific(). Change-Id: Ie01feaa0b7d430f8782c2f6805ccdf8026e401f4 BUG: 3636 Reviewed-on: http://review.gluster.com/547 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 9ef8eabae21a3073f3dc09602d0680d631cbd576 Author: Raghavendra Bhat Date: Thu Sep 29 12:11:44 2011 +0530 statedump: do not print the inode number in the statedump Since gfid is used to uniquely identify a inode, in the statedump printing inode number is not necessary. Its suffecient if the gfid of the inode is printed. And do not print the the inodelks, entrylks and posixlks if the lock count is 0. Change-Id: Idac115fbce3a5684a0f02f8f5f20b194df8fb27f BUG: 3476 Reviewed-on: http://review.gluster.com/530 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 161ab1b9664abf3561902c94b8748e9a95d4867c Author: Kaushal M Date: Mon Sep 26 10:24:46 2011 +0530 glusterd: cleanup unneeded volumes after peer detach Performs cleanup on the detached peer and in the cluster after a peer detach, and also adds a new check before starting detach. Cleanup - On the detached peer, cleanup removes the entries of those volumes on the peer that do not have all their bricks on it. This prevents these stale volumes from being added to a new cluster when peer is attached to one. In the cluster, all those volumes which have all their bricks on the detached peer are removed. Checks- Checks if all the peers in the cluster are online and connected, except the peer being detached, before starting detach. Using force will bypass this check and do detach. Change-Id: I4fef9ea3cc72ce8c4ce0a82b4ee8a1663a502061 BUG: 1926 Reviewed-on: http://review.gluster.com/431 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit acea7409a35d03c438ff2738f701add26f0061c9 Author: Kaushal M Date: Wed Sep 14 18:29:18 2011 +0530 glusterd, cli: adds 'force' for 'peer detach' Adds add a 'force' option to 'peer detach' to forcefully detach a peer from a cluster, even when the cluster contains volumes with bricks on the peer. Change-Id: I134df51c16a07345c8869b318141d427b572eba5 BUG: 3549 Reviewed-on: http://review.gluster.com/429 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 795c8996c18f5e8ef5986581644374d0c5068772 Author: Amar Tumballi Date: Fri Sep 30 12:53:16 2011 +0530 distribute rebalance: preserve proper mode in destination * don't set 'sticky' and 'sgid' bits to 0 without checking if the source had those bits prior to rebalance. Change-Id: Ia826cb3cfb55312cdbf00d3421f2bd06b3103ce6 BUG: 3656 Reviewed-on: http://review.gluster.com/541 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 36ef90d6de0e97812bebb303a7fa5215ae4c6ebe Author: Amar Tumballi Date: Fri Sep 30 12:22:34 2011 +0530 rebalance process: propagate proper errors to user * cluster/distribute: while rebalance, differentiate between valid errors, validation check failures (may not be migrate failure), and success. * mgmt/glusterd: differentiate the errors based on errno. If a valid error has happened, mark the rebalance status as failure, and stop the rebalnace crawl. Change-Id: I2d7bd7b73d2b79bfaf892ad4364bc89830a0d5bb BUG: 3656 Reviewed-on: http://review.gluster.com/540 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ba20df9f1a218177e7c7dcc15a11143183d28243 Author: Krishnan Parthasarathi Date: Thu Sep 29 16:44:40 2011 +0530 locks: dump client pid and time of blocking/granting. Change-Id: Icaa919f3009fb70f6af9b95fceaf800f3beca447 BUG: 3662 Reviewed-on: http://review.gluster.com/532 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b9c48822413fad5caaafa92c039dae6494476d76 Author: Pranith Kumar K Date: Thu Sep 29 08:12:22 2011 +0530 cluster/afr: Don't unlock sh_frame on failure in algo Change-Id: I0ef541c1f387c397c345e3f2bc9a57f1eff282a1 BUG: 3647 Reviewed-on: http://review.gluster.com/527 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b1bf3edb6cf153277f37d1a899e7c6b9e6cb6c24 Author: Rajesh Amaravathi Date: Mon Sep 26 11:08:48 2011 +0530 gnfs/server: allow 255-char file names * Posix requires 255 character filenames(NAME_MAX), so buffer to store a filename should be 256(+1 for terminating '\0' character). BUG: 3572 Change-Id: I9d3dbb49d96b3da946cbab97f927209d71ece620 Reviewed-on: http://review.gluster.com/531 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Krishna Srinivas commit d82f740d34f3a0b353408caf6509bef709f877a8 Author: Amar Tumballi Date: Fri Sep 30 10:51:54 2011 +0530 glusterd rebalance: allow 'status' and 'stop' from all the peers * the check to see which command is issued to do the source node check had an error. Change-Id: I5cebe6e263c416d859af4f413d47c7b643815f6f BUG: 3655 Reviewed-on: http://review.gluster.com/537 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 5cfca9f388cd153bcbcb963ba91867acf3bfac25 Author: Pranith Kumar K Date: Fri Sep 30 07:07:59 2011 +0530 cluster/afr: set fd ctx on opendir Change-Id: Ica845035781f47de990e9dcfefdeb37bed99d515 BUG: 3637 Reviewed-on: http://review.gluster.com/536 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit abb4cbeea35c40d69f18aba599f58d7e2dc5fdaf Author: Jeff Darcy Date: Thu Sep 8 11:07:10 2011 -0400 Second round of warning suppression. Used a #pragma to kill ~170 in rpcgen code. Added GF_UNUSED to deal with a few more from macros elsewhere. The remainder are function return values (mostly context and dict calls) that really should be checked. Those would be harder to fix without real understanding of the code where they occur, so they remain as reminders. (Patchset 2: deal with older gcc that doesn't handle #pragma GCC diagnostic) (Patchset 3: fix include paths in generated files) (Patchset 4: keep up with trunk, squash 9 new warnings) (Patchset 5: six more, all in AFR) Change-Id: I29760c8c81be4d7e6489312c5d0e92cc24814b7b BUG: 2550 Reviewed-on: http://review.gluster.com/378 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b43596fb4cdb84ae8b5665537914fe72517b8722 Author: Pranith Kumar K Date: Thu Sep 29 19:37:18 2011 +0530 mgmt/glusterd: skip shd graph generation for non-replicate vols Change-Id: I1bb83342bc0fa883ede527527ec8fd6ee470f781 BUG: 3666 Reviewed-on: http://review.gluster.com/535 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit ce8a569e9f18cfff2f2befe259c2022d9b37538f Author: Kaushal M Date: Wed Sep 14 09:50:45 2011 +0530 performance/io-cache,quick-read: increase cache-size limit Does the following: 1. Increases cache-size limit from 6GB to 32GB. 2. Prevents 'volume set'from failing when cache-size is set over the limit. Just issues a warning. 3. Performs check on cache-size by comparing with total system memory available in init () and reconfigure () methods. Change-Id: I7dd4d8c53051b89a293696abf1ee8dc237e39a20 BUG: 3495 Reviewed-on: http://review.gluster.com/409 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit f3a6752cc455676d6e1f946b513636d991825da8 Author: Rajesh Amaravathi Date: Tue Sep 27 16:25:58 2011 +0530 glusterd: allow non-related directories with same prefix Earlier, using two directories with names like /test and /test1 failed volume creation. This patch sees that the next character is checked to be '/' to conclude that they are recursive. Eg: /test and /test2 succeed, while /test and /test/alpha does not. Change-Id: Idee1e15b7e0a0d0965d1aea910b52f1da286d64b BUG: 3645 Reviewed-on: http://review.gluster.com/511 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Krishnan Parthasarathi commit 6d1e6a5b7c447d612684de1a75b6701b1f628fb6 Author: Raghavendra Bhat Date: Thu Sep 29 18:04:01 2011 +0530 glusterd: prevent rebalance being called in volume status execution Change-Id: I70e7d38a5cb3f6b0033ab9cabd7dfed0c68b77b8 BUG: 3668 Reviewed-on: http://review.gluster.com/534 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit a8270c537c257da13c4b48c1524ecb77ee67308f Author: Raghavendra Bhat Date: Thu Sep 29 11:04:35 2011 +0530 protocol/server: check for the fd being NULL and unwind Change-Id: I400e515431cf739fe0b2f90840359496a2b529d2 BUG: 3158 Reviewed-on: http://review.gluster.com/528 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit fb648cf39c8715e5a25752defdfc95ec0ba04217 Author: Pranith Kumar K Date: Tue Sep 27 14:44:01 2011 +0530 cluster/afr: Handle files without gfid in self-heal Change-Id: Ibcaaa9c928195939ff1e31b28b592e524e63a423 BUG: 3557 Reviewed-on: http://review.gluster.com/519 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 09cfa5dffa79abd833354a26783db9edcfb69105 Author: Pranith Kumar K Date: Tue Sep 27 14:42:28 2011 +0530 libglusterfs: wipe other variabes in loc Change-Id: I0553bb7f64d69f5684c3d21f3809da4e9e3529c1 BUG: 3557 Reviewed-on: http://review.gluster.com/515 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit c7985fe0d384846fb8974ab75eda7995bb354d79 Author: Amar Tumballi Date: Tue Sep 27 15:52:31 2011 +0530 glusterd : 'volume stop' to check if other ops are in progress * handles the case of 'rebalance' in progress * inturn it will also handle the case of decommissioning in progress * also now checks if a replace-brick is in progress Change-Id: I0266483089515d16fe8167afe06a07696328a8e3 BUG: 3358 Reviewed-on: http://review.gluster.com/518 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit dd400b5c5c49f1479db668b185a81fd434f7b219 Author: Amar Tumballi Date: Tue Sep 27 23:10:58 2011 +0530 glusterd rebalance: minor enhancements * honor 'stop' command as early as possible * don't send a setxattr() call if file doesn't have dht linkfile Change-Id: I159641d03cd15e5818b811ad113d298f7f0112db BUG: 3584 Reviewed-on: http://review.gluster.com/520 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 8b539b2a3d91df2be314665bda15bdedd898d347 Author: krishna Date: Wed Aug 10 13:00:16 2011 +0530 by default make option rpc-auth.addr.namelookup off. Change-Id: I11c1d55bebfc86c634cf446c50585f6c56c02665 BUG: 3345 Reviewed-on: http://review.gluster.com/204 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 45172a5415abc6b2f17eea74d51805ac85cc0072 Author: Kaushal M Date: Mon Sep 5 14:33:43 2011 +0530 cli : new volume statedump command Changes: 1. Add a new 'volume statedump' command, that performs statedumps of all the bricks in the volume and saves them in a specified location. 2. Add new server option 'server.statedump-path'. 3. Remove multiple function definitions in glusterd.h Statedump Information: The 'volume statedump' command performs statedumps on all the bricks in a given volume. The syntax of the command is, gluster volume statedump [type]...... Types include, * all * mem * iobuf * callpool * priv * fd * inode Defaults to 'all' when no type is specified. The statedump files are created by default in /tmp directory of the server on which the bricks are present. This path can be changed by setting the 'server.statedump-path' option. The statedump files will be named as, ..dump Change-Id: I01c0e1a8aad490da818e086d89f292bd2ed06fd4 BUG: 1964 Reviewed-on: http://review.gluster.com/321 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 16b7e3bf201686ca03f8c35c20295e05abe52df8 Author: Kaushik BV Date: Mon Sep 26 14:38:58 2011 +0530 build: Solaris build fixes Change-Id: Ic47d07a199ecbc42a141e391bbc75096e270e404 BUG: 3446 Reviewed-on: http://review.gluster.com/503 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 370ecfbf3e9a778282100d85747f506cdeb2b40a Author: Krishnan Parthasarathi Date: Tue Sep 27 14:18:38 2011 +0530 glusterd: Should not cleanup peerinfo too soon. friend_remove_cbk cleans up peerinfo and the unrefs the associated rpc_clnt obj. When the cbk is run inside call_bail or saved_frames_unwind, we might end up destroying the rpc_clnt and associated saved_frames_pool while we are still using saved_frames to iterate through the frames. Change-Id: Idf7768478a6d07a87c7faeac5b70e13bcacd2641 BUG: 3511 Reviewed-on: http://review.gluster.com/510 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 2e00396e04f261af45c33b55b9b73157a2e8fc72 Author: Kaushal M Date: Tue Sep 27 12:37:22 2011 +0530 storage/posix : prevent unmount of underlying fs posix xlator now performs opendir () on the brick directory during init (). This will prevent the underlying filesystem mounted to that directory from being unmounted. Change-Id: I02c190ab8a91abc4ab06959b36f50e0a3fa527ae BUG: 3578 Reviewed-on: http://review.gluster.com/509 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 9dc9fb48f1790a76c499b105687cee82b2840865 Author: Kaushal M Date: Mon Sep 26 10:33:56 2011 +0530 glusterd: support for resetting single option Allows resetting of only single options using 'volume reset' command. New syntax of volume reset is: 'volume reset [option] [force]'. Giving "all" as options or not specifying an option, causes all options to be reset. Change-Id: Ib9e220f326adeb1be1a774737a0b12c910012cea BUG: 2980 Reviewed-on: http://review.gluster.com/450 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit ea71efe027e9f741032b6bf9dd995bcaa2fa7947 Author: Amar Tumballi Date: Mon Sep 26 17:42:40 2011 +0530 cluster/distribute: fixed a spurious inode ref While bringing in support to open-fd migration, dht_local_init() itself started doing 'loc_copy()'. I had left one case in dht_lookup() where there is a extra loc_copy() on existing copied 'local->loc', which would cause 2 inode_refs on a given inode, and only one inode_unref() happens in dht_local_wipe(). Change-Id: Idd0375bdf9a6408db1e97e80389249ef8d802adb BUG: 3590 Reviewed-on: http://review.gluster.com/504 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 0286dd866a89c035073294c348a43beca3109c38 Author: Kaushal M Date: Mon Sep 26 11:19:24 2011 +0530 glusterd: more checks before starting rebalance Checks if specified volume is of a distribute type and has more than one brick before attempting to start rebalance. Change-Id: I9a3405019e7af4a7d7e162b0dc054bf9a99364e7 BUG: 3561 Reviewed-on: http://review.gluster.com/501 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 68ff38bd2f77c62cd0c5729b047003694a7d63af Author: Amar Tumballi Date: Mon Sep 26 20:43:17 2011 +0530 glusted: while doing add-brick, handle distribute volume separately so the logic of different type of counts etc won't come into action, which would fail the add-brick operation. Change-Id: I5c8769d6d1c2433ffb084e5dce9c1e01678cff40 BUG: 3630 Reviewed-on: http://review.gluster.com/505 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit b894944857a7ce61a3bd31566d6169ed8d19ce8b Author: Anand Avati Date: Sun Sep 25 18:34:14 2011 +0530 rpc: fix wrong wiping of state machine's state The macro __socket_proto_read() is used to read one sub-header in a fragment after another. It also has to 'get out' of the state machine's switch/case construct in two situations - a) finished reading the full header b) after a partial read, (and return in the same state at next pollin) The 'reset' of the state should happen only after a full read of the header and not if there was a partial read of the header. Change-Id: I3650a83e1fae0f317cfd1b549835c72e39dc5253 commit 76580479033087f6dde080c27618baf19b18b658 Author: Amar Tumballi Date: Thu Sep 15 12:57:44 2011 +0530 glusterd: cleanup of volinfo '*_count' definitions earlier, sub_count was having different meaning depending on the volume type. now, for replica and stripe count, one can directly access the 'replica_count' or 'stripe_count' to get the corresponding value from the volume info. 'sub_count' is preserved as is for backward compatibility. there is a new variable 'dist_leaf_count' to get info about how many bricks are present in one distribute sub volume. Change-Id: I5ea1c8f9ae08f584cca63b91ba69035c7e4350ca BUG: 3158 Reviewed-on: http://review.gluster.com/435 Reviewed-by: Krishnan Parthasarathi Tested-by: Gluster Build System commit 1b096c3ff0a4c25ff22a32d9594d2e289a3d67ea Author: Amar Tumballi Date: Fri Sep 23 16:19:20 2011 +0530 glusterd-volgen: prevent a crash when volume type is stripe-replicate when volgen tries to check for decommissioned nodes, a check for stripe replicate volume was missed Change-Id: Ie3aa97da2ec0d94fcf65f96bb4006b3fb54f59dc BUG: 3616 Reviewed-on: http://review.gluster.com/494 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 1fdcbb61872b0a849490d1f0de4fdb545e2865aa Author: Krishnan Parthasarathi Date: Wed Sep 21 11:53:45 2011 +0530 rpc: No timeouts for lock fops. As of today, all fops bail out after 30 mins by default. This is not desirable with lock fops since it could be 'rightfully blocked' for a really long time. But the client would assume that the lock fop has 'expired' after 30 mins and clean up its references to the locks. Later when the locks xlator decides to grant it, we are left with an orphan (stale) lock . This fix exempts lock fops from timeouts. Only on network disruptions both client and server decide to 'clean up' the locks held. Change-Id: If1d74ba21113650b976728e9b764c551a0a49e59 BUG: 3617 Reviewed-on: http://review.gluster.com/478 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 95876fa0ee03b0ee4cd31fa9874b4de596ae70a4 Author: Amar Tumballi Date: Wed Sep 21 14:16:46 2011 +0530 statedump: dump important details of oldgraph also * with this, it helps to find out most of the leaks in the process Change-Id: I70b476e4d63d74843d6664cfe407164f2b79b781 BUG: 3567 Reviewed-on: http://review.gluster.com/491 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2b21ea3c625fab19e88c21f4c104dca321eef262 Author: Krishnan Parthasarathi Date: Fri Sep 23 11:49:29 2011 +0530 libglusterfs: Adding missing event strings for events. Change-Id: Idf55abfa77712d32b27798fedcfddb65599b562b Reviewed-on: http://review.gluster.com/493 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4765dd1a1c51c67ab86687fbd871c89156680c34 Author: Krishnan Parthasarathi Date: Fri Sep 16 10:40:32 2011 +0530 glusterd: Implemented cmd to trigger self-heal on a replicate volume. This cmd is used in the context of proactive self-heal for replicated volumes. User invokes the following cmd when (s)he suspects that self-heal needs to be done on a particular volume, gluster volume heal . Change-Id: I3954353b53488c28b70406e261808239b44997f3 BUG: 3602 Reviewed-on: http://review.gluster.com/454 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 53b5da6dfab2e6b11ab2e40119e92ff7d4527b2c Author: shishir gowda Date: Thu Sep 22 12:53:55 2011 +0530 posix-getxattr: Honor xattr name if specified Currently, getxattr works like listxattr, and does not honor a call with a name (key) being specified. The fix handles such scenarios when a name is passed. If the name param is NULL, then it behaves like a listxattr. Changing key size to 4096, as 1024 might not be sufficient length for keys. Change-Id: I317b2e6372e97048e3166d91145c19c9e92e647e BUG: 3599 Reviewed-on: http://review.gluster.com/486 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit eede6ce87fc19878873e8320c172d1acb2deaa33 Author: Csaba Henk Date: Thu Sep 22 10:26:02 2011 +0200 geo-rep: disallow some special characters in url syntax - space is disallowed to make rsync target unambigous for gsyncd wrapper - *, ?, [ is disallowed so that we can tell away globs from urls Nothing too bad would happen without these restrictions, but this way gluster errs out early instead of producing some mystical error further down on the way. Change-Id: Idd4e68f7d91598a7a8e30ccbc6d395da570cdf2e BUG: 3610 Reviewed-on: http://review.gluster.com/490 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 21eabe9bae81b3cc732fcf773fb5c1995f19d0d7 Author: Csaba Henk Date: Thu Sep 22 10:12:24 2011 +0200 geo-rep: add support to glob patterns with "geo-rep config" Change-Id: I0d54cea72e4363eab85ade774cc918081d8036e9 BUG: 3610 Reviewed-on: http://review.gluster.com/489 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b27b9d36de798bb18eaa95524f3900f9e17ce3e5 Author: Csaba Henk Date: Tue Sep 20 16:20:18 2011 +0200 geo-rep: implement IP address based access control - gsyncd gets allow-network tunable which is expected to hold a comma-separated list of IP network addresses - for IP addess matching, bring in ipaddr module from Google (http://code.google.com/p/ipaddr-py/, rev. trunk@225) This will let users control master's access to slave's volumes until we implement unprivileged geo-rep (delayed due to some technical issues). It's also needed for the completeness of our hardening efforts, as plain file slaves won't be able to work with an unprivileged gsyncd. Change-Id: I58431cba6592f8672e93ea89a5eef478905b00b9 BUG: 2825 Reviewed-on: http://review.gluster.com/488 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d7c9d2bfbd20727f90b0118c982ff9612aacacf2 Author: Csaba Henk Date: Mon Sep 19 15:47:46 2011 +0200 geo-rep: gsyncd: make sure path operations do not act outside the volume Change-Id: I2da62b34aa833b9a28728fa1db23951f28b7e538 BUG: 2825 Reviewed-on: http://review.gluster.com/462 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7e04913aa6f4ddb45e95099ef648564bf90da0b3 Author: Csaba Henk Date: Tue Sep 13 13:12:38 2011 +0200 gsyncd: control rsync target - require/perform rsync invocation with unprotected args (so that target is revealed to gateway program) - make use of some procfs wizardry to find gsyncd sibling and match rsync target against its working directory Change-Id: Iae1e39b0e61f22563c0f2a2e0605567e0d1902df BUG: 2825 Reviewed-on: http://review.gluster.com/461 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2ab00369e7ef99d287dad5301d2f334dcfd67a70 Author: Csaba Henk Date: Sun Sep 11 19:45:57 2011 +0200 gsyncd: implement restricted mode and utility dispatch With this change, the suggested way of setting up a geo-sync slave is to use an ssh key with gsyncd as a forced command (see sshd(8)), or set gsyncd as shell. This prevents the master in executing arbitrary commands on slave (a major security hole). Detailed list the changes: - All gsyncd invocations that are not done by glusterd are considered unsafe and then we operate in so-called "restricted mode" (see below) - if we are invoked on purpose (ie. it's not the case that sshd forced us to run as frontend of a remote-invoked command), we execute gsyncd.py - if invoked by sshd as frontend command, we check the remote command line and call the required utility if it's among the allowed ones (rsyncd and gsyncd) - with rsync, we check if invocation is server mode and some other sanity measures - with gsyncd, in restricted mode we enforce the usage of the glusterd provided config file, and in python, we enforce operation in server mode and some other sanity checks Impact on using geo-rep the old way: remote file slave now also requires a running glusterd (to pick up config from). Missing: we not implemented check of the rsync target path. The issue of master being able to modify arbitrary locations is planned to be mitigated by using geo-rep with an unprivileged user. Change-Id: I9b5825bfe282a9ca777429aadd554d78708f1638 BUG: 2825 Reviewed-on: http://review.gluster.com/460 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 1098aaa51d2e3dca9e6c48ee1e9cb43bc87936f4 Author: Csaba Henk Date: Fri Sep 2 19:03:33 2011 +0200 geo-rep: rewrite gsyncd wrapper in C This rewrite does not change functionality; it's purpose is to prepare followup modifications which will let all slave side helper programs being dispatched to through gsyncd. The string processing that's required for that task would be too much cumbersome in shell. Change-Id: Ia7858aba5efeb5dcff16a918ea1c02253f0e49ab BUG: 2825 Reviewed-on: http://review.gluster.com/459 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3672c989f369c5b57aff8d0d01fc221804ada6eb Author: shishir Date: Mon Sep 19 18:23:04 2011 +0530 Peer probe: Handle probe of friend with multiple hostname Currently, when a peer is probed with a different hostname already belonging to a cluster, a duplicate entry is created with uuid to set to 0. This leaves the peerinfo in a inconsistent state, and when a detach of this peer is issued, the correct entry gets removed. The fix is to identify a peer with a hostname not matching to the probed hostname and remove the incorrect entry. Change-Id: I2f6c02f505f4426871623a4a8b45a12996095098 BUG: 3200 Reviewed-on: http://review.gluster.com/456 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2e61c86ba89d546c7cab522b53d6b9c7f164cd8c Author: Gaurav Date: Thu Sep 22 12:48:41 2011 +0530 NFS : Posix compliance fixes. Change-Id: I4f1d8883a3eedee20557e306815674a6dc062bfe BUG: 1337 Reviewed-on: http://review.gluster.com/487 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit b8f2f460f9a5f977ef6debc2e59cae75324c95ca Author: Amar Tumballi Date: Mon Sep 19 13:01:26 2011 +0530 statedump: add more memory accounting related stats * iobuf: add variable to keep count of total number of allocations * iobuf: include 'purged' and 'filled' arenas also in dump * mempool: more details added (with a name to tell why mem-pool is created) * memory-accounting: print number of allocs in each type this would give us much better understanding of the memory allocation pattern Change-Id: I117ac0c1da943a4cc91543a01963ba7940db2b5f BUG: 3567 Reviewed-on: http://review.gluster.com/376 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5619b2dc4189e9de4a2327dc63ccb647f863f2b1 Author: Kaushal M Date: Wed Sep 21 12:06:14 2011 +0530 glusterd: fix 'volume status' showing incorrect online status glusterd now checks if a brick process is running to set online status, instead of using brickinfo->signed_in. The earlier method used to show incorrect online status as brickinfo->signed_in was not updated when brick process was killed with SIGKILL Change-Id: Id5589ea8abbcffebe5c794e5a4adf4f0e6e489f0 BUG: 3573 Reviewed-on: http://review.gluster.com/476 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit aa7815c29a849346a75389f6ad15d8190f5a6710 Author: Rahul C S Date: Tue Sep 20 17:44:07 2011 +0530 cluster/distribute: validate buf before accessing. The macro to check & reset rebalance flags was accessing the iatt structure even in case of failures leading to null dereference. Change-Id: I518f4cc9086cecbe6cf791c8a351287fe3613650 BUG: 3594 Reviewed-on: http://review.gluster.com/472 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 8fc81caf43d491a49134e6491b813843e490bb99 Author: krishna Date: Wed Sep 14 16:09:16 2011 +0530 nfs: enhance NFS log messages. Change-Id: I6c2eaa2795756f515b5fb2ea5098d3dcb4ef77c4 BUG: 3527 Reviewed-on: http://review.gluster.com/433 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit abe47d434308e2ac5926fc8e292cced3688b7ca4 Author: shishir gowda Date: Wed Sep 21 17:11:49 2011 +0530 Rebalance: Mount rebalance client with assert-on-child-down set to on This will prevent rebalance to be started when a brick is down, or stop rebalance if a brick goes down during a rebalance op. On restarting the rebalance once all the bricks are up, rebalance proceeds as usual. Change-Id: I196ae658c3a3856cce5314eca194e62d42171b9d BUG: 3574 Reviewed-on: http://review.gluster.com/481 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b274b8792c6bf6d95cad078fadad0ffe4c2bf43a Author: Amar Tumballi Date: Tue Sep 20 13:23:08 2011 +0530 glusterfs protocol: handshake to log the version of the peer * As RPC program's name is just used for logging, we now have 'PACKAGE_VERSION' part of the string, which gets logged in client side. * From client, we send the PACKAGE_VERSION in handshake dictionary, which gets logged on serverside handshake. The change doesn't break any compatibility between client or server as it would only enhance the logging part of handshake. Change-Id: Ie7f498af2f5d3f97be37c8d982061cb6021883ce BUG: 3589 Reviewed-on: http://review.gluster.com/467 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 4a8981eb99c09d76872b8aa167863b49f74b52f2 Author: Lakshmipathi Date: Tue Sep 20 13:06:11 2011 +0530 build : rpm spec file changes Thanks to Scott Zahn - Fixed spec file to add the correct ldconfig path addition for i386 and x86_64.(BUG:2279) Persson - Fixed without_georeplication macro (BUG:3541) JoeJulian - Minor rpm cleanups.(BUG:3546) Patch create the library references for both 64bit and 32bit rpms Change-Id: Ia281fa0d3d8b32ff19b74f379cda7ca9315a4beb BUG: 2279 Reviewed-on: http://review.gluster.com/466 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 03591027b06c556baa95c6fa4569be0bff4adcd8 Author: Pranith Kumar K Date: Tue Sep 20 18:30:42 2011 +0530 cluster/afr: Make local->child_up immutable Afr transaction performs lock, pre-op, op, post-op and unlock steps in that order. The child_up[] is overloaded with the information of where all the first two steps succeeded. This works perfectly fine for Transaction, but the locking/unlocking part of the code is re-used by data self-heal. In that each loop_frame does lock, rchecksum, read-from-source and write-to-sinks, unlock steps. Rchecksum fop assumes that the fop needs to happen on one source + all sinks and sets the call_count to that number. But if the lock step fails on any of the sinks it will mark the child_up of that child to 0, which will result in call_count mismatch and the frame will hang thinking that some more cbks need to come. When this happens loop_frame will never go to unlock step leading to hangs on that file. Change-Id: I3dd0449cc6193a980bacf637d935881f4b22210a BUG: 3597 Reviewed-on: http://review.gluster.com/474 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 82d1a445b92526629d699f947a2d2bd029c8db75 Author: Amar Tumballi Date: Wed Sep 21 12:20:34 2011 +0530 glusterd rebalance: set the proper status as per command given for both 'migrate-data start' or 'migrate-data start force' commands the defrag status should start with 'migrate-data-started' state. Change-Id: Ic645bc764c4d24ab438187fb139c4a1c3ade8949 BUG: 3593 Reviewed-on: http://review.gluster.com/477 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 4c0efe75411112d6e386fe10a138ec2d9218b8b8 Author: Pranith Kumar K Date: Wed Sep 21 08:12:32 2011 +0530 mgmt/glusterd: Create volfile in correct path Change-Id: Ie52e4b1a338282f2697e2ce374dd566d2c5cf5d1 BUG: 3586 Reviewed-on: http://review.gluster.com/475 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b30f66e20d830daec057075d67f181e904984a27 Author: Venky Shankar Date: Tue Sep 13 22:11:33 2011 +0530 geo-rep: gsyncd: add --ignore-deletes option When this option is set, a file deleted on master will not trigger a delete operation on the slave. Hence, the slave will remain as a superset of the master and can be used to recover the master in case of crash and/or accidental deletes. This options is not enabled by default. Change-Id: I9244d9dfa4f38f19436036f36bec0d9c3a1f7993 BUG: 3552 Reviewed-on: http://review.gluster.com/426 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit e8b81f72d7a45ce443e72c45ae68952911deac50 Author: Pranith Kumar K Date: Mon Aug 29 16:54:50 2011 +0530 storage/posix: Filter custom getxattrs in lookup Change-Id: If948ff1b355ea4fd92036bcc43e7b32325aeb3e4 BUG: 3470 Reviewed-on: http://review.gluster.com/325 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit cb2c6982bd6d588a91fa2827f95f0d9cf3ff2560 Author: Amar Tumballi Date: Wed Sep 14 09:02:01 2011 +0530 cluster/distribute: minor fixes in open file migration * incorporated Avati's comments on the first patch. * send proper stat information while unwinding Change-Id: I36982cec610753c241c372272620ab2bd581fd9f BUG: 3071 Reviewed-on: http://review.gluster.com/408 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b5b0bb056391659802099908f4bccde5afdb9e34 Author: Raghavendra Bhat Date: Tue Sep 20 11:03:32 2011 +0530 features/locks: free the string allocated by inode_path Change-Id: I1b7d4059610713b92c4bb78676c3b48335e3a0fe BUG: 3468 Reviewed-on: http://review.gluster.com/465 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8d4d8088c73f2ffc60b8e5c23a33e6b996fb5053 Author: Kaushal M Date: Tue Sep 6 17:18:20 2011 +0530 glusterd: run 'volume top read-perf/write-perf' in different thread Runs the 'volume top read-perf/write-perf' operations in a different thread without blocking glusterd. Prvents glusterd from being unresponsive when large values of 'bs' and 'count' are given. Also increase cli timeout for top/profile commands , from 120s to 300s to allow large i/o top read-perf and write-perf to return result. Change-Id: I4b7de1d735f33643d836772db7f25133f112b75a BUG: 2720 Reviewed-on: http://review.gluster.com/375 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit e0178776546f06646c11bcb1ea345f82436d73aa Author: Vijay Bellur Date: Mon Sep 19 22:01:13 2011 +0530 rpc:memcpy data of right size to auth params Change-Id: I6999e0a1463ee3475f7607990337326b3f008538 BUG: 3587 Reviewed-on: http://review.gluster.com/464 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit e163bc5b3ab062e3cb22b0386dbe056ab4a54952 Author: Csaba Henk Date: Wed Aug 31 16:03:28 2011 +0200 s@GFS_PREFIX"/sbin@SBIN_DIR@ $sbindir is the install path for gluster* binaries, so this is what should be used in their invocation Change-Id: Ie748b4cbf59c3ee77f721ff6e0ab7151742ce0ab BUG: 2825 Reviewed-on: http://review.gluster.com/458 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b23d329608163ee2aa1aa89b907a5a6e50291464 Author: Rajesh Amaravathi Date: Mon Sep 12 17:29:47 2011 +0530 glusterd: provide a option to start processes with valgrind By enabling the brick-with-valgrind option in glusterd, one can automatically start all bricks with valgrind monitoring them. Change-Id: Ib0a97a83c4461c0878454e96bc84462f6cad6bc8 BUG: 3461 Reviewed-on: http://review.gluster.com/311 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 8ad4d3f53000724389db6003ca6d6d777b880017 Author: Rajesh Amaravathi Date: Mon Sep 19 16:43:50 2011 +0530 glusterd/top: volume top succeeds on partial brickpath Rewrite of glusterd_volume_brickinfo_get in glusterd-utils.c An additional argument to glusterd_volume_brick_info_get_by_brick and glusterd_volume_brickinfo_get enables matching brick path in two ways: Complete or partial(ancestor and descendent paths matched). Change-Id: Ia87833a6f0c139599c3e40b59d60c64281b4084b BUG: 3271 Reviewed-on: http://review.gluster.com/162 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Vijay Bellur commit 608f2d698569abc82cc671e81477e89e9c553bda Author: Kaushal M Date: Mon Sep 19 15:13:43 2011 +0530 cli: enable order checking stripe-replicate volumes This is a followup patch to e378778686fca24934e76c41e6496b12162a5420 Enables brick order checking for volumes of type stripe replicate. Change-Id: Ib9b090a3514d05bb7602c423de7d3123f107a3b5 BUG: 2441 Reviewed-on: http://review.gluster.com/455 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 39fee9a8f8264df61f77563acb048a441265afcf Author: Rajesh Amaravathi Date: Mon Sep 19 14:25:47 2011 +0530 glusterd: make sort portable fixed for fd leaking. reopening of file was not needed BUG: 3491 Change-Id: I1351bdcaa41a5901574f5e779c33bf6f80a938f9 Reviewed-on: http://review.gluster.com/453 Reviewed-by: Csaba Henk Tested-by: Gluster Build System commit 909f80181c9a6985c49964de4854f5d5460dbf09 Author: Rajesh Amaravathi Date: Mon Sep 19 13:22:54 2011 +0530 protocol/client: minor log enhancements minor changes to the log enhancements of bug 3473. Change-Id: Id38d29db5a744e0ab7342d10ead6d16866228062 BUG: 3473 Reviewed-on: http://review.gluster.com/452 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit d70f640ea121643fadef2f19a33d18d81c9f5bb5 Author: Sachidananda Urs Date: Mon Sep 19 12:32:33 2011 +0530 Fix typo in log message. Change-Id: Ia51ffe03c8b94ddfe21c6609bc0d54b5bd29eca7 BUG: 3158 Reviewed-on: http://review.gluster.com/392 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 02db3a0e457654b35c1a147403f1e99f691dcd52 Author: Raghavendra G Date: Sat Sep 10 15:22:37 2011 +0530 features/marker: Use appropriate loc struct to do removexattr on newpath after rename. Change-Id: I060e62c1fbb288179063a6d64d73bad1a6572661 BUG: 3493 Reviewed-on: http://review.gluster.com/390 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 9895baf2719ac9911bc20ca54d0ff84f761baaed Author: Kaushik BV Date: Fri Sep 16 14:03:40 2011 +0530 cli: check wordcount to validate volume set help Change-Id: I93650af9fb29cffc48733d9bba5fd2fb580c44a1 BUG: 3543 Reviewed-on: http://review.gluster.com/436 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 0cb13b43c612dffe6aa8ba9367c5f808e725efff Author: Rajesh Amaravathi Date: Mon Sep 12 11:11:56 2011 +0530 glusterd: make sort portable The result of sorting the volume info file has been programmatically redirected, instead of using the -o option. Change-Id: Id789fab8dc92b254571a4fc7239e4872f3ac055f BUG: 3491 Reviewed-on: http://review.gluster.com/395 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit e378778686fca24934e76c41e6496b12162a5420 Author: Kaushal M Date: Wed Aug 3 18:12:21 2011 +0530 cli : check for bad brick order while creating replicate volume gluster cli now checks the brick order when creating a replicate or distributed-replicate volume. If a non-optimal order is found the user is given a warning and asked if the volume creation can proceed. Change-Id: I38c4cb65bffb40ccf95319cf3f4f3423a4cdebe9 BUG: 2407 Reviewed-on: http://review.gluster.com/151 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 46a7adafe94b14778328d77a7f743fbce17341e3 Author: Kaushal M Date: Tue Aug 16 13:17:38 2011 +0530 glusterfsd: enable max fetch attempts Enables usage of 'volfile-max-fetch-attempts' option of glusterfsd. Also, adds an option to 'mount.glusterfs' for setting the max fetch attempts. For a server with multiple ips, each call to gf_resolve_ip6() returns a different ip. Since gf_resolve_ip6() is called for each fetch attempt, this change also enables rrdns support for gluster. Change-Id: I3edadbf0ff43ff414b30eb50dd9ca4a6fd6b1089 BUG: 2441 Reviewed-on: http://review.gluster.com/239 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit 5de8c537936c547d8eafa3913e63a84646134f36 Author: Raghavendra G Date: Fri Sep 16 15:17:24 2011 +0530 performance/quick-read: fix memory corruption. - macro QR_STACK_UNWIND destroys the stub present in local and hence no need of explicitly calling call_stub_destroy on it. Change-Id: Ib81c9a0d382765e783722b14fdbd7877086b1bec BUG: 3562 Reviewed-on: http://review.gluster.com/439 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 003a578d9b324e769e231451a53688b48550e0f0 Author: Csaba Henk Date: Thu Sep 15 02:29:54 2011 +0200 libglusterfs: run: fix closing of redirection fd in child When run was doing a program invocation like "echo foo > foof", the file descriptor to foof was closed before stdout could be reopened to it. To fix this, we change the order of actions: first do redirections, then do the fd cleanup. This also simplifies code (as there are less fds which are exempt of the cleanup). Change-Id: I5f74e41f2999e59916a40c8a89d7fb730d808c27 BUG: 2562 Reported-by: Rajesh Amaravathi Reviewed-on: http://review.gluster.com/428 Tested-by: Gluster Build System Tested-by: Rajesh Amaravathi Reviewed-by: Rajesh Amaravathi Reviewed-by: Amar Tumballi commit 35bbb34a3f4a74f0d2288aacd984c71c7ebdfa3c Author: Rajesh Amaravathi Date: Fri Sep 2 15:10:30 2011 +0530 protocol/client: log enhancements * print paths wherever it is possible to log, to help debugging. * bring uniformity in log level. Change-Id: I2fa85b629de5dd0f0057ed96cba08ecb0ff1a798 BUG: 3473 Reviewed-on: http://review.gluster.com/328 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 9eec7900639684e5a2fd80b273437fefe6b5b930 Author: krishna Date: Wed Sep 14 16:13:27 2011 +0530 rpc: Use correct variable for volume-specific insecure ports check Change-Id: Ica59a3154c4e7d980d3477dd3879c7cebe92ad87 BUG: 3515 Reviewed-on: http://review.gluster.com/418 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 16a4d4352c762f6035e1a39f619d358ba7688502 Author: Raghavendra Bhat Date: Fri Sep 16 15:03:32 2011 +0530 cli: if the create volume command does not contain bricks, exit gracefully Change-Id: I41f896d5a9c514994874b6e4e956d38fed742d4b BUG: 3571 Reviewed-on: http://review.gluster.com/438 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 4ee093305a0237368118e425723792a028b02a94 Author: Krishnan Parthasarathi Date: Thu Sep 15 17:09:00 2011 +0530 glusterd: profile cmd incorrectly reports all bricks down. If there are no bricks of a volume running 'local' to glusterd where the 'profile info' command is issued, glusterd incorrectly reports that all bricks of the volume are down. Change-Id: Idd703c991f0bcf59b76b9ef8f4ad8cd71960a55b BUG: 3553 Reviewed-on: http://review.gluster.com/430 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 77cce4c7df9a61b599a27522696720e747714ff2 Author: Csaba Henk Date: Thu Sep 15 18:14:53 2011 +0200 rpc: fix up mountbroker xdr defs and regenerate headers Change-Id: I8a88d2b9228c3614ee7cbaf48782a419e6aee0f6 BUG: 3482 Reported-by: Krishnan Parthasarathi Reviewed-on: http://review.gluster.com/432 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi Reviewed-by: Vijay Bellur commit 45f03a58a0fbfc1d5e647c764b10e37d0a9ebb26 Author: Pranith Kumar K Date: Thu Sep 8 14:06:32 2011 +0530 Proactive self heal process implementation Change-Id: I96db0d94566ceabf1649f890318363f738c06553 BUG: 2458 Reviewed-on: http://review.gluster.com/403 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3bea46c1f232a4480e57ac482f92f7673af7034f Author: Pranith Kumar K Date: Wed Sep 7 21:26:41 2011 +0530 dict: add reset function which empties the dict Change-Id: I267c81a129197534fb318671eafb76e144a15c8c BUG: 2458 Reviewed-on: http://review.gluster.com/402 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 78dee45ef829296dbcb4cf28e06feb8e25458c91 Author: Pranith Kumar K Date: Tue Sep 6 13:56:03 2011 +0530 debug/io-stats: Allow multiple children in graph Change-Id: Ie4fb75d8000ff95daa8bf9f6757926822de28a65 BUG: 2458 Reviewed-on: http://review.gluster.com/401 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 4a7d4dcd70bfc480ea20ae10d44257e56e86789c Author: Raghavendra G Date: Tue Sep 13 15:15:10 2011 +0530 features/quota: explicitly create xattrs in marker_create_cbk - the earlier approach of creating quota related xattrs through side-effect of updating size and contribution values won't work, since when no contribution xattr is present, the updation process treats contribution value as zero and hence will be equal to size of freshly created files Change-Id: If9b2063b1ac3a4cf50d3fe2c81e907bc8eccb677 BUG: 3531 Reviewed-on: http://review.gluster.com/385 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid commit 9a16332d518c6318b761b230a0e1bb8ce357228e Author: Raghavendra G Date: Fri Sep 9 17:14:41 2011 +0530 features/quota: implement mknod fop. Change-Id: If8f2a0bb635160ee78f35787ee9f8a4db87ae8ac BUG: 3531 Reviewed-on: http://review.gluster.com/384 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid commit b57e956caaf4536218b3b55ae78b4597858bdfde Author: Amar Tumballi Date: Wed Sep 14 15:59:21 2011 +0530 glusterfsd: log the package version just after log init helps getting output of 'glusterfs --version' from the users while debugging any issues/bugs. Change-Id: I4f15aca143c1e403c70409378afc9ed7a678b286 BUG: 2346 Reviewed-on: http://review.gluster.com/415 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7a153f17b1892ca8747d5b570d80795b4006790a Author: Amar Tumballi Date: Wed Sep 14 13:51:40 2011 +0530 libglusterfs/common-utils: resolve_ip6() to take AI_ADDRCONFIG AI_ADDRCONFIG flag is needed for 'getaddrinfo()' call as hint so that while resolving a hostname, ip list will be taken from proper configured address family Change-Id: Iad6067ad64444d3930d5be593ca819a8de5fc0c1 BUG: 3548 Reviewed-on: http://review.gluster.com/414 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d705b28fd1bb066632854da493031118776d00df Author: Venky Shankar Date: Tue Sep 13 11:36:55 2011 +0530 GlusterFS Hadoop specific DSL for mountbroker Change-Id: Ie379992bdea0974c8c5e1a4d7bc3e87cefe0d256 BUG: 3539 Reviewed-on: http://review.gluster.com/404 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b039cb193eddc51c6f31bf9a230281faada475fe Author: Amar Tumballi Date: Tue Sep 13 16:54:24 2011 +0530 glusterd rebalance: fix minor issues there were bugs introduced due to parallelizing rebalance op. * argument to dict_set_str () should be static as for the life of dict * uuid_utoa() output should not be considered as static * overloading 'volinfo->defrag' in other nodes is a overkill, just KISS Change-Id: I43d00c8e22beb2dd5c5f9824552f7337543b2255 BUG: 2112 Reviewed-on: http://review.gluster.com/407 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 25daa42911d2ff697880ee29c591cac5f2abebed Author: Amar Tumballi Date: Fri Sep 9 09:42:51 2011 +0530 support for de-commissioning a node using 'remove-brick' to achieve this, we now create volume-file with 'decommissioned-nodes' option in distribute volume, then just perform the rebalance set of operations (with 'force' flag set). now onwards, the 'remove-brick' (with 'start' option) operation tries to migrate data from removed bricks to existing bricks. 'remove-brick' also supports similar options as of replace-brick. * (no options) -> works as 'force', will have the current behavior of remove-brick, ie., no data-migration, volume changes. * start (starts remove-brick with data-migration/draining process, which takes care of migrating data and once complete, will commit the changes to volume file) * pause (stop data migration, but keep the volume file intact with extra options whatever is set) * abort (stop data-migration, and fall back to old configuration) * commit (if volume is stopped, commits the changes to volumefile) * force (stops the data-migration and commits the changes to volume file) Change-Id: I3952bcfbe604a0952e68b6accace7014d5e401d3 BUG: 1952 Reviewed-on: http://review.gluster.com/118 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 17e57f27c714c94dd5d9fa91650f83d069f2f4e4 Author: Kaushik BV Date: Mon Sep 12 15:51:42 2011 +0530 mgmt/glusterd: check the availability of fuse for few glusterd operations Change-Id: I410cc6a86c32637566e5498f69f46cb40322e7fb BUG: 2715 Reviewed-on: http://review.gluster.com/364 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit 8778c0bf72cc28a56becf0fd989bf66df51fd8a3 Author: Kaushik BV Date: Wed Aug 31 18:04:19 2011 +0530 mgmt/glusterd: fail glusterd if gsyncd does not behave as expected Change-Id: Ic54220328f15c579dcf441de2aad8620751a97ef BUG: 2744 Reviewed-on: http://review.gluster.com/331 Tested-by: Gluster Build System Reviewed-by: Csaba Henk commit 58c5e9feae1fdf618bb120f4c8ea318cc628dd06 Author: Amar Tumballi Date: Tue Sep 13 12:11:52 2011 +0530 socket: provide proper arguments to getaddrinfo ----- from 'man getaddrinfo' : If hints.ai_flags includes the AI_ADDRCONFIG flag, then IPv4 addresses are returned in the list pointed to by res only if the local system has at least one IPv4 address configured, and IPv6 addresses are only returned if the local system has at least one IPv6 address configured. ----- Change-Id: Ie30344daf1bb9d41ac58741b38e83af35cd8b5e9 BUG: 2456 Reviewed-on: http://review.gluster.com/405 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit a07bb18c8adeb8597f62095c5d1361c5bad01f09 Author: Amar Tumballi Date: Wed Sep 7 12:53:09 2011 +0530 distribute rebalance: handle the open file migration Complexity involved: To migrate a file with open fd, we have to notify the other client process which has the open fd, and make sure the write()s happening on that fd is properly synced to the migrated file. Once the migration is complete, the client process which has open-fd should get notified and it should start performing all the operations on the new subvolume, instead of earlier cached volume. How to solve the notification part: We can overload the 'postbuf' attribute in the _cbk() function to understand if a file is 'under-migration' or 'migration-complete' state. (This will be something similar to deciding whether a file is DHT-linkfile by its 'mode'). Overall change includes below mentioned major changes: 1. dht_linkfile is decided by only 2 factors (mode(01000), xattr(trusted.glusterfs.dht.linkto)), instead of earlier 3 factors (size==0) 2. in linkfile self-heal part (in 'dht_lookup_everywhere_cbk()'), don't delete a linkfile if there is a open-fd on it. It means, there may be a migration in progress. 3. if a file's revalidate fails with ENOENT, it may be due to file migration, and hence need a lookup_everywhere() 4. There will be 2 phases of file-migration. -> Phase 1: Migration in progress * The source data file will have SGID and STICKY bit set in its mode. * The source data file will have a 'linkto' xattr pointing the destination. * Destination file will have mode set to '01000', and 'linkto' xattr set to itself. -> Phase 2: File migration Complete * The source data file will have mode '01000', and will be 'truncated' to size 0. * The destination file will have inherited mode from the source. (without sgid and sticky bit) and its 'linkto' attribute will be removed. 4. Changes in distribute to work smoothly with a file which is in migration / got migrated. The 'fops' are divided into 3 categories, inode-read, inode-write and others. inode-read fops need to handle only 'phase 2' notification, where as, the inode-write fops need to handle both 'phase 1' and phase2. The inode-write operations will be done on source file, and if any of 'file-migration' procedures are detected in _cbk(), then the operations should be performed on the destination too. when a phase-2 is detected, then the inode-ctx itself should be changed to represent a new layout. With these changes, the open file migration will work smoothly with multiple clients. Change-Id: I512408463814e650f34c62ed009bf2101d016fd6 BUG: 3071 Reviewed-on: http://review.gluster.com/209 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 09eeaf4e68c225b8e5ccc0a9b4f10f8c4748e205 Author: Csaba Henk Date: Wed Aug 24 23:01:31 2011 +0200 geo-rep: partial support for unprivileged gsyncd via mountbroker gsyncd: - mounting code is split to a direct and a mountbroker based backend - option gluster-command gone - new options: gluster-params, gluster-cli-options, mountbroker - mountbroker mount backend is used if either a mountbroker label is given through the mountbroker option, or if gsyncd is unprivileged; in this case the username is used as label - have gluster cli invocations log to stderr so that we don't hit a permission issue with the logfiles glusterd: - do gsyncd pre-config with new options - add option geo-replication-log-group, so if that specified geo-rep logfile directories are given to that group (and thus members of the given group can do logging there) This is just WIP as geo-rep relies on trusted extended attributes and those are not accessible for unprivileged users. Even if we solved this issue, glusterd security settings are too coarse, so that if we made it possible for an unprivileged gsyncd to operate, we would open up too far. Change-Id: Icd520b58cbadccea3fad7c0f437b99de1e22db14 BUG: 2825 Reviewed-on: http://review.gluster.com/399 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 37ac355cbbd36497f914905615bffb3e35805f0a Author: Csaba Henk Date: Sat Jul 30 17:50:22 2011 +0200 glusterd / cli: mount-broker service Mountbroker is configured in glusterd volfile through a DSL which is restriced enough to be able to appear in the role of the value of a volfile knob. Basically the DSL describes set-theorical requirements against the option set which is sent by the cli (in the hope of getting a mount with these options). If the requirements meet and the volume id and the uid who is to "own" the mount can be unambigously deduced from the given request, glusterd does the mount with the given parameters. The use case of geo-replication is sugared by means of volume options which then generate a complete mount-broker option set. Demo: - add the following option to your glusterd volfile: option mountbroker-root /tmp/mbr option mountbroker.fool EQL(volfile-id=pop*|user-map-root=*|volfile-server=localhost)&MEET(user-map-root=john|user-map-root=jane) - before starting glusterd, create /tmp/mbr owned by root with mode 0755 - with cli, do $ gluster system:: mount fool volfile-id=pop33 user-map-root=jane volfile-server=localhost - on succesful completion (volume pop33 exists and is started, jane is a valid username), the mount path will be echoed to you - you can get rid of the mount by $ gluster system:: umount Change-Id: I629cf64add0a45500d05becc3316f67cdb5b42ff BUG: 3482 Reviewed-on: http://review.gluster.com/128 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 78170472e6c7f0bce95ab035cc4ed86ec662e80d Author: Csaba Henk Date: Sat Jul 30 16:45:50 2011 +0300 add --user-map-root option This makes client fake that given user is a superuser, by changing FUSE requests coming with uid of user so that uid is set to 0. User can be given in numeric form, in which case it's treated as an uid directly, or else it's tried to be resolved to an uid with getpwnam(3). Implies --acl. Change-Id: I2d5a3d3e178be7ffdf22b46a56f33a7eeaaa7fe1 BUG: 3242 Reviewed-on: http://review.gluster.com/127 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 32b96d66890a16fd23c8ae065297c7a98097d340 Author: Csaba Henk Date: Sat Jul 23 12:16:07 2011 +0200 cli: add --log-{file,level} options Apart from diagnostic purposes, it's needed when cli is ran by unprivileged user who most likely has no write access to the canonical log file. Change-Id: Ib9d1a31711966ff1efe2592fbc0a911820cf8ee3 BUG: 3242 Reviewed-on: http://review.gluster.com/95 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 3d67836dba4f5a94f33e9ac13b7ebbf01344ac37 Author: Csaba Henk Date: Sat Jul 23 12:14:48 2011 +0200 cli: fix option parsing bug which implied that only a single option can be used Change-Id: I89467d00030f4714568ef63650ecef0aef1bf753 BUG: 3242 Reviewed-on: http://review.gluster.com/94 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d58382182ee53fcc83ec04f211c000a5a4db9a0b Author: Csaba Henk Date: Fri Jul 15 11:44:56 2011 +0200 cli: reimplement "--version" without excess bloat Change-Id: I787d241e72b6a6c43db96c220d68fe369bb700a4 BUG: 3242 Reviewed-on: http://review.gluster.com/93 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 74bf2c1fc5d7377472d8c6ba8e27a333fc618899 Author: Csaba Henk Date: Fri Jul 15 11:34:35 2011 +0200 Revert "cli: Only admin should run gluster CLI" This reverts commit 8d64ca70b4c2467d4ed8c76a9eae385abdebd7a7. Change-Id: Id2c6b491c7dd133510380f576ad59655a01d6121 BUG: 3242 Reviewed-on: http://review.gluster.com/92 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 36059b73949a1eee32a3b2aa16b09263628ff050 Author: Csaba Henk Date: Fri Jul 15 11:34:25 2011 +0200 Revert "cli: gluster --version implementation" This reverts commit e93b270e8d09fc9d36a39b22987d3a172197e73b. Conflicts: cli/src/cli.c Change-Id: Ibc0f6f752f713b15afc8b5458be5045ecb21235e BUG: 3242 Reviewed-on: http://review.gluster.com/91 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit e139eeeb627368112aa1341d2f0ef6770dd7078e Author: Csaba Henk Date: Wed Aug 10 20:04:20 2011 +0300 gsyncd: python3 compat fixes Also add __codecheck script which can verify if source is OK at the syntactical level with a given Python interpreter. Change-Id: Ieff34bcd3efd1cdc0e8f9a510c05488f35897bbe BUG: 1570 Reviewed-on: http://review.gluster.com/320 Reviewed-by: Kaushik BV Tested-by: Gluster Build System commit f3081a22740c70485c50d3837fa93da5fd843f26 Author: Csaba Henk Date: Mon Aug 15 03:17:18 2011 +0300 glusterd: fix cleaning up of runner object in lack of that, if geo-rep component is not installed, glusterd got a zombie child Change-Id: Ic4a2a4ffc943de68dd02db76a32b1618821ddf56 BUG: 2744 Reviewed-on: http://review.gluster.com/317 Reviewed-by: Kaushik BV Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 417de9db670650edd96e82a6e43087bea49deeee Author: Krishnan Parthasarathi Date: Mon Sep 5 20:14:21 2011 +0530 rpc: Need to keep ref when handling cbk in call_bail. Change-Id: Ic944599cfa2696a0ae77105185d49fb510ce6fec BUG: 3511 Reviewed-on: http://review.gluster.com/361 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5d03ebd31f2984614ecdc8f117bd4599ade497d1 Author: Raghavendra Bhat Date: Mon Sep 12 11:45:37 2011 +0530 glusterd: free the allocated string to avoid memory leak Change-Id: I520abf3c57a15be8bb7dd1e92ad0b049ef5c8970 BUG: 3341 Reviewed-on: http://review.gluster.com/394 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 225dd7da8959c78331d16ba2c2a955b1432bc873 Author: Raghavendra Bhat Date: Wed Aug 31 13:02:21 2011 +0530 protocol/client: avoid code duplication in fd based operations Change-Id: I012f78bac8ba82333628c59ef51d5e5f43d05ac7 BUG: 3158 Reviewed-on: http://review.gluster.com/329 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a2ef31b01537d8edd5ecf3738967704b0a19b137 Author: Raghavendra Bhat Date: Mon Aug 22 22:37:43 2011 +0530 features/marker: unref the local incase of errors before unwinding Change-Id: I4dcad7ddf84bf98b4b7f4a0e407a418426674280 BUG: 2784 Reviewed-on: http://review.gluster.com/299 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 02b30e294b46cf54edf005db5ce5b0c2dc75919f Author: Vijay Bellur Date: Fri Sep 9 13:17:10 2011 +0530 mgmt/glusterd: volume set help-xml format change Change-Id: I503364c855d52605e301f4d3c205af6c9fc0e1df BUG: 3366 Reviewed-on: http://review.gluster.com/380 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 5efdbef0d74359122dbf76539e0975bea691456a Author: Junaid Date: Fri Sep 9 14:35:57 2011 +0530 features/marker-quota: Prefix the function names with mq (marker-quota). This is to fix to bug marker translator and quota translator cannot co-exist in same process. Change-Id: I9f132b663f03641f4f2c7e168df8400adbc5570f BUG: 3020 Reviewed-on: http://review.gluster.com/381 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit a0695e0524cc61d05156b66ebe3542870712daae Author: Pranith Kumar K Date: Wed Sep 7 13:50:19 2011 +0530 cluster/afr: perform self-heal with least priority Change-Id: Id8a1dffa3c3200234ad154d1749278a2d7c7021b BUG: 3502 Reviewed-on: http://review.gluster.com/336 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 85a2f0ec5021d53f34fe1630028f413835abd31e Author: Amar Tumballi Date: Wed Sep 7 12:46:30 2011 +0530 glusterd rebalance: make co-operate with all other 'op' that way, we can share the rebalance state with other peers and can prevent confusion/conflicts when multiple rebalances are done by different peers. Change-Id: I24159e69332644718df7314f6f1da7fce9ff740e BUG: 2112 Reviewed-on: http://review.gluster.com/343 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 77eb7bdfd02f2ba61847fb9c35e9e19e3da4fcc4 Author: Amar Tumballi Date: Thu Sep 8 00:34:32 2011 +0530 cli: 'gluster create volume' - improve option parsing now 'replica' 'stripe' and 'transport' options can be given in any order Change-Id: Ied992ae55e86028bd4f2d662ebd246db138d4548 BUG: 3521 Reviewed-on: http://review.gluster.com/370 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0a2de8337e7111d9cb860329d83b5aae3ecacd2f Author: Junaid Date: Wed Sep 7 17:36:09 2011 +0530 features/marker-quota: Perform xattr related operations with root permissions in rename fop. Change-Id: Id9ac1ecdd9753377c9eb24464f51dcbdc0cd2821 BUG: 3194 Reviewed-on: http://review.gluster.com/367 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f655fa043fc65ecad1d633a52a40a4c20ff18c97 Author: Pranith Kumar K Date: Fri Sep 2 15:59:40 2011 +0530 performance/io-threads: treat -ve pid as request for fop with least priority Change-Id: Ib6730a708f008054fbd379889a0f6dd3b051b6ad BUG: 3502 Reviewed-on: http://review.gluster.com/335 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 550148f3bb3505335909cde9e937c2362a1e67e3 Author: Pranith Kumar K Date: Fri Sep 2 08:50:48 2011 +0530 cluster/afr: Make data selfheal trigger to be configurable. By default, lookup triggers data self-heal but that is not the preferred way of operating replicated volumes. We would like the data self heals to be triggered in open instead. Number of back-ground self-heals allowed is 16 and lookups block until self-heal is completed. We want to prevent blocking in fops. We can not make lookups independent of self-heal frames because when there are gfid conflicts the decision of which file is correct is determined in self-heal phase. So in afr, lookup self-heal is going to guarantee name space consistency and open/fd fops will take responsibility for data consistency, these are non blocking. The user needs to set the option cluster.data-self-heal "open" for this behavior. Change-Id: If9463cdb9ebac114708558ec13bbca0270acd659 BUG: 3503 Reviewed-on: http://review.gluster.com/334 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4d2afaae2f3c42b710acf8c7ebdb4b50d502b813 Author: Anand Avati Date: Wed Aug 31 22:57:34 2011 +0530 posix-acl: configurable super user ID In configurations with a uid mapper, super user ID could be mapped to a non-zero value. Hence making it configurable in access control would be necessary for proper super-user semantics. Change-Id: I51e8e0395680e9b96a99657a0af547659bd9affe BUG: 2815 Reviewed-on: http://review.gluster.com/332 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c83856797fd55fa59c885ba5efd3ac912fcb9a96 Author: Anand Avati Date: Tue Aug 16 12:56:21 2011 +0530 cluster/afr: eager locking of FD writes This patch is a change in the way write transactions hold a lock which optimizes the case of sequential writes from a single writer. Lock phase of a transaction has two sub-phases. First is an attempt to acquire locks in parallel by broadcasting non-blocking lock requests. If lock aquistion fails on any server, then the held locks are unlocked and revert to a blocking locked mode sequentially on one server after another. The change in this patch is to make the initial broadcasting lock request attempt to acquire lock on the entire file. If this fails, we revert back to the sequential "regional" blocking lock as before. In the case where such an "eager" lock is granted in the non-blocking phase, it gives rise to an opportunity for optimization. i.e, if the next write transaction on the same FD arrives before the unlock phase of the first transaction, it "takes over" the full file lock. Similarly if yet another transaction arrives before the unlock phase of the "optimized" transaction, that in turn "takes over" the lock as well. The actual unlock now happens at the end of the last "optimzed" transaction. Any operation which arrives before the unlock phase of the previous transaction is a potential candidate to become an "optimized" transaction. In cases where the previous transaction had aquired lock as a "regional" blocking lock, and the next transaction comes in before its unlock phase, then it would not be an "optimized" transaction. Implied assumption ------------------ Since two or more transactions can now operate within the same large lock, there is a possibility that overlapping transactions can arrive at oppoosite orders on the servers. However in the larger picture this is not possible as write-behind already ensures that no two overlapping writes on an inode are in transit at the same time. Overlapping writes across clients are not a problem as they compete at locks anyways. Theoretical benefits and potential harms ---------------------------------------- In case of a single writer: The benefits are large for sequential writes. In the best case the entire file write can happen with just one lock and unlock per server, provided writes are coming in fast enough and getting pipelined by write-behind soon enough (which is usually the case). If the writes are not coming in fast enough, then the optimization "kicks in" for only those subsets of writes which are close enough to get "piggybacked". For random writes the benefits are the same as well. In any case the overall performance is better than or equal to the performance without this optimization for a single writer. In case of multiple writers: When multiple writers are not writing concurrently, there is no negative performance impact. When multiple writers are writing concurrently to the same region, there is no negative impact either, as they were previously getting arbitrated at the locks translator too. In the case of multiple writers writing to different regions concurrently, there will be an increased number of "failovers" from failed parallel non-blocking to sequential blocking regional locks. This above "worst case" has a simple workaround that as soon as we detect > 1 open-fd-count in lookup xattr, we can disable this optimization on those fds. Beneficial side-effects ----------------------- There is another similar optimization in AFR for changelogs which goes by the name of "changelog-piggybacking". That works in a similar way where pending flags get 'taken over' or 'piggybacked' by the next transaction if its 'pre-op' phase kicks in before the 'post-op' phase of the previous transaction. It has been observed that this changelog-piggybacking optimization gives a saving of about ~55% savings of xattr calls hitting the wire, measured across various types of network interfaces. The side effect of this eager-lock optimization is that it gives an almost 100% saving of xattr calls by making the optimistic-changelog work much more efficiently as it gives a wider overlap of the xattr phases of two consecutive transactions. Change-Id: I41c02eb3b64c14c68ef66a344610ec3f024cd59d BUG: 3409 Reviewed-on: http://review.gluster.com/240 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 73ae561db9054c67ce120eb87fa955943bdc06bd Author: Rajesh Amaravathi Date: Tue Sep 6 17:29:31 2011 +0530 storage/posix: posix getxattr log enhancement Now the key is logged with getxattr failure. Change-Id: I96a9234cf138ae0922dc403e2fddcd4df0d89df8 BUG: 3283 Reviewed-on: http://review.gluster.com/373 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d7b1463bf35a9c5ac30456d143cb4b67a03a93a6 Author: Rajesh Amaravathi Date: Mon Aug 29 10:30:56 2011 +0530 mount/nfs: Gluster nfs crashes with subdirectory mount Glusterfs used to crash trying to dereference a NULL pointer. Also, in mnt3_resolve_export_subdir, volume name was prefixed to sub directory exported, resulting in mount fail of sub directory. Fixed both issues. Change-Id: I746f0c244b4cbf03033d73ac3e40518762d76385 BUG: 3481 Reviewed-on: http://review.gluster.com/323 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 51138e1cbf602e16011768040440cf829367c40c Author: Pavan T C Date: Wed Sep 7 18:05:57 2011 +0530 Save the mode flags set by the application when ACLs are in use While inheriting the ACLs from a directory that has default ACLs, make sure that the mode flags set by the application are saved. It is required to inherit only the Read, Write and Execute permissions while leaving the others viz. setuid, setgid and sticky bit untouched hence honouring the requests made by the application during create operations (mknod, mkdir et al). For a description of the problem, root cause and evaluation, refer: http://bugs.gluster.com/show_bug.cgi?id=3522 Change-Id: I994077fb321a35d8254f0cc5a7de99a17ec40c47 BUG: 3522 Reviewed-on: http://review.gluster.com/368 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 7d4560cbcdcae0d74cf486c544d5eb58775da51f Author: Csaba Henk Date: Wed Aug 10 05:02:43 2011 +0300 gsyncd: do the homework, document _everything_ Change-Id: I559e6a0709b8064cfd54c693e289c741f9c4c4ab BUG: 1570 Reviewed-on: http://review.gluster.com/319 Tested-by: Gluster Build System Reviewed-by: Kaushik BV commit d39a7fad09a6b4abcb23d132fd7dfdf0d440e928 Author: Shehjar Tikoo Date: Sat Sep 3 14:51:45 2011 +0530 nfs3: Resolve entry vs. hash conflict at same dir depth Intro Note ========== The current code in hard fh resolution takes the first-match approach, i.e. which ever dirent either matches the hash or matches the gfid first is the one chosen as the result for the next step of fh resolution. In the latter case, i.e., dirent matches the gfid, we the next step is to conclude the fh resolution by returning the entry whose gfid matched. In the former, i.e., the hash matches the dirent, we choose the hash-matching dirent as the next directory to descend into, for searching the file to be operated upon. Problem ======= When performing hard fh resolution, there can be a situation where: o the hash of the primary entry,i.e. the entry we're looking for and the hash of another sibling directory, match. Note the use of "sibling", meaning both the primary entry and the hash matching one are in the same directory, i.e., their filehandle.hashcount will be same. o the sibling directory is encountered first during the dir search. Because of the current code described in "Intro", we'll end up descending into the sibling directory even though the correct behaviour is to ignore this and wait till we encounter the primary entry in the same parent directory. Once we end up descending into this sibling directory, the directory depth validation check fails. The check fails because it notices that the resolution is attempting to open a directory that is deeper in the fs tree than the file we're looking for. When this check fails, we return an ESTALE. So basically, a false-positive results in an estale to Specsfs. This is not a theoretical situation. Me and Avati saw this on specsfs test where sfs created terabytes-sized file system for its tests. The number of files was so huge in a single directory that the hashes of two entries ended up colliding. Change-Id: I4a6df11d326a67a507b1cd716c2c8e00b5a858a4 BUG: 3510 Reviewed-on: http://review.gluster.com/357 Tested-by: Gluster Build System Reviewed-by: Shehjar Tikoo commit 694ef54978f382507a5127ce66da7770929ba2c2 Author: Jeff Darcy Date: Wed Sep 7 20:03:24 2011 -0400 Eliminate many "var set but not used" warnings with newer gcc. This fixes ~200 such warnings, but leaves three categories untouched. (1) Rpcgen code. (2) Macros which set variables in the outer (calling function) scope. (3) Variables which are set via function calls which may have side effects. Change-Id: I6554555f78ed26134251504b038da7e94adacbcd BUG: 2550 Reviewed-on: http://review.gluster.com/371 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 81530d227deb52af38c7df770aef2200b9de539f Author: Amar Tumballi Date: Wed Sep 7 20:46:20 2011 +0530 glusterd: send the 'stripe-count' value to peer during handshake without which, if a peer is added after volume of type 'stripe-replica' is created, it won't be reflected in the newly added peer. Change-Id: I77ee6aa3f33994bd4c6dbfefd853cc7e7491c1db BUG: 3523 Reviewed-on: http://review.gluster.com/369 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 34be428d5640a0ad4c47a05ee3e716189b4a54ed Author: Amar Tumballi Date: Thu Aug 25 17:51:18 2011 +0530 glusterd: fail the 'peer probe' if the first connect attempt fails so 'gluster peer probe' command doesn't hang till timeout (120s), instead it will send the proper error msg to client. Change-Id: I398fa16d526f869f1d27eeb57aeb7ee4451fbecd BUG: 1852 Reviewed-on: http://review.gluster.com/342 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f0f3b040dfa062021d3a193e5a19c380eb5e908d Author: Amar Tumballi Date: Mon Aug 29 17:53:24 2011 +0530 modify to the way we used XDR definitions files (.x files) Earlier: step 1: copy the existing .x files to /tmp step 2: generate '.[ch]' files using 'rpcgen .x' step 3: check diff with the to the existing files, add only your part of changes back to the original file. (ignore other changes). step 4: there is another file to write wrapper functions to convert structures to/from XDR buffers, update it with your new structure. step 5: use these wrapper functions in the newly written procedures. step 6: commit :-| Now: step 1: update (mostly adding only) the .x file step 2: run '/extras/generate-xdr-files.sh .x' command step 3: implement rpc procedure to handle the request/response. step 4: commit :-) Change-Id: I219f9159fc980438c86e847c6b030be96e595ea2 BUG: 3488 Reviewed-on: http://review.gluster.com/341 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f78c8253d7fb75762effcf64683cbce10783a55b Author: Amar Tumballi Date: Sun Aug 28 12:53:12 2011 +0530 glusterfs protocol: bring in variable sized iobuf support is a step towards reducing glusterfs memory footprint. should also help a bit in overall performance. Change-Id: I074d5813602b2c960d59562e792b3dc6e43d2f42 BUG: 3475 Reviewed-on: http://review.gluster.com/322 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 10d49cf0878e96301ea366276e27e91b5527483e Author: Pranith Kumar K Date: Sat Sep 3 14:13:06 2011 +0530 cluster/afr: Prevent double big lock when data self-heal loops are not spawned The steps in normal data self heal: 1) take big lock by self-heal frame. Get the xattrs/stat to decide source, sink information. 2) spawn loop frames which perform self-heal by taking small locks on the file. Every time a new lock is taken and the old lock is released. 3) Before releasing the final small lock a big lock is taken by the self-heal frame, and unlock on small-lock. Erasing of the pending xattrs happen then the big unlock happen and that is the end of the data self-heal. When a data self-heal is needed for a file and the fop that triggers the self-heal is open with O_TRUNC. Fuse sends open then an explicit truncate for this. Open triggers the self-heal but by the time it tries to spawn the loops the file size is truncated to 0, so no loops are formed. These are the steps: 1) Take big lock by self-heal frame. Get the xattrs/stat to decide source, sink information. 2) loop frames are not spawned. The big lock is not released. 3) One more big lock is taken by the same self-heal frame, Erasing of the pending xattrs etc happen, now it does two big unlocks, but after the first unlock, the information on which the locks were performed is forgotten, so the next unlock becomes a no-op. So there is a stale big lock on that file preventing further writes. As a fix, if the loops are not spawned, use the previous big lock to perform the rest of the operations needed in completing the data self-heal. No need to have one more big lock. Change-Id: Id03171269594e447b2b6d1331e362d83bd1e3430 BUG: 3506 Reviewed-on: http://review.gluster.com/339 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit f1fec244b043fc74999692b181d321827daf8677 Author: Pranith Kumar K Date: Wed Aug 31 10:06:45 2011 +0530 cluster/afr: Bring down the self-heal window size to 1 This is brought in an effort to be nice to the system resources when self-heal is in progress. Change-Id: I123f1eb4d8000613a35c0117f0aa27f926f3a921 BUG: 3503 Reviewed-on: http://review.gluster.com/333 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur Reviewed-by: Anand Avati commit 992e580df4a38bb96b0114a3b033d0dc0b8425b7 Author: Amar Tumballi Date: Tue Aug 23 10:25:35 2011 +0530 mgmt/glusterd: code re-structuring created new files per operations, (or group of operations) Change-Id: Iccb2a6a0cd9661bf940118344b2f7f723e23ab8b BUG: 3158 Reviewed-on: http://review.gluster.com/281 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 0504c5c24a8d8329321b9d5cdbc873c0fda32935 Author: Krishnan Parthasarathi Date: Wed Aug 3 11:30:20 2011 +0530 glusterd: Removed local cli lock This change contains, - removal of the local cli lock used to serialize cli ops to a glusterd. - glusterd's state-machine can handle competing 'lockers' with guaranteed progress. - flush cluster lock on 'owner' disconnecting and as 'owner', send unlock to all on first peer disconnect. Change-Id: I25961436b0790b4196f2b3438b105c37279399ad BUG: 3320 Reviewed-on: http://review.gluster.com/123 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit e795fcf2895496ad5412bfd4ac50a358567ecabb Author: Pranith Kumar K Date: Thu Aug 25 14:46:52 2011 +0530 performance/io-threads: Introduce new priority and priority-thread-limits Change-Id: I7b4e7c467b833bc5896808e6e1d1b1a0322c4fdb BUG: 3483 Reviewed-on: http://review.gluster.com/318 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit cd567c063ec25b280d3fb5686a69b068c2d6d6df Author: shishir gowda Date: Wed Aug 10 16:58:38 2011 +0530 mem-pool: Make mem-pool ptr avialable in ptr The header of the ptr returned from mem-pool will now store the mem-pool ptr it belongs to. mem_put will now take only the pointer to be freed. Also, changing MALLOC call to GF_CALLOC in mem_get when we run out of entries in mem-pool. This also will have the header information saved. Change-Id: I3de182663a7f5b49c9e9425e9531775b70bdff67 BUG: 3390 Reviewed-on: http://review.gluster.com/205 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 9c68f3b53ffd27ea03e90da883c43e84bf94dd15 Author: Raghavendra Bhat Date: Wed Aug 24 12:57:18 2011 +0530 rdd: changes in rdd.c and whitespace cleanup Change-Id: Ic117c6a3f9234a0181db1a106ef8a6574248f010 Reviewed-on: http://review.gluster.com/313 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b617b89372f9f6cb5031dfb8513029a7fa490f73 Author: Csaba Henk Date: Fri Jul 15 02:45:18 2011 +0200 gsyncd: refine command invocation Use subprocess module instead of os.spawn* / ad-hoc fork/exec. With this, we do now: - close uneeded files in children - watch childrens' stderr: - have a thread which collects childrens' stderr into a ring buffer (so that stderr pipe doesn't get stuffed) - on command failure show stderr - distinguish between rsync exit values, tolerate only partial errors - if connection is broken to slave, show ssh/slave gsycd's stderr Change-Id: Ia92f57b5bdfa47f8c44375c50cf279006a0bf69b BUG: 2946 Reviewed-on: http://review.gluster.com/85 Tested-by: Gluster Build System Tested-by: Kaushik BV Reviewed-by: Kaushik BV commit f9b09cd2be47c044c1396e70724a427ef46f8b81 Author: Csaba Henk Date: Mon Jul 25 11:53:55 2011 +0300 glusterd: do preparative gsyncd invocations with proper logging Change-Id: I28de4cce140faf1b35ecdc5cbd408f21c9926341 BUG: 3231 Reviewed-on: http://review.gluster.com/96 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit f16a44f94f76e6c677cee37090d059e8bb5443f5 Author: Kaushal M Date: Fri Aug 19 15:07:36 2011 +0530 cli: "profile info" output improvements Some changes to profile info output. Change-Id: I94a4bec1ca1c0670b3d9643f8321683b59c665aa BUG: 3028 Reviewed-on: http://review.gluster.com/260 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 9848ac8bf7a6854e9d4dee2dcb53621c67b33d6e Author: Raghavendra Bhat Date: Wed Aug 24 12:49:48 2011 +0530 features/locks: avoid using reqlock to prevent race Change-Id: Id8613f9641f748f996062342878070ba8fb27339 BUG: 2473 Reviewed-on: http://review.gluster.com/312 Tested-by: Gluster Build System Reviewed-by: Pranith Kumar Karampuri commit 7f459fc826346c33a58412fb45a6781c5fd1cc0d Author: Csaba Henk Date: Thu Jul 7 02:02:50 2011 +0200 glusterd / geo-rep: in status, display slave URLs in simpler normalized form Ie. instead of writing out the fully expanded canonical URL like ssh://root@192.168.3.4:gluster://127.0.0.1:bar we just display ssh://root@starship::bar Change-Id: I2bd70650cbc9973d925f652bccb163d391e406c9 BUG: 2536 Reviewed-on: http://review.gluster.com/79 Tested-by: Gluster Build System Reviewed-by: Kaushik BV commit b827cdb230b8253c53d646793dd8f21df8202d41 Author: Raghavendra Bhat Date: Tue Aug 23 13:47:41 2011 +0530 xlator: fix for the volume set help crash Change-Id: I1649ed61b13b935d714ca024e6883f3903c5edeb BUG: 3460 Reviewed-on: http://review.gluster.com/310 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 6e02c879ad847b760a05f9afd3fddc9f152bda23 Author: Raghavendra G Date: Tue Aug 23 12:32:36 2011 +0530 performance/stat-prefetch: fix memory leak Change-Id: I84580e297ba93a9a093c2e3432ea52e3c0db4a1a BUG: 3467 Reviewed-on: http://review.gluster.com/307 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit dd996d529d155143e3ad49dc3b30461d9eb3ff43 Author: Amar Tumballi Date: Tue Aug 23 11:44:05 2011 +0530 cluster/distribute: unwind the proper dict in getxattr_cbk without which, quota would get confused about the total size Change-Id: I0fb822ee67e3c1585f783ae35292fe71c47ee249 BUG: 3421 Reviewed-on: http://review.gluster.com/304 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 601f5725a0a2e4855d9a4a952709e5c0cadbd846 Author: Junaid Date: Mon Aug 22 17:32:08 2011 +0530 features/marker-quota: Fix invalid reads in readdir_cbk. Change-Id: Icc1e9dc039f1f2d7ee94c689779a715a69d373fa BUG: 3389 Reviewed-on: http://review.gluster.com/296 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d9ead57226faf82f3f1375a29e06d348625ba905 Author: Vijay Bellur Date: Mon Aug 22 14:55:09 2011 +0530 mgmt/glusterd: Initialize local variable in volgen Change-Id: I84b4f7c9c2787334ce67e5c3e0534953b691c8e0 BUG: 3460 Reviewed-on: http://review.gluster.com/295 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat commit 4f9396545ba9c91d4bebfc81148c0082237141f4 Author: Pranith Kumar K Date: Mon Aug 22 13:54:15 2011 +0530 cluster/afr: Perform flush on all the children involved in self-heal Change-Id: I66362a3087a635fb7b759d7836a1f6564a6a7fc9 BUG: 3456 Reviewed-on: http://review.gluster.com/294 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b9ae4b19da2898fa610d1bfd4b9e5829acabb121 Author: Pranith Kumar K Date: Mon Aug 22 12:14:22 2011 +0530 cluster/afr: Change definition of stale child The code is checking for priv->child_up[i], which can change while the fop is in progress. Since pending[child][id-of-transaction] alone is enough to tell if the child became stale or not, use just that. Change-Id: I494bf02cca66f4fd41526195fafce86a202c6bd1 BUG: 3455 Reviewed-on: http://review.gluster.com/293 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b249ff7505392ae5cac1421a6a44310800d26feb Author: Pranith Kumar K Date: Mon Aug 22 11:59:11 2011 +0530 cluster/afr: Paused fop should not continue with fop Change-Id: Idce22a6266c354e327d5d717715d2e62533eec58 BUG: 3448 Reviewed-on: http://review.gluster.com/292 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit b6e3e9c480be4226925b51c5e9ee0c368aa94a6d Author: Raghavendra Bhat Date: Sun Aug 21 18:53:04 2011 +0530 features/marker: changes in marker to avoid race conditions and corruptions Change-Id: I38ddfab200d59dd4c8e9f9dd964a98f3d7aa7ab7 BUG: 3389 Reviewed-on: http://review.gluster.com/289 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 08e8c966869b091fb4df8bfc8cadc37cb40719a5 Author: Vijay Bellur Date: Sun Aug 21 18:21:21 2011 +0530 protocol/client: Changes to be benign to replace-brick Change-Id: Ic227781760a5f6dbf8aad69a19f90e45d4aaec13 BUG: 3415 Reviewed-on: http://review.gluster.com/288 Reviewed-by: Krishnan Parthasarathi Tested-by: Gluster Build System commit af32ab6bc031347289201f33f496b6b713f7a3f6 Author: Vijay Bellur Date: Sun Aug 21 17:46:57 2011 +0530 debug/io-stats: Handle loglevel in init Change-Id: I5aa6ee7509a8f730ca64e2f7bada56d502785a6c BUG: 3415 Reviewed-on: http://review.gluster.com/287 Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System commit 5ace31ac2160b216a396c0d8c992fa19dbad6f47 Author: Krishnan Parthasarathi Date: Thu Aug 18 18:20:24 2011 +0530 glusterd: replace-brick status was not 'shared' with peer. Change-Id: Ia2d89fd919b077232a37debc2aebe1bc72150856 BUG: 3432 Reviewed-on: http://review.gluster.com/285 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 45acdcbbdc2de50c59a8c3e21884a02902e6571f Author: Pranith Kumar K Date: Sun Aug 21 16:58:15 2011 +0530 cluster/afr: fop should not continue if it is paused, until resumes Change-Id: Ie026ebed98cf5ff75ae1a13437d29f67d0e0254a BUG: 3448 Reviewed-on: http://review.gluster.com/286 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat Reviewed-by: Vijay Bellur commit aa07e855859d6a175fccb309ec3158e6ca894b0c Author: Vijay Bellur Date: Sun Aug 21 16:34:19 2011 +0530 debug/io-stats: Handle log-level properly. Change-Id: I8e5b8841705b161068bdb2ccd2ac119d6b250c88 BUG: 3415 Reviewed-on: http://review.gluster.com/284 Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System commit 22b5de922b7d4ce57db48b3ad518e98a9c91f4ee Author: Pranith Kumar K Date: Sun Aug 21 15:56:33 2011 +0530 cluster/afr: set frame local Change-Id: I861b3c4494735b0ba6e038cdc39c50b9866747a8 BUG: 3448 Reviewed-on: http://review.gluster.com/283 Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 350ae611cad29a0ad95d3e209a858d693579c1b2 Author: Vijay Bellur Date: Sat Aug 20 19:26:05 2011 +0530 rpc/xdr: Fix for Solaris build failure Change-Id: I4704dfad655a79afb87ab275ba09413f785a97a4 BUG: 3446 Reviewed-on: http://review.gluster.com/280 Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat commit 1af420c700fbc49b65cf7faceb3270e81cd991ce Author: Pranith Kumar K Date: Sat Aug 20 15:48:27 2011 +0530 cluster/afr: Perform self-heal without locking the whole file Change-Id: I206571c77f2d7b3c9f9d7bb82a936366fd99ce5c BUG: 3182 Reviewed-on: http://review.gluster.com/141 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 2ebacdfdd3c39bf2d3139cb7d811356758a2350a Author: Vijay Bellur Date: Sat Aug 20 18:26:08 2011 +0530 mgmt/glusterd: Correct generation of nfs options in volfile Change-Id: If3db4f81215271072030d7119081de5d8b1b3d78 BUG: 3414 Reviewed-on: http://review.gluster.com/279 Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System commit fdb7636bd719e560d9d8c0895a3b80bf3973b9d0 Author: Amar Tumballi Date: Sat Aug 20 16:11:02 2011 +0530 while validating options, make sure memory accounting is init()ed. Change-Id: Ifad5827c6b022de7d84e081ce77effda0c245a13 BUG: 3415 Reviewed-on: http://review.gluster.com/277 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 80694bb5ff2f61cfd6e2bb7908add6c853490407 Author: krishna Date: Sat Aug 20 14:32:35 2011 +0530 if nfs.port is not configured init the transport.socket.listen-port to GF_NFS3_PORT Change-Id: I6c0db600ba2010b0a0272f58b16c4955b4b570f2 BUG: 3308 Reviewed-on: http://review.gluster.com/273 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 64b12d90f39dd474a1a403594cf3f4598f21cd25 Author: Vijay Bellur Date: Sat Aug 20 15:52:27 2011 +0530 xlators/nfs: Fix a typo in option description Change-Id: I626893fd16094742869d4abfa488b66924c2796e BUG: 3445 Reviewed-on: http://review.gluster.com/276 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 7fe3d3fe2b0bec8085b15fb4d9db8fdead826d57 Author: Vijay Bellur Date: Sat Aug 20 15:18:09 2011 +0530 libglusterfs: Fix a crash in gluster volume set help Change-Id: I585e8e685f5c23b6fa632ef708adf2e349ba6704 BUG: 3415 Reviewed-on: http://review.gluster.com/274 Reviewed-by: Raghavendra Bhat Tested-by: Gluster Build System commit 7c6cf654700fb05502591e84b2000bb5230283e2 Author: Csaba Henk Date: Fri Aug 19 13:51:14 2011 +0200 cli: remove bogus assertion Since 86c818a9 (cli: taking my revenge ...) we cannot assert an exact match for the op/subop keywords in the followup parser functions. That is, # gluster vol stat foo is a valid invocation. Change-Id: I3f7f410f64f440744141f458886e4bba8ceeca17 BUG: 3439 Reviewed-on: http://review.gluster.com/268 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d9c6513289ca33204cdc110112ff8e45cbc8970a Author: Pranith Kumar K Date: Fri Aug 19 15:56:49 2011 +0530 cluster/afr: Update fresh_children in lookup if no other ops in progress If write/truncate fails we should remove the child that failed the fop from the fresh children. The previous code assumes that the children that succeeded the fop are fresh children, which is wrong. Fixed that in this patch. Change-Id: I1e6e21e20faea00516a0fdd2e95f2d7e9cf9076d BUG: 3411 Reviewed-on: http://review.gluster.com/263 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 5e89fda5180e66b1757bc620dfdb5701ce4d43f1 Author: Anand Avati Date: Fri Aug 19 22:49:41 2011 +0530 options handling: remove missing options check in reconfigure last minute change broke things. undo'ing damage. Change-Id: I330cf819b03e09f80d609d580d8b4c3497a98bbf BUG: 3415 Reviewed-on: http://review.gluster.com/271 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit c4dd6f5771e9a530c90cb6e23d6f43a7224fb654 Author: Anand Avati Date: Fri Aug 19 15:19:44 2011 +0530 smoke-test.sh: script used by gerrit as part of pre-commit test Change-Id: Idc3be3e22cca5fc623b27c2f500f59785cbd332b BUG: 3234 Reviewed-on: http://review.gluster.com/262 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit dd2c197c1d5d5942a65c860997ec1d5793ef249f Author: Anand Avati Date: Fri Aug 19 14:56:13 2011 +0530 option validation: further fixes fixes in option handling changes Change-Id: I0a44cdb088e3f08cd43d583a580736d0903fa88c BUG: 3415 Reviewed-on: http://review.gluster.com/261 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 0143a2ef653d0f7a337c8220f127655dadbca942 Author: Vijay Bellur Date: Thu Aug 18 23:19:22 2011 +0530 mgmt/glusterd, cli: Introduce gluster volume status Change-Id: Iea835b9e448e736016da2e44e3c9bfff93f2fa78 BUG: 3439 Reviewed-on: http://review.gluster.com/259 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d2849bd349081b332540713cfeaa561f57356b2a Author: Anand Avati Date: Thu Aug 11 16:08:36 2011 +0530 xlator options: revamp xlator option validation/reconfigure code - move option handling to options.c (new file) - remove duplication of option validation code - remove duplication of gf_log / sprintf - get rid of xlator_t->validate_options - get rid of option validation in rpc-transport - get rid of validate_options() in every xlator - use xlator_volume_option_get to clean up many functions - introduce primitives to init/reconfigure option types Change-Id: I51798af72c8dc0a2b9e017424036eb3667dfc7ff BUG: 3415 Reviewed-on: http://review.gluster.com/235 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 6073fc29bf79fad0b0a3ae423d637ded39a00a3a Author: krishna Date: Wed Aug 17 12:22:49 2011 +0530 do rpcsvc_init() after we fill nfs_state structure and add to nfsx->options keys for allowing insecure client ports. Change-Id: Iae755d1460f2c7296fc7980b5257afcf778e7767 BUG: 3296 Reviewed-on: http://review.gluster.com/247 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit d41eda762e4e98d95d3c80dd849a11e6aec11b56 Author: Anand Avati Date: Thu Aug 18 11:27:06 2011 +0530 rpc-clnt: fix merge error of http://review.gluster.com/248 cherrypicked patch did not have the logic to reset port number to reconnect to glusterd. Change-Id: I78c903d5a28626f83b5024bd323e77b5f159e374 BUG: 3409 Reviewed-on: http://review.gluster.com/254 Reviewed-by: Amar Tumballi Tested-by: Gluster Build System commit c0180cc22f5f52f5776c74a6d1ae90100dbb5087 Author: Kaushal M Date: Wed Aug 10 17:57:04 2011 +0530 glusterd: fix for volume stop causing inconsistent volume status This fixes problem caused by race between glusterd and glusterfsd occuring when they try to unlink pidfile during volume stop, which led to the volume being stopped, but the status of the volume remained in started state. Change-Id: Ia99bb1a1fc6c78db138211538dfd10c577e82917 BUG: 3147 Reviewed-on: http://review.gluster.com/206 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit cef6d3596fcbda71c19e66c5a6de502847aece9e Author: Anand Avati Date: Fri Aug 12 00:46:50 2011 +0530 rpc-clnt: perform XDR encoding in unlocked region Change-Id: Ia11c3ced4bec5959a5f0d8fcd4c6070b2ead220a BUG: 3409 Reviewed-on: http://review.gluster.com/248 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2902b6f325d4bbb6cd947cee0301bf75d9634196 Author: Venky Shankar Date: Wed Aug 17 15:19:05 2011 +0530 allocate extra bytes (for \0) when calling realloc We use strcat to concat pathinfo strings. strcat appends a \0 at the end. Therefore allocate extra bytes for the same to avoid asserts being hit during gf_free call Change-Id: I582f5858e7375a5bacfc5c702c612ee09c3bb355 BUG: 3413 Reviewed-on: http://review.gluster.com/249 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 7d15ee5ee37384e40600306e3efbc037ff6f9e9b Author: Anand Avati Date: Wed Aug 17 04:18:48 2011 -0700 Revert "Make sure glusterd and glusterfsd use the same address family" This reverts commit 1dade36a6dfc6cae5559d5139f6b733e1b6fded1 This commit breaks glusterd. The insertion of --xlator-option= in between --brick-port and fails command line validation during glusterfsd start. Change-Id: I40186ca89d1d16cf798404747771353b1f1a3e1d Reviewed-on: http://review.gluster.com/251 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 61a9ed994d817ffe9aab4b5adb31ffcb6ca6820c Author: Anand Avati Date: Wed Aug 17 04:16:59 2011 -0700 Revert "Remove white spaces" This reverts commit 6ab425e4f3d34b1467f694ada9a36eacfac9bf3c Dependency revert for http://review.gluster.com/229 Change-Id: I7c4fcc45a6c25aedf4f06cbdeedc1fecbe424f45 Reviewed-on: http://review.gluster.com/250 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b1b952d62d452641cd17ab5bf1a386cc4a05b17b Author: krishna Date: Wed Aug 17 12:48:46 2011 +0530 do not init nfs->override_portnum to GF_NFS3_PORT Change-Id: I7dc26b64a177ce5d30352cf7c531f38517c0368a BUG: 3308 Reviewed-on: http://review.gluster.com/155 Tested-by: Gluster Build System Reviewed-by: Shehjar Tikoo commit 12895212d64e2f209190f389a92be7f5e67ec84e Author: Emmanuel Dreyfus Date: Wed Aug 17 06:19:05 2011 +0200 Remove white spaces Change-Id: I646c0c8e70268de6a20bb23dc3834ac6f5d2bbf2 BUG: 3422 Reviewed-on: http://review.gluster.com/245 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 02f45250af3fcb58a309e4089b64e2b147b1b265 Author: Emmanuel Dreyfus Date: Fri Aug 12 16:20:14 2011 +0200 Make sure glusterd and glusterfsd use the same address family NB: This was heavily tested on 3.2.2, but code has changed a lot in the area. This patch itself is untested. Change-Id: Ie472f04b0804276c2d8a9efc5c96106c33029498 BUG: 3422 Reviewed-on: http://review.gluster.com/229 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 023969d911b90420bd1733bae57d04e24dee5eda Author: Venky Shankar Date: Tue Aug 16 11:32:35 2011 +0530 adjust allocated length to memory overrun fix size of the allocated length is incorrectly calculated which could cause memory overrun while filling the buffer Change-Id: I4fbdbd1fff937ca15bae9f634ef5757dda52caa8 BUG: 3413 Reviewed-on: http://review.gluster.com/236 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit a0071bdf2a0f73fd17ac769298ed65b245f0607c Author: Pranith Kumar K Date: Sat Aug 13 21:52:35 2011 +0530 cluster/afr: read_child should be >= 0 Change-Id: I447fb6a93cdd77de322cd5ded30673411c4cf79e BUG: 3251 Reviewed-on: http://review.gluster.com/233 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit e618c1b59debbb9184874a06cbc64b8ac846a0d3 Author: Emmanuel Dreyfus Date: Fri Aug 12 09:12:27 2011 +0200 - Use linkat(2) instead of link(2) so that linking to symlink work on non Linux systems - Also use mkfifo to create FIFO on NetBSD: it does not wotk with mknod Change-Id: I19ffd22b4d79009ef5f9d4a50fc6dd556c3c3ff4 BUG: 2923 Reviewed-on: http://review.gluster.com/226 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 53da3edbe5b43a994cc916b6571563491a8a414b Author: Emmanuel Dreyfus Date: Fri Aug 12 12:00:49 2011 +0200 POSIXly correct: \n replacement is GNU sed specific Change-Id: I5e4ca551b60477d454964e568209ad06f21cc64e Reviewed-on: http://review.gluster.com/227 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit abe7843ca6faa03a9b6e1ece3fb85d4c5b02580a Author: Emmanuel Dreyfus Date: Fri Aug 12 09:17:44 2011 +0200 Allow georeplication for NetBSD Change-Id: Id8d62f4f83255c67a5aa615aed23ba44c182290e BUG: 2923 Reviewed-on: http://review.gluster.com/220 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c5d7fa2bf4c766200971cfbb877d4a25b3cb32b0 Author: Emmanuel Dreyfus Date: Fri Aug 12 06:46:15 2011 +0200 Build fix for NetBSD Change-Id: Icb0163d61bfbd3bad520c06a655f80ec05fc3fb2 BUG: 2923 Reviewed-on: http://review.gluster.com/214 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 22105b3c741a26f525e0b31bb3d880c1eaa05c30 Author: Emmanuel Dreyfus Date: Fri Aug 12 06:48:07 2011 +0200 Build fix Change-Id: I10dca7aee73df31f8b279591852d6ac19eab8ccc BUG: 2923 Reviewed-on: http://review.gluster.com/228 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 139e03445e590911dbf00f30b0cfc005ee8a106b Author: Emmanuel Dreyfus Date: Fri Aug 12 06:34:54 2011 +0200 For systems where O_DIRECTORY does not exist, we defined it as 0, therefore ((flags & O_DIRECTORY) == O_DIRECTORY) is always true even if the flag is not set. Change-Id: Ie7837d521ea20b36ed70cf93c1763c226ff0e9f0 BUG: 2923 Reviewed-on: http://review.gluster.com/213 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 8a24e3179fc822e3ec59eaac8f6a2050b8dd9b40 Author: Emmanuel Dreyfus Date: Fri Aug 12 09:23:15 2011 +0200 Do not distribute UFS1 extended attribute backing store Change-Id: Ie05751aa8d96a2f7996843a914e1a66df2777eba BUG: 2923 Reviewed-on: http://review.gluster.com/222 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 5b6be1cdb500b375d673d9b2f2dfe7cfbda5d2b8 Author: Emmanuel Dreyfus Date: Fri Aug 12 10:26:47 2011 +0200 One more missing change :-/ Change-Id: I6eeaee73e7c9124a1959acb2fe47d5cad3a3baac Reviewed-on: http://review.gluster.com/225 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 9fa3aeadfe162483e01f285c7fd4d5f0fb712c18 Author: Emmanuel Dreyfus Date: Fri Aug 12 09:51:28 2011 +0200 Use bourne shell, fix error in previous commit Change-Id: Id2a304d5090eb2564c5d56ea260fa53b9b17d0d5 Reviewed-on: http://review.gluster.com/223 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit cc756d0075ff9829700cfc74d1bf3e2080523f65 Author: Emmanuel Dreyfus Date: Fri Aug 12 06:43:07 2011 +0200 sed -i is available from GNU sed, but is not portable. Output to a new file and move it to the original one on success instead. Change-Id: Ib23dd9becd035054e6490dcb4d64b3f9eff89bf4 Reviewed-on: http://review.gluster.com/212 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b4d166be42acd65d083a6e839f96989746b0ef46 Author: shishir gowda Date: Thu Aug 11 14:59:19 2011 +0530 RO: fix read-only xlator support broken due to worm xlator fix Change-Id: I7234909eecdc6af1b8482465f19d0490fcba94ad BUG: 3166 Reviewed-on: http://review.gluster.com/210 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 86999525240983dcbd3fe66eb40a0947730c695c Author: shishir Date: Tue Jul 19 16:02:12 2011 +0530 WORM: Write Once Read Many times xlator support This xlator will allow files to be opened for write in append mode only. Mount with --worm(glusterfs) or -o worm (mount) option to enable worm xlator Change-Id: I1be02fcf2aee2182ea2c66b514357918136fabeb BUG: 3166 Reviewed-on: http://review.gluster.com/23 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 5ce1b5c357d490f68ae89bfd3ce31326a81a1183 Author: Anand Avati Date: Wed Aug 10 23:11:36 2011 +0530 posix-acl: disable permission checks for fd based ops If write calls are coming in through an fd with O_RDWR or O_WRONLY flag then a permission check is unnecessary. However writes from NFS ideally need a "stateless" check in each call and this results in a permission failure due to the read-only mode (disregarding the FD's writeability). For now it is acceptable to disable write checks as almost always the NFS client would already be doing such basic access control. Also because the previous access-control translator (prior to posix ACL introduction) too was permitting writes and reads unconditionally. In fact the Linux KNFS server too assumes the NFS client would have done the permission check. Change-Id: I33e5de8911a87881f9341b8b92574780c2dfbeba BUG: 3388 Reviewed-on: http://review.gluster.com/208 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b58dc65f2ac305056a25a2177cee9a03cd1bdca2 Author: Pranith Kumar K Date: Tue Aug 9 12:30:19 2011 +0530 Change Copyright current year Change-Id: I2d10f2be44f518f496427f257988f1858e888084 BUG: 3348 Reviewed-on: http://review.gluster.com/200 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2153b8400bc05f1a9e10c7b650dd96a4617121f1 Author: Amar Tumballi Date: Tue Aug 9 11:37:38 2011 +0530 fix build issues in Mac OS X (10.6) Change-Id: Ifc6f156441f6545d579c3fac2fffca36fb395951 BUG: 3354 Reviewed-on: http://review.gluster.com/196 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit eddb2069f3b0e122cbd034328d87e08e737f4c4e Author: Amar Tumballi Date: Mon Aug 8 16:54:12 2011 +0530 fuse-resolve: prevent linking of inodes of different inode-table This can happen in deep_resolve_cbk, which happens after a graph switch. Root cause was because the graph change happened while a FOP was in transit and by the time the call came back, the active translator of fuse is now changed. Fix is to make sure the resolve operation happens on a given inode table, instead of taking the latest graph of fuse for each operation Change-Id: Idd6e2d5c2d5fc5d571f7a1fbc174e210babf8a2b BUG: 3355 Reviewed-on: http://review.gluster.com/195 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda Reviewed-by: Anand Avati commit 1b5a860f159916f0b289069ef3223e6fd754d36b Author: krishna Date: Thu Aug 4 15:51:28 2011 +0530 pass xlator pointer to rpcsvc_init() so that it can init svc->mydata to xlator Change-Id: Icfd95cc67400c16a951d6a9f922fbdc07f40c5b6 BUG: 3314 Reviewed-on: http://review.gluster.com/180 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 09ed778309cd4d4cdbc19ad7cbdcea3da7408a66 Author: krishna Date: Fri Aug 5 15:25:16 2011 +0530 NFS server: allow clients to connect from insecure (>1024) ports and support for both rpc-auth-allow-insecure and rpc-auth.ports.insecure Change-Id: I4e3fbfe37d6d3e8443d5b7b79faf6e364fdb87be BUG: 3296 Reviewed-on: http://review.gluster.com/178 Reviewed-by: Shishir Gowda Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d62c0abf597a2e77e3fb0cfa0d4598aedea64d33 Author: Vijay Bellur Date: Mon Aug 8 10:47:53 2011 +0530 Changes to EXCEPTIONS and included EXCEPTIONS in packaging Change-Id: I6c5c1536016489bf6b981356942901f69862393a Reviewed-on: http://review.gluster.com/188 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 0cf100b58c34b40eb7f35fa6913996539e0e3aa9 Author: Pranith Kumar K Date: Sat Aug 6 14:00:03 2011 +0530 LICENSE: s/GNU Affero General Public/GNU General Public/ Change-Id: I3914467611e573cccee0d22df93920cf1b2eb79f BUG: 3348 Reviewed-on: http://review.gluster.com/182 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4e116e2af014754e88170986820312e755617476 Author: Anand Avati Date: Sat Aug 6 18:00:49 2011 +0530 cluster/dht: clear local->cached_subvol when switching to do_fresh_lookup The presence of local->cached_subvol makes dht_lookup_everywhere_done behave as though it was a lookup on a file where linkfile needs to be recreated. In a fresh lookup, local->cached_subvol should be NULL. Change-Id: Ie6bd6ad536def03d970526d51e20c6daeb00922b BUG: 3317 Reviewed-on: http://review.gluster.com/187 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit bed8d32a52b2a58b905e91828c3155cba2544058 Author: Sachidananda Urs Date: Thu Aug 4 16:59:52 2011 +0530 Replace mktemp(3) with mkstemp(3). Man page states: Some implementations follow 4.3BSD and replace XXXXXX by the current process ID and a single letter, so that at most 26 different names can be returned. Since on the one hand the names are easy to guess, and on the other hand there is a race between testing whether the name exists and opening the file, every use of mktemp() is a security risk. The race is avoided by mkstemp(3). Change-Id: Ida95403b55024ecd07ef811a0835e01a9a7f092b BUG: 3331 Reviewed-on: http://review.gluster.com/163 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit b510ec361482a57c32b81aebb9d61a50676727f9 Author: Junaid Date: Thu Aug 4 15:47:15 2011 +0530 features/marker-quota: Performance improvement. With this patch new transactions will not be triggered if an updation is already in progress on that inode. Change-Id: I587385498c4b2af8bd9624ca41c60742c5ef2485 BUG: 2988 Reviewed-on: http://review.gluster.com/76 Tested-by: Gluster Build System Reviewed-by: Raghavendra G commit 22c6a64f851e844091b4060f20ee3c24b28c80f7 Author: Anand Avati Date: Fri Aug 5 14:52:01 2011 +0530 save even more trees make the build even more quiet. make anush even more happy by saving even more trees. Change-Id: I301aba34e4470805114989650a13f9fe35f42d35 BUG: 3255 Reviewed-on: http://review.gluster.com/176 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit b22ffeec89bbefd2d7b9fa62a25ede5545f1cbe6 Author: Anand Avati Date: Fri Aug 5 14:04:43 2011 +0530 save more trees make the build more silent Change-Id: Ied4c87c40af4b1f1034af4a13c1153d82883751b BUG: 3255 Reviewed-on: http://review.gluster.com/171 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 4b640273b05dec6923c13d14d4d40e136e2df99f Author: Louis Zuckerman Date: Fri Jul 29 18:03:41 2011 -0400 Provides an upstart job for glusterd on Ubuntu, solving Bug 3282 Mounting from localhost in fstab fails at boot on ubuntu when glusterd is started by debian initscript. A new directory, extras/Ubuntu, contains the new upstart job (glusterd.conf) and a brief README.Ubuntu file. This makes the upstart job available to package maintainers like the SysV initscripts are in extras/init.d. This has been tested on Ubuntu 10.10 Maverick. Change-Id: I6ccd06054e920cd6dc45dba4eb8ab89aa30f8b47 BUG: 3282 Reviewed-on: http://review.gluster.com/126 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 3780881e1bc4387f55e065508fb8fad371fc2b51 Author: Amar Tumballi Date: Mon Aug 1 16:20:12 2011 +0530 storage/posix: handle dictionary being NULL in a function also print a warning message if dictionary is NULL, while sending a mkdir request in distribute self-heal. Change-Id: Ib9cac6ed1635203802f089986f8acb1ce416265d BUG: 3215 Reviewed-on: http://review.gluster.com/136 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 3778cb5f668149d893ff6ae09d73878afc957133 Author: Raghavendra G Date: Thu Jul 14 01:41:48 2011 +0000 features/marker: log failures due to file not being present during quota updation transaction in DEBUG. Change-Id: I6733586ba56ed4fdc2abbef63c38b8c491f89819 BUG: 3143 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/32 Tested-by: Gluster Build System Reviewed-by: Mohammed Junaid Reviewed-by: Anand Avati commit 03aa9ecde933269282ca1043a16378e0d1e5cb49 Author: Amar Tumballi Date: Mon Aug 1 17:11:59 2011 +0530 glusterd rebalance: handle a race condition while starting a rebalance due to the race, there was a possibility of having two (or more) threads doing glusterd_defrag_start(), which would cause different thread to access same pointer, and at some point making it NULL, causing other threads to crash with SEGV. Change-Id: Id05b99dd6f33329027b8a07f1c8da5a65fd6dae9 BUG: 3295 Reviewed-on: http://review.gluster.com/138 Reviewed-by: Anand Avati Tested-by: Gluster Build System commit 5bd8f537da3fe570e481713a1c2c4ee6e88ac38e Author: shishir gowda Date: Tue Aug 2 15:30:06 2011 +0530 DHT rename: Recreate linkfile after unlink This is done, so that there is no gfid mismatch. Unlink the older linkfile if it exists, and recreate it with the correct gfid. Also removed unused rename related code. Change-Id: Ice0cdff51db786dafb1a019f7642c7d000e8c5f3 BUG: 2522 Reviewed-on: http://review.gluster.com/142 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit a08927b04e2d55edcb12be77128949798ed8f142 Author: Pranith Kumar K Date: Wed Aug 3 14:09:17 2011 +0530 mgmt/glusterd: Ignore case in friend find by hostname Change-Id: I8dabf07ebb30ec500d847c11d5c72c2d87d10239 BUG: 3309 Reviewed-on: http://review.gluster.com/145 Reviewed-by: Vijay Bellur Tested-by: Gluster Build System commit 8da4623f2274faa9e9d88f7d30babb9ea80fb141 Author: Sachidananda Urs Date: Fri Jul 29 16:26:03 2011 +0530 Remove redundant function `cli_path_strip_trailing_slashes'. Use cli_canonicalize_path instead, to remove trailing/duplicate slashes. Change-Id: Ie76267a4fa9ee9986cb36039afad4dfff830d5f8 BUG: 3183 Reviewed-on: http://review.gluster.com/124 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit df0a72d9c118c2a1146f2787eee6d5f0a58853f0 Author: shishir gowda Date: Fri Jul 29 16:36:27 2011 +0530 Variable IOBUF: Use variable iobuf for cli/glusterd/glusterfsd(mgmt) By using variable iobufs, xfer data size is no more limited to 128K (default). This helps in scaling. Change-Id: Iab453db9223d887306d150cd6fe0b1eae9c422cc BUG: 2472 Reviewed-on: http://review.gluster.com/13 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 76acac485b9f06f36d145b4c31fa6f4da3c70f52 Author: shishir gowda Date: Fri Jul 29 16:30:36 2011 +0530 IOBUF: Bring in variable iobuf support Rebasing Raghavendra's patch to master Change-Id: Ie7a0c9a7b8e73cfe48c4573a5153460d5126208e BUG: 2472 Reviewed-on: http://review.gluster.com/12 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 9867f3954138e795123b4b308e256e641c55f3ec Author: Anand Avati Date: Mon Aug 1 11:24:35 2011 +0530 glusterfsd: initialize sigset_t in sigwaiter Thanks to kkeithle@redhat.com for pointing out. Change-Id: I8167ffffddbdbc3dc09f7474bd834dbf4a49db9b BUG: 3280 Reviewed-on: http://review.gluster.com/129 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit a13fbaca0512cae3853a2372d0d8237eb24dd225 Author: Csaba Henk Date: Wed Jul 13 00:52:14 2011 +0200 gsyncd: do some basic sanitization on logs - exceptions raised by us will be logged as single-line error messages (full stack strace is shown only at DEBUG loglevel) - common/well understood exceptions are mapped to "user-parsable" error logs Change-Id: I75f1fb848483372364b2093878d9cfed576c9739 BUG: 2778 Reviewed-on: http://review.gluster.com/125 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 6c7a89321af50925fb53da378d996881a1907f31 Author: krishna Date: Wed Jul 27 18:16:59 2011 +0530 RPC unify code change Change-Id: Ibe18a2a63fd023ac57652c4dfc8ac8a69d983b83 BUG: 3112 Signed-off-by: krishna Reviewed-on: http://review.gluster.com/116 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 8b9cb1701f6365f7b4f5ed166f37020781f59467 Author: Csaba Henk Date: Tue Jul 12 03:38:01 2011 +0200 geo-rep: minor fixes Change-Id: I5c5211858bdb2bd28324818362d95edd97f94207 BUG: 2778 Reviewed-on: http://review.gluster.com/81 Tested-by: Gluster Build System Reviewed-by: Kaushik BV commit 8efbc829490420ebe75b42a1e0f268b950aaba91 Author: Rajesh Date: Fri Jul 29 13:18:20 2011 +0530 cli: Improve message in gluster top Removed "volume top successful" message. If top fails,"volume top unsuccessful" is displayed. If errstr is set, it is displayed. "No entries in list" messages deleted. Change-Id: I8ed35ea7db365b7af6b10833672fcab0e4e8751d BUG: 2722 Reviewed-on: http://review.gluster.com/121 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 9759d7e6d8f11ef6111fd6d313ced098efa2e38b Author: Raghavendra G Date: Tue Jul 19 15:09:13 2011 +0530 performance/io-cache: hold lock on ioc_inode whereever a page is being accessed/modified Change-Id: Ifc435c2e289b2a8ceeed2a091e555953af179936 BUG: 2939 Reviewed-on: http://review.gluster.com/21 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit dbc567ec9f97a540e6cab8006ba285ab62fc372c Author: Raghavendra G Date: Fri Jul 15 01:54:31 2011 +0000 performance/quick-read: Handle unwinding of frame corresponding to read fop properly, while validating cache. - there was a possibility of double unwind in case of errors. - use a new frame to do open in fd-based fops. In case of errors, qr_resume_pending_ops will be called to resume all the fops waiting on open. Hence if we use frame corresponding to fop (without creating a new one), there is a possibility of frame being freed by the time open would've returned to quick-read. Change-Id: Ie4cc19907f9d6362860bdb984779c8f4cf822332 BUG: 3168 Signed-off-by: Raghavendra G Reviewed-on: http://review.gluster.com/34 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit cfec0be455f388f4106e3df55b00c691631c40ea Author: shishir gowda Date: Tue Jul 26 16:35:10 2011 +0530 IO-threads: Support for loading io-threads xlator on client side New set option performance.client-io-threads added to enable/disable it. Default behavior is io-threads is off on client side Loaded only on fuse volume below io-stats. Change-Id: I13aea9a564d5270901c3c356fa6bede836c6a66d BUG: 3122 Reviewed-on: http://review.gluster.com/105 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Vijay Bellur commit bc16882a04baaac214f1b41598827038e8872363 Author: Junaid Date: Mon Jul 25 14:59:25 2011 +0530 features/marker-quota: Perform removexattr with frame uid and gid set to root. Change-Id: Iabd8ff835c76d828e4af50ce4941d2ff86797eee BUG: 3194 Reviewed-on: http://review.gluster.com/98 Tested-by: Gluster Build System Reviewed-by: Raghavendra G commit bed25e47ee047d2f3af1120ee66f17147171bd6e Author: Junaid Date: Tue Jul 19 11:26:43 2011 +0530 mgmt/glusterd: Read the contents of vol-info file into a dynamically alloced string. Change-Id: I06173a4cf22e12bc543f8ff2d151078333b500e1 BUG: 3154 Reviewed-on: http://review.gluster.com/8 Tested-by: Gluster Build System Reviewed-by: Pavan T C commit f3c0281d9b4654888a5525b443f1e6090d874725 Author: Amar Tumballi Date: Fri Jul 22 15:23:32 2011 +0530 glusterfsd-mgmt: initialize ctx->mgmt before calling rpc_clnt_start() this is required because if 'CONNECT' event comes before the clnt_start() function ends, we may loose the event if it is not initialized. Thanks to Jeff Darcy for pointing it out Change-Id: Iebbd651b7563265800f41922367ca133fbbf4fc3 BUG: 3207 Reviewed-on: http://review.gluster.com/77 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit ff5fddcf54805464c1033ee4665835784e260831 Author: shishir Date: Wed Jul 27 15:03:40 2011 +0530 Stripe_readdirp: Fix race in wind/unwind which led to crash Scenario - The race window exists when before we wind to a stat call in readdirp_cbk, whereas stats have returned to cbk. We would free up local, which leads to a crash. Fix - We assume all entries to be regular files, and set the wind_count as a multiple of entries * subvol (stat calls). When we encounter a non regular file, we decrement the windcount accordingly (subvol times). If the last entry happens to be a non-regular file, and all stat calls have wound back, we unwind from here itself. Change-Id: Ia8e225ef557cbe1fedb9b72de9bd9fa61f371a24 BUG: 3257 Reviewed-on: http://review.gluster.com/115 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 2a6de14e22445fc3017c9aa25b9c56bc4259d373 Author: Csaba Henk Date: Tue Jul 12 22:18:58 2011 +0200 gsyncd: exit in slave when RePCe session came to an end Change-Id: I4317e60fce3280c45dbcc4a5f233a4344aba9500 BUG: 2778 Reviewed-on: http://review.gluster.com/83 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit cf4501899ca75a6641a31cf7116d439dfb6dd4de Author: shishir Date: Tue Jul 26 12:56:54 2011 +0530 NFS: Implement nfs_forget call Make sure the inode_ctx is deleted nfs_release is not needed, as __nfs3_fdcache_remove_entry cleans up the ctx Change-Id: I690efa1eb1d4cd39cee258bb29692cc58ab9c380 BUG: 3250 Reviewed-on: http://review.gluster.com/103 Tested-by: Gluster Build System Reviewed-by: Shehjar Tikoo commit fa979753d9fe27c6338a0d384d0f183ea716003d Author: Csaba Henk Date: Tue Jul 12 21:59:24 2011 +0200 gsyncd: log exit properly Change-Id: Iedd8c0ce9dec2d8dcb01e0e5b409cb53185b1716 BUG: 2778 Reviewed-on: http://review.gluster.com/82 Tested-by: Gluster Build System Reviewed-by: Kaushik BV commit 06af690050b5b0ca4da34d4c89fda3d3deffe908 Author: Csaba Henk Date: Mon Jul 11 14:57:18 2011 +0200 geo-rep: compactify logging Change-Id: I19f6cf539289062b39e3c0f73fa88f4ff9488349 BUG: 2778 Reviewed-on: http://review.gluster.com/80 Tested-by: Gluster Build System Reviewed-by: Kaushik BV commit 55219903e32e750cfdf58260e7c3a2c4f2bfe16e Author: Vijay Bellur Date: Mon Jul 25 15:31:21 2011 +0530 libglusterfs: Bring in os_daemon_* routines to replace modified FreeBSD code Change-Id: I41f4635b1b75adb6d22e2e325b99941f8d7a0b42 BUG: 3206 Reviewed-on: http://review.gluster.com/100 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 98b32b5798c7d782cae4c16b608f600ab51fffce Author: Junaid Date: Thu Jul 21 23:51:45 2011 +0530 features/marker-quota: Fix some random memory leaks. Change-Id: I1b01adf1d0ecf494f960d125f2bdcc9c10137115 BUG: 3169 Reviewed-on: http://review.gluster.com/75 Tested-by: Gluster Build System Tested-by: Raghavendra G Reviewed-by: Raghavendra G commit 58e3c67007d52b5c2383badf32d5809edfc0c6cb Author: Csaba Henk Date: Tue Jul 26 17:23:27 2011 +0300 save the trees Change-Id: I394621c76a95ed596aedcd45030d80a79de30acf BUG: 3255 Reviewed-on: http://review.gluster.com/108 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi Reviewed-by: Anand Avati commit 58ccea44011065f57968114c9a8e89307ec05276 Author: Amar Tumballi Date: Wed Jul 27 14:36:56 2011 +0530 rpc: in client connection init(), return the proper error code without the proper error code, rpc won't know if transport is successfully loaded or not. Change-Id: Idc3ad56d2f47cf1e81ba39f90a7f7b47305d7d9a BUG: 3260 Reviewed-on: http://review.gluster.com/112 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit baf66413aa1d7ea65d092f2301d2ec749b6a217e Author: Krishnan Parthasarathi Date: Wed Jul 6 14:10:25 2011 +0530 glusterd: handle replace-brick in paused state. This change ensures that glusterd retains 'state' information of an ongoing replace brick operation even if it went down midway. Change-Id: I697c2f27a96b3200c7865bd1d3a1de9692ce0da1 BUG: 3252 Reviewed-on: http://review.gluster.com/6 Tested-by: Gluster Build System Reviewed-by: Vijay Bellur commit 48665f87f55d07eb790c882e5b10217416140319 Author: Gaurav Date: Tue Jul 26 11:34:10 2011 +0530 Glusterd: Remove dependency on AI_ADDRCONFIG for AF_UNSPEC Change-Id: I0a22b2cc5a0ea1a57633fddabad54aca7b3d4e86 BUG: 2456 Reviewed-on: http://review.gluster.com/102 Tested-by: Gluster Build System Reviewed-by: Csaba Henk Reviewed-by: Vijay Bellur commit b922437795a68b32cd6fb337dfd66a4ead13b4ee Author: Amar Tumballi Date: Thu Jul 14 16:17:57 2011 +0530 cluster/distribute: while fixing layout, consider ENOSPC errors in case of layout 'creation', layout->err == ENOSPC should be ignored where as, while layout 'fixing' we should consider what was already present in the layout. Change-Id: Ifb613b41065813c9f1202e65e94b4b0282766d11 BUG: 2258 Signed-off-by: Amar Tumballi Reviewed-on: http://review.gluster.com/15 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit 73eca3be5c5ccc71bbad934338c1ef58ed37c483 Author: Rajesh Date: Tue Jul 19 15:57:30 2011 +0530 rpc-transport/socket: avoid logging socket read fails An option, transport.socket.read-fail-log was added in glusterd. This can also be added to any translator which uses socket.c. A gf_boolean_t flag(read_fail_log) is added in socket_private_t. Using this, logging of socket read failures can be controlled. The options is set to 'off' in glusterd.vol by default. Change-Id: I85cf4afc1f534f5f51018449d5d84baef18fce23 BUG: 3156 Reviewed-on: http://review.gluster.com/22 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit d35e17152720a074c15f54f5c3b8a400e456b19e Author: Anand Avati Date: Fri Jul 22 03:45:34 2011 +0530 cluster/dht: dht_rename() - handle GFID situations In the pre-GFID era, the linkfile of the destination file could be reused the linkfile for the renamed file when dst_cached == src_cached. This patch handles this situation and reverts the previous (wrong) fix. Change-Id: Iba57b5eb91cf8b1fb40e74f6399cdf99b8b00410 BUG: 2464 Reviewed-on: http://review.gluster.com/90 Tested-by: Gluster Build System Reviewed-by: Amar Tumballi commit 65cc08d80d5db6a6854249cc04bece0a9554adfb Author: shishir gowda Date: Wed Jul 13 09:21:55 2011 +0000 glusterd: Add bind-insecure xlator-option for glusterd This is required if the number of connections from the glusterd increases. Change-Id: Iff78773f593a8bfae13ec9eec52c5a67ea936ef2 BUG: 3142 Signed-off-by: shishir gowda Reviewed-on: http://review.gluster.com/11 Tested-by: Gluster Build System Reviewed-by: Pavan T C commit b06ba047f48e92323d8dc8af7ed485d35fbbccf2 Author: Vishwanath S Bhat Date: Thu Jul 21 15:19:14 2011 +0530 glusterd - Removed hardcoding of transport type in replace-brick. Replace-brick didn't support transport types other than tcp. Test case: replace-brick should work with tcp and rdma. Change-Id: If33f108b70247d81791d25a1a05247f49847b4d7 BUG: 3092 Reviewed-on: http://review.gluster.com/72 Tested-by: Gluster Build System Reviewed-by: Krishnan Parthasarathi commit 2c068a98e4b0bf54e7553ed7411fa8c7fe3173ba Author: Csaba Henk Date: Sat Jul 23 06:03:18 2011 +0200 gerrit: add a dry-run mode to rfc script With DRY_RUN=1, rfc.sh will not perform the git push just display the push command. This can be useful if one wants to give a final review for the submitted change list (check for typos, misplaced bug id-s) or if one is offline. Change-Id: I90e2016ba78e2a0ecf37044b3db0277a25914f77 BUG: 3234 Reviewed-on: http://review.gluster.com/87 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 434da60ba4ce9a2b47ea47a7790ce48a342de00a Author: Csaba Henk Date: Sat Jul 23 05:50:53 2011 +0200 gerrit: some fixes for the rfc script In rebase_changes(): - Using "--all" for git fetch is bogus: the scope of this quantification is not over the tracked refs of the upsteam repo (which we do want, but that kind of universal quantification is already implied by the notion of "tracking"), but over the set of all the registered remotes, which is an annoying side effect. - $EDITOR is weaker than the git configuration settings. For the purpose of the script, we need to override any kind of setting, and that can be done via $GIT_EDITOR. Cf. git-fetch(1), git-commit(1). Change-Id: Ia91ee5c4d42dce9248f26f7697528e3c97355871 BUG: 3234 Reviewed-on: http://review.gluster.com/86 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 2d29b67a63779ac7b115d214bb037c12b122cf2f Author: Kaushal M Date: Tue Jul 19 09:05:54 2011 +0530 glusterfsd: check for process mode before performing mount create_fuse_mount() now checks if it is a client process before performing mount. If not a client process, it returns an error. Added changes suggested Change-Id: If8548ad60d345bb8cd09686ceed0d83522799761 BUG: 2469 Reviewed-on: http://review.gluster.com/5 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 37b4b7ccad5a479ed2ce96598e902a12fd457bd5 Author: Raghavendra Bhat Date: Wed Jul 20 12:21:12 2011 +0530 debug/io-stats: allow log-level to be set to INFO Change-Id: Ieba6591b0641dcb7dad724c1d8199dc5e91b6bfd BUG: 3198 Reviewed-on: http://review.gluster.com/43 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit c6053cac7794dfd9bf693e91cd76c2a45d7859eb Author: Raghavendra Bhat Date: Wed Jul 20 12:35:14 2011 +0530 debug/io-stats: print the time at which maximum fds were open in gluster top Change-Id: I257bc29945d5acf8fb316f396fb011a2ab652d7a BUG: 3076 Reviewed-on: http://review.gluster.com/54 Tested-by: Gluster Build System Reviewed-by: Shishir Gowda commit a7e38564ec859afc15274a0d9a16d6e04ed3f6e2 Author: shishir gowda Date: Wed Jul 20 14:53:04 2011 +0530 Top/Profile: Report error when all bricks are down on volume Profile - If all bricks are down, report errror. Top - If all bricks or the specified brick is down, report error. Change-Id: I39d4acd631b481233ab2e9f66c8f4160caef5762 BUG: 2600 Reviewed-on: http://review.gluster.com/63 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit 46afd33ebe184604443a695ebf8eaea8c2098443 Author: Amar Tumballi Date: Tue Jul 19 21:08:14 2011 +0530 glusterd rebalance: use lstat() instead of stat() so the symlinks pointing to directories are not considered as directories themself and the control flows outside gluster's scope Change-Id: Iae910ce6c68886d34ae6e5efe46062481b40cd25 BUG: 3191 Reviewed-on: http://review.gluster.com/30 Tested-by: Gluster Build System Reviewed-by: Anand Avati commit e74bf1ae7d974ae3681818a0a6240adee5983323 Author: Kaushal M Date: Tue Jul 19 14:36:13 2011 +0530 cli: modifications to "profile info" output Units are now shown for the latencies and duration Changed some text to be more meaningful Change-Id: I1891d6ac541421606dda30ed10f9b40b21e2fa52 BUG: 3028 Reviewed-on: http://review.gluster.com/18 Tested-by: Gluster Build System Reviewed-by: Vikas Gorur commit 9e7f02aa79e889e4b91604ef84b5f948dc3787f9 Author: Amar Tumballi Date: Mon Jul 18 17:13:54 2011 +0530 news: note the move to gerrit Review changes incorporated Change-Id: I3d19a68ea22873a5fdd1a3cacea1ba37bf8dbd0f BUG: 1 commit fbe8cc85a10bf57689d836457cfb59c5c51554c7 Author: Anand Avati Date: Mon Jul 18 16:06:59 2011 +0530 s/Patchwork/Gerrit/ Change-Id: I3d2e0c081cce5c69a6a168ddd0d850cdba84f53e commit 15d2e7dd88f640c7e30989d37e735e37070119d8 Author: Anand Avati Date: Mon Jul 18 15:47:05 2011 +0530 fixed URL in README Change-Id: I2ce02b67ee844119f854a0a2e83b5ebeb036801a BUG: 1 commit 1357fa6fa07bc34248643d2b9a329bddc873b15a Author: Anand Avati Date: Mon Jul 18 14:54:25 2011 +0530 Fixed URL in README Change-Id: I134e8d57b188025a115fcfc363009bb3893676a1 BUG: 1 commit 0773f5a34e3b5c503674bceaa1902454fc841879 Author: Sachidananda Date: Sun Jul 17 08:10:29 2011 +0000 Strip extra `/' from filenames. While peforming replace-brick, delete-brick, remove-brick... and related operations resolve extra slashes as single path separator. i.e treat /foo//bar// as /foo/bar. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3183 (When creating volumes brick paths are not handled properly.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3183 commit 613a6369d63e3ec87735a5427e4e87894f884749 Author: Raghavendra Bhat Date: Mon Apr 11 03:13:34 2011 +0000 mgmt/glusterd: allow add brick in pure replicate setup Currently in pure replicate if the replica count is 4 and there are 4 bricks, then suppose 3 bricks are removed then add brick works only if 3 bricks are provided. Providing lesser bricks fails. This patch fixes that scenario. Signed-off-by: Raghavendra Bhat Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 1574 ([glusterfs-3.1.0qa18]: add-brick to a replicate volume fails if a brick is removed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1574 commit 273f898364463cd10165fc82c8c5250a0962c452 Author: Sachidananda Date: Sat Jul 16 12:54:00 2011 +0000 Canonicalize path names while creating volumes. When a volume is created resolve symbolic links, delete duplicate slashes in the path name. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3183 (When creating volumes brick paths are not handled properly.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3183 commit 260edb905171ebed3692eaeca404d13202cd5fd0 Author: Pranith K Date: Sat Jul 16 08:20:11 2011 +0000 PUMP: set pump lk_owner,pid to frame->root Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 3182 (Afr self-heal should happen with out big lock) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3182 commit b43038ee84839fa6b0e6aee037f7d952d8f52b6d Author: Pranith K Date: Sat Jul 16 08:19:47 2011 +0000 cluster/afr: Don't depend on fuse lk_owner for inodelks Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 3182 (Afr self-heal should happen with out big lock) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3182 commit 97807e75956a2d240282bc64fab1b71762de0546 Author: Pranith K Date: Thu Jul 14 06:31:47 2011 +0000 storage/posix: Remove the interim fix that handles the gfid race Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2745 (failure to detect split brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2745 commit 61f68b31f24311d09f4d2a02968ff52fd7b5a73f Author: Pranith K Date: Thu Jul 14 06:31:33 2011 +0000 storage/posix: Succeed lookup even if there is no gfid on the file Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2745 (failure to detect split brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2745 commit 5dff9a2938c199285662bb5b33d7e3aeda0e3fb6 Author: Pranith K Date: Thu Jul 14 06:31:08 2011 +0000 cluster/afr: Fix conflict files and gfid self-heal Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2745 (failure to detect split brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2745 commit 84c3d7a83a8c84ca11514202a1bc365026fd1c87 Author: Pranith K Date: Thu Jul 14 06:30:40 2011 +0000 cluster/afr: Detect conflict/gfid self-heals Added some helper functions that can be reused Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2745 (failure to detect split brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2745 commit 10e50f9df6de9efccd66dc8b37c73c52569e3559 Author: Pranith K Date: Thu Jul 14 06:30:20 2011 +0000 cluster/afr: make expunge/impunge re-usable Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2745 (failure to detect split brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2745 commit b0a3a3fda3f0993cd8c0e1b135bb569b6543e7c0 Author: Pranith K Date: Thu Jul 14 08:07:46 2011 +0000 cluster/afr: Choose next call child from fresh-children for inode-read-fops Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2840 (files not getting self-healed when the first child goes down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2840 commit bfc0e16e43815ab6d6e67f4bd26694ebd72b3360 Author: Pranith K Date: Thu Jul 14 08:07:04 2011 +0000 cluster/afr: Add fresh children along with read-child to inode context Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2840 (files not getting self-healed when the first child goes down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2840 commit 64b2a56ad0f8ddae9ece8696f7d50a3129c145a3 Author: Pranith K Date: Mon Jun 27 03:10:23 2011 +0000 cluster/afr: Move afr local alloc functions from header files to sources Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2840 (files not getting self-healed when the first child goes down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2840 commit bf8e3a864eafe7eef5795cd134f6c0d5812a4f17 Author: shishir gowda Date: Fri Jul 15 01:22:51 2011 +0000 io-threads: Initialize mutex and cond Thanks to Emmanuel Dreyfus for sending out the fix. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3170 (Uninitialized mutex and cond in io-threads) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3170 commit 1742383787355241d5aaa4b2bdd92d089ef2d508 Author: Anand Avati Date: Fri Jul 15 01:05:16 2011 +0000 posix: perform readdir filling in locked region When two application threads share an open dir fd (DIR *) and issue readdirs, storage/posix will receive separate readdir fops in separate threads in parallel. This has two-fold issues 1. In the following pair of operations - entry = readdir(dir) and strcpy (gf_dirent->name, entry->d_name) @entry is a static buffer in libc which can get reused by another thread to get filled with a longer name. This can cause the second operation to overflow the buffer as the allocation was for the smaller name. 2. In the following pair of operations - seekdir (dir, offset) and entry = readdir(dir) If two threads are executing these sequence in parallel in separate threads, then one of them will end up reading wrong/unexpected entries. It would be sufficient to fix 1. by using readdir_r but that still keeps the second race open. Hence the patch moves all the set of operations to a locked region which solves both races. Signed-off-by: Anand Avati BUG: 3171 (Crash in server) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3171 commit f50e5eb7777ee31701f5d757ffa8de2c238b5e50 Author: Gaurav Date: Mon Jun 20 07:59:27 2011 +0000 Glusterd: IPV6 support for glusterfs. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2456 (IPv6 support for glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2456 commit ded0a9a2a0a9024def7a4b199ac3bbfa5d66485a Author: Amar Tumballi Date: Wed Jul 13 02:08:05 2011 +0000 cluster/stripe: send the xattr keys with create/mknod itself. so stripe is more acl friendly Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3160 ([818f8c87d56bc46d0d0903275699351b66f17e57] Posix compliance test hangs during link tests in distributed-stripe.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3160 commit 5d7657c4b48a73305cf35986323121e7dfe92bef Author: Amar Tumballi Date: Tue Jul 12 05:20:10 2011 +0000 storage/posix: make sure we are starting on a genuine backend also do the check in 'glusterd' to let the user know of the problems (if any) during the volume create/start time itself. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3065 (make sure the export directories are not re-used as part of another volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3065 commit 7f4f7765597a7f0daa5bca7c3bcb2479d7ed15bc Author: Amar Tumballi Date: Fri Jul 1 04:42:14 2011 +0000 glusterd-rebalance: utilize distribute's internal rebalance feature Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3070 (After 'rebalance', the gfid of the file gets changed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3070 commit 8d18bc22d1cfc8a481bc8d20da5843c65b567226 Author: Amar Tumballi Date: Fri Jul 1 04:41:54 2011 +0000 distribute: bring in feature to do rebalance from inside do the 'rebalance' on a file with 'setxattr()' with 'distribute.migrate-data' key. the valid 'value' is "force" or anything else. current implementation of 'rebalance' is same as 'glusterd-rebalance', and hence comes with limitation of not rebalancing hardlinks, non-regular files, and files with open-fds. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3070 (After 'rebalance', the gfid of the file gets changed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3070 commit 3f76fe277ec0a826bf3052134ad877ee65ce9e79 Author: Amar Tumballi Date: Fri Jul 1 04:40:05 2011 +0000 cluster/distribute: bring in directory-spread-count option global spread count option is given through volume file Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2257 (enhance distribute to control the spread count (ie, control the hashing range)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2257 commit 6cf06cfd4bf72b16ac7665323629d354b78b6b05 Author: Amar Tumballi Date: Fri Jul 1 04:39:41 2011 +0000 cluster/distribute: handle layout overlaps while giving a new fix Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit 05a1422bbd82a28ccf7fa7c17b357f8350508e6e Author: Junaid Date: Sun Jun 26 09:35:21 2011 +0000 Revert "features/marker-quota: hold lock on dirty inode's parent while healing a dirty inode." This reverts commit cd2518b4ab627471db74d7f4a473416f318754db. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 9dd6f5a66b3d1ba703e55e06a26f1121ef96c1d4 Author: Kaushik BV Date: Wed Jul 13 04:33:43 2011 +0000 mgmt/Glusterd: Fix build warning Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit b5938787afbf3c24ee4fc995e72577f1369ceb7a Author: Kaushik BV Date: Wed Jul 13 04:33:42 2011 +0000 io-stats: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 5c6fb46c64f2c8e51da2090dd554abfdbfd2b53e Author: Kaushal M Date: Wed Jul 13 04:11:53 2011 +0000 Changed error message displayed and logged, on rebalance failure Signed-off-by: Kaushal M Signed-off-by: Anand Avati BUG: 3106 (Rebalance start failure message is not appropriate) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3106 commit c4da48f0dc9858e70555bf92374cb9e6a6f088b9 Author: Pavan Date: Wed Jul 13 03:34:18 2011 +0000 nfsrpc: Re-order NFS auth array contents Some NFS client implementations can default to AUTH_NULL given a certain order of auth_array in MOUNT reply. We re-order it here to make sure that such clients (Example - 2.6.26), do not have such security loop holes. Signed-off-by: Pavan T C Signed-off-by: Anand Avati BUG: 3144 (permissions given in fuse mount don't have effect in nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3144 Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3144 (permissions given in fuse mount don't have effect in nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3144 commit c77014be787a1d8ff23923b53b39054da35785de Author: Anand Avati Date: Wed Jul 13 03:34:02 2011 +0000 posix-acl: perform access checks on read/write/truncate for NFS calls Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit e27c4da87295a210e77ca13ff23a24078abc25c0 Author: shishir gowda Date: Wed Jul 13 03:33:47 2011 +0000 access-control: Handle F_OK in perm check, and O_APPEND, O_TRUNC in open Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit 4223545bdc67383e622d34ee878d3461ad4f63b0 Author: shishir gowda Date: Wed Jul 13 03:33:26 2011 +0000 DHT access: For nfs calls, op_ret is always 0, and mode is op_errno Return the values received from the subvol Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit e103ab41f3fd917e9a6df3d6113e2c4c3603b29b Author: shishir gowda Date: Wed Jul 13 03:32:53 2011 +0000 NFS access control list: Decode the NFS requests into mode format Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 3057 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit 9388760b9aad1ae2512eb108a4ca6b5c8638ea07 Author: shishir gowda Date: Wed Jul 13 03:32:41 2011 +0000 access-control: NFS access control expects a return of valid mode The permission check is same as that of posix. We break the requests into single checks, aggregate all the valid modes and return in reply. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 3057 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit 9f2adc333dad1beb17b81bd55f5e32366320a4dc Author: shishir gowda Date: Wed Jul 13 03:32:02 2011 +0000 access-control: Save group permissions returned from backend The backend permissions returned in stat for group is already masked value. Use the xattr value Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 3102 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3102 Signed-off-by: Anand Avati BUG: 3102 (Read calls go ahead even when the group has no permissions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3102 commit 843ffc77e0f1ba6cc1b2332f0a57e2fa339c9f4c Author: shishir gowda Date: Wed Jul 13 03:31:47 2011 +0000 access-control: Return mode part of NFS access control request Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 3057 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit e89725cd62430addf09d9c1afbfb07d8c86b9ef0 Author: Rahul Date: Tue Jul 12 13:47:51 2011 +0000 Check type for a value greater than Distribute and not for stripe Signed-off-by: Rahul Signed-off-by: Anand Avati BUG: 3161 ([818f8c87d56bc46d0d0903275699351b66f17e57] Volume type incorrect.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3161 commit 7c4ad6d3321cc440590a6132b7dc8d0d0a58ce3b Author: Amar Tumballi Date: Wed Jul 13 00:37:25 2011 +0000 storage/posix: set all keys present in 'params' dict while creating an entry so, there is no need to do a 'setxattr()' after entry creation, which could now fail due to ACL on server side. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3164 (set xattr keys while entry creation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3164 commit 8b57a5c2fb16f2c85c0f74edbe7b841a6dc4a265 Author: Kaushik BV Date: Tue Jul 12 05:33:39 2011 +0000 protocol/client: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit e312fb0ffaaf4e5bcf69dcebaabcbd3898ba8765 Author: Kaushik BV Date: Tue Jul 12 05:33:38 2011 +0000 write-behind: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 2f457d1a6441903327b0da5e01f9cad186b13ef5 Author: Kaushik BV Date: Tue Jul 12 05:33:37 2011 +0000 quick-read: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit aa9f9c3113009f136642e9bdedfcef6d04d85b44 Author: Kaushik BV Date: Tue Jul 12 05:33:36 2011 +0000 io-threads: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 14426adfe61fde6c6e6367a6025f314046ed8aa5 Author: Kaushik BV Date: Tue Jul 12 05:33:35 2011 +0000 io-cache: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit a3009537811b4343c86f13555717eef5e0ea2641 Author: Kaushik BV Date: Tue Jul 12 05:33:34 2011 +0000 quota: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 61f4b2b5f10bc1f36c86dac5a9a9d640975dee11 Author: Kaushik BV Date: Tue Jul 12 05:33:32 2011 +0000 stripe: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 6b40f3eba97c8aad653f0602754127f7ae5a9707 Author: Kaushik BV Date: Tue Jul 12 05:33:31 2011 +0000 dht: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit e87432be87c37c36467a85e3d2c55970f8439915 Author: Kaushik BV Date: Tue Jul 12 05:33:30 2011 +0000 afr: changes in volume_options to assist volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit 1d0cb953bb117689fb8381d65932ead486d13b05 Author: Kaushik BV Date: Tue Jul 12 05:33:29 2011 +0000 mgmt/Glusterd: Implementation volume set help/help-xml Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2041 (volume set help option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2041 commit f9e0638b7597f4b1a4245f63c94d3d6bd3158136 Author: Shehjar Tikoo Date: Mon Jul 4 06:32:32 2011 +0000 nfs: Change NFS3 access op to use access fop This change is needed so that we have a uniform dependence on posix-acl for permission checks as well as ACL checks. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand Avati BUG: 3057 (acl permissions don't work on nfs mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3057 commit 43d6d33d35618eb684975d6f0d1263e25ae6466c Author: Vijay Bellur Date: Thu Jul 7 03:03:40 2011 +0000 features/locks: Do not block UNLOCKs Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit e30c38b783c728182eb9cc478fabc7a7830c8efc Author: Raghavendra G Date: Wed Jul 6 08:35:14 2011 +0000 mnt/fuse: generate uuids in fuse_lookup, not in fuse_lookup_resume. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3041 ([glusterfs-3.1.5qa2]: stat gives EINVAL) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3041 commit 67f6fc6156cb14875600cd7e44d937587196e3b3 Author: Raghavendra Bhat Date: Mon Jul 4 02:27:06 2011 +0000 glusterd: check replica_count for 0 before using it for volume creation in stripe replicate volume Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 3123 ([a7cdaf3de307c96cb55219a0743962ee1e1fc955]: glusterd crashed when started) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3123 commit 4c55f76d6a4d13ec1ed3cffd31ff4acc3d3122f0 Author: Venky Shankar Date: Fri Jul 1 00:18:53 2011 +0000 afr/stripe: collect pathinfo xattrs from all childs Signed-off-by: Venky Shankar Signed-off-by: Anand Avati BUG: 3046 (getxattr for afr should returns realpath from all childs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3046 commit 1a82b4539b69390dfb1a158c420385c7ad5d999f Author: Pranith K Date: Fri Jun 17 07:20:08 2011 +0000 cluster/afr: Handle lookups when self-heal is off Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2586 (read child is set without checking the xattr) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2586 commit 9866f23b9b0ceb8be876600be9832987b8646540 Author: Amar Tumballi Date: Fri Jul 8 02:56:03 2011 +0000 mount.glusterfs: fix to handle the error cases better Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3085 (backupvolfile-server option doesn't work) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3085 commit 44f57f49309116de175a9c91c84fb7b8999a05ad Author: Amar Tumballi Date: Fri Jul 8 02:55:40 2011 +0000 cluster/stripe: quick-read friendly behavior in lookup Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3140 (contents of files are invalid after apply patch 7573) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3140 commit fcce7c289a0c27345404ab17e2cce6e8f5ad7fc9 Author: Amar Tumballi Date: Fri Jul 8 02:55:20 2011 +0000 cluster/stripe: cleanup and memory leak fixes Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3140 (contents of files are invalid after apply patch 7573) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3140 commit fa1feca4172776ba4ae011ffa679a02055951e37 Author: Krishnan P Date: Tue Jul 12 02:31:05 2011 +0000 server: Reassociating 'old' conn can lead to chaos. Since we moved to a single socket connection b/w client and server, inherting connection state is unnecessary and can sometimes be dangerous when clients reconnect even before the server detects a socket error on the old connection. Dirty detail: This reassociation results in 'ref count' not decreasing in tandem with the connection disconnects. This results in a resource leak. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3104 (Self-heal does not work in dis-rep!) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3104 commit 42e0b1731d925fd5a0bfaa107a2e01ba47fae125 Author: Amar Tumballi Date: Tue Jul 12 05:29:25 2011 +0000 cluster/distribute: send proper 'params' dictionary during linkfile creation when the code path enters the 'subvol_filled()' case, local->params is set, which contains the 'gfid-req' value, but the linkfile creation was not checking for its existance. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3159 (mknod (linkfile creation) with no 'gfid-req' key) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3159 commit 2c688714a2a081fc1be30febcd839caf8e201456 Author: Amar Tumballi Date: Tue Jul 12 05:16:46 2011 +0000 storage/posix: move the helper functions to separate file helper functions were more than 800 lines Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3158 (Keep code more readable and clean) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3158 commit 79f4135994e5051c711595c791d5831bdad24738 Author: Amar Tumballi Date: Tue Jul 12 05:16:32 2011 +0000 storage/posix: call 'gfid_heal()' instead of 'gfid_set()' in lookup() Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2994 ([glusterfs-3.2.1qa2]: untar and rm in parallel hangs untar) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2994 commit 818f8c87d56bc46d0d0903275699351b66f17e57 Author: Sachidananda Date: Mon Jul 11 05:37:39 2011 +0000 Fail volume creation on existing directories of a read-only file system. Thanks to kp@ for the fix. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2609 (Error message not properly provided when trying to create a volume from a read-only source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2609 commit 03df277c7880541570107bbaa7f91e5cf7ad5a69 Author: Krishnan P Date: Tue Jul 12 01:51:17 2011 +0000 pump, afr: dict related memory fixes. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2489 (GlusterFS crashing with replace-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2489 commit 1f5119627b278b98518afb68a7eb88752932976c Author: Anand Avati Date: Tue Jul 12 02:11:59 2011 +0000 cluster/dht: fix race between two directory renames let the race get arbitrated at the dst_hashed subvolume. Signed-off-by: Anand Avati BUG: 2522 ([glusterfs-3.1.3qa8]: rm -rf shows invalid argument) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2522 commit b894a5c79f93707149181a51bfab67fdbffcc43b Author: Anand Avati Date: Tue Jul 12 02:11:42 2011 +0000 storage/posix: detect race in posix_rename() detect a race in rename between two clients by checking for reassigned gfid or presence of dir when not expecting. checks not necessary for rename of files. Signed-off-by: Anand Avati BUG: 2522 ([glusterfs-3.1.3qa8]: rm -rf shows invalid argument) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2522 commit a9080b7c706be4ac917866d73e70e36fd933b54d Author: Raghavendra G Date: Thu Jul 7 01:33:05 2011 +0000 client-handshake: skip CHILD_DOWN notifications when client is querying port using different volume names in the presence of rdma. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3091 (rebalance fails with "transport endpoint not connected" in 3.2.1 rdma set-up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3091 commit e9c29f722776a91993403428cafdb2b7e1056bd8 Author: Junaid Date: Thu Jun 23 03:20:09 2011 +0000 debug/io-stats: Added sys-log-level option. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 3044 (provide option to set syslog loglevel through CLI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3044 commit 089ae1b7299f2d30a7b56da0c700f42d7a0341d7 Author: Junaid Date: Thu Jun 23 03:19:15 2011 +0000 mgmt/glusterd: Make glusterd aware of sys-log-level options. There are two options: * brick-sys-log-level * client-sys-log-level Which set the log-level on brick and client respectively. Uset gluster volume set -sys-log-level value to set the option. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 3044 (provide option to set syslog loglevel through CLI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3044 commit ae5f7c2c1d88cee0029c555f2416fe7c998cc1c2 Author: Junaid Date: Wed Jun 29 03:13:56 2011 +0000 libglusterfs/logging: Added functions to set sys-log-level. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 3044 (provide option to set syslog loglevel through CLI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3044 commit e9d960391794db917bd3e984c8dc3fd7e3cec706 Author: Raghavendra G Date: Wed Jun 1 08:00:03 2011 +0000 quota: update limit stored in inode-ctx when limit is removed on a directory. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2971 (quota remove command doesn't remove quota on directories.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2971 commit cf395e9af76de16162328fbcf0aef4e8c72adfb8 Author: Raghavendra G Date: Wed Jun 22 02:35:58 2011 +0000 fuse: fix inode-leaks in fuse_lookup_and_resume codepath. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2525 ([glusterfs-3.1.3qa8]: inode leak in rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2525 commit b320532ca74643108df399663e3c002af3e0e219 Author: Raghavendra Bhat Date: Wed Jul 6 02:18:49 2011 +0000 fd: put the fd back to fd_mem_pool of inode table instead of freeing in case of failure Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 3103 (memleak in inode table creation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3103 commit 500813986241a8b5f6ff0658f4471a8f58e6c48e Author: Vishwanath Date: Fri Jul 1 07:39:21 2011 +0000 remove hardcoding of transport type to "tcp" while generating vol files in replace-brick Please ingore previous patch for this. Please consider this one. Signed-off-by: Vishwanath S Bhat Signed-off-by: Anand Avati commit a36225a984240629a906608c85a9ac7e432aacfe Author: Rahul Date: Fri Jul 1 05:53:10 2011 +0000 Fixes missing ".." entry in the mount point Signed-off-by: Rahul Signed-off-by: Anand Avati BUG: 3097 ([b7aeaa619b82509fbe8d187bbc1618cb319d6877] ".." entry in mount point missing.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3097 commit bf4a7bed6420377aac26693f450a450bc54d005c Author: Amar Tumballi Date: Mon Jun 27 07:59:52 2011 +0000 libglusterfs/syncop: add more functions do proper 'ref's and implement 'write()' and 'ftruncate()' Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3081 (synchronous operations should be enhanced) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3081 commit a879613637f54a7a2016549b308b359b7577b5ad Author: Vijay Bellur Date: Tue Jul 5 23:08:40 2011 +0000 cli: Exit if glusterd is not operational in non-prompt modes Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 3120 (Provide connection timeout between cli and glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3120 commit 8f14d85777c93277403bcac727c0447dcba3cdc0 Author: Anand Avati Date: Fri Jul 1 17:19:39 2011 +0000 mount.glusterfs: support -o acl parameter Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 57b3b7e62487eef4c534e3fe65f954cf5d6d0ce4 Author: Anand Avati Date: Fri Jul 1 17:19:29 2011 +0000 glusterfs: add --acl command line option to load ACLs on the client side also set the turn off filtering of ACL keys in FUSE xattr FOPs. Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 4b643cfa8847be71bb381b5a8a1a420837722e51 Author: Anand Avati Date: Fri Jul 1 17:19:15 2011 +0000 access-control: superseded by posix-acl translator Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 04ed499a8eef1c77c491227941d187778fb5c2e4 Author: Anand Avati Date: Fri Jul 1 17:18:10 2011 +0000 posix-acl: implementation of POSIX ACL as a translator Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 6433214452c5d8d3ae63c5f4f578862be348ca63 Author: Anand Avati Date: Fri Jul 1 17:18:04 2011 +0000 storage/posix: set ACL keys during new entry/inode creations honor "system.posix_acl_access" and "system.posix_acl_default" keys in params dict to setxattr into the backend while creating new entry/inodes Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 54aaf46e5b6e95fe9df257728b76f67bdb5dd17c Author: Anand Avati Date: Fri Jul 8 03:23:08 2011 +0000 fuse: introduce "noacl" option to disable ACL checks Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 8af1177029b7103ba84bc59eb58d7c5c8635e6cd Author: Anand Avati Date: Fri Jul 1 17:17:11 2011 +0000 fuse: fill frame->root->groups with aux gids of the process Pick the groups in /proc//status from the line starting with "Groups: " by parsing the list of integers which follow Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 14d65cb9e0c6f5a6176014701c86760a392d3a44 Author: Anand Avati Date: Fri Jul 1 17:17:04 2011 +0000 dht: set linkto xattr with linkfile create (mknod) Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit 1a70453c6501e149cd415f5f11048cf44e526d6c Author: Anand Avati Date: Fri Jul 1 17:16:50 2011 +0000 byte-order: htole*/letoh* and htobe*/betoh* for forced endian conversions Signed-off-by: Anand Avati BUG: 2815 (Server-enforced ACLs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2815 commit a40c52707762258eddb35a63ee1f78bc4e0a52dd Author: shishir gowda Date: Wed Jul 6 03:10:05 2011 +0000 dht disk usage: Correct free blk calculation Use f_bavial instead of f_bfree for %free calculation This fixes mismatch of df output wrt backend and glusterfs where: f_bfree = /* # free blocks */ f_bavail; /* free blocks avail to non-superuser */ Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3084 (Correcting percent calculation of disk space) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3084 commit a7cdaf3de307c96cb55219a0743962ee1e1fc955 Author: Junaid Date: Fri Jul 1 05:17:42 2011 +0000 features/marker-quota: call stack destroy when hardlink count is not greater 1. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit ac683df2322123472ba52dbeecb9cd5512ecc58c Author: Raghavendra G Date: Fri Jul 1 00:12:35 2011 +0000 mnt/fuse: Do a pthread_cond_broadcast for both CHILD_UP and CHILD_DOWN events. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3091 (rebalance fails with "transport endpoint not connected" in 3.2.1 rdma set-up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3091 commit a21c3bb99e5ad59e8e9ec0a050ce8617ce3fe167 Author: Raghavendra Bhat Date: Thu Jun 30 06:59:12 2011 +0000 inode table: avoid memleak by freeing the allocated structures incase of failure Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 3103 (memleak in inode table creation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3103 commit 64316c419f013464641b84900acc0ff4eeeaf2ae Author: Raghavendra G Date: Thu Jun 30 03:20:31 2011 +0000 rpc-transport/rdma: call ibv_fork_init to make rdma work with fork. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3091 (rebalance fails with "transport endpoint not connected" in 3.2.1 rdma set-up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3091 commit ea6763a5b956c29f4c1862ed355398631ff4a9cc Author: Raghavendra G Date: Thu Jun 30 03:20:50 2011 +0000 mount/fuse: wait till CHILD_UP event is recieved to do the first lookup. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3091 (rebalance fails with "transport endpoint not connected" in 3.2.1 rdma set-up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3091 commit 935d7744674ec961dd967133721de1429460c91f Author: Pranith K Date: Thu Jun 23 01:12:48 2011 +0000 cluster/afr: fix the range of the lock taken in [f]truncate Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 3077 (afr [f]truncate locks wrong region in transaction) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3077 commit 91086a2a7dcbfa30cdb5c188e9268ae4379bd28e Author: Junaid Date: Tue Jun 28 03:01:12 2011 +0000 mgmt/glusterd: return 0 when glusterd_op_get_ctx fails on other glusterd's. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 3078 (Quota: list comamnd fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3078 commit 41650a8c03ad86bcebe8c595ab9e7f13ec899a4f Author: Junaid Date: Thu Jun 30 00:46:20 2011 +0000 features/marker-quota: Change the log-level of gf_log to debug in quota_inodelk_cbk(). Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 7388f9f5910c0c69039a1476d902b48dda98b394 Author: Junaid Date: Wed Jun 29 20:41:27 2011 +0000 mgmt/glusterd: 'Quota' use quota-crawl.log to store logs of maintainence mount. Allow to set limits even when quota is disabled. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2620 (CLI improvements in quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2620 commit 7cd21dec47426e32be9f4548f4ec716b0575867e Author: Junaid Date: Wed Jun 29 20:41:17 2011 +0000 cli: 'Quota' use quota-list.log to store logs of maintainance mount. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2620 (CLI improvements in quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2620 commit b7aeaa619b82509fbe8d187bbc1618cb319d6877 Author: Junaid Date: Mon Jun 20 07:11:47 2011 +0000 features/marker-quota: Skip contribution creation on root. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 83d1f9642e7310f085caaeb0c5b72a88c445d31b Author: Vishwanath Date: Thu Jun 23 05:41:39 2011 +0000 spelling corrections in glusterfs code Signed-off-by: Vishwanath S Bhat Signed-off-by: Anand Avati BUG: 2903 (Last spelling errors in source code) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2903 commit a846faead3d416d9af75106694e85a776f7d07a8 Author: Amar Tumballi Date: Wed Jun 22 23:23:06 2011 +0000 distribute: handle 'fix.layout' key in setxattr() instead of getxattr() as 'fix.layout' command does changes to directory layout, its not a 'read/get' type of operation, and hence as per the symantics, it suits setxattr() better also fix a memory leak in getxattr(), where 'local' was allocated twice in few cases Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3075 (the 'fix.layout' command should happen through 'setxattr', not getxattr().) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3075 commit 308668c055b542724d226a3b7a835e7ea06082ed Author: Amar Tumballi Date: Thu Jun 23 08:07:23 2011 +0000 libglusterfs: added syncop_* functions * implemented open,close,readv,writev,listxattr,create,unlink * also fixed a dictionary ref issue with lookup_cbk Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3081 (synchronous operations should be enhanced) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3081 commit f948a24e51e447642c35bff881057f306768a5e0 Author: Amar Tumballi Date: Thu Jun 23 01:51:47 2011 +0000 bring in strict check on export directory being re-used for different volume Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3065 (make sure the export directories are not re-used as part of another volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3065 commit 89452c4db44966bb80601c73c3b835d002af9fd5 Author: Amar Tumballi Date: Thu Jun 16 23:42:53 2011 +0000 gluster volume info: fix the output of 'stripe-replicated' volumes also fix the glusterd-store to preserve the required information Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3040 (need a way to create volumes with 'stripe+replicate' setup..) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3040 commit c9854677fcd5a0a68e885cc18b6d9d6d92218f23 Author: Amar Tumballi Date: Tue Jun 21 04:56:41 2011 +0000 gluster volume create: option for stripe + replicate volume So RAID01 like option is a possibility Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3040 (need a way to create volumes with 'stripe+replicate' setup..) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3040 commit 0d87bfca5c9a95977215599d5800e751ec8f2205 Author: Sachidananda Date: Wed Jun 22 05:57:06 2011 +0000 Fix typos in manpages. Thanks to: Patrick Matth?i for patches. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2902 (Errors in manpages) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2902 commit d7642fb9bc13bb9c2da35bd8e80c311d5fc5096c Author: shishir gowda Date: Wed Jun 22 04:24:58 2011 +0000 Stripe selfheal: Prevent spurious STACK_DESTROY call The stack is destroyed in the cbk Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3056 ([4597929cc527f8abaf9ef9e1d5499ea416e5c7ff] Crash in client at client3_1_mknod_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3056 commit 9123fd82ab1946ed6f2c3d025043da1183d84d31 Author: Raghavendra G Date: Wed Jun 22 02:51:50 2011 +0000 fuse: consider a lookup as revalidate even if the inode is present in new graph. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3041 ([glusterfs-3.1.5qa2]: stat gives EINVAL) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3041 commit 305b40239fda0b01537f05f94c3184e9523594c4 Author: Vijay Bellur Date: Tue Jun 21 05:07:04 2011 +0000 performance/quick-read: Perform error handling only when GF_CALLOC fails Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 3011 (Uninterruptible processes writing(reading ? ) to/from glusterfs share) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3011 commit f63dabd5d68a0904967705937380fed1eb9c99cf Author: shishir gowda Date: Tue Jun 21 03:22:09 2011 +0000 Stripe lookup: aggregate xattrs stripe default setxattr works on first child. If the first cbk is not the first child, then we were loosing the xattrs. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 3066 (aggregate xattrs in stripe lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3066 commit 1d85e0dc80c19645f924c8fcbbb32c53ef09e701 Author: Junaid Date: Tue Jun 21 00:51:25 2011 +0000 mgmt/glusterd: Enable quota only when volume is started. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2620 (CLI improvements in quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2620 commit 71a13f09978dc3858b9dd2771f605582e0c2e0dd Author: Gaurav Date: Mon Jun 20 08:32:59 2011 +0000 NFS : Pass valid argument in mnt3svc_dump. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2692 (NFS server crashes on showmount -a) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2692 commit 8c24158f2bda14e9debcc2f4ccde53aa9629c2b7 Author: Raghavendra G Date: Mon Jun 20 01:46:07 2011 +0000 performance/quick-read: reset open_in_transit to zero in case of an error. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 3011 (Uninterruptible processes writing(reading ? ) to/from glusterfs share) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3011 commit 608b22609793549eb8e8e2b2899af2d1ff5c193c Author: Krishnan P Date: Mon Jun 20 01:01:20 2011 +0000 pump: mark pending before notify to children to avoid race in single CPU. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3050 ('replace-brick' hangs on vm's) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3050 commit 96ae0db506f43ceed0d3346d0351b1bb73b0b19c Author: Junaid Date: Sun Jun 19 23:41:25 2011 +0000 features/quota: Print a log when reconfigure fails. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2775 (crash in reconfigure) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2775 commit 1748b0c7925fa2165cbf11c4aab90e07bff7d4cb Author: Krishnan P Date: Mon Jun 20 00:56:10 2011 +0000 afr: bg self-heal must be off if self-heal-count=0. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3036 (self-heal problem in replace-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3036 commit b64dd21f05016065e0b825db62da87981554df88 Author: Sachidananda Date: Sun Jun 19 12:51:45 2011 +0000 Fix the command line log to display correct error message. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3054 (Typo in cli message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3054 commit d4df768b6efff0da2931396b8b9b28c5174e4d7a Author: Sachidananda Date: Sun Jun 19 11:07:31 2011 +0000 Print error message to report missing mount point. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3053 (No proper error is shown when the mount point is not present) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3053 commit 58cf35b353f5a9fedfddd6da2f5811c58f1be3cc Author: Gaurav Date: Thu Apr 7 01:42:33 2011 +0000 CLI : Display possible options in proper format. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2598 (Volume access option suceeds with any string value) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2598 commit 2f07f751bf69a196df85d3e715c0ad1a7a26419c Author: Raghavendra G Date: Wed May 11 02:42:21 2011 +0000 extras: Add quota-related debugging scripts. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit e2685adcb71b30621e34905584910390e0b248e1 Author: Raghavendra Bhat Date: Fri May 27 01:17:12 2011 +0000 print the owner and the transport for the blocked locks in server statedump Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2949 (self-heal hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2949 commit 4c81f6268d254f452b861bcd63608982c3ddb560 Author: Anand Avati Date: Sat Jun 18 03:53:46 2011 +0000 stack: make process state dump more debug friendly store points of stack wind and unwind (function names) for each frame and dump them in process state dump Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit 50001216d26a16736691ab06758049c22e664936 Author: Junaid Date: Wed Jun 15 02:41:36 2011 +0000 cli: Print the error message sent by glusterd when quota list cmd fails. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2856 ([glusterfs-3.2]: Misleading 'quota remove' output.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2856 commit 4e1ec35ef4f7bbf70c3e08e7c246946551f19e93 Author: Amar Tumballi Date: Thu Jun 16 07:48:22 2011 +0000 core: fill 'ia_ino' from 'ia_gfid' in 'storage/posix' to preserve same ino number take the least significant 64bit from gfid and assign it to 'ia_ino', hence for a given file (or directory), the 'ia_ino' number is always same, and we need not worry about the 'itransform' in 'cluster/*' translators. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3042 (inode number should be constant on storage) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3042 commit f04898973f15cfa13fcf39a903786983885352bc Author: Pranith Kumar K Date: Fri Jun 10 00:34:10 2011 +0000 cluster/afr: Give proper device id for mknod Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2840 (files not getting self-healed when the first child goes down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2840 commit 17d3a0fc214c347d9e0a6cc4855302a41a09b535 Author: Junaid Date: Thu Jun 16 21:57:40 2011 +0000 mgmt/glusterd: chdir into mount in second child process while crawling the fs in quota enable. Because the management mount is waiting for glusterd's response and glusterd is doing waitpid on the child which is trying to do chdir into mount, thus causing a deadlock situation. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2560 (Lazy umount should be done for the maintainance mode mountpoint) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2560 commit 0101eb0b6444dc22860d8fdc82170aefa87ff0b3 Author: Amar Tumballi Date: Thu Jun 16 06:43:12 2011 +0000 logging: fill proper domain names at places where it is missing also changed some error messages where it was not explicit Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 25e8700721a71128c9f6143dc2effcdbcee692fc Author: Amar Tumballi Date: Thu Jun 16 05:30:05 2011 +0000 gluster rebalance: handle the migration of files with 'holes'. treat a block (512bytes) of '0' as hole too (something like 'rsync') Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit e3a061d6fa5f436fe37493b7257860014ae75950 Author: Amar Tumballi Date: Thu Jun 16 07:39:43 2011 +0000 gluster rebalance: bring in a 'force' option * also correct the free space available logic to check the size without the file in migration (this considers the sparse files too) * 'force' option will bypass the free-space check logic, hence will cleanup all the linkfile * 'force' option is valid only with 'migrate-data' option Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit 442f64a83bd2c5da085bc6dc50533df2d483be3b Author: Amar Tumballi Date: Thu Jun 16 04:36:46 2011 +0000 build: fixes to work on solaris Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3002 (build issues on solaris) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3002 commit 41263d553f25e4f59d2751e7e3b2a23b264370f8 Author: Raghavendra G Date: Tue Jun 14 23:56:01 2011 +0000 features/marker-quota: use contribution value to reduce parent's size, if the value to be subtracted is not passed as argument to reduce_parent_size. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit cd2518b4ab627471db74d7f4a473416f318754db Author: Raghavendra G Date: Tue Jun 14 23:55:51 2011 +0000 features/marker-quota: hold lock on dirty inode's parent while healing a dirty inode. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 1040e5149c90e5452c4e86bec5763c392840d160 Author: Mohammed Junaid Ahmed Date: Tue Jun 14 23:55:40 2011 +0000 features/marker-quota: hold parent inodelk during creation of xattrs on directory. Signed-off-by: Junaid Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 5c1c571ad6582142772351e4c106a5b1182a77bc Author: Raghavendra G Date: Tue Jun 14 23:55:30 2011 +0000 features/marker-quota: check for refcount being zero holding lock in quota_local_unref. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit d773462f7c6d1c3c81fa691fc5911641c5bf4394 Author: Raghavendra G Date: Tue Jun 14 23:55:21 2011 +0000 features/marker-quota: wipe parent_loc in marker_local_unref. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 1bdf3cdb86209af56c415151863d6cf67290944a Author: Raghavendra G Date: Tue Jun 14 23:55:09 2011 +0000 marker-quota/rename: use contribution values from backend instead of in-memory while reducing parent sizes during rename Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 7e598e4baa1952d407c1edab329e01634fe719c4 Author: Raghavendra G Date: Tue Jun 14 23:55:00 2011 +0000 features/marker-quota: use mutexes while accessing contribution values. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit acbf2d5dd4782c4236373237d73980163936d17c Author: Raghavendra G Date: Tue Jun 14 23:54:47 2011 +0000 features/marker: fixes in dirty inode self-heal codepath. - fix fd-leak of fd opened on the directory. - don't add (instead just assign) next offset at which readdir has to be sent to local->d_off. - assign to local->d_off before winding lookup call to get child contribution. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit c4c0f7cd9b951bf0f201fa6a52eaebfd4b86c45b Author: Raghavendra G Date: Tue Jun 14 23:54:36 2011 +0000 libglusterfs/call-stub: Allow unwinding of frames for rename during call_resume_unwind. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 8dac046fb727995aca517cceadcc5c59efc8c3f2 Author: Raghavendra G Date: Tue Jun 14 23:54:27 2011 +0000 features/marker-quota: performance optimization. - abort updation process if delta is zero. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit a87555181d47522e985325c67b7d17c49dbd38de Author: Raghavendra G Date: Tue Jun 14 23:54:16 2011 +0000 features/marker-quota: fixes in rename path. - remove xattrs from newpath after rename is complete. - hold inodelk on both parents (if they are different) before doing rename and gather contribution values of oldpath and newpath to their parents while still holding the locks. Use these contribution values to reduce parent sizes. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 01d67311c83ae272f3ee3632c1e8f13ccebaca81 Author: Raghavendra G Date: Thu Jun 9 00:00:10 2011 +0000 features/quota: after validation on a path, reset variable just_validated to zero before checking the size of parent. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2741 (Quota: new files not getting created even if space is available) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2741 commit 9d2b83aaecd66c161863379be3ec22d45ffbe4fb Author: Pranith K Date: Wed Jun 15 06:17:44 2011 +0000 PUMP: perform opendir on pump xlator instead of its child When replace-brick is performed, there is a high probability for the directories on the source brick to not have any pending entry xattrs. So for proper self-heal we need the force merge to kick in. If the opendir is performed on pump xlator directory is examined and if the entries on its children do not match then force merge is triggered, so missing entries will be created on the sink. Pending xattrs are set from source to sink on the files present on source in this process. So when the lookup happens the self-heal is triggered. Before this fix, the code is working because the self-heal source is decided based on what file is biggest in size which is a wrong and removed. Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2586 (read child is set without checking the xattr) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2586 commit 1b70ee9a2e469d2d970abf8e07c1c522c8bdc1df Author: Amar Tumballi Date: Fri Jun 10 06:56:49 2011 +0000 cluster/distribute: remove the unused variable from 'conf' Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 3013 (error in the log file upon taking the statedump) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3013 commit e1aa1e0e20e32e30284c5ffc1add92aebaaaf87e Author: Amar Tumballi Date: Thu Jun 9 00:15:59 2011 +0000 rdma: fix the excessive logs Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit a7a2b8218958579006778b1200a0e40125291e0f Author: Amar Tumballi Date: Wed Jun 8 23:37:46 2011 +0000 build warning fixes mainly fixes all the sockaddr related 'strict aliasing' warnings Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2550 (build warnings) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2550 commit e719518e561033af0ffd07d0c8ad7d777715fe89 Author: Amar Tumballi Date: Wed Jun 8 23:37:22 2011 +0000 fixing some build issues in Mac OS X Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2966 (MacOSX compile failure: duplicate symbol _k) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2966 commit dad63fa8ac00397e337f328b0bb7b641e2680932 Author: Sachidananda Date: Thu Jun 16 07:56:33 2011 +0000 Update man pages to include newer options. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2444 (keep man pages upto date with new codebase.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2444 commit 1d4378e0e78309682c13d0fc0c97c3c3bb6674b7 Author: Krishnan P Date: Thu Jun 16 01:28:28 2011 +0000 pump: cleanup xattrs on both commit and abort path. This change makes glusterd to send a setxattr command for replace-brick commit operation similar to abort. Earlier we could commit even before the 'migration' of data was complete, with this change we fail that operation. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3033 (Changes to replace-brick and syntask interface.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3033 commit 4e6f6408b0e177dcdc0b19561bbaab6b7e26c23a Author: Krishnan P Date: Thu Jun 16 01:27:42 2011 +0000 glusterd: do_operation_abort and then kill dst_brick. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3033 (Changes to replace-brick and syntask interface.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3033 commit 87508c1edc7b8f4a88b2506ac642e878b1f2ac16 Author: Krishnan P Date: Thu Jun 16 01:26:55 2011 +0000 afr: holding stack var via dict_set_static_bin corrupts. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3033 (Changes to replace-brick and syntask interface.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3033 commit 84fe7114833aed4efc31a1beaf7fcff0124c0ab4 Author: Krishnan P Date: Thu Jun 16 01:26:00 2011 +0000 syncop: Modified to accept one 'non-frame' arg. Earlier syncops used to accept one argument which was a call frame to carry out the fops synchronously. Now we have two args passed to synctask function, one call frame and another void pointer. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 3033 (Changes to replace-brick and syntask interface.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3033 commit 3f2c74a941f34b29dd92e4754d01ebea9db42218 Author: Sachidananda Date: Thu Jun 16 01:21:25 2011 +0000 Delete/correct deprecated options in sample vol files. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3031 (Fix share/{doc,man} directory) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3031 commit 8791651c43337c081d684c04c4018c2c3eb56ac5 Author: Raghavendra Bhat Date: Wed Jun 15 23:52:48 2011 +0000 features/locks: check for inodelk lists and blocked inodelks instead of entrylk in inodelk.c Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 3032 (entrylks are checked instead of inodelks while checking the blocked inodelks conflict) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3032 commit 4566fb78c16948f91e7d5b1934d8722b51508053 Author: Sachidananda Date: Wed Jun 15 06:54:22 2011 +0000 Bring `examples' directory upto date. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 3031 (Fix share/{doc,man} directory) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3031 commit 4ba661f5989db0148c7c1f4631645f932a99fe56 Author: Raghavendra Bhat Date: Tue Jun 14 12:31:07 2011 +0000 features/locks:update the refcount while releasing a lock Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 3025 (open lock and close leads to memleak) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3025 commit 9e59ce6d30f4ffd3dc7fb88c29fbd0ea79b9de28 Author: Raghavendra G Date: Tue Jun 14 01:42:10 2011 +0000 performance-translators: print path to file while dumping fdctx. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit 90117ca1c28b54845d617cdba0887d6453f875a4 Author: Raghavendra G Date: Tue Jun 14 01:41:56 2011 +0000 performance/read-ahead: dump pages in read-ahead cache. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit aae8ad0cf080ff3e4f704f3bcccef39a07cabb05 Author: Raghavendra G Date: Tue Jun 14 01:41:36 2011 +0000 performance/stat-prefetch: dump cache and list of ops waiting for lookup completion. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit e8f67179ca60eb81a4b1fa92e37bd0eb6213d659 Author: Raghavendra G Date: Tue Jun 14 01:41:24 2011 +0000 rbthashtable: implement traverser procedure. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit 72d56ff2a8bd0eacfa8036f7583fc0dd4de460d0 Author: Raghavendra G Date: Tue Jun 14 01:41:11 2011 +0000 libglusterfs/inode.c: Add version of inode_path which can be called holding inode->lock. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit 837f172e8775c908cb90c14a956ed010d468a0ad Author: Raghavendra G Date: Tue Jun 14 01:40:58 2011 +0000 performance/quick-read: dump inode and fdctx during statedump. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit dd4a0d45a91104117c0ad5de85deaabe6df88677 Author: Raghavendra G Date: Tue Jun 14 01:40:45 2011 +0000 performance/io-cache: print cache information during state dump. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059 commit 1f14a1fccd5a8eed92936d9910d4b9a45ca1b56c Author: Junaid Date: Tue Jun 14 03:28:59 2011 +0000 cli: 'QUOTA' Display the limit-set and size of the directory in KB, MB, etc Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2829 (Display the quota limit as it is configured) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2829 commit 6ae674eef777fda74191e2186d95778b9d5671f3 Author: Junaid Date: Tue Jun 14 03:28:40 2011 +0000 libglusterfs/common-utils: Added gf_uint64_2human_readable function. This function converts the given number to its corresponding representation in KB, MB, etc. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2829 (Display the quota limit as it is configured) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2829 commit a383d5b22aae9837f5609f304ee0488bcf8bafba Author: Junaid Date: Tue Jun 14 03:44:30 2011 +0000 mgmt/glusterd: Set the generic options in the graph before merging it with the parent graph while building nfs-server volfile. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 3003 (Modification of one of the options of volume is reflected in all the volumes in the nfs-server-volfile) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3003 commit 4a95dd213c039834c958bc1e3845037aa87fcde2 Author: shishir gowda Date: Mon Mar 21 05:35:06 2011 +0000 Prevent spurious getxattr for gfid-req in posix_lookup Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2570 (getxattr failed msgs seen in log when log-level is DEBUG) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2570 commit 2a2060359a6991e310e6532376273bccb9cfbadc Author: shishir gowda Date: Tue Apr 12 05:19:22 2011 +0000 DHT: check for mis-matching user xattrs Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2717 (Detect user_xattr mismatches for dir's) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2717 commit b81ab76a2b3163b9326c5c024c7dc5f51e6ae868 Author: Amar Tumballi Date: Wed Jun 1 04:51:08 2011 +0000 gluster rebalance: fix the mount command string error creeped in while bringing in 'runner' options Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit c31eb96811e6e99f79466fdf9c1dbb0c6fb00f7f Author: Lakshmipathi Date: Mon Mar 21 04:32:26 2011 +0000 removed unused old sample files Signed-off-by: Lakshmipathi.G Signed-off-by: Anand Avati BUG: 2552 (remove old sample vol.files) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2552 commit 1b8376013d2358a50bd7487e1abaa377d51ec4e6 Author: Junaid Date: Mon May 30 09:18:23 2011 +0000 cli: Display a warning upon disabling quota. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2912 (Display warning upon disable quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2912 commit f87ec977c2c6bf8c562c11ad72069648beb6d8cd Author: shishir gowda Date: Fri Jun 10 05:11:51 2011 +0000 DHT selheal dir: Recreate dirs with correct gfid. When selfheal of dir is triggered, make sure the dirs are recreated with the correct gfid, to prevent mismatch of gfids in the backend. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2994 ([glusterfs-3.2.1qa2]: untar and rm in parallel hangs untar) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2994 commit 89e277a5deb2cd5191106119e91bf285a5b74e51 Author: Anand Avati Date: Fri Jun 10 04:37:14 2011 +0000 cluster/afr: propagate proper errno returned by lock fops If locks could not be held on any of the servers, then propagate the errno returned by the lock FOPs instead of hardcoding EAGAIN/EINVAL. Signed-off-by: Anand Avati BUG: 2993 ([glusterfs-3.2.0qa2]: hang while doing the selfheal) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2993 commit 42c85439fe470a8cb4eb82944cb5ed094b740f8e Author: Anand Avati Date: Thu Jun 9 02:32:01 2011 +0000 cluster/dht: use GFID returned from hashed subvolume .. to perform lookups on remaining subvolumes. This way, if there is a race between two clients to 'fix' GFIDs with gfid-req, then the hashed subvolume will arbitrate and return the winner in stbuf->ia_gfid. This patch uses the returned gfid as the new gfid-req thereby preventing mismatching GFIDs on other servers due to further races. Signed-off-by: Anand Avati BUG: 2522 ([glusterfs-3.1.3qa8]: rm -rf shows invalid argument) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2522 commit 29397bda249d8d3f93dd6ee5c449b3590dbaf15e Author: Lakshmipathi Date: Tue Jun 7 03:47:11 2011 +0000 build : use pid file to kill nfs process Signed-off-by: Lakshmipathi.G Signed-off-by: Anand Avati BUG: 2969 (add --pidfile option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2969 commit 2b53a40350afa4dd9e0d77502700cdee0299766c Author: Amar Tumballi Date: Wed Jun 8 09:29:21 2011 +0000 rpc-transport/rdma: don't return '0' in case of un-initiated rdma_connect() needed to handle the re-configuration of the port in client protocol. If there is a successful 'connect()' after the query port, the remote-port value gets reset to '0'. In this case, if the connect() return 0 for already connected socket, the query_portmap will keep happening in a loop. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit d9db06e6ca108cada080de93d3cc25ba2b14becb Author: Raghavendra Bhat Date: Wed Jun 8 09:29:06 2011 +0000 nfs:command to change the transport type of nfs server for volumes of transport tcp, rdma Signed-off-by: Raghavendra Bhat Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit 19f375da5b43f940131623b2f33675aa2b3f5c8a Author: Amar Tumballi Date: Wed Jun 8 09:28:49 2011 +0000 fix multiple transport portmap issues in client handshake Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit fe4eb7c3ac96218fe151633c5ccd34b7c0bea783 Author: Amar Tumballi Date: Wed Jun 8 09:28:23 2011 +0000 glusterd-volgen: fix rdma volume file path in case of 'tcp, rdma' transport. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit aa9a6bc1bfd87aa70018dc6acc90fb94cba811c6 Author: Gaurav Date: Wed Jun 8 05:59:03 2011 +0000 NFS : Don't set setattr_valid for exclusive create call. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit a9fd99f0d0206d4951aa50630b7921a50523bf23 Author: Kaushik BV Date: Thu Jun 2 04:39:27 2011 +0000 cluster/stripe: check if key is a valid ptr. before dereferncing Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2978 (Geo-replication fails on stripe(Master) setup.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2978 commit ddb2505383441b0bf41e31c13f90420f5d14d1dc Author: Lakshmipathi Date: Mon Jun 6 04:11:19 2011 +0000 rpmbuild : restart glusterd after installing geo-replication rpm Signed-off-by: Lakshmipathi.G Signed-off-by: Anand Avati BUG: 2901 (Cannot start geo-replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2901 commit d11c17b8dae415f0f5c9af2cd4ec3423419ff996 Author: Raghavendra Bhat Date: Fri Jun 3 01:05:32 2011 +0000 protocol/server: logging changes Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2982 ([glusterfs-3.2.1qa2]: logging changes is server protocol) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2982 commit 2c421f21040e1f9273cb9850c95756d3a4ca91af Author: Amar Tumballi Date: Thu Jun 2 02:59:07 2011 +0000 performance/io-cache: fix the check of min and max file size. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2974 (volume set for 'cache-min-file-size' succeeds even if 'min-file size' is greater than 'max-file-size') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2974 commit 7959e867632baad702d1d5c8dc4fc4854d17e3e1 Author: Krishnan Parthasarathi Date: Mon Jun 6 04:22:47 2011 +0000 glusterd: replace brick status grows with dir tree. replace-brick status message's size can grow long with deep directory trees. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2489 (GlusterFS crashing with replace-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2489 commit 125fc0ca98332cd20917daab0a170342b7f5e156 Author: Krishnan Parthasarathi Date: Mon Jun 6 04:22:46 2011 +0000 syncop: Increase stack size for deep call stack. pump performs a depth-first traversal of directories using the syncop stack and this necessitates a larger stack when handling deeper directory trees. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2489 (GlusterFS crashing with replace-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2489 commit e45c3e22a13332253fcc89ea528a4d77aa9ecc0f Author: Junaid Date: Mon Jun 6 22:36:43 2011 +0000 mgmt/glusterd: Updated the error messages sent on cli quota command failure. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2856 ([glusterfs-3.2]: Misleading 'quota remove' output.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2856 commit 99588612db403dffdb6380ceaaec1a8b10a3be5d Author: Pranith Kumar K Date: Mon Jun 6 03:10:39 2011 +0000 cluster/afr: Log errors in afr self-heal with GF_LOG_ERROR Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2986 (Failed operations should should be logged `E' or `W') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2986 commit c997393c8a546e28648d56d2e86651f4bb4b38d8 Author: Pranith Kumar K Date: Mon Jun 6 03:10:38 2011 +0000 protocol/client: Change log level of error to GF_LOG_ERROR Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2986 (Failed operations should should be logged `E' or `W') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2986 commit 1c034335054090c7dd967ea21a234c1dd8e78c9c Author: Raghavendra Bhat Date: Wed Jun 1 00:31:07 2011 +0000 cli: fix the build warning message Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2944 (warnings in cli_out) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2944 commit 197d850ff62ddcb266e3a9fab30ce753bf123540 Author: Gaurav Date: Tue May 31 23:40:27 2011 +0000 NFS : Handle buffer overflow in nfs3_create_exclusive. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2972 (Buffer overflow in nfs3_create_exclusive.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2972 commit 37b562b1605f900927494ec501dff4190eb26097 Author: shishir gowda Date: Fri May 27 04:28:15 2011 +0000 glusterd: add upgrade/downgrade xlator options If started with upgrade-option, the current behavior is to recreate brick volfiles, as from 3.2 marker xlator is default. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2904 (glusterd should have upgrade/downgrade xlator options) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2904 commit f4c4007263255c49b00eaf62542ec2386ca60302 Author: Amar Tumballi Date: Tue May 31 01:01:01 2011 +0000 gluster rebalance: prevent data migration from higher disk space to lower this is done using the 'statfs()' on inode feature. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit 0d2d861849a3b066eac676ebed4e16accdfe8598 Author: shishir gowda Date: Thu Apr 14 05:11:33 2011 +0000 DHT:first_up_subvol should be the one up the longest Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2684 (Dir missing from mount point) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2684 commit dd476eb4678df02ff22f9aa7db7453f857721c42 Author: Raghavendra Bhat Date: Mon May 30 03:42:50 2011 +0000 stripe: changes to print stripe information in statedump Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2958 (stripe information is not printed in statedump) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2958 commit 8b53f87878d0eae5bab521d3d429ca19ea903d9a Author: Lakshmipathi Date: Mon May 30 04:45:19 2011 +0000 build : with rpm install invoke glusterd upgrade option to modify vol files and start Signed-off-by: Lakshmipathi.G Signed-off-by: Anand Avati BUG: 2904 (glusterd should have upgrade/downgrade xlator options) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2904 commit 5f1c41d9088272617fd1afeccd679abdb5f36a3f Author: Amar Tumballi Date: Wed May 25 05:14:25 2011 +0000 cli: bring in format checking option for 'cli_out()' Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2944 (warnings in cli_out) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2944 commit d150340907efe888cdabfd4e49552fa8c75f2445 Author: Amar Tumballi Date: Wed May 25 05:14:04 2011 +0000 cli: fix format string build warnings Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2944 (warnings in cli_out) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2944 commit d720547e9e5960481930f532fe208f7c6db4cd93 Author: shishir gowda Date: Tue May 31 06:40:27 2011 +0000 client_bind: When allow-insecure xlator option is set, donot bind. There is no need to bind a client, as connect will assign a port. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2868 (Add xlator-option to support insecure-bind for clients) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2868 commit 756c7aea3fef2a77b13ed731ab202c5426db3768 Author: Amar Tumballi Date: Tue May 31 06:39:41 2011 +0000 glusterfsd: prevent giving '-s' option without '--volfile-id' option Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2934 (for glusterfs binary, -s option without --volfile-id will fail without any notice to user) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2934 commit 753f17aca63057e4c4a70c1f3cbf7729f890cb69 Author: shishir gowda Date: Fri May 27 00:41:55 2011 +0000 dht-rename: Unlink older link files before creating new one If a older link file exists, unlink it and then create the linkfile. This will prevent mis-match of gfid's. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2464 ([7b07d444a77526f27f860210930bf1d4c7fbea9b]: rm -rf gives Invalid argumenrt error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2464 commit c5a7947e6a7422360816e45fc3c12cf9c0152802 Author: Pranith Kumar K Date: Tue May 31 06:08:12 2011 +0000 pump: init last_event array to be used in afr_notify Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2870 (Inconsistent xattr values when creating bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2870 commit 1b0c33f8960fb1fae03012b479d6cac9ce4d8941 Author: Sachidananda Date: Mon May 23 12:23:11 2011 +0000 Fix typo in log message related to io-threads. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2926 (Typo in log message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2926 commit 793aba82fa9585985b4285a92f9bce5b28f5c8db Author: Gaurav Date: Mon May 30 05:00:50 2011 +0000 RPC : Valid typecasting for ipv4 and ipv6 in rpcsvc_get_listener_port. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2956 (Invalid typecating for ipv4 and ipv6 in rpcsvc_get_listener_port.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2956 commit d7497c4f1b361b1d1c42c157cbcf7ce8bc16fd44 Author: Amar Tumballi Date: Thu May 26 07:45:49 2011 +0000 statfs(): honor the 'inode' on which the statfs() call is made fuse-bridge : fill the 'loc' properly with correct 'inode'. dht : if directory, send statfs() to all subvol, else send it to only cached subvol. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit 411aa2902d304495a4a374a09b767e588b330e88 Author: Raghavendra G Date: Wed May 25 04:26:00 2011 +0000 performance/stat-prefetch: return ESTALE if inode's gfid is not the same as cached gfid for a path. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2927 (Mismatched link/target gfid and ESTALE/ENOENT) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2927 commit fcd35ea786dea454b11837f818be959082c8e731 Author: Pranith Kumar K Date: Mon May 30 07:55:00 2011 +0000 features/locks: Unwind with SUCCESS on non-blocking entrylk success Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2949 (self-heal hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2949 commit f1a6ff00a1a4d5bb1124d853c60f68c55d42ad4d Author: Pranith Kumar K Date: Mon May 30 07:54:59 2011 +0000 cluster/afr: Send Non-blocking lock in non-blocking entrylk Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2949 (self-heal hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2949 commit b8957c72e34d9f3174722059618d148b4a4ff38e Author: Pranith Kumar K Date: Fri May 27 01:13:39 2011 +0000 cluster/afr: Send the first child up/down after all its children notify Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2870 (Inconsistent xattr values when creating bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2870 commit 865c74963525bba325c6262a14e37764d1bc0a8a Author: Pranith Kumar K Date: Fri May 27 01:13:40 2011 +0000 cluster/dht: notify should succeed when waiting for all subvols first event Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2870 (Inconsistent xattr values when creating bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2870 commit 493274b4051beca13f7153bc583cb60661a546c0 Author: Anand Avati Date: Fri May 20 16:56:32 2011 +0000 glusterfsd-mgmt: include signal.h Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit b0c07f4db5f1ed2eeb58709d1021e11ca8fd5600 Author: Anand Avati Date: Fri May 20 16:56:31 2011 +0000 rpc: NetBSD portability fixes NetBSD's does a #defiine d_ino d_fileno. Since glusterfs declares structs with d_ino members, we must include early so that d_ino get preprocessed into d_fileno conssitently. Also define proper xdr types for NetBSD. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 7eb3ba062cd0d8ad2d4692c99185af2afde0ee05 Author: Anand Avati Date: Fri May 20 16:56:30 2011 +0000 fuse: NetBSD portability fixes Make sure NetBSD pulls proper FUSE header Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 24d94224ea8c9b67dd7bb9a2ee929f63717d51d7 Author: Anand Avati Date: Fri May 20 16:56:29 2011 +0000 quick-read: Fix dirname(3) usage glibc dirname() modify the string it is given and returns it. glusterfs takes this behavior for granted, and assume that if it gives a malloc'ed string to dirname(), then it can free()) the return value. Here is what SUSv2 says: http://opengroup.org/onlinepubs/007908799/xsh/dirname.html "The dirname() function may modify the string pointed to by path, and may return a pointer to static storage" At least NetBSD returns a static storage. glusterfs will return it to a calling function that has the responsability to free it, causing a SIGSEGV. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit fa19eabd89c0efc52830ad5f6ac63285175acce7 Author: Anand Avati Date: Fri May 20 16:56:28 2011 +0000 stat-prefetch: fix dirname(3) usage glibc dirname() modify the string it is given and returns it. glusterfs takes this behavior for granted, and assume that if it gives a malloc'ed string to dirname(), then it can free()) the return value. Here is what SUSv2 says: http://opengroup.org/onlinepubs/007908799/xsh/dirname.html "The dirname() function may modify the string pointed to by path, and may return a pointer to static storage" At least NetBSD returns a static storage. glusterfs will return it to a calling function that has the responsability to free it, causing a SIGSEGV. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 80b84f4b852c2794c46af4de1e8ab48673163dc3 Author: Anand Avati Date: Fri May 20 16:56:27 2011 +0000 fuse: NetBSD portability fixes - NetBSD uses libperfuse(3). - Add @GF_FUSE_LDADD@ to fuse.so library dependecies so that -lperfuse is added at configure time for NetBSD. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit beb2b28ff105bad260c4fda891c174a6bff0abd4 Author: Anand Avati Date: Fri May 20 16:56:26 2011 +0000 rpc: TCP_KEEPALIVE undeclared in NetBSD Works around "error: 'TCP_KEEPALIVE' undeclared" on NetBSD Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 291588c6d912e137ef4d8c19d0447e43c7d87bc4 Author: Anand Avati Date: Mon May 30 04:18:00 2011 +0000 fuse: NetBSD portability fixes On NetBSD use libperfuse(3), rename umount2(2) as unmount(2), and skip inexistant /etc/mtab management. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit f2e0b36ea6d31a09f4013b2e6f6ffccc4aca9c0b Author: Anand Avati Date: Fri May 20 16:56:24 2011 +0000 errno: NetBSD does not have EDOOFUS Thanks to: Emmanuel Dreyfus [avati@gluster.com: check for EDOOFUS instead of !NetBSD] Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 7f1c2eb4d473b9323b3a31b33473f7fe06cee449 Author: Anand Avati Date: Fri May 20 16:56:23 2011 +0000 rpc: use AI_ADDRCONFIG selectively NetBSD does not have AI_ADDRCONFIG. This patch has a side effect: glusterfsd listens on IPv6 adresses only by default. Option transport.socket.bind-address in volume server-tcp must be used to listen on an IPv4 address. Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit 9737ef5bbaaf2b4c02ea1710dccbd5464173b2e3 Author: Anand Avati Date: Fri May 20 16:56:22 2011 +0000 mount.glusterfs: The == operator is a non-standard bash extension. = should be used instead Thanks to: Emmanuel Dreyfus Signed-off-by: Anand Avati BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923 commit dd55755e0ccc94f721e8ada7e50c976c9cb68c4b Author: Amar Tumballi Date: Wed Apr 13 00:27:02 2011 +0000 rpc-clnt: consider the (re-)configured port for only one connect() call this way, if remote_port is set due to queryport, that can fall back to default port (or 'option remote-port' value) when it disconnects. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2709 (issues with port (re-)configuration in client protocol) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2709 commit dbd9dfdba36bee1a249c0e29edbfe0ded59e8c2d Author: Junaid Date: Tue May 17 06:29:22 2011 +0000 cluster/stripe: Fix a typo in strncmp. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2760 (Quota: stripe volume not showing the quota size properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2760 commit f2d0baecfffe96231b52304ad0560c0697150fff Author: Kaushik BV Date: Sun May 15 04:59:53 2011 +0000 mgmt/glusterd: Display a warning message to CLI in case of a corrupt geo-rep session Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2828 (gluster geo-rep stop should not show unsuccessful when the status is corrupt) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2828 commit e1f79413774939bd23563b1d85b0c64a989301bc Author: Krishnan Parthasarathi Date: Fri May 27 00:29:10 2011 +0000 pump: Detect 'empty' brick and finish migration. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2909 (replace brick of empty brick never says migration completed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2909 commit fdf3bd3e548c380820219b135e16e9731e31c7c6 Author: Vijay Bellur Date: Sun May 29 08:11:22 2011 +0000 mgmt/glusterd: Set option listen-backlog to 128 Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 2941 (glusterd breaks when starting ~100 volumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2941 commit b4fc412a46d8a71cf02d847b0e359b6668e218f2 Author: Vijay Bellur Date: Sun May 29 08:10:48 2011 +0000 rpc: Introduce option for listen()'s backlog Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 2941 (glusterd breaks when starting ~100 volumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2941 commit 4c1c8feee4afd6cabeabc17c85bbc7634adb683f Author: shishir gowda Date: Thu May 26 05:45:07 2011 +0000 TOP: exit status should be non-zero for success The fault was incorrect loop. An extra iteration was being performed, and dict_get failed due to non-existant data leading to status being set to non-zero Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2882 (Make volume top command exit status as zero on success) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2882 commit 7dc5a648caee92ce6d62bbe7b4dc1406662c3858 Author: Pranith Kumar K Date: Thu May 26 04:17:15 2011 +0000 mgmt/glusterd: Start nfs after all bricks are started on glusterd re-start Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2941 (glusterd breaks when starting ~100 volumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2941 commit 235938a9137cf261de20df365f4feae7a33ce5d9 Author: Amar Tumballi Date: Wed May 25 07:30:15 2011 +0000 performance/io-cache: fix annoying logs during reconfigure Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2945 (disturbing logs in io-cache reconfigure()) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2945 commit 4e9c47c4b5ae3209c2853cf034aa00777c76d55e Author: Anand Avati Date: Fri May 20 15:32:27 2011 +0000 cluster/dht: detect linkfiles mismatching gfids and delete+recreate Signed-off-by: Anand Avati BUG: 2522 ([glusterfs-3.1.3qa8]: rm -rf shows invalid argument) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2522 commit 9072b817b0803f999081c6244b18a9ae8fb0234c Author: Csaba Henk Date: Thu May 26 03:32:27 2011 +0000 reimplement invocation of external programs with run API Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2562 (invoke external commands precisely with fork + exec) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2562 commit 302ad26982d1eb7762e743e14dda627ffb317379 Author: Csaba Henk Date: Thu May 26 03:32:26 2011 +0000 libglusterfs: add 'run' sub-lib for safe and convenient invocation of external programs Summary: - arguments first collected, then the invocation happens with fork + exec - flexible specification of arguments (besides si{mp,ng}le argument addition, support for adding multiple of them at a time / specifying one with printf style formatting) [ ==> goodbye printf percentage soup when composing commands ] - single point of error check - simple command runs are done in just one line - support for redirection, popen(3) like functionality API is documented in details in libglusterfs/src/run.h Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2562 (invoke external commands precisely with fork + exec) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2562 commit 3435813379c276c3c020cb4e3942554be0040ecc Author: Csaba Henk Date: Thu May 26 03:32:25 2011 +0000 libglusterfs: clean up memory types Unify them in one header, weed out overlap. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2562 (invoke external commands precisely with fork + exec) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2562 commit 6ff690a54ea7d26089be29470e499292971dd30e Author: Csaba Henk Date: Thu May 26 03:32:24 2011 +0000 Revert "temporary workaround for mtab update race thingy" This reverts commit 59b9ab45a01d52e197ab6f76fd71e64910396d57. [c5d781e0 made this temporary workaround unnecessary] Conflicts: xlators/features/marker/utils/syncdaemon/resource.py Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2690 (race between mtab updates of mount and umount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2690 commit 19b08a3b627cb8a7f74fc608bfcaddc4e063aa6f Author: Raghavendra Bhat Date: Wed Apr 13 02:24:49 2011 +0000 replicate: print favorite child as an int instead of unsigned int Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2668 ([glusterfs-3.2.9qa7]: createbench error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2668 commit 2cd8411a0278f98ed820aad3e482de079d0540c0 Author: Venky Shankar Date: Mon Apr 25 03:10:01 2011 +0000 cli log level command and per translator log level Signed-off-by: Venky Shankar Signed-off-by: Anand Avati BUG: 2714 (implement cli log level command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2714 commit 03c58c782d99440a5947289d0ff216bca8ef7c57 Author: Raghavendra G Date: Wed May 18 23:21:02 2011 +0000 debug/error-gen: include error-gen-mem-types.h in distribution tarball. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2915 (error-gen-mem-types.h is not included in distribution tarball generated by doing 'make dist') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2915 commit c5d781e05599e9e7ad736d42c9c1033992c76ded Author: Csaba Henk Date: Sun May 15 04:52:33 2011 +0000 upon daemonizing, wait on mtab update to terminate in parent This fixes the race in between the mtab update attempts of mount and umount when we do a lazy umount right after mounting, in order to hide the given fs instance; yet this way we still avoid the deadlock of the fs and mount which we can hit if we wait unconditionally for the mtab update to terminate (cf. bz #511). Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2690 (race between mtab updates of mount and umount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2690 commit 357df32e16dd21e7aedb699c7bd99cac9b95a040 Author: shishir gowda Date: Mon May 2 03:47:39 2011 +0000 Introduce client-allow-insecure xlator-option. Allows glusterfs clients to bind to any port and does not restrict it to 1024. This is a xlator-option only, and is not supported in volume set cmd. The reason is, few clients may choose this, and few may not. Hence only supported as a xlator-option during mount time. For this to work with glusterfs, server.allow-insecure should be set to on Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2868 (Add xlator-option to support insecure-bind for clients) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2868 commit afad4e2d64c6bb01ff5dceb29b20ebcc02c1747b Author: Amar Tumballi Date: Wed Apr 20 23:46:05 2011 +0000 cluster/stripe: make sure gfid is checked with valid data earlier logic of determining if different subvolumes have different gfid for same file had a flaw. It could have checked with a empty gfid field in case a reply comes from other subvolumes before first subvolume Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2773 ([glusterfs-3.2.0qa12]: stripe lookup says gfid different) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2773 commit ef3d2a48f480d29c2087a5562c73681530f2c727 Author: Shehjar Tikoo Date: Mon Apr 18 00:58:49 2011 +0000 gnfs-loganalyse: Track fh & entry operations given filename Introduces support for outputting only those NFS operations that operate on a given filename and all the filehandles that are seen in the log file for that filename. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand Avati BUG: 913 (NFS-specific log analyzer tool) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=913 commit 4ba7635f4d3f199dbb082b45cfe7b49f7e243587 Author: Raghavendra Bhat Date: Mon May 2 05:36:17 2011 +0000 glusterd: send the duplicate brick info to the cli Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2803 ([glusterfs-3.2.0qa14]: volume create succeeds even though there is a volume with an export directory in the path of current volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2803 commit 276c0cecadbe763e98c5cfd18b3ad32822964789 Author: shishir gowda Date: Mon May 2 05:08:39 2011 +0000 Validate stripe-block-size option Minimum size is 512 bytes and should be a multiple of 512 bytes. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2861 (Stripe block-size has no check for valid option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2861 commit 0f020affb2cbbcf7c3a25f9f10fe8f14bf012b8e Author: Sachidananda Date: Mon May 2 03:32:31 2011 +0000 Move `self-heal completed' message to log level INFO. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2867 (Move self-heal completed message to INFO level) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2867 commit e08383ca1236924e292dc4ce0b8ff2208f4f5170 Author: Raghavendra G Date: Sun May 8 23:41:23 2011 +0000 features/marker: whitespace cleanup Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 86c818a98a18a3b6c33a494202922f1cd275ac7b Author: Csaba Henk Date: Wed May 11 02:39:14 2011 +0000 cli: taking my revenge for forcing "geo-replication" into commandline Accept unambigous initial fragments of keywords, eg. gluster vol geo stat is recognized. Compared to readline integration: - no external dependency - works in shell too - works for inner keywords of operations (as in above example, or "vol crea repl 3 ...") - you save pressing tabs :) If not desired in customer builds, can be disabled by an #ifdef (not integrated into build system as of now); however, I think folks in house could like it. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2757 (refactory gsync/gsyncd/syncdaemon/whatever to geo-replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2757 commit 0652f9f92123e8bb3c0fee02c9fb3bbe23d9f7c6 Author: Csaba Henk Date: Fri Apr 29 12:25:36 2011 +0000 syncdaemon: fix listing xattrs when there is none and failure handling Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2859 (gsyncd crashes if master vol root has no xattrs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2859 commit 6f2ed82bfcfe494ef273bff55cf69480a7472cc5 Author: Csaba Henk Date: Fri Apr 29 06:24:45 2011 +0000 syncdaemon: some refactor on monitor - detect faulty state early - keep the feedback fd in gsyncd module Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2537 (gsync autorestart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2537 commit 9ffd9c51f3833e04a60373648ba3c69c2ed7a68a Author: Csaba Henk Date: Fri Apr 29 06:24:43 2011 +0000 marker: fill out the volume-mark properly in case of marking corruption Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2858 (volume-mark corruption swallowed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2858 commit a8addec412a7d6816e06dbbef2e14022edc6ec39 Author: Csaba Henk Date: Fri Apr 29 06:24:42 2011 +0000 syncdaemon: add --normalize-url option Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2828 (gluster geo-rep stop should not show unsuccessful when the status is corrupt) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2828 commit fa445b44c66eeebc09a3df74d5e924037a3d89c6 Author: Csaba Henk Date: Fri Apr 29 06:24:41 2011 +0000 glusterd / geo-rep: set session owner to the uuid of the master vol instead of that of glusterd Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 97fdc05ab86ca2af992c42b09ed40413be2ef0d8 Author: Csaba Henk Date: Fri Apr 29 06:24:40 2011 +0000 glusterd / cli / rpc: move geo-replication reply parameters into dict Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 6dd0282fbfa14eb5a6ae3df1083ef1eea443ea20 Author: Krishnan Parthasarathi Date: Wed Apr 27 04:46:24 2011 +0000 posix: glusterfs.test should be removed xattr immediately after use. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2609 (Error message not properly provided when trying to create a volume from a read-only source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2609 commit a7ca559bdebfcef9a38dfedb8e4757d42431bf94 Author: Krishnan Parthasarathi Date: Wed Apr 27 04:46:23 2011 +0000 Detect read-only filesystem and fail the brick creation operation. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2609 (Error message not properly provided when trying to create a volume from a read-only source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2609 commit 57b53ca592c8d2d01767c7943cb071eb24e6835f Author: shishir gowda Date: Mon May 2 01:38:09 2011 +0000 set: Fix incorrect nfs.rpc-auth strings in nfs_option_handler Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2866 (volume set for nfs rpc-auth.addr* option succeeds, but vol file not updated) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2866 commit 68a7f34104854101dcc2c54a797f5aced90908e5 Author: Anand Avati Date: Wed May 4 06:02:02 2011 -0700 configure.ac: set default version to 3git commit 44fca3bae2092c50bad31427eaf5b2aec9672e09 Author: Amar Tumballi Date: Fri Apr 15 01:27:25 2011 +0000 add 'logrotate' config file to the package Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2053 (We need to support the standard *nix 'logrotate' for server and client log files.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2053 commit 581ee51454d70ace694acfdd6a5b8abb12050dc9 Author: shishir gowda Date: Mon May 2 03:47:19 2011 +0000 gf_auth also needs to handle server.allow-insecure When server.allow-insecure option is set, the connection from client can be from any port. gf_auth also needs to check for this option Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2868 (Add xlator-option to support insecure-bind for clients) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2868 commit e3571d4aab9b727715f0e51d12e6e0596f0111ce Author: Krishnan Parthasarathi Date: Tue May 3 05:04:57 2011 +0000 glusterd: Checked brick path length in 'staging'. Added checks for brick path length in 'staging' of add/replace brick and create_volume subcommands. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2847 (volume creation fails if brick path is long) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2847 commit f5708f4d0696529faf1fb0ad108123a76c816d78 Author: Krishnan Parthasarathi Date: Tue May 3 02:05:38 2011 +0000 glusterd: Cleaned up 'store' if vol create fails. glusterd's internal 'store' needs to be cleaned up if volume creation operation fails. Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2847 (volume creation fails if brick path is long) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2847 commit 53af855f2aad8c19f2bbc7561534b473ae8c7dc4 Author: Pranith Kumar K Date: Wed May 4 04:14:02 2011 +0000 cluster/afr: set loc gfids for fresh lookup Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 0336456447f636f6fcf8e53bbfb6295d40434fdf Author: Gaurav Date: Thu Apr 21 03:58:48 2011 +0000 NFS : Use proper exit point in nfs_init_state. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2695 (Mac host showmount -a not working.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2695 commit 6b02f2ac6a3889af0b0e1cdb4402352379b37539 Author: Amar Tumballi Date: Thu Apr 21 03:43:20 2011 +0000 cluster/distribute: corrected layout mismatch handling logic Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2281 (I/O operations exit when add-brick is done) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2281 commit 27deebbf6c67f5076cae241e98043aa8b8b57ff8 Author: Gaurav Date: Wed Apr 27 03:20:11 2011 +0000 NFS : Maintain common state for MOUNT1 and MOUNT3. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2695 (Mac host showmount -a not working.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2695 commit 7e8da0f5a8bfdd2d1db084fb508b417194754bff Author: Sachidananda Date: Mon May 2 02:56:40 2011 +0000 Move the log `self-heal pending' message to INFO level. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2867 (Move self-heal completed message to INFO level) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2867 commit ea5eec6b7e736c1ce149b32e8fcd1180c1c2db9f Author: Sachidananda Date: Mon May 2 02:47:53 2011 +0000 Move self-heal completed log message to INFO level. Signed-off-by: Sachidananda Urs Signed-off-by: Anand Avati BUG: 2867 (Move self-heal completed message to INFO level) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2867 commit cadd9a1b75fb1f78d2fb7c578212ee0225cfeb83 Author: Amar Tumballi Date: Mon May 2 03:11:54 2011 +0000 loc_t: add 'gfid' and 'pargfid' fields these fields are used mainly in case of selfheal path, where 'inode->gfid'||'parent->gfid' is not yet set. These fields in 'loc' will have lower precedence than 'inode->gfid' in client protocol. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit fd7e3b6052881319d4671771aae44933bbf858d4 Author: Raghavendra Bhat Date: Sat Apr 9 01:54:19 2011 +0000 enable memory accounting for error-gen xlator Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 329 (Replacing memory allocation functions with mem-type functions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=329 commit 1f06da6875d8ecff5efa2b6db387ef6084bb68a1 Author: Raghavendra G Date: Sun Apr 24 22:45:31 2011 +0000 performance/write-behind: initialize lock in wb-file before wb-file is set in fd-ctx. - Consider a combination of fuse->quick-read->read-ahead->wb->client. quick-read can do open-behind (open is returned as success even before it is issued to backend) and hence the fd can already be in the list of open fds of the inode. A flush call on some other fd opened on the same inode, will result in ra_flush issuing flush calls to all the fds opened on the same inode. This can result in wb_flush trying to hold a lock on non-initialized lock there by causing memory corruption. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2679 (Crash in GlusterFS 3.0.5 in GSP) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2679 commit 77f485dc30e5cd81d63cb7a92dc77b3ace69d40d Author: Anand Avati Date: Thu Apr 28 01:08:32 2011 +0000 marker: fix NULL deref in logging Fix bad gf_log argument Signed-off-by: Anand Avati BUG: 2852 (Glusterfsd crashes on AMI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2852 commit 28cea0ebbd4ce4cd64e1da4e43512230a0050ee9 Author: Pranith Kumar K Date: Fri Apr 22 11:55:58 2011 +0000 mgmt/glusterd: Fix ret value in importing of options/gsync slaves In case the volume options or gsync slaves are absent the import should succeed. Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2832 (peer probe hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2832 commit 625f779dba824d40626473cd85aaacdefbfae1ce Author: Csaba Henk Date: Thu Apr 21 17:38:10 2011 +0000 cli: fix up parsing of geo-replication status Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 775323c1b2fa9a557d3ea74d57e843575f7b1278 Author: Csaba Henk Date: Thu Apr 21 16:43:49 2011 +0000 syncdaemon: have the monitor kill the worker if it does not connect in 60 sec Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2736 (gsyncd hangs if crash occurs in the non-main thread) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2736 commit de809504282731332c9bc0fc7f7da5be34f206ce Author: Csaba Henk Date: Thu Apr 21 16:43:48 2011 +0000 cli: adhere to timeouts properly Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 5e59de561e49e8f401cf0786635c05c31cc3dfb8 Author: Kaushik BV Date: Thu Apr 21 06:55:46 2011 +0000 mgmt/glusterd: fix up the buffer sizes to accomodate a correct estimate of sizes of the snprintf invocations, and errout if not feasible Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2561 (gsyncd command's must be preconfigured) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2561 commit 2017d5ed79a0843262695394bfff61968902e9ef Author: Kaushik BV Date: Thu Apr 21 06:55:45 2011 +0000 cli: check if gsyncd is present in the configured place, enable geo-replication if present Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2744 (make geo-replication package friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2744 commit 49603aec03e98a2a38fad66627593b69b6269cbf Author: Kaushik BV Date: Thu Apr 21 06:55:44 2011 +0000 cli: changes in struct cli_cmd to disable gluster command at run-time Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2744 (make geo-replication package friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2744 commit b5848ed21b9e718011a8f3f3870c4ed978ff17a5 Author: Csaba Henk Date: Thu Apr 21 08:56:09 2011 +0000 syncdaemon: handle errors in glusterfs mount more carefully Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2826 (stale auxiliary mounts are left over) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2826 commit 92e982b9d2f37ae88b22406be9ee88bf14b57197 Author: Amar Tumballi Date: Fri Apr 15 01:10:48 2011 +0000 gluster volume create: fix help message with transport option 'tcp, rdma' used to create a volume which listens on both sockets and ibverbs Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2742 (cli help for volume create is not upto date) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2742 commit 81c04158559f9f61ff0581544541cc18778cb1de Author: Amar Tumballi Date: Thu Apr 21 07:08:28 2011 +0000 prevent few excessive logs Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 2c12b90a84c544343e384e1d60d03b10be9fc45b Author: Raghavendra G Date: Thu Apr 21 05:03:56 2011 +0000 features/marker-quota: handle creation of regular files using mknod. - Add the disk-used to parents' size. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2649 (Quota: size field is not getting updated properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2649 commit 14f9c126c1237410bd9ef159e746afd7ff8c2753 Author: Csaba Henk Date: Thu Apr 21 05:22:23 2011 +0000 glusterd / cli: make the needed changes to let a masterless geo-rep config request get thru Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 58465cdca9386fe2fa15049911223f7282e1b412 Author: Raghavendra G Date: Thu Apr 21 04:16:44 2011 +0000 features/marker-quota: handle overflow of counter used to set frame->root->lk_owner. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2804 (Occasional log messages seen indicating failure of inodelk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2804 commit 1f074563ecdaf92b2ecf12d7ea79b2b5d8f50c2d Author: Raghavendra G Date: Thu Apr 21 04:10:17 2011 +0000 features/marker-quota: Add the disk space used to parent sizes during creation of new-files or symlinks. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2649 (Quota: size field is not getting updated properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2649 commit c1b2279adcc3b3a311221f247c6ee563214cf32c Author: Raghavendra Bhat Date: Mon Apr 18 14:23:17 2011 +0000 do not allow create volume or add-brick if given path or any brick is a part of either Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2803 ([glusterfs-3.2.0qa14]: volume create succeeds even though there is a volume with an export directory in the path of current volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2803 commit 14b9fab371eb7a160fbf15ea4b979d0d98a0e5e0 Author: Csaba Henk Date: Tue Apr 19 08:59:26 2011 +0000 cli: change geo-replication syntax to support slave-only invocation (for sake of slave side configurability). Also pulled out sub-op, now we have volume geo-replication [] [] {start|stop|config|status} [options...] -- more convenient to use when working on a given session (ie. we just change the geo-rep subcommands), and aligns better with other volume commands, cf. eg. volume replace-brick {start|pause|abort|status|commit} Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 0dd8c38d17e51c4b8bd1471854315e27c25cc615 Author: Csaba Henk Date: Tue Apr 19 07:19:17 2011 +0000 geo-replication: revamp CONFIG command Drop the config_type RPC req field, use just a "subop" key in the param dict. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 29ac0febecbca0700bb4b1e2335b8dace5ff452c Author: Csaba Henk Date: Tue Apr 19 09:35:45 2011 +0000 syncdaemon: fix double wait in monitor Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2816 ([glusterfs-3.2.0qa14]: gsyncd monitor crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2816 commit 19e4ef605fe95c08c48bcade95096082a54cdd2d Author: Raghavendra Bhat Date: Wed Apr 20 00:59:26 2011 +0000 glusterd: log the error immedietly after the syscall failure Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 746aa1faa4d2f3a3186e8f660e6a140457580fb3 Author: Gaurav Date: Wed Apr 20 05:12:58 2011 +0000 NFS : Check proper permissions in access control for setattr. Signed-off-by: Gaurav Signed-off-by: Anand Avati BUG: 2818 (Permission problems with gluster NFS works with native FUSE) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2818 commit 2d8f4fae7c06c73cd828c247e462a2b1017f5679 Author: Raghavendra G Date: Wed Apr 20 12:47:12 2011 +0000 features/marker: reduce the size corresponding to destination file if it is already present from parent directories. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2697 (Quota: add-brick creates the size go awkward, though it was perfect earlier) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2697 commit 698d972d8256662dc23a012c4328dca37aaced56 Author: Raghavendra G Date: Tue Apr 19 04:56:58 2011 +0000 features/marker-quota: initialize dentry_child_count to total number of children a directory has in a single go. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2809 ([e89f2a1f5daf1513c533a47b90aec8f90702d09f]: glusterfsd crashed in quota_dirty_inode_readdir) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2809 commit 450a7be2cede5a44c74f5f74224292af0c81a45f Author: Amar Tumballi Date: Mon Apr 18 21:53:45 2011 +0000 marker: fixes to bypass marker fops in case features are enabled mainly in unlink and rename Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2801 (glusterfsd process crash while running rebalance on simple volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2801 commit 3776483431bfcd867a07b83ebd7d303a5d3538b6 Author: Csaba Henk Date: Mon Apr 18 17:25:31 2011 +0000 glusterd / geo-rep: harvesting further benefits of static gsyncd pre-config - log-file does not need to be a reserved option anymore as we wouldn't overwrite the user setting - reimplement glusterd_gsync_get_param_file(): all use cases have now pre-configured values, so instead of putting together the needed pathname by ourselves, we can just get it from gsyncd config - refactor it to a common backend with glusterd_get_canon_url() Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit ced2d41bfdf6ee3ee820fa6090e4bf3147ab0d84 Author: Csaba Henk Date: Mon Apr 18 17:25:30 2011 +0000 glusterd / geo-rep: do all gsyncd pre-configuration in glusterd init This is made possible by gsyncd config templating, by which session specific settings can be expressed in a generic form. Benefits: - in glusterd we use only generic (rx pattern based) config settings so we don't violate users' freedom to make settigs for their sessions - don't have to invoke gsyncd in excess to prepare a session - we can pre-configure slave side too (relying on the templates and gsyncd service auto-discovery) - much leaner, much more expressive code Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 8d034b840e957d96a3c3e1f86a3ff28aabb8c896 Author: Csaba Henk Date: Mon Apr 18 17:25:29 2011 +0000 syncdaemon: add session-owner option Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 369f66ea51506315545501ab3fd4fe87d011a0e5 Author: Csaba Henk Date: Mon Apr 18 17:25:28 2011 +0000 syncdaemon: implement template substitutions for config values So, for example, a log file setting of /var/log/${mastervol}/${eSlave}.log will be substituted with the volume name of the master and the canonicalized-escaped name of the slave for each master-slave pair. As template expanders, beyond the various forms and derivatives of master and slave, the following are also available: - gsyncd tunables (set in command line or in config) - for regexp sections, regexp group captures can be accessed via "match_", where i=1,2 corresponds to the i-th peer-rx in the section title and n=1,... to the n-th capture. This will enable us to have a static configuration (not having to add new entries on each gsyncd start). Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 5a0d15682fb62d768ce088b5d9c9aad974a1460c Author: Csaba Henk Date: Mon Apr 18 17:25:27 2011 +0000 gsyncd service auto-discovery If glusterd is running, gsyncd will find it out and adopt related settings automagically (even if started from not by glusterd) Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 0a38334bd3b21df2448a869760292c499c59bb0c Author: Csaba Henk Date: Mon Apr 18 17:25:26 2011 +0000 cli: make it possible to set per-command timeouts for connection Also make getwd command impatient, having it to time out in 1 sec Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 184fba37889b87c27af90adf357b38fa95f1e78d Author: Csaba Henk Date: Mon Apr 18 17:25:25 2011 +0000 cli: implement "system:: getwd" command Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit cc6d5c66090f576383c26bd0bdefadbcad708435 Author: Csaba Henk Date: Mon Apr 18 17:25:24 2011 +0000 cli: preliminary cleanup for system:: commands Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2785 (gsyncd logs on slave side go to /dev/null) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2785 commit 853293b6dd759a20418a4878821db57f933cc50d Author: Csaba Henk Date: Mon Apr 18 17:21:24 2011 +0000 mgmt/glusterd: geo-rep: restart-upon-reconfig: don't bail out if the gsync session we adjust does not exist Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2777 (geo-replication config setting should have effect on already running sessions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2777 commit d884d4ce74e3d2c582698c9b54b58b4529472a4e Author: Csaba Henk Date: Mon Apr 18 17:21:23 2011 +0000 syncdaemon: fix swallowing of exit value Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2736 (gsyncd hangs if crash occurs in the non-main thread) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2736 commit 8ac5926d11cb66c7ef226bb466604414593bab87 Author: Csaba Henk Date: Mon Apr 18 17:21:22 2011 +0000 syncdaemon: pythonize accidentally copied ruby line in code Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2791 (trying to set up geo-replication with a gluster slave on the LAN screws up geo-rep irrecoverably) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2791 commit 7280a000aaea2d6c6294a82f64a626714cbe2702 Author: Csaba Henk Date: Mon Apr 18 17:21:21 2011 +0000 syncdaemon: don't accept simple identifiers anymore as sugared urls - we want to enforce the separation of the volume name and the url namespaces - resolving simple ids as relative paths was lame anyway Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2786 (Having to prepend geo-replication master vol with colon spoils the UI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2786 commit c6a18b8db0719c0d86c412de6eb386419777d871 Author: Pranith Kumar K Date: Mon Apr 18 12:29:51 2011 +0000 mgmt/glusterd: Fix compiler warning Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2797 ([glusterfs-3.2.0qa13]: peer probe fails with gsync running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2797 commit 7f61b4d1c31181a2c01285a45a99a3ded22349ee Author: Kaushik BV Date: Mon Apr 18 10:42:03 2011 +0000 mgmt/glusterd: Send the gsync sessions that are running to the new peer. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2797 ([glusterfs-3.2.0qa13]: peer probe fails with gsync running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2797 commit 94d32434fdb1d7fc333ab9bf4bf8d3a4eb0dff9e Author: Kaushik BV Date: Mon Apr 18 08:49:54 2011 +0000 mgmt/glusterd: do not allow replace-brick operations when geo-rep sessions are active on this volume. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2765 (geo-replication should have mercy on brick failure) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2765 commit e89f2a1f5daf1513c533a47b90aec8f90702d09f Author: Raghavendra G Date: Mon Apr 18 08:30:54 2011 +0000 features/marker-quota: reduce contributions to parents during unlink only if it is the last link. - since we are not having different contributions for different (parent, name) pairs, but only for different parents, links present in the same directory will have only one contribution representing all of them. Hence parents will not be updated for each link call and parents account for just file-size instead of (numlinks * filesize). However this patch will cause issues for links present accross directories, as only one of their contributions is subtracted when all of them removed (Here all the links are accounted in their parents, thereby total size accounted is [numlinks * filesize]). Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2689 (Quota: xattrs getting corrupted) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2689 commit bb4c33f65f3e7eaeb03f3ac249d6eedd123c5ba6 Author: Raghavendra G Date: Mon Apr 18 08:30:35 2011 +0000 features/marker-quota: remove contribution xattrs from oldloc in rename. - Though we are setting in memory contribution to zero, during updation process contribution is actually fetched from backend. If they are not deleted and if newpath did not exist before doing rename, contributions from oldloc->inode will be retained even for newloc->inode, there by preventing addition of file-size to parents in newpath. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2689 (Quota: xattrs getting corrupted) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2689 commit c034f263c0ced77b6b8f806b4533a612631a9c77 Author: Kaushik BV Date: Mon Apr 18 07:34:54 2011 +0000 mgmt/glusterd: geo-rep config set/del restarts the geo-rep process so that it takes up the new configuration values Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2777 (geo-replication config setting should have effect on already running sessions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2777 commit 4d644dda668e5b55f3f9516e8552e689608b7ad7 Author: Pranith Kumar K Date: Mon Apr 18 05:03:00 2011 +0000 cli: Fix profile info alignment Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2794 (Alignment is not proper in profile volume info) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2794 commit 2f9ce3f4fd23d1a9256e84830805a62f1ebe76fb Author: Kaushik BV Date: Mon Apr 18 02:09:00 2011 +0000 mgmt/glusterd: change the cli output of geo-rep start/stop to resemble the output of volume start/stop Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 67705d888c4e038f188da8a21ade8db447cd7009 Author: shishir gowda Date: Thu Apr 7 04:45:40 2011 +0000 DHT: Propogate error if dht_rmdir_opendir_cbk Earlier rmdir would succeed on all up subvols, but fuse would get an error if one of the subvol was down. In follow up lookup, self heal would be triggered, and since st_mode would be 0, the permissions would be bad. The behaviour now is to fail rmdir if subvol is down Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2591 (Directories changing to d--------- permission after trying to delete) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2591 commit 72b57e311fe8634d26b4c56a78016f9359208443 Author: Kaushik BV Date: Sun Apr 17 11:21:51 2011 +0000 cli: UI cleanup for geo-replication command * provide a unified output in case of failure of geo-replication session * provide a better formatting of the output geo-replication status command * update the help option of geo-replication command * fix few typos Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2536 (gsync service introspection) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2536 commit 91b3d10880678cfa9c5ce03204eb62897a4564e8 Author: Kaushik BV Date: Sun Apr 17 10:46:08 2011 +0000 cli: removal of dead code due to the code movement of geo-rep start from cli to glusterd. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2676 ([glusterfs-3.2.0qa7]: glusterfs server crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2676 commit 3a621ae053a31db49f7adc506bd5ffbd24a0c64d Author: Kaushik BV Date: Sun Apr 17 10:46:07 2011 +0000 mgmt/glusterd : change of syntax of geo-replication command master is referred as a volume name rather than a URL scheme. old syntax: > volume geo-replication start :vol-foo /bar/boo new syntax: > volume geo-replication start vol-foo /bar/boo Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2786 (Having to prepend geo-replication master vol with colon spoils the UI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2786 commit 4b813b3d14476a5cf6a3a54c32c2939a31fe9ba9 Author: Kaushik BV Date: Sun Apr 17 10:46:06 2011 +0000 mgmt/glusterd: unify the geo-replication status rpc messages. the intelligence of determining the type of status command is now at glusterd, rather then explicitly setting it while parsing at cli. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2536 (gsync service introspection) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2536 commit 666e43aca607c90d95379caa13b42a4ed976e8a7 Author: Csaba Henk Date: Sun Apr 17 04:45:59 2011 +0000 syncdaemon: minor cleanups on termination Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2736 (gsyncd hangs if crash occurs in the non-main thread) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2736 commit 856a7ee345713b66ccb6eba6fca276273807fe30 Author: Csaba Henk Date: Sat Apr 16 16:04:27 2011 +0000 glusterd/volgen: make it possible for builders to set the op_errstr during graph validation Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2559 (provide two options in CLI for gluster volume gsync indexing ) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2559 commit 4ade518a232418ccccc6a7bc3c381022465b6c84 Author: Csaba Henk Date: Sat Apr 16 13:36:04 2011 +0000 glusterd: some cleanups needed for 70adbe7b [refactor gsync_status() ...] Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2780 (geo-replication operations take too much time to complete) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2780 commit c9d85b6268523f1872dde05f271e16afd0358939 Author: Amar Tumballi Date: Sat Apr 16 04:13:35 2011 +0000 cli: check for connectivity before doing mount in quota limit list. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2732 (Quota: the local mount on server fails while using quota list command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2732 commit 87e4d4814458c57a3337e7c610f6ead76d0cb28f Author: Raghavendra G Date: Sat Apr 16 09:31:24 2011 +0000 marker/quota: use correct byte ordering when updating parent's size. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2649 (Quota: size field is not getting updated properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2649 commit 26dc794e6586ca911678fc80e831e18cd99973fa Author: Raghavendra Bhat Date: Sat Apr 16 09:45:49 2011 +0000 marker: avoid memleak by unrefing dict, fd and local Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2784 ([glusterfs-3.2.0qa13]: memleak in marker) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2784 commit 3e873600920a180960e6730a531ba7a5912f5543 Author: Raghavendra G Date: Sat Apr 16 10:03:53 2011 +0000 features/marker-quota: fixes in self-healing of dirty inode code path. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2649 (Quota: size field is not getting updated properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2649 commit e52a0cc23b16bf653ce544caaffa0e7ffb5fab4e Author: Raghavendra G Date: Sat Apr 16 10:07:29 2011 +0000 extras/quota-xattr-cleanup: don't follow symbolic links. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2664 (Quota: recreating the volume on same bricks shows similar info as for earlier one using "list") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2664 commit 70adbe7b71771b48e5bd8d79e38132afa04e4752 Author: Csaba Henk Date: Sat Apr 16 10:32:54 2011 +0000 glusterd: refactor gsync_status() so that we can get at the pidfile This is useful for iterated polling of gsyncd's status, without having to incoke gsyncd to find out about the pidfile. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2780 (geo-replication operations take too much time to complete) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2780 commit c78dafac7f82de8a7b72f42fcd58c01dbc4a88df Author: Csaba Henk Date: Sat Apr 16 10:32:53 2011 +0000 syncdaemon: load xattrs from libc on-demand This reduces startup time for invocations other than master / slave role (kind of which now proliferates glusterd) Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2780 (geo-replication operations take too much time to complete) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2780 commit 679c3986b9b72d19d6057d400ec8f1fba1569853 Author: Raghavendra Bhat Date: Sat Apr 16 06:05:31 2011 +0000 quota: do not assign frame->local to NULL which leads to memleak Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2772 ([glusterfs-3.2.0qa12]: excessive quota local NULL errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2772 commit d5110f12ac0352991f22cbf4f80d855a8f35ba42 Author: Raghavendra Bhat Date: Sat Apr 16 05:23:58 2011 +0000 quota: assign local to frame local to prevent memleak Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2772 ([glusterfs-3.2.0qa12]: excessive quota local NULL errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2772 commit a70c0034cc5c7e38390167ebfa9c8706be16fd6d Author: Pranith Kumar K Date: Sat Apr 16 00:48:46 2011 +0000 mgmt/glusterd: Fix percentage latency formula Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2783 (Fix percentage latency and precisions of profile info) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2783 commit 426eed2dd4992f3fb6048dff49b0e2db38d2a87b Author: Pranith Kumar K Date: Fri Apr 15 22:58:12 2011 +0000 mgmt/glusterd: Send the error msg to user if gsync start fails Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2781 (geo-replication start error message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2781 commit 1f5ad47e48cf4901b027a674179025c078c00953 Author: Amar Tumballi Date: Fri Apr 15 22:05:21 2011 +0000 features/quota: set 'frame->local' to local in fsync so fsync call can succeed Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2772 ([glusterfs-3.2.0qa12]: excessive quota local NULL errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2772 commit f727e847133e479a37e86a7feb5826496a7313f7 Author: Csaba Henk Date: Fri Apr 15 09:10:03 2011 +0000 syncdaemon: yet another try to exit properly The final cleanup sequence + call to _exit, which was just done in the main thread, now is called for in each thread when the thread crashes. Seems we aren't left there hanging this way. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2736 (gsyncd hangs if crash occurs in the non-main thread) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2736 commit 43d95c00ee49cb4852d199f11e2647a5930b07c8 Author: Csaba Henk Date: Fri Apr 15 09:10:02 2011 +0000 syncdaemon: when getting a single config option, don't display the option name, just the value This intends to ease scripting (you can just pass on the value to xargs etc.) Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 5c9c2555911d8d7131e3c0d918f6ee9c0b3b612f Author: Kaushik BV Date: Fri Apr 15 09:15:23 2011 +0000 mgmt/glusterd: does not allow disabling of indexing (xtime marking), if a gsync session is active. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2559 (provide two options in CLI for gluster volume gsync indexing ) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2559 commit 2479f442ca8f9e2dd23988e1f2dc20238443a769 Author: Pranith Kumar K Date: Fri Apr 15 07:00:42 2011 +0000 mgmt/glusterd: handle error condition in quota fs crawl Quota enable starts a crawl on the maintenance mount point, but if the chdir to the mount point fails it will start the crawl on '/'. So the child should exit with EXIT_FAILURE when the chdir fails. Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2770 (Handle error cases in quota fs crawl) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2770 commit 49b796949c9a3cc9d5a541503e03589fb7bcbde2 Author: shishir gowda Date: Fri Apr 15 07:56:47 2011 +0000 TOP: validate bs/count pair for write/read-perf measurement If either one the above args are supplied, the other arg should be supplied too. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2771 (bs or count tag missing with volume top write-perf/read-perf command blocks glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2771 commit baaa7286ed6b70121efa6a83a8adb3a2f1ec45da Author: Raghavendra G Date: Fri Apr 15 07:05:38 2011 +0000 cluster/stripe: aggregate xattrs holding quota-size in lookup and getxattr calls. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2760 (Quota: stripe volume not showing the quota size properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2760 commit 2ca0f2d3ab4c80ed4d002bcb2ca1425d1db42c78 Author: Raghavendra G Date: Fri Apr 15 07:05:24 2011 +0000 features/quota: use disk usage instead of file-sizes. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2760 (Quota: stripe volume not showing the quota size properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2760 commit cdcbfcd3900ad450023c8b3d06174dfb81644788 Author: Raghavendra G Date: Fri Apr 15 07:05:10 2011 +0000 features/marker-quota: Use the actual disk-space consumed instead of ia_size returned in iatt for calculation of sizes. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2760 (Quota: stripe volume not showing the quota size properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2760 commit da66edbe927152ba12c9a702fd157a45a3f3cb42 Author: Raghavendra G Date: Fri Apr 15 14:02:39 2011 +0000 mgmt/glusterd: fix double free. - the limit-usage string should be stored as static, since remove-limits will be modifying it and probably freeing it. - this static string should also be explicitly freed in glusterd_quota_disable since dict_del won't free it. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2776 (gluster quota remove crashed glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2776 commit cfe11cd627f8322ad2701dad6c021d3570bbbf1d Author: Krishnan Parthasarathi Date: Fri Apr 15 01:00:56 2011 +0000 top: Modified integer bounds check for count/bs Signed-off-by: Krishnan Parthasarathi Signed-off-by: Anand Avati BUG: 2721 (Incorrect validation message in gluster top CLI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2721 commit 7a56f1b9a18e4863917e4b6aaeacba2e28073ab6 Author: Lakshmipathi Date: Fri Apr 15 05:08:47 2011 +0000 rpm : create new package for geo-replication and preserve symlinks Signed-off-by: Lakshmipathi.G Signed-off-by: Anand Avati BUG: 2744 (make geo-replication package friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2744 commit b5d944f911f1638a8063235443410de36df6f2fd Author: Pranith Kumar K Date: Fri Apr 15 02:55:46 2011 +0000 mgmt/glusterd: Memory leak and message cleanup Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2764 (Cleanup memory leaks seen in quota and gsync code paths) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2764 commit b565cf8bfc75e6f6c85a47bc8a06737cd6e79fae Author: shishir gowda Date: Fri Apr 15 02:49:51 2011 +0000 DHT: Make assert-no-child-down a boolean option Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2765 (geo-replication should have mercy on brick failure) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2765 commit dc75b9889d0dca8cde08860e96be1c88059644c6 Author: Csaba Henk Date: Fri Apr 15 02:26:24 2011 +0000 syncdaemon: name tempdirs used by gsyncd more characteristically to ease debugging Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 78ca8b9fb8790f5741d5bf01aa870d7b77b9c57f Author: Csaba Henk Date: Fri Apr 15 01:48:36 2011 +0000 glusterd / geo-replication: have gsync's glusterfs client use assert-no-child-down for dht volume Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2765 (geo-replication should have mercy on brick failure) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2765 commit 8699c929fb9e07303a6a779e8d4713c4a837b33d Author: Csaba Henk Date: Fri Apr 15 01:09:01 2011 +0000 glusterd / geo-replication: set location of ssh keyfile for gsyncd Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2756 (support for providing custom ssh private key) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2756 commit 0c77e6f156e57717f9cd3feb35d589e36dcb831f Author: Csaba Henk Date: Thu Apr 14 16:35:02 2011 +0000 glusterd/volgen: partially revert 50ab0ad4 Moving the adjustment of marker's timestamp file to generation phase was not correct, as generation should be side effect free. Moved it back to the point where volfiles are written. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2529 (Starting Gsync causes ENOTCONN to glusterfs client) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2529 commit 0dfe24fc9fc8bf92044fa59e27f61169dfdcd5bc Author: Csaba Henk Date: Fri Apr 15 00:58:00 2011 +0000 use "geo-replication" all over as the official name of this feature Use GEOREP macro if you want to refer to the feature in code. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2757 (refactory gsync/gsyncd/syncdaemon/whatever to geo-replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2757 commit e1be6195464836dd910e3b62f518c897dd06740d Author: Csaba Henk Date: Thu Apr 14 16:35:00 2011 +0000 glusterd/volgen: refactor some things - use macros for exported volume tunables - introduce glusterd_volinfo_get_boolean as retrieval of boolean optuions was a recurring pattern and became somewhat cumbersome Also fixed illegal access to volinfo dict. @pranith: use always the glusterd_volinfo_get* API for that purpose so that defaults are taken to consideration. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2757 (refactory gsync/gsyncd/syncdaemon/whatever to geo-replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2757 commit 066074291fad64a78923bbca06d25b5a6a5307d7 Author: Csaba Henk Date: Thu Apr 14 16:34:59 2011 +0000 syncdaemon: split gluster_command to make it possible to set options for glusterfs Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit f689a077d3f0a8c75d7ef083d92ef0faeb2ba5a0 Author: Csaba Henk Date: Thu Apr 14 16:34:58 2011 +0000 syncdaemon: work around python feature of allowing double leading slashes in canonicalized paths Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 4175e092e3521c1f095d6307ea9b05c7c49b02c6 Author: Pranith Kumar K Date: Thu Apr 14 11:53:12 2011 +0000 mgmt/glusterd: restart gsyncd on glusterd restart Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2761 (Restart gsyncd processes on glusterd restart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2761 commit 4055c85a23043afdf3ad708d28aedc55805b1043 Author: Amar Tumballi Date: Thu Apr 14 07:04:20 2011 +0000 features/marker: fix the excessive logs in marker Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2754 ([glusterfs-3.2.0qa11]: excessive logging in marker) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2754 commit 9b0374043ebe59fa638b8af330ea1d403503c143 Author: Amar Tumballi Date: Wed Apr 13 00:29:16 2011 +0000 cli: add log file for cli instead of '/dev/null' Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2737 (there is no log file for gluster cli) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2737 commit 4d6e05f0aac70fbdec6b9530ed7b5d6ce4de0f03 Author: Pranith Kumar K Date: Thu Apr 14 04:31:22 2011 +0000 mgmt/glusterd: Prevent dict unserialize for buf with 0 length Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2753 (perf-test failed with "buf is null!" message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2753 commit d6cbfe3b4be0af43a14df76e2305488158cff3e1 Author: Raghavendra Bhat Date: Thu Apr 14 05:10:34 2011 +0000 quota: resume the stub when its not NULL Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2758 ([glusterfs-3.2.0qa11]: symlink hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2758 commit 1d1452e070f990cc91fea87408ea4905abde2fb7 Author: shishir gowda Date: Thu Apr 14 04:21:48 2011 +0000 DHT: Add xlator-option assert_no_child_down If this is set, when CHILD_DOWN event is received, call exit Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2536 (gsync service introspection) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2536 commit 6c16974a0ed485c72f84922fcf67b76ac8f64358 Author: Pranith Kumar K Date: Thu Apr 14 03:45:20 2011 +0000 cluster/afr: Avoid null dereference Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2750 ([glusterfs-3.2.0qa11]: nfs server crashed in afr_sh_entry_expunge_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2750 commit 1c5706c43d17beb2dd8eb78c5b740bafd5b05506 Author: Raghavendra G Date: Wed Apr 13 10:23:03 2011 +0000 marker: pass cookie properly while filtering quota xattrs. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 8c833f1ecab9af3762f4e332126399e61fae090c Author: Kaushik BV Date: Wed Apr 13 23:30:22 2011 +0000 mgmt/glusterd: fail the volume stop opeeration if Gsync sessions are active. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2751 (Volme stop must not be proceeded if gsync sessions are active for the volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2751 commit 93cb168fb362c7aea3c10371574a5c5566bb0222 Author: Kaushik BV Date: Wed Apr 13 22:14:37 2011 +0000 mgmt/glusterd: Implementation of volume gsync status [master [slave]] Changes made in the path of gsync start/stop as well, where we maintain a list of active gsync sessions, hence gsync stop could be executed at all nodes. A new dict in glusterd_volinfo_t added to maintain an active list of gsync slaves running on each master. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2536 (gsync service introspection) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2536 commit 77cd50a12887b13db4c49be6a979a5ecb8239570 Author: Raghavendra G Date: Wed Apr 13 10:37:31 2011 +0000 quota/(f)truncate: pass correct delta for updating parent sizes after successful completion. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2741 (Quota: new files not getting created even if space is available) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2741 commit 55594008c2d719c7097998b3d8aa9771bcc9d3ff Author: Amar Tumballi Date: Wed Apr 13 01:13:56 2011 +0000 mgmt/glusterd: check for 'peerinfo->mgmt' before accessing it Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2728 ([glusterfs-3.2.0qa11]: glusterd crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2728 commit 1875dd6c05a5964b46ce38f1bd3c0679ad5d17bf Author: shishir gowda Date: Thu Apr 14 00:05:39 2011 +0000 glusterd: Respond to cli with empty iobref is serialize fails. This usually happens if the size exceeds 128k. Earlier the cli used to hang if the response exceeded 128k size. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2725 (volume top displays "error" for path max) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2725 commit b3c2bbab35695a2358a4031aa05e31eb5e19c28b Author: Pranith Kumar K Date: Thu Apr 14 01:08:22 2011 +0000 mgmt/glusterd: Handle the features/quota for quota Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2540 (quota enablement yields bogus client volfile) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2540 commit efd0f26ba8116da1148c75c950f2490dbe42ebc5 Author: Raghavendra Bhat Date: Wed Apr 13 05:13:19 2011 +0000 glusterd: report the user if disable quota is given on already disabled quota Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2620 (CLI improvements in quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2620 commit 9c46226f7a98e843b1c95ecdcf44830e05d5e1f5 Author: Pranith Kumar K Date: Wed Apr 13 07:36:14 2011 +0000 PUMP: initialize loc at declaration Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2726 ([glusterfs-3.2.0qa11]: glusterfs server crashed due to stack overflow) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2726 commit 41df71222e0d3975b8160d82a630d70ac15786be Author: Pranith Kumar K Date: Wed Apr 13 07:36:13 2011 +0000 mgmt/glusterd: server graph should have io-threads below pump Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2726 ([glusterfs-3.2.0qa11]: glusterfs server crashed due to stack overflow) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2726 commit 6608d60aa6ba733fbdc612e27499524b28adadbf Author: Csaba Henk Date: Wed Apr 13 01:46:10 2011 +0000 cli: simplfy gsysnc configuration command New syntax is volume gsync config [[!]opt [val]] In details: - instead of "volume gsyncd configure M S config-get-all" : "volume gsyncd config M S" - instead of "volume gsyncd configure M S config-get O" : "volume gsyncd config M S O" - instead of "volume gsyncd configure M S config-del O" : "volume gsyncd config M S !O" - instead of "volume gsyncd configure M S config-set O V" : "volume gsyncd config M S O V" Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2738 ("volume gsync configure config- ..." is overly verbose) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2738 commit ebd99e25bf811ab14540f74dd50b445c217e7ee0 Author: Kaushik BV Date: Wed Apr 13 01:46:09 2011 +0000 cli: join value arguments of "gsync config-set" with spaces When a given gsync tunable is supposed to hold a command (which can take options), it's quite possible that it spaces in its value. Try to approximate this situation by joining the leftover arguments. Signed-off-by: Kaushik BV Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2713 ([glusterfs-3.2.0qa10]: config-set works only for one value) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2713 commit 72f88e50dbf1f492db7bcc70b074bc64e6b994cb Author: Csaba Henk Date: Wed Apr 13 01:46:08 2011 +0000 glusterd: sanitize gsyncd config option validation - rely on --config-check functionality of gsyncd to find out if option exists - maintain a list of those options with which we don't want the user to fiddle with (glusterd internals imply these so it' just the proper component for it) - fail if user does a set/del on these Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2659 (gsync config-del option is not working properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2659 commit ac27e6980869d52ea90b869de01538dec28620ae Author: Csaba Henk Date: Wed Apr 13 01:46:07 2011 +0000 syncdaemon: ensure -/_ invariance in tunables, in all components Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2659 (gsync config-del option is not working properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2659 commit b1cad2780c34f9dd664f67565ceac3b5a5cf3bcb Author: Csaba Henk Date: Wed Apr 13 01:46:06 2011 +0000 syncdaemon: refactor gsyncd.py cmdline interface to configuration - existence of given tunable is checked - add --config-check option to just do a check for existence of tunable Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2659 (gsync config-del option is not working properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2659 commit e5c38128fa76b3e11047d49448aab77d3a551804 Author: Csaba Henk Date: Wed Apr 13 01:46:05 2011 +0000 syncdaemon: force termination for unhandled exception in any thread Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2736 (gsyncd hangs if crash occurs in the non-main thread) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2736 commit 13d1856a40122008dee35a96771f832945c220f8 Author: Csaba Henk Date: Wed Apr 13 01:46:04 2011 +0000 syncdaemon: streamline user-visible messages (and control flow a bit, too) Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2644 (no volume-mark, if the behaviour persists have to check if master gsyncd is running.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2644 commit ea2e55bae0203b00dc4872a3333dce84cf7bef7d Author: Csaba Henk Date: Wed Apr 13 01:46:03 2011 +0000 syncdaemon: fix parsing of the volume-mark structure The parsing error implied that all xtimes were considered to be valid, regardless of the volume mark. Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2535 (gsync cascading) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2535 commit 9a81400a4accc68bfe55a0bee69ca7e2ed5894f3 Author: Csaba Henk Date: Wed Apr 13 01:46:02 2011 +0000 syncdaemon: return exit code properly Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 64161529ebe151e36c7fc86b419543b4ac02a681 Author: Csaba Henk Date: Wed Apr 13 01:46:01 2011 +0000 syncdaemon: fix pidfile deletion on failed pidfile acquisition (not triggered in glusterd instrumentation of gsyncd as glusterd does pidfile probing by itself) Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit c0139158ae8992513e93932d8670b5db8605ead2 Author: Csaba Henk Date: Wed Apr 13 01:46:00 2011 +0000 syncdaemon: minor fixes - whitespace fix - remove superfluous imports Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 7cf0dbcd300f554985ebde4759511c048927c53a Author: Pranith Kumar K Date: Tue Apr 12 01:21:57 2011 +0000 mgmt/glusterd: Remove excessive INFO logs Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 4e928f1d9a9cbbf18d3df3481f1d985f12a9c5ba Author: Pranith Kumar K Date: Tue Apr 12 22:40:14 2011 +0000 mgmt/glusterd: log stats commands to cmd log Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2735 (log stats commands (top/profile) to cmd log) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2735 commit bc16a1e999648ba58f863d26281c152fb477174a Author: Pranith Kumar K Date: Tue Apr 12 07:17:44 2011 +0000 mgmt/glusterd: volume reset force implementation Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2729 (Implement force option for volume reset) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2729 commit fb3e469e29578393a0d5f964991d26b5449bffb0 Author: Raghavendra G Date: Tue Apr 12 09:00:02 2011 +0000 features/quota: update quota-limit stored in directory contexts after reconfigure. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit bdb3e709e3eec1863181339bf1a5b66b702ac1bb Author: Junaid Date: Tue Apr 12 10:01:28 2011 +0000 features/marker: Filter the quota xattr's on getxattr with NULL name argument. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 4b6a08fba53d895c84676d8c3ae6a5ef45fa2286 Author: Junaid Date: Tue Apr 12 12:03:06 2011 +0000 features/marker: Call update txn when the directory size and its contribution are not same. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit ba365f725a91bcd3dcfae1d8311f9f148ce69055 Author: Amar Tumballi Date: Tue Apr 12 10:30:24 2011 +0000 remove excessive logs due to log enhancement Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d7cba3b0bb4867e02a5999f830e5315cd7022520 Author: Raghavendra Bhat Date: Tue Apr 12 04:00:35 2011 +0000 script: fix the typo while doing replace brick Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 1436 (script for running basic gluster commands) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1436 commit b71aa0cdb7113dfa7e94720da48cc46c476cde4a Author: Raghavendra Bhat Date: Mon Apr 4 14:50:11 2011 +0000 declare favorite child as int instead of unsigned int In afr_private_t structure favorite child is declared as unsigned int. In init function of afr we set favorite child to -1, if that option is not found in volfile. But favorite child value will be set to a huge value instead of -1 since it is an unsigned int and in statedump file favorite child value is displayed as a huge value instead of -1. Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2668 ([glusterfs-3.2.9qa7]: createbench error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2668 commit 2e4eeb06adc1e6a8a7ded02752ade780ac977200 Author: Vijay Bellur Date: Tue Apr 12 14:22:15 2011 +0000 libglusterfs: Check for null dereference in statedump Signed-off-by: Vijay Bellur Signed-off-by: Anand Avati BUG: 2731 (coredump when process state dump command is issued immediately after mounting fuse client) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2731 commit 10ad4b52e03dbdc3674f49a5d9322f220ea65088 Author: Pranith Kumar K Date: Tue Apr 12 10:03:52 2011 +0000 cli: Fix typo in top help string Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2719 (Incorrect help string for volume top) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2719 commit 5ca2445270b4b77f2399a9f6332083ff933234a1 Author: Raghavendra G Date: Tue Apr 12 09:20:53 2011 +0000 features/quota: check for proper return value in case failure of dict_get_bin Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2723 ([glusterfs-3.2.0qa11]: glusterfs client crashed in quota_validate_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2723 commit 470bef24d742165a6499128f0b7a8748bdc8be96 Author: Raghavendra G Date: Tue Apr 12 09:17:55 2011 +0000 features/quota: add error checks for failure of quota_inode_loc_fill. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2727 ([glusterfs-3.2.0qa11]: nfs server crashed in quota_check_limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2727 commit cc734698b6edcbf54b244a23ff757ae6f2f669b5 Author: Raghavendra Bhat Date: Tue Apr 12 09:07:57 2011 +0000 quota: assign frame->local to local before checking op_ret Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2733 ([glusterfs-3.2.0qa11]: nfs server crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2733 commit 35998844040cf713f229e896524a1a6be249e31d Author: Junaid Date: Tue Apr 12 08:19:27 2011 +0000 features/quota: Validate the quota options. and donot include into the client volfile. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2541 (insufficient option validation in quota translator) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2541 commit 1fd570380ba5def514ff42e81008a7ddd588348f Author: Junaid Date: Tue Apr 12 05:06:03 2011 +0000 features/marker: Adding NULL checks. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 9c26fbc70ab797eea7967bc77857e73eca9aeffe Author: Amar Tumballi Date: Tue Apr 12 05:02:00 2011 +0000 protocol/client: convert to errno before checking for EAGAIN in *lk_cbk() functions. Network error code may be different than what is actual errno code. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 6a2c2fa4f13f9ed96098c4fec40f747e171e6819 Author: Amar Tumballi Date: Tue Apr 12 05:00:18 2011 +0000 protocol/client: fix the fd_count decrement logic the error creeped in during some code cleanup and logging enhancement Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 1761 (incorrect self-heal behaviour when files are deleted) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1761 commit 59b9ab45a01d52e197ab6f76fd71e64910396d57 Author: Csaba Henk Date: Tue Apr 12 02:47:45 2011 +0000 temporary workaround for mtab update race thingy Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2690 (race between mtab updates of mount and umount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2690 commit 1b18a7d64574ca08b937113fcb19b9d851abd43c Author: Junaid Date: Tue Apr 12 08:11:32 2011 +0000 libglusterfs/dict: Donot perform NULL check on data in dict_foreach Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 1816 (send volume options in friend add) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1816 commit 214ceccb0758e62724dc2548d140aff5885391a0 Author: Junaid Date: Tue Apr 12 04:37:16 2011 +0000 mgmt/glusterd: Mount a maintainance client only on the glusterd which received quota enable through cli. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 2a6598646824da9d6a957fb5b3e4c6bb40fb6835 Author: Venky Shankar Date: Mon Apr 11 05:48:36 2011 +0000 build fixes Signed-off-by: Venky Shankar Signed-off-by: Anand Avati BUG: 2550 (build warnings) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2550 commit cfd85789c44ce3f88d6bf87d7b0a47dafb8c6d57 Author: Pranith Kumar K Date: Tue Apr 12 00:26:25 2011 +0000 mgmt/glusterd: Fix warning in glusterd build Signed-off-by: Pranith Kumar K Signed-off-by: Anand Avati BUG: 2718 (Fix warning in glusterd build) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2718 commit 9ccb1e7b152ea9d27356482d51bd1946d377b799 Author: Amar Tumballi Date: Mon Apr 11 03:19:25 2011 +0000 libglusterfs/src: bring in VALIDATE_OR_GOTO to args so we can capture places which are calling these function with invalid arguments Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 902478bf9e2e1fee15ef979020d28d2095211e93 Author: Junaid Date: Mon Apr 11 11:32:39 2011 +0000 mgmt/glusterd: Quota client lazy umount. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2560 (Lazy umount should be done for the maintainance mode mountpoint) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2560 commit dff1a8bd5bcd392826561c93058f8a52606a2832 Author: Kaushik BV Date: Mon Apr 11 08:38:40 2011 +0000 mgmt/Glusterd: Do not disable marker on gsync stop. Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2559 (provide two options in CLI for gluster volume gsync indexing ) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2559 commit f0ef00478f1f2722d349606924d0d3479eb5da80 Author: Junaid Date: Mon Apr 11 07:13:40 2011 +0000 features/quota: Adding the option "timeout" to quota. This option tells the quota translator when to perform the next aggregation. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 3a709be6850e50915c9e188cc308d7bfa5f781e5 Author: Csaba Henk Date: Mon Apr 11 05:42:20 2011 +0000 syncdaemon: do not use os.getlogin() for getting the name of the current user This function relies on the terminal (cf. getlogin(3)), which is not available if we run as daemon Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2712 (username resolution in gsyncd fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2712 commit 78bd9a86c3e87c9e79f62990773767f81cab896d Author: Kaushik BV Date: Mon Apr 11 02:25:18 2011 +0000 mgmt/Glusterd: logging of few commands in cmd_log_history Signed-off-by: Kaushik BV Signed-off-by: Anand Avati BUG: 2449 ([glusterfs-3.2.0-cisco1]: gsync commands are not logged in the cmd_log_history) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2449 commit 882085db173a031a4cc24b5dec7e369f1b512747 Author: Raghavendra Bhat Date: Mon Apr 11 05:00:31 2011 +0000 marker: check the return value being less than zero instead of -1 Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2711 ([glusterfs-3.2.0qa10]: glusterfs server crashed in marker_setxattr operations) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2711 commit 204db674a9c6a724f5fe887c02cd98386043f4fe Author: Raghavendra G Date: Mon Apr 11 01:13:58 2011 +0000 features/quota: handle failed fops gracefully. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2701 ([6db2b422f05d0553d0a83af603ae4d176b41cbdf]: crash in quota_readlink_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2701 commit f5625e628f1959331eed85082cb6bfdc324db3c2 Author: Junaid Date: Mon Apr 11 01:15:53 2011 +0000 cli: Validating the cli quota options. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2612 (quota limit-set not in line with help) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2612 commit 974be663a9113d4aed684dce00f5288669d511e8 Author: Raghavendra G Date: Sun Apr 10 22:38:03 2011 +0000 features/quota: Add checks for any of the parents of file being NULL while checking limits. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2685 (nfs server crashed in quota_check_limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2685 commit 1992dc12443f376f9b2974f4e830b4b17e3574c0 Author: Raghavendra G Date: Sun Apr 10 10:53:36 2011 +0000 features/quota: use signed type to store delta. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit 67d77aa96dccefe68a44473bf45cf6796e741b7d Author: Raghavendra Bhat Date: Fri Apr 8 14:46:54 2011 +0000 buf and statpost should be checked for NULL before accessing it Signed-off-by: Raghavendra Bhat Signed-off-by: Anand Avati BUG: 2701 ([6db2b422f05d0553d0a83af603ae4d176b41cbdf]: crash in quota_readlink_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2701 commit 86a091ac0d46ce2b06b79ceafe728ee65fc6ebbf Author: Csaba Henk Date: Mon Apr 11 04:09:17 2011 +0000 syncdaemon: fix transaction code Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2659 (gsync config-del option is not working properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2659 commit 2f38fdac226b5b5bd02a78e9933ec46b05cac32d Author: Csaba Henk Date: Mon Apr 11 04:09:16 2011 +0000 syncdaemon: minor fixes - fix yet another instance of calling exit (instead of {sys.,os._}exit) - fix logging to stderr with "-" as logfile - whitespace fix Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit dd3cc7d398c3b4432097b7cc2716e2afec9a8e47 Author: Csaba Henk Date: Mon Apr 11 04:09:15 2011 +0000 syncdaemon: fix setting None as new master We checked for the event of a new master being adopted by: - checking for state change in list of masters - checking if our chosen master is a foreign one and if these held, then wrote out the actually available master to config However this was flaky: if (1) native master changed (2) there was already a foreign master adopted (3) actually the master was not available then we wrote out the None to config. This could occur if: - on syncd startup, native master just changes from None to the volume native [implies (1)] - foreign master adopted from earlier run via config [implies (2)] - actually foreign master was not available [implies (3)] Signed-off-by: Csaba Henk Signed-off-by: Anand Avati BUG: 2670 (strange behaviour with intermediate-master and slave) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2670 commit b003ee6e9e8316a59a1de204f727748e442ef0af Author: Amar Tumballi Date: Sun Apr 10 05:30:45 2011 +0000 protocol/server: prevent unnessary logs in INFO level 'op_ret == 0' in readdir() is a valid return code. Signed-off-by: Amar Tumballi Signed-off-by: Anand Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit a6ec94de9346f2973d013237cc6584ff9aa89974 Author: Raghavendra G Date: Sun Apr 10 05:06:04 2011 +0000 cluster/distribute: Account for the first lookup sent to check whether the path is a directory while aggregating quota-xattrs. - The total number of lookups sent for a directory is equal to (no of children + 1). Hence we should not aggregate the xattrs from the first lookup. Signed-off-by: Raghavendra G Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit 0a05984fd99577a1ea5bf8d2cdddd08d9a88ba75 Author: Junaid Date: Sat Apr 9 05:34:23 2011 +0000 cli: Cleanup the maintainence mount points used by quota. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2704 (Stale mount-points seen after execting quota list command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2704 commit 11c2526e045a5a9b168175d5fd658302a8dcb31b Author: Raghavendra G Date: Sun Apr 10 05:11:29 2011 +0000 marker/quota: use correct byte order while storing xattr values in backend. Signed-off-by: Junaid Signed-off-by: Anand Avati BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit ef19a8ba4c0628566c01ebd247869797a7ba5dde Author: Raghavendra G Date: Sun Apr 10 10:55:08 2011 +0000 features/quota: Fix race-condition while resuming stub. - call-stub is resumed in fops calling quota_check_limit and quota_check_limit when validate_count is zero, indicating no pending validates. During validates, validate_count was decremented in quota_validate_cbk, but check for validate_count being zero was done in quota_check_limit (which is called by quota_validate_cbk). Hence there is a time window b/w decrementing validate_count in quota_validate_cbk and checking whether validate_count is zero in quota_check_limit, during which if the control is passed to code in fop checking for validate_count being zero, same stub will be resumed twice - once in fop and once in quota_check_limit. Signed-off-by: Raghavendra G Signed-off-by: Anand Avati BUG: 2686 ([glusterfs-3.2.0qa8]: nfs server crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2686 commit 3ea5bff8dfebbf325daccf81511c5d4534b2ca86 Author: shishir gowda Date: Thu Apr 7 17:06:25 2011 +0000 DHT: send revalidate to all subvols and not just first subvol Reverting commit 23d9783a192669b638d42b8dd127ad69ea36f950. When first subvolume is down, mount point becomes inaccessible. Signed-off-by: shishir gowda Signed-off-by: Anand Avati BUG: 2532 ([glusterfs-3.1.3qa8]: bringing first subvolume down makes mount point inaccessible) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2532 commit ee96f768b99362ec724c8918d24028def065536a Author: Raghavendra G Date: Sun Apr 10 10:43:05 2011 +0000 libglusterfs/xlator: set THIS properly whenever some operation is done iteratively on more than one xlator in the graph. Signed-off-by: Raghavendra G Signed-off-by: Anand Vishweshwaran Avati BUG: 2683 ([glusterfs-3.2.0qa8]: glusterfs client crashed in reconfigure) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2683 commit 6db2b422f05d0553d0a83af603ae4d176b41cbdf Author: Pranith Kumar K Date: Fri Apr 8 02:50:03 2011 +0000 mgmt/glusterd: Fix op_ctx issue with replace brick Replace brick recognizes command originator by the presence of op_ctx. Brick op uses the op_ctx to collect the brick response on all the machines in cluster. This patch satisfies both these assumptions to make glusterd functional in replace-brick. This is a hack for 3.2.0. Need to Fix the assumptions in later release. Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2691 ([glusterfs-3.2.0qa9]: glusterd error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2691 commit 64cefcee88c6164f20668187929c76ec54a72d23 Author: Gaurav Date: Fri Apr 8 00:54:33 2011 +0000 NFS : Exclusive create storing verifier. Signed-off-by: Gaurav Signed-off-by: Vijay Bellur BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit d6a7e92da11663cdb6068466f22e230ceb0dc31d Author: Raghavendra G Date: Thu Apr 7 23:57:58 2011 +0000 features/quota: Add checks for any of the parents of file being NULL while checking limits. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2685 (nfs server crashed in quota_check_limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2685 commit 25837b52939398bf3964d20301f0e641033c5c68 Author: Amar Tumballi Date: Thu Apr 7 00:22:23 2011 +0000 gluster rebalance: don't move a hardlinked file. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit 0d440ddb80c55320fe9deda15cecec8e31cab2c1 Author: Amar Tumballi Date: Wed Apr 6 05:46:44 2011 +0000 gluster rebalance: don't depend on the sticky bit for validating link file. do the getxattr() with 'trusted.distribute.linkinfo' key, which returns success only if the file has a link. With this we can preserve the exact same permission as old file. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2530 (Rebalance not working properly (file permission issues)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2530 commit 12de69e4204c0dced7cccc8450954ad2e20c1075 Author: Junaid Date: Fri Apr 8 01:12:40 2011 +0000 features/marker: Synchronise the read and write of marker_local_ref. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2663 (glusterfsd crash with bonnie++ when marker is enabled) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2663 commit ca381e5aeadb4e2fdced09c3e86b12498ce84c11 Author: Junaid Date: Thu Apr 7 15:38:25 2011 +0000 mgmt/glusterd: Quota cli message improvements. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2620 (CLI improvements in quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2620 commit 54558cfc3653d5b5201ec7fd45594cb610eefbca Author: Pranith Kumar K Date: Thu Apr 7 21:11:15 2011 +0000 mgmt/glusterd: serialize the dict only if its not NULL Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2691 ([glusterfs-3.2.0qa9]: glusterd error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2691 commit 56814fefa0a4cff5d08528aa9103e01350d0e53a Author: Raghavendra Bhat Date: Thu Apr 7 09:41:47 2011 +0000 do not access the empty loc inode Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2611 ([glusterfs-3.1.0-qa5]: crash in quota_rename) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2611 commit 62e1096fb01f7a12c5bc5ff77e3cb427248b80ad Author: Amar Tumballi Date: Thu Apr 7 07:44:51 2011 +0000 removed reference to GF_LOG_NORMAL instead used GF_LOG_INFO, which is more standard log level. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2669 (RuntimeError: cannot recognize log level "normal") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2669 commit 19b2e01f1c53c358c5673c3d216c0349b55481a6 Author: Raghavendra Bhat Date: Thu Apr 7 07:10:42 2011 +0000 do not change the arguments of a function Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2685 (nfs server crashed in quota_check_limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2685 commit 4bf80aa399f70aa976796154728d518362708792 Author: Junaid Date: Thu Apr 7 06:53:27 2011 +0000 features/marker: Perform quota updation on rmdir and unlink by holding inodelk on parent. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2664 (Quota: recreating the volume on same bricks shows similar info as for earlier one using "list") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2664 commit a99c9b5ffd92ac05d173ff2bad698a0f7947b327 Author: Pranith Kumar K Date: Thu Apr 7 06:40:47 2011 +0000 debug/io-stats: Fix races and performance issues in profile Fix the race in update_latency and memset of interval stats. Update fop hits and latencies only when both the options are set. Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2636 ("profile info" lists 'nan' in latency when heavy i/o is running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2636 commit db347c756609e5fb6792bfd69046c97fd6aacc0e Author: Pranith Kumar K Date: Thu Apr 7 06:40:46 2011 +0000 mgmt/glusterd: Fix gluster-profile performance issues Add count-fop-hits option to io-stats use count-fop-hits instead of dump-fd-stats for profile Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2636 ("profile info" lists 'nan' in latency when heavy i/o is running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2636 commit 476b672347641c3f0d6b346b13feaf530ecbbe93 Author: Raghavendra G Date: Thu Apr 7 02:51:50 2011 +0000 extras: scripts to cleanup xattrs stored by quota. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2664 (Quota: recreating the volume on same bricks shows similar info as for earlier one using "list") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2664 commit 7a32aa912ea4e49d3ef922ec6e0cb3d394109962 Author: Junaid Date: Mon Apr 4 12:03:04 2011 +0000 features/marker: Check for NULL before dereferencing pointers stored in local. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2607 (Fileop fails when quota is enabled) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2607 commit ee494c7519e5da09b66003de514db5e700c3001d Author: Raghavendra Bhat Date: Sun Apr 3 12:01:41 2011 +0000 print the gfid of the inode for which dentry is not found Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2652 ([glusterfs-3.2.0qa6]: dbench keeps on running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2652 commit af4604ad4cf58f4b9b3fab26121c3ebd105428ca Author: Vijay Bellur Date: Wed Apr 6 12:41:12 2011 +0000 mgmt/glusterd: Reset context upon operation completion Signed-off-by: Vijay Bellur BUG: 2650 (replace brick failed in distributed-replicated setup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2650 commit 50a0adf03e1401395b04c7bba3d5007658cae9e4 Author: Junaid Date: Wed Apr 6 23:57:24 2011 +0000 features/marker: Check if gsync is enabled in getxattr fop before performing gsync related operations. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2681 (marker returns dummy data for volume-mark attribute if xtime is switched off) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2681 commit 35dea20e40958ebbf018354e040570e654eb6bfc Author: Raghavendra Bhat Date: Tue Apr 5 14:24:59 2011 +0000 check buf for NULL before accessing it Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2675 ([glusterfs-3.2.0qa7]: glusterfs client crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2675 commit 06c954a910fe8749b362490c62e5b49be5b0c385 Author: Raghavendra Bhat Date: Thu Mar 31 06:05:41 2011 +0000 check dict before unrefing it Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2642 ([glusterfs-3.2.0qa5]: invalid reads in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2642 commit 8e8d4e0869623f352c7993293c6e132d795a34bf Author: Raghavendra G Date: Wed Apr 6 05:37:05 2011 +0000 nfs: convert errno EDQUOT into appropriate nfs-errno. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2607 (Fileop fails when quota is enabled) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2607 commit 9bff4a73fedd388bb9c57a3e999361540ac333eb Author: Vijay Bellur Date: Wed Apr 6 00:59:04 2011 +0000 protocol/client: Avoid logging when EAGAIN is received for *lk requests Signed-off-by: Vijay Bellur BUG: 1887 (logging mess) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1887 commit 7bfaed649bf8a479afd051ea3c5adc7a4717b2fa Author: Vijay Bellur Date: Tue Apr 5 10:22:57 2011 +0000 change occurrences of marker_gsync to marker-gsync Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 282109ed02a1ad220027bc69398941ba2b115cd2 Author: Raghavendra G Date: Tue Apr 5 09:02:53 2011 +0000 features/marker, cli: use appropriate conversion specifiers. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2649 (Quota: size field is not getting updated properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2649 commit 322ed6812d9a5b3c975b5c949ff5adfd16d40eb4 Author: Amar Tumballi Date: Tue Apr 5 04:00:26 2011 +0000 protocol/client: make sure to send only genuine events up to parent that way parent notify logic is fine. also, remove 'xlator_notify()' call in code, instead use 'default_notify()' Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2584 (Inode number changes on a directory when one of subvolumes is down in replicate) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2584 commit b8ae8d95a814d9329c34e6bf3d705c0fc07115b7 Author: Gaurav Date: Thu Mar 31 05:42:47 2011 +0000 NFS : Store verifier for exlusive mode craete. Signed-off-by: Gaurav Signed-off-by: Vijay Bellur BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit e4c5ad45612e845eb476b29d51ec12b963660855 Author: Amar Tumballi Date: Wed Mar 30 00:03:59 2011 +0000 cluster/dht: send back the proper inode number in the cbk functions Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2584 (Inode number changes on a directory when one of subvolumes is down in replicate) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2584 commit 8a4e51fcc1d8fd69038c513712729bf9dba5c4e2 Author: Amar Tumballi Date: Wed Mar 30 00:03:43 2011 +0000 cluster/dht: log level fixes in lookup* functions Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 99af7219c54b2264ede898fa619125c629519174 Author: Amar Tumballi Date: Wed Mar 30 00:03:20 2011 +0000 log gfid mismatches for the same file in cluster xlator lookup This can help in pin pointing some of the issues resulted in gfid mismatch for the same file, which is harder to find through basic debugging/logging of current codebase. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit a1a0e929534cb56e3a938229c7f87bfd0f1c17ec Author: Amar Tumballi Date: Thu Mar 24 07:28:00 2011 +0000 cluster/afr: log enhancements - part 1 Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit ba044581fa8781886fbd4f4675f388c79f599b2c Author: Raghavendra G Date: Fri Apr 1 03:00:04 2011 +0000 features/quota: use a double pointer to uint64_t as an argument to dict_get_bin while getting size. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit ff9e63c0975e786a69e5ecede78b178f20baceb7 Author: Raghavendra G Date: Fri Apr 1 02:56:18 2011 +0000 features/quota: add NULL check before doing strcasecmp Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2646 (glusterfs-client crashes during getxattr) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2646 commit f338193a707ae5b6b5ab6f820bea32612c4311bb Author: Csaba Henk Date: Sun Apr 3 15:44:17 2011 +0000 syncdaemon: refine intermal configuration of gsyncd Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2561 (gsyncd command's must be preconfigured) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2561 commit 01b3dff29adee2041b0ef1b374eda8c88fb07678 Author: Csaba Henk Date: Sat Apr 2 19:40:49 2011 +0000 syncdaemon: add monitor mode to support autorestart Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2537 (gsync autorestart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2537 commit e77c35248e8ce796bc5b108c10013089a0c65bde Author: Csaba Henk Date: Sat Apr 2 19:40:48 2011 +0000 syncdaemon: provide transactional semantics to config file writing So updating the config file from multiple contexts won't mess it up. This prepares the next commit where we'll set options internaly (which lacks the serial nature of user actions). Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2537 (gsync autorestart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2537 commit cfb9c834f96dc57c47dac8d27da4266d0dab1f3f Author: Csaba Henk Date: Sat Apr 2 19:40:47 2011 +0000 syncdaemon: give some refactoring to cascading code - expiry check of foreign volinfo moved back to GLUSTERServer, so that under the hood we can removexattr the expired ones; a nice side-effect is that we can use the same dict layout for foreign and native volinfo (ie., foreign needs no timeout field) - get_volinfo() is renamed to get_sys_volinfo() and most of the logic is stripped off of it (what remained there is the check against foreign master ambiguity) - volinfo transition logic is cut out to an almost purely functional static method (only impurity is the exeption raised upon forbidden volinfo change) - ping renamed to keep-alive, as something called "ping" is not supposed to have payload (yeah, keep-alive is a bit fishy on this front too, but could not come up with better...) Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2535 (gsync cascading) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2535 commit f007eb1a0701cd3e13e6ba67208cd1db9325a370 Author: Csaba Henk Date: Thu Mar 31 11:59:52 2011 +0000 syncdaemon; adding corresponding pcloses to gsyncd invocation via popen Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit 913da6c337cfe342d60f3773057a14d645248421 Author: Csaba Henk Date: Thu Mar 31 05:58:58 2011 +0000 syncdaemon: fix up fallback xtime value for slave Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2535 (gsync cascading) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2535 commit c0e6146f53d3e91764e9ff602ccba9a637b2db7d Author: Pranith Kumar K Date: Fri Apr 1 03:44:02 2011 +0000 debug/io-stats: Fix bugs in re-configure options If the options are not present in vol file reset the option values. If there is an invalid option log an error and continue, no need to exit Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2638 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2638 commit cd4fd271c6636ecc100171403b324a65a9e77fe2 Author: shishir gowda Date: Fri Apr 1 03:24:12 2011 +0000 Replace strdup call to gf_strdup as GF_FREE is being called Also, fix validation of bs and count to <= 0. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2645 (volume top write-perf results in memory corruption) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2645 commit 5c709704ab5767b55f4eef7cddea52e18e2a6d42 Author: Amar Tumballi Date: Tue Mar 29 07:07:05 2011 +0000 cluster/afr: log enhancement - part 3 Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d983f04c961304dc57d14c305751b0d1113c3a5d Author: Amar Tumballi Date: Tue Mar 29 07:06:45 2011 +0000 cluster/afr: log enhancement - part 2 Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit fa6ba86900abc9b023adf4ce642aba5eb0a35500 Author: Anand Avati Date: Mon Mar 28 09:30:38 2011 +0000 nfs: capture attrs of create request in cs->stbuf for later use when attrs coming in as part of create request contain modes other than mode, they were getting discarded previously and a setattr was getting performed on a 0-filled iatt structure. This would result in EPERM at the access control translator as non-root users cannot chown a file to uid 0. Not seen with Linux NFS client as it (very likely) relies upon auth-unix to set the ownership of the file or sends an explicit setattr after the create. Signed-off-by: Anand Avati Signed-off-by: Vijay Bellur BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit 9c09f44f716df2c45e25b6a9a6465592fde19ea3 Author: Csaba Henk Date: Thu Mar 31 11:59:51 2011 +0000 syncdaemon: fix gsyncd invocation for config-set Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2555 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2555 commit 0f67ad828895960ab96f9e237eae8acbc6c63988 Author: Csaba Henk Date: Thu Mar 31 08:13:31 2011 +0000 syncdaemon: minor cleanups in cascading code Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2535 (gsync cascading) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2535 commit 05daec675f1716554864e34e0a3c9c71423b6594 Author: Vijay Bellur Date: Thu Mar 31 22:11:00 2011 -0700 Revert "Process dir/link from other subvol if error in dht_readdir" This reverts commit cd3d977b10e24c4b46e55f9831113aba3a241583. commit 498dbbc506ec9c694e18c3ae9a0d3d346abe338d Author: shishir gowda Date: Thu Mar 31 04:57:22 2011 +0000 TOP: Improve output format Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2614 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2614 commit c68b1e28ae9b7528aa844764e719c7267976be83 Author: shishir gowda Date: Thu Mar 31 04:57:05 2011 +0000 TOP: Validate command options Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2628 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2628 commit 58974b02b6ebb65ee1f7baf23b0fe6c3e7fcf8cd Author: shishir gowda Date: Thu Mar 31 04:56:10 2011 +0000 TOP: handle list-cnt behaviour uniformly. Valid range is 0-100. if list-cnt is 0 or there are no files in the list, handle it uniformly. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2622 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2622 commit 3b5195cfa4976e1d83646b70b0f08f583a7a1094 Author: Junaid Date: Thu Mar 31 04:28:43 2011 +0000 features/quota: Use appropriate inodes while logging and create contexts in inode for files. - It also fixes limit checks if limit set in the directory. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2604 (Quota: crossing the set limit) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2604 commit 1c148f85c5abf561faeb68c699a13c8bd683de5e Author: Junaid Date: Thu Mar 31 04:28:26 2011 +0000 features/marker: Fix memory corruption. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2629 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2629 commit 99779326d09f7ac98bb75bb1432d53c7c320a5c9 Author: Pranith Kumar K Date: Thu Mar 31 04:27:22 2011 +0000 mgmt/glusterd: Delete volume profile options on profile stop Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2638 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2638 commit a728fc84b67f8ba37cf63a8e3ef67cf8b0bb1f32 Author: Pranith Kumar K Date: Thu Mar 31 03:31:01 2011 +0000 mgmt/glusterd: Improve profile output messages Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2616 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2616 commit 43700ed04c1bac15f5df3702410c83fb63607476 Author: Pranith Kumar K Date: Thu Mar 31 03:31:00 2011 +0000 cli: Improve profile output messages Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2616 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2616 commit 215a8352e2219c7ead29693ccab3452054a89041 Author: Csaba Henk Date: Thu Mar 31 03:29:35 2011 +0000 syncdaemon: fix "--debug" option of gsyncd.py also be explicit about logging to a stream (ie. don't rely on the feature of accessing stdin through /dev/stdin) Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2637 (gsyncd --debug broken) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2637 commit e0f03d7430f6b79e9ed0fa68234753e33368e3e6 Author: Pranith Kumar K Date: Wed Mar 30 23:47:59 2011 +0000 mgmt/glusterd: Fix space in error message Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2623 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2623 commit 5f6e7aecdb4dba8b181e90be99eb21ad40129315 Author: Pranith Kumar K Date: Wed Mar 30 23:43:41 2011 +0000 mgmt/glusterd: Mark the brick stopped when kill -SIGTERM is done Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2621 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2621 commit 0cccbefebfd2e95dbbf7f078f5e45267c60d48ed Author: Amar Tumballi Date: Tue Mar 29 07:06:26 2011 +0000 cluster/afr: white-space cleanup - part 2 Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit f7fb326c250997f274e4e928faec9aeca4ce12c9 Author: Shehjar Tikoo Date: Tue Mar 15 01:57:15 2011 +0000 nfs-rpc: Append replies to end of connection's txlist ..instead of prepending. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 2491 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2491 commit c294df619656798b107933a42a0f5613c1df0830 Author: Shehjar Tikoo Date: Tue Mar 15 01:57:14 2011 +0000 core: Add list_append_init To append to end of list, as compared to list_splice_init which prepends. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 2491 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2491 commit a54e0358b1d66c04448b22c1a01e076b5a527008 Author: Shehjar Tikoo Date: Tue Mar 15 01:57:13 2011 +0000 nfs-rpc: Exit txbuf transmission loop on EAGAIN ..instead of looping till the buffer is completely transmitted. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 2491 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2491 commit 325ee7aeab629a7435922d9e61d04fd3418ec6d7 Author: Mohammed Junaid Ahmed Date: Wed Mar 30 07:54:41 2011 +0000 return after stack winding instead of destroying the frame Signed-off-by: Raghavendra Bhat Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2624 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2624 commit ca67876f15347faccba9fdd3f3f2997c58ef3fa6 Author: Kaushik BV Date: Wed Mar 30 06:03:06 2011 +0000 mgmt/Glusterd: prevent memory overflow Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2632 (possible memory overflow in one of the code paths in volume gsync stop) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2632 commit f8c798350a5efa537418d1453f3e547574e68b55 Author: Kaushik BV Date: Wed Mar 30 06:03:05 2011 +0000 mgmt/Glusterd: add pid extension to the pid file of the gsyncd Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2538 (pidfile naming) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2538 commit d1c0e5b0dc64bb431c384b7584ea362143d8ef46 Author: Anand Avati Date: Wed Mar 30 01:18:46 2011 +0000 nfs: more fixes to capture sattr for further usage in - mkdir - mknod Signed-off-by: Anand Avati Signed-off-by: Vijay Bellur BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit d1700d209431e19a2ecca43f644935533d705af1 Author: Raghavendra Bhat Date: Tue Mar 29 14:08:04 2011 +0000 assign local to frame->local before checking for error conditions Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2617 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2617 commit 3ce486929518da2673b6cef5ef1047849f587729 Author: Raghavendra Bhat Date: Tue Mar 29 13:37:26 2011 +0000 access the proper loc structure when inode ctx get fails in quota Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2611 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2611 commit b40d510cf534b6fa1acb827ed7c26bcdebc5fd36 Author: shishir gowda Date: Wed Mar 30 00:28:29 2011 +0000 io-stats list: init counter to 0 for counting members By setting init the counter cnt to -1, we were loosing 1 entry when displaying the list on the cli. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2606 (gluster volume top open lists only 99 entries) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2606 commit d088ffe14da46247052e34c5cfaced46f5079b24 Author: Raghavendra G Date: Tue Mar 29 14:15:32 2011 +0000 debug/io-stats: fix memory corruption. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2619 (Memory corruption in io-stats) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2619 commit 4597929cc527f8abaf9ef9e1d5499ea416e5c7ff Author: Kaushik BV Date: Tue Mar 29 09:10:07 2011 +0000 Gsyncd: Cascading of gsync daemons This patch allows the slave of a gsyncd to be started as the master of another slave gsyncd. Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2535 (gsync cascading) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2535 commit 4c246c02f4ab569fca92255b7efb819243711d6b Author: Mohammed Junaid Ahmed Date: Mon Mar 28 07:21:51 2011 +0000 mgmt/glusterd: Fix double free on quota limit-usage. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2595 (Quota: re-setting the space-limit crashes the glusterd on the same node) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2595 commit b6ffe3ed1d44fddaed2a5eb2586b0584bfc17d5a Author: Pranith Kumar K Date: Mon Mar 28 04:32:32 2011 +0000 mgmt/glusterd: Add rpc-auth-allow-insecure option Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit 94a2118801138db92dda0cf74691fea95d7f9d12 Author: Gaurav Date: Mon Mar 28 04:30:28 2011 +0000 NFS : Volume access option accepts only valid values. Signed-off-by: Gaurav Signed-off-by: Vijay Bellur BUG: 2598 (Volume access option suceeds with any string value) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2598 commit 61b669c8366bc43e62324bbd0ce381cdbe633b93 Author: Mohammed Junaid Ahmed Date: Mon Mar 28 04:04:55 2011 +0000 features/marker: check for op_ret before doing any operations in lookup callback Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2497 (client crashes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2497 commit b65f54c9aa1e3405b731769e56460592ba69ed60 Author: Pavan T C Date: Mon Mar 28 03:50:29 2011 +0000 Loosen restrictions on hostnames Signed-off-by: Pavan T C Signed-off-by: Vijay Bellur BUG: 2249 (Problems with hostname validation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2249 commit b691214fd9114e2b4c7d419ef06aedd28614127a Author: Amar Tumballi Date: Thu Mar 24 07:27:26 2011 +0000 cluster/afr: whitespace cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 408a2b029824a3915ce094aed520061e80c078c8 Author: Raghavendra Bhat Date: Sun Mar 27 14:03:10 2011 +0000 check the local for NULL before accessing it Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2592 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2592 commit 2406e21dd2d63b4ab69d8179d69dae17f0e4a0d9 Author: Pranith K Date: Sun Mar 27 08:51:29 2011 +0000 mgmt/glusterd: Add the new volume only after all ops succeed - Print errors to the user when any of the op fails in create volume - Add the volume to the list only after all the ops succeed Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1888 (volfile generation error ignored) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1888 commit 48b0c02ba2b9c828b29ce236c838ab0e56ddab08 Author: Pranith K Date: Fri Mar 25 21:43:44 2011 +0000 protocol/server: change allow_insecure option in reconfigure Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit 8b32b9ab363639888938c631882c8cfd6b00a3f5 Author: Pranith K Date: Fri Mar 25 21:43:31 2011 +0000 mgmt/glusterd: Provide volume option to allow insecure ports for server Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit f6e0e614fbd07a57de44f0d16c304d01d1a5b269 Author: Pranith K Date: Fri Mar 25 21:43:17 2011 +0000 mgmt/glusterd: Allow insecure ports by default Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit 8a15f00cd8ad19fa414d2ef63dc71147ae191d73 Author: Pranith K Date: Fri Mar 25 21:43:03 2011 +0000 rpc: Don't warn on failure to bind to privileged port Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit 3f37921807fc84af6d9529ae18aa8575e2458fc5 Author: Pranith K Date: Fri Mar 25 21:42:49 2011 +0000 rpc: Provide an option to allow insecure ports Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582 commit a9a6d95ecb86f45b197bc36d8e6a504d65367c3a Author: Junaid Date: Fri Mar 25 01:49:07 2011 +0000 cluster/dht: Fix double freeing in quota aggregate. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 0952bbb30564e8a2359039841290f9956c96e1b9 Author: Junaid Date: Fri Mar 25 01:48:52 2011 +0000 features/quota: Return dynamically allocated address of local. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit c55d855c74d860ff0dae942f95c290eba45f15f8 Author: Junaid Date: Fri Mar 25 01:44:20 2011 +0000 mgmt/glusterd: Fix double memory free. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 3f6be7a12972684500d4357a170a3de4f452a63b Author: Junaid Date: Fri Mar 25 01:39:12 2011 +0000 features/marker: Handle fop's gracefully when none of the feaures are enabled. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2529 (Starting Gsync causes ENOTCONN to glusterfs client) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2529 commit 2339b9e87e8e48df9b64ba016949a2f40b50324e Author: Pranith K Date: Wed Mar 23 21:44:13 2011 +0000 mgmt/glusterd: Avoid printing no-error message to user when op fails - Prints the peer hostname/uuid where the error happened in case the peer does not return an error string. Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2585 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2585 commit 1180b2136f6cf014a08f072f8ecc4aac2b69580f Author: Pranith K Date: Fri Mar 25 05:58:35 2011 +0000 mgmt/glusterd: Fix import friend volumes - Sync transport type of the volume - Stop stale bricks - start new bricks if the volume is started - Restart/Stop nfs server based on the new information Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2549 (Quota[glusterfs-3.2.1qa3]: enable/disable crashes the glusterd on other node) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2549 commit fc06afc8cd1a646f71e0ed1713b05b8aa533c6d2 Author: Pranith K Date: Wed Mar 23 05:25:26 2011 +0000 mgmt/glusterd: fail create volume on create-volfiles failure Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1888 (volfile generation error ignored) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1888 commit e488f48ebc3d545b9924b828e59f08a5d42571ba Author: Kaushik BV Date: Wed Mar 23 00:52:22 2011 +0000 Gsyncd: fix a typo for the command-line arg of gluster process Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 89b45f610dfc455dd6c8fd84c1d3c9945ad62f4c Author: Raghavendra Bhat Date: Tue Mar 22 05:01:56 2011 +0000 send proper device id to posix while self healing device file entry Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2567 (self heal on device files changes the major and minor number) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2567 commit cd3d977b10e24c4b46e55f9831113aba3a241583 Author: shishir gowda Date: Tue Mar 22 04:43:56 2011 +0000 Process dir/link from other subvol if error in dht_readdir Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2137 (dhtafr - self heal after renaming directory) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2137 commit 0ed446b7c8c8bcda74a5d64cdb8f0ac2d11b2389 Author: shishir gowda Date: Tue Mar 22 04:43:20 2011 +0000 Implement stripe readdirp fops Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2159 commit c1f1345e6fc2a008ef03632cd64211bf20c244bb Author: Shehjar Tikoo Date: Mon Mar 21 02:00:19 2011 +0000 nfs3: Flush file I/O call states on open failure Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 2566 (NFS read hangs when arequal-checksum script is run) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2566 commit f2a9ce7abacc8749589d0b931ca155d2c7578774 Author: Vikas Gorur Date: Thu Mar 17 19:08:49 2011 +0000 nfs: Remove redundant and erroneous check for create mode EXCLUSIVE. nfs3.c/nfs3_create_common: The if condition checks for create mode being EXCLUSIVE. However, when create mode is EXCLUSIVE, this function never gets called (nfs3_create_exclusive is called). Also, instead of checking, it actually sets the value of createmode (= instead of ==). Signed-off-by: Vikas Gorur Signed-off-by: Vijay Bellur BUG: 2553 (NFS file create with Mac client and UNCHECKED mode returns "Operation not permitted") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2553 commit bd132d8e410dbc24cbef751925cd937939f35747 Author: shishir gowda Date: Wed Mar 23 03:53:28 2011 +0000 Prevent deadlock in io-stats list management of top. Senario: thread t1 has lock on the queue, and waits on the element lock to remove it and unref it. Thread t2 has a lock on the element being removed from the queue, but waiting on the queue on the list to update it. The fix is to move list management to outside of the lock. Additonal to this change is adding locks to ios_stat_ref Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2578 (Mountpoint hung while running the dbench) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2578 commit 9bd4f25b6b0ea8103324b685fcc21525a29849a8 Author: Gaurav Date: Wed Mar 23 00:50:17 2011 +0000 CLI : Validate options farmework. Signed-off-by: Gaurav Signed-off-by: Vijay Bellur BUG: 2064 (NFS options are removed upon glusterd restart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2064 commit 6f6c817314a2a867be996c2ad6d9a1337617ded4 Author: Raghavendra Bhat Date: Tue Mar 22 07:08:24 2011 +0000 do not check loc and fd since they can be passed as NULL only Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit e4957b1ae771fa7a1e56cfd25f55deaa527dff4c Author: shishir gowda Date: Tue Mar 22 06:30:44 2011 +0000 TOP: remove trailing '/' from brick path Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2573 (trailing '/' with brick name says "volume top unsuccessful" while running 'top' command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2573 commit 384f81cf412c0da9d13a547c0aeb2cd33e59774d Author: shishir gowda Date: Tue Mar 22 05:20:01 2011 +0000 Moved stats cleanup to forget from unlink and rmdir Additionally, replace inode_ctx_get with inode_ctx_del in cleanup Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2575 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2575 commit 95f59725adbefd574cfd694dc101ee9c803f167a Author: Raghavendra Bhat Date: Tue Mar 22 04:50:07 2011 +0000 free priv structure if something fails in init for locks Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit a4233a41bf6a2f9ddbce15a530b1678c55ba24a5 Author: Pranith K Date: Fri Mar 11 05:02:15 2011 +0000 cluster/afr: skip openfd flush when the file is already deleted Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2497 (client crashes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2497 commit e115072f4b654d407fcf435256334645ab471776 Author: Mohammed Junaid Ahmed Date: Tue Mar 22 04:36:39 2011 +0000 features/marker: Donot fail init when both gsync and quota are not enabled. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2529 (Starting Gsync causes ENOTCONN to glusterfs client) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2529 commit 9c7bc4f5da67a630fe543bd8bdf5d1aaf2acef99 Author: Vikas Gorur Date: Thu Mar 17 19:01:02 2011 +0000 libglusterfs/compat.h: Fix build warning in dirent_size(). Signed-off-by: Vikas Gorur Signed-off-by: Vijay Bellur BUG: 2550 (build warnings) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2550 commit c077bd932beff169a366c99c94ff45e432d1d793 Author: Raghavendra Bhat Date: Tue Mar 22 03:01:03 2011 +0000 remove the names from the log files Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2573 (trailing '/' with brick name says "volume top unsuccessful" while running 'top' command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2573 commit b230793b8b345ff25168567209cae10294b53f23 Author: Pranith K Date: Mon Mar 21 07:26:30 2011 +0000 cli: Fix memory leak in gluster profile Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2571 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2571 commit 6167c66758de454284560474f3b4a893d8a69965 Author: Amar Tumballi Date: Fri Mar 18 00:41:08 2011 +0000 spelling errors fixed across the code base recieve -> receive maintainence -> maintenance verison -> version commited -> committed Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2262 (Spelling errors in source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2262 commit c0d8f11be283637622b0ece82ba8392f0a67e87c Author: Amar Tumballi Date: Thu Mar 17 08:00:49 2011 +0000 man pages updated Thanks to Divya MN for all the effort Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2444 (keep man pages upto date with new codebase.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2444 commit 50ab0ad4ffb5ea844c6fe1f708df65b769c88db1 Author: Mohammed Junaid Ahmed Date: Mon Mar 21 07:16:17 2011 +0000 mgmt/glusterd: Glusterfsd not restarted on changes to marker option. Bricks are not restarted when some marker options are changed and the Marker translator is included statically in the server volfile. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2529 (Starting Gsync causes ENOTCONN to glusterfs client) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2529 commit 1ef501b5c526a2dec6592cb8693996a81e5834c4 Author: Raghavendra G Date: Mon Mar 21 01:54:42 2011 +0000 cluster/distribute: aggregate quota-sizes in lookup and getxattr. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 7852c982ffd85ee38b42894f3c966d1634d550be Author: Raghavendra G Date: Mon Mar 21 01:54:26 2011 +0000 features/quota: Client side quota. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit d0e3c762318673a6081ab96abc525a568f82170b Author: Raghavendra G Date: Mon Mar 21 01:53:58 2011 +0000 features/quota: removed quota.c and quota-mem-types.h files. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 941442ced02900128c6893caa6159bac2f1d9683 Author: Pranith K Date: Sun Mar 20 03:25:50 2011 +0000 mgmt/glusterd: Dont reset the port on brick stop Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2564 (replace brick fails on master) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2564 commit 24d326a5180adaedf8d49a2d087afa0ec470a537 Author: shishir gowda Date: Fri Mar 18 05:37:24 2011 +0000 Change NFS_PATH_MAX value to 4096 This is tmp fix for crash seen on solaris gnfs server is received path is longer than PATH_MAX. On solaris default PATH_MAX is 1024, and linux default PATH_MAX is 4096. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2476 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2476 commit dece0547259a5d73fd6c2616802f83388b5ff4da Author: Gaurav Date: Fri Mar 18 03:52:08 2011 +0000 CLI : Fix memory free for key_fixed. Signed-off-by: Gaurav Signed-off-by: Vijay Bellur BUG: 2554 (Invalid memory access in glusterd.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2554 commit bb5b31fb96dbc2092e2967924462c59863845749 Author: Amar Tumballi Date: Fri Mar 18 00:56:14 2011 +0000 fuse: set 'graph->used' after graph change Because in the current way, we have chances of changing the graph to old one too. with this, we can control this. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2503 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2503 commit 26dcbc729395b00dae45cd62222aaccbd2ab7aff Author: Amar Tumballi Date: Fri Mar 18 00:38:36 2011 +0000 debug/io-stats: don't log the dangling volume message Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 131d82cacd4600654d3e931287d2556f50bd9db5 Author: Amar Tumballi Date: Fri Mar 18 00:38:13 2011 +0000 libglusterfs: added graph id in logging Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 3d912aa905105098db1eea1e4c3e9c42aa0c7da7 Author: Rahul Date: Thu Mar 17 01:55:43 2011 +0000 Added checks for fix-layout & migrate-data usage. Signed-off-by: Rahul Signed-off-by: Vijay Bellur BUG: 2547 (rebalance command usage and help mis-match) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2547 commit 6d8077eb9c7129f4bdb352132e565906568dfb66 Author: Csaba Henk Date: Thu Mar 17 11:44:25 2011 +0000 Revert "syncdaemon: make /usr/libexec/gsyncd the default remote gsyncd (incomplete hacky quickfix)" This reverts commit 8c801cfd05eb533ae64ea9f06e49e632955cf0c0. The commit in question was just a temporary fix (which violated component boundaries). Since 9043b0f8 we don't rely on this fix. Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit 223bfc4d19a2b7cccc62e05129e09591233edc44 Author: Csaba Henk Date: Thu Mar 17 00:46:38 2011 +0000 syncdaemon: fix up exit value Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 2380 (TypeError: 'str' object is not callable) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2380 commit 236600d7de4e900ad3905908853785dc2ac6629f Author: Csaba Henk Date: Thu Mar 17 00:46:37 2011 +0000 syncdaemon: don't try to set log level to None Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 0a1f00cdcb087e00c184c62c1a9f22803c257cf2 Author: Amar Tumballi Date: Wed Mar 16 09:38:49 2011 +0000 libglusterfs/src/*.c: log enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 0f39192ef6bc7b1c74cfaeb04ed21305996d67e9 Author: Amar Tumballi Date: Wed Mar 16 09:43:33 2011 +0000 protocol/client: log enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 0349ec857004428f29b50f3604e5ab126dfb407e Author: Amar Tumballi Date: Wed Mar 16 09:43:27 2011 +0000 protocol/server: log enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d3e9a97b6ef340f827cf55de5340a8bf5c732f3e Author: Mohammed Junaid Ahmed Date: Wed Mar 16 09:43:21 2011 +0000 protocol/server: White space cleanup and NULL check validations. Signed-off-by: Junaid Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 0d7628c6c2b0c1d1e1bdcc6dc3904d30d6ebf38e Author: Amar Tumballi Date: Wed Mar 16 09:43:13 2011 +0000 protocol/auth directory updated with whitespace cleanup and proper logs Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d643c1093a89398de6cbe333aeea5cf91a56b3ad Author: Amar Tumballi Date: Wed Mar 16 09:43:04 2011 +0000 cluster/dht: log enhancements Signed-off-by: Shishir Gowda Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 7df49c62422d33d19eaebeddd3fcdacccc9c7bce Author: Amar Tumballi Date: Wed Mar 16 09:42:29 2011 +0000 cluster/dht: whitespace cleanup also fill tabs by spaces (untabify), and indent the code Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit a938b273338094599c79dad7f60883599450e4ac Author: Amar Tumballi Date: Wed Mar 16 09:42:19 2011 +0000 features/locks: logging enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 56b86533b1e2eca1535a7b20955b72baf25cd2ae Author: Pranith K Date: Wed Mar 16 09:42:12 2011 +0000 features/locks: White space related changes to adhere to coding guidelines. Signed-off-by: Pranith Kumar K Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 825a104afe892f91c77dfc3622b50116341c5bb2 Author: Amar Tumballi Date: Wed Mar 16 09:42:06 2011 +0000 features/access-control: logging enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d5bbe1e4d45a96f3a68c8e862ad051e675970911 Author: Pranith K Date: Wed Mar 16 09:41:58 2011 +0000 features/access-control: White space related changes to adhere to coding guidelines. Signed-off-by: Pranith Kumar K Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 4e6c54e75436c7e922981a2513a3a5c9fd293568 Author: Amar Tumballi Date: Wed Mar 16 09:41:52 2011 +0000 performance/stat-prefetch: logging enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit eb537b0e5f97a74b4562fa8cb0ce24b60732323c Author: Raghavendra G Date: Wed Mar 16 09:41:44 2011 +0000 performance/stat-prefetch: whitespace related changes to adhere to coding guidelines. Signed-off-by: Raghavendra G Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit b75f0fd11c4eba196ad236a5618df2befd137df0 Author: Raghavendra G Date: Wed Mar 16 09:41:31 2011 +0000 performance/write-behind: logging enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit aad5b36d0f04b3c7bf1cec0af63b158fd37b2183 Author: Raghavendra G Date: Wed Mar 16 09:41:25 2011 +0000 performance/write-behind: whitespace cleanup. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 3629c2880488ea9d4fa34f9e026bd9007b91bd4a Author: Raghavendra G Date: Wed Mar 16 09:41:16 2011 +0000 performance/read-ahead: logging enhancements. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d0b82760dc06b16f323d65506337c8373ce6ceb1 Author: Raghavendra G Date: Wed Mar 16 09:41:09 2011 +0000 performance/read-ahead: white space related changes to adhere to coding guidelines. Signed-off-by: Raghavendra G Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit f6da369103a3a8962f3d6b7f9df6bd2f1f8cc8db Author: Amar Tumballi Date: Wed Mar 16 09:40:50 2011 +0000 performance/quick-read: logging enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 4aeaa48108d924ea67d77fedfadb7d96a13712dd Author: Raghavendra G Date: Wed Mar 16 09:40:43 2011 +0000 performance/quick-read: propagate errors during open back to actual fops. - If open fails and there are any other fops waiting on that open, those fops should also unwind with appropriate errors. Before this patch, irrespective of success/failure of open, fops waiting on it were stack_wound and since fd was invalid, they would fail with EBADFD errors. Due to this actual error would've got masked by EBADFD. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 094d42b9a8d1d5d68d29bfb9b0b735f5c94f8a36 Author: Raghavendra G Date: Wed Mar 16 09:40:35 2011 +0000 performance/quick-read: whitespace related changes to adhere to coding guidelines. Signed-off-by: Raghavendra G Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 39b953c2749f1d9a9302276e6c829dc4681758a8 Author: Raghavendra G Date: Wed Mar 16 09:40:22 2011 +0000 performance/io-cache: logging enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 67609fd909f8fa0dc5fa812cc17c5441747ca4b8 Author: Raghavendra G Date: Wed Mar 16 09:40:14 2011 +0000 performance/io-cache: whitespace related changes to adhere to coding guidelines. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit e02171f1b86cfb3cd365c4c47edc83b8230985bd Author: Amar Tumballi Date: Wed Mar 16 09:40:06 2011 +0000 rpc-transport: log enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 02d8dcbb5c7483ade3dd052d75e6430cb0253d1f Author: Amar Tumballi Date: Wed Mar 16 09:39:57 2011 +0000 rpc-transport: whitespace cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit d4aae8327ac5581cd47dd0fcea796ddbb03be5ea Author: Amar Tumballi Date: Wed Mar 16 09:39:46 2011 +0000 rpc/rpc-lib : log enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit abc2a6b0b91a82bb59327cd2a4ca72b8954e1425 Author: Amar Tumballi Date: Wed Mar 16 09:39:21 2011 +0000 glusterfsd: log enhancement Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit ca6528592eed88ff1598b25f1aaa1c99c14a2e32 Author: Amar Tumballi Date: Wed Mar 16 09:39:15 2011 +0000 glusterfsd: whitespace cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 532edf1c4a8f0db7447d12657a100e8dd91a74e0 Author: Amar Tumballi Date: Wed Mar 16 09:39:07 2011 +0000 storage/posix: log enhancements Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 75bda6e41d9b244ab9d040a035582ea6bd4c8120 Author: Amar Tumballi Date: Wed Mar 16 09:38:35 2011 +0000 libglusterfs/src/*.c: whitespace cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 858944850adf7ec04898a15db90e231655ac4965 Author: Amar Tumballi Date: Wed Mar 16 09:38:56 2011 +0000 storage/posix: whitespace cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 924d2ed32d19a2a0014f803edd3d4511a0af99c2 Author: Amar Tumballi Date: Wed Mar 16 09:38:28 2011 +0000 libglusterfs: all header files updated * whitespace cleanup (M-x whitespace-cleanup) * indentation fixes (M-x indent-region) * replaced tab with spaces (M-x untabify) Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit ebe47d5dae42da18b289e7be44eb67a8157a56b1 Author: Amar Tumballi Date: Wed Mar 16 09:38:21 2011 +0000 libglusterfs: gf_log_nomem() and other minor updates log will be done when the memory allocation fails, hence in code, no explicit logs required for memory allocation failures. also, if there are logs before actually doing a log_init(), they will be logged in 'stderr'. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit ce01662eefb575d1afe397486653920ec101f40f Author: Amar Tumballi Date: Wed Mar 16 09:37:55 2011 +0000 libglusterfs: logging/mem-pool section white-space cleanup Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit b44b06a9d0adb50b426e0ee195a9867e01240ada Author: Mohammed Junaid Ahmed Date: Wed Mar 16 13:11:45 2011 +0000 mgmt/glusterd: Use PATH_MAX for pid_file. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2534 (Glusterd crashes on gsync stop.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2534 commit 9796d4bf3015042f1b2bef22a2be6c22fed4cf4d Author: Mohammed Junaid Ahmed Date: Wed Mar 16 12:59:54 2011 +0000 features/marker: Invalid option "marker", use "gsync" instead. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 6ddc55874985008ee51982d755743f0d01161a44 Author: Mohammed Junaid Ahmed Date: Wed Mar 16 05:58:09 2011 +0000 mgmt/glusterd: Use dict_set_dynstr in place of dict_set_str. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 10eafa32914f2458f3bb30073724758a95a82310 Author: shishir gowda Date: Wed Mar 16 03:35:46 2011 +0000 TOP: glusterd/mgmt related changes Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2516 (Implement gluster volume top command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2516 commit 3d1fc9ebe2b0292108dd0737cf8f40d6fcb8cf51 Author: shishir gowda Date: Wed Mar 16 03:35:16 2011 +0000 TOP: cli, rpc/xdr related changes Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2516 (Implement gluster volume top command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2516 commit f208d7148fefd55b4073bda978816d71831ffefa Author: shishir gowda Date: Wed Mar 16 03:34:53 2011 +0000 TOP: io-stats related changes Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2516 (Implement gluster volume top command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2516 commit 4db0bc5977eb3e2d5bc0e3666bb6de5719d153a4 Author: Mohammed Junaid Ahmed Date: Tue Mar 15 22:25:55 2011 +0000 features/marker: QUOTA related changes in marker translator. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit fa4e997970fb0e1d0abaae742a35701bcb576150 Author: Mohammed Junaid Ahmed Date: Mon Mar 14 22:22:04 2011 +0000 storage/posix: Added GF_XATTROP_ADD_LONG_ARRAY flag to perform 64bit xattrop operations. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 031eee923d8fd79bc1cf78b7b24fe82e44186848 Author: Mohammed Junaid Ahmed Date: Tue Mar 15 05:35:45 2011 +0000 mgmt/glusterd: QUOTA Glusterd related changes. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit c5d93456dcd17ddeb189c3e1390e58f95e30b851 Author: Mohammed Junaid Ahmed Date: Tue Mar 15 05:36:18 2011 +0000 cli: QUOTA cli related changes. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 8221c3cae1ce5c2f7d897e5637591c5437aeea69 Author: Mohammed Junaid Ahmed Date: Tue Mar 15 05:36:33 2011 +0000 rpc: QUOTA rpc related changes. Signed-off-by: Junaid Signed-off-by: Vijay Bellur BUG: 2473 (Support for volume and directory level quota) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2473 commit 7d61416a443b1786158c6236f182b6c11b3619f7 Author: Kaushik BV Date: Tue Feb 15 03:08:17 2011 +0000 features/marker: open the timestamp file with O_TRUNC to update the ctime Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2354 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2354 commit ab7dc7aafa61ae66db4ce7aa5e33e3ee408fd878 Author: Kaushik BV Date: Tue Feb 15 03:09:02 2011 +0000 Revert "features/marker: Use touch TimeStamp file instead of futimens, to avoid the dependency of newer libc" This reverts commit e045741f2bb75344a557cd618e1c7b1691238703. Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2354 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2354 commit da57b8e7541ced2be0464f461e29dc7428bbcb14 Author: Amar Tumballi Date: Mon Mar 14 05:36:16 2011 +0000 used S_ISVTX instead of 01000 in code for sticky bit check Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2369 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2369 commit c886643f97373944030c118b7f78d0a8c06b2291 Author: Pranith K Date: Mon Mar 14 04:20:51 2011 +0000 cluster/afr: Fix wrong memory allocation Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2517 (the size of allocated memory may be wrong) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2517 commit ac408b608130768fc9d67b836cef7c3f69f24de5 Author: Vijay Bellur Date: Mon Mar 14 10:13:36 2011 -0700 Revert "Eliminate syscall tight loop when handling EAGAIN in NFS." This reverts commit 689c1b5044e701e1b695a6e6c80647b9471ba454. commit d66758b4930224ba8d050f728b701b3259bf9cc7 Author: Vijay Bellur Date: Mon Mar 14 10:13:08 2011 -0700 Revert "Make sure we are looking at the right errno in the fix for bug 2452." This reverts commit dae57d72a58ff61fe6eda800d386bf83574ef5c2. commit 9043b0f8b927e687decc738cf736e603436e9e51 Author: Kaushik BV Date: Mon Mar 14 05:01:31 2011 +0000 mgmt/Glusterd: Make use of regexp pattern-matching sections to set a sane value for remote-gsyncd Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit eadce9083876fb71d1be8f77715866fc8af45ba4 Author: Kaushik BV Date: Fri Mar 11 07:57:52 2011 +0000 Gsyncd: Explicitly mention the path for the gsyncd.py script Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2437 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2437 commit 086ef357b64d4b7e5340226ada639813b1efd101 Author: Kaushik BV Date: Sun Mar 13 23:10:14 2011 +0000 Gsyncd: Include a directory glusterfs in the libexecdir, so that it is not cumbersome with other scripts Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2477 (Cleanup up the installation of geo-replication scripts.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2477 commit 2108ee66f226a124fd2ec20692e9941ed15464a5 Author: Anand Avati Date: Thu Mar 10 03:21:21 2011 +0000 afr-entry-self-heal: fixes to detected renames (gfid based) - perform expunge first (before impunge) to be able to delete renamed away files - perform readdirp instead of readdir to get gfid along with entry names - if gfid mismatch is found, expunge the entry Signed-off-by: Anand Avati Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 2500 (Self Healing not working) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2500 commit 3145f70fc27d8259b885049bcf7a737f4b7de569 Author: Kaushik BV Date: Sun Mar 13 23:33:13 2011 +0000 mgmt/Glusterd: remove the checks performed for all ops in brick_op Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit 05dbcd0cb2415bb218221eccc1e7005645aa318b Author: Pranith K Date: Thu Mar 10 21:49:04 2011 +0000 mgmt/glusterd: remodel glusterd store Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1754 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1754 commit 5a8edf3fc4deb4713d390690b144342e24659f8c Author: Raghavendra G Date: Sat Mar 12 01:08:34 2011 +0000 rpc-transport/rdma: handle cases where peer is NULL in send_completion. - There can be valid cases where peer is NULL - For eg., race b/w pollin received on handshake socket and as a result transport getting disconnected and handling of a send/recv completion on the same qp for some previous read/write - in send/recv_completion_process. Hence we should be checking for a valid peer pointer before accessing it. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 2514 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2514 commit 40a5e452bea79d1c7c78af480354e16ef970ca63 Author: Shehjar Tikoo Date: Fri Mar 11 01:48:57 2011 +0000 nfs-rpc: Fix order of freeing request and connection objects ..to prevent segfaults due to double frees and dereferencing of freed up memory. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 2504 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2504 commit 57d4551c05cdc17d2a9d687aca66802ce7af53f0 Author: Shehjar Tikoo Date: Fri Mar 11 04:32:20 2011 +0000 posix: Set op_errno to ENOMEM on failed iobuf_get This prevents a situation where op_ret for the read fop is -1 but the op_errno is still 0. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1977 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1977 commit 1c6e8fdf678d18e3b1a5472ebc076e7b3cb323e4 Author: Shehjar Tikoo Date: Fri Mar 11 02:21:10 2011 +0000 posix: Handle offset greater than file size of EOF determination Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1977 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1977 commit 190ef2ee5006614615144ed46935d1f8267bd021 Author: Csaba Henk Date: Tue Mar 1 03:59:48 2011 +0000 syncdaemon: fortify handling of failed xtime queries Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur commit 3e95176263e31135039bc65b9aa510801af20d4d Author: Raghavendra Bhat Date: Wed Mar 9 07:14:54 2011 +0000 do not access the inode while doing statfs in trace Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 2502 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2502 commit b42578dbff924a2c0f70f379e4bcf67950d4ce9a Author: Kaushik BV Date: Wed Mar 9 06:16:45 2011 +0000 mgmt/glusterd: mem-factor added as an option Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2501 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2501 commit 4f1639f6bffa0b882ce826e55c65025ba2630656 Author: shishir gowda Date: Tue Mar 8 02:06:22 2011 +0000 Fix solaris build failure in latest git Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 2440 (Fix solaris build issues seen on latest git) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2440 commit be00f14b935f775b4df45e2acf281b19a28f8f7e Author: Amar Tumballi Date: Tue Mar 8 01:07:26 2011 +0000 gluster rebalance: set the proper permission of the file remove the sticky bit from the mode. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 2369 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2369 commit a0aafa365dd355864d24232bd6d7f399ef38f9ef Author: Pranith K Date: Thu Mar 10 02:20:39 2011 +0000 cli: gluster profile CLI Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 496a04f3b2d46893635f93e5a33032969a826cd2 Author: Pranith K Date: Thu Mar 10 02:20:20 2011 +0000 libglusterfs: Add sort routine Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 9c945fdebc195c030701257abf42c4959f97234e Author: Pranith K Date: Thu Mar 10 02:20:00 2011 +0000 glusterfsd: translator info event handling implementation Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 34bf8de743aaff3e7c242833a10791aedc404ea3 Author: Pranith K Date: Thu Mar 10 02:19:39 2011 +0000 mgmt/glusterd: gluster profile implementation Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 970b22e377e20408df8646cdc61a968b55c145b1 Author: Pranith K Date: Thu Mar 10 02:19:20 2011 +0000 rpc/xdr: Add gluster profile and brick op structures Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 332508e8e3b5cd2ffe1c68e496d294d4fef2dea4 Author: Pranith K Date: Thu Mar 10 02:18:44 2011 +0000 debug/io-stats: Changes for handling gluster profile Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit d23585307a0e333c9b1ff627df4c7e30b3642201 Author: Pranith K Date: Thu Mar 10 02:18:22 2011 +0000 rpc: Changes for handling unix domain sockets avoid race Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965 commit 45fd0d904d11f07f8b523af2d1357f081e3c5dc1 Author: Csaba Henk Date: Thu Mar 10 00:43:03 2011 +0000 syncdaemon: don't follow symlinks on entries query Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 38d57757b33983052594e14582611ef05f753581 Author: Csaba Henk Date: Thu Mar 10 00:42:48 2011 +0000 syncdaemon: fortify purge implementation to not do silly things like following symlinks Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2377 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2377 commit 19e65beb16d2dc337d144e25337561ff6e82826a Author: Csaba Henk Date: Thu Mar 10 00:42:33 2011 +0000 syncademon: fortify handling of failed entries queries Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 6cfb0fe84547db1ce8c21f0710cd0c74e88607c0 Author: Csaba Henk Date: Thu Mar 10 00:41:29 2011 +0000 Revert "syncdaemon: Syncdaemon should not crash on ENOENT while performing setxattr()" This reverts commit d6407c59a4fd262749edd11ecb457b1e5be7a77a. Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2342 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2342 commit 8717ef57a7b2554fe35da27f3cfd775083538313 Author: Csaba Henk Date: Thu Mar 10 00:41:10 2011 +0000 Revert "syncdaemon: Handling of deleted symlinks (of directories). When a symlink of a directory of master is deleted. The corresponding delete in slave is handled as rmdir() of the symlink assuming the file to be directory" This reverts commit bee672e5f70b3c6712280130aeb61da0674add11. Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2377 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2377 commit 0121c4c9574e09181f73f9ca7316bce2c5ec7ba9 Author: Csaba Henk Date: Thu Mar 10 00:40:52 2011 +0000 Revert "syncdaemon: Create conf directory if not preset" This reverts commit 38ae1720be39b62a4f199aa5be4ac85948bc23f0. Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit fa04a42cc5b9f187ea169b26cc60ee25ac8a3c31 Author: Csaba Henk Date: Thu Mar 10 00:40:38 2011 +0000 syncdaemon: improve loglevel handling Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit f2dd7abbf1af9832c891e6edadba696cefbccbe1 Author: Csaba Henk Date: Thu Mar 10 00:40:21 2011 +0000 syncdaemon: ensure stdio is flushed before exit Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit 50492481a2b1e5a1425598fb44d802ec047f6c2f Author: Csaba Henk Date: Thu Mar 10 00:40:05 2011 +0000 syncdaemon: add support from dumping urls in canonical and escaped canonical form Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit cbdf22d79ada40e483583a4277aba2faaa769892 Author: Csaba Henk Date: Thu Mar 10 00:39:47 2011 +0000 syncdaemon: add versioning to config file Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit f9a982f30922d812097a70b87628a590b2f51f15 Author: Csaba Henk Date: Thu Mar 10 00:39:27 2011 +0000 syncdaemon: configinterface: add support for regexp based pattern-matching sections Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit cad088fe3a77bd3322de278c0337c1e29906f9cc Author: shishir gowda Date: Sun Mar 6 22:14:32 2011 +0000 build fixes in mac os x Looks good. ----- Original Message ----- From: "Amar Tumballi" To: rfc@dev.gluster.com Sent: Thursday, March 3, 2011 6:30:52 PM Subject: [PATCH BUG:625] build fixes in mac os x Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 625 (Gluster Fails to build on OS X 10.6.2) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=625 commit 7ef59472f10a69c90d94b73e97bca385c6b4b29e Author: Pranith K Date: Mon Mar 7 07:23:51 2011 +0000 mgmt/glusterd: preserve delete volume payload structure for backward compatibility Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2494 ([glusterfs-3.1.3qa4]: replace brick and delete volume fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2494 commit f3dc620caaa7068ff12323a0001075140624733c Author: Pranith K Date: Mon Mar 7 04:38:35 2011 +0000 mgmt/glusterd: reset pending count before sending the op Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2493 ([glusterfs-3.1.3qa4]: glusterd not reaching default state on errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2493 commit 108de35b1775db82cccaf0bd1b62ccacfb1c61e8 Author: Pranith K Date: Mon Mar 7 04:38:15 2011 +0000 mgmt/glusterd: fix payload errors Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2492 ([glusterfs-3.1.3qa4]: gluster operations fail) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2492 commit 135aca330b0429776125bdd98be4ccd85dcfa715 Author: Pranith K Date: Fri Mar 4 02:41:35 2011 +0000 mgmt/glusterd: Handle race in peer connect and reverse probe Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2486 ([glusterfs-3.1.3qa2]: Core generated due to SegFault in glusterd_sm.c) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2486 commit 5b909c83de45e9457eef773cb24770b47d51a632 Author: shishir gowda Date: Fri Mar 4 02:22:37 2011 +0000 Solaris xattr support for symlink and special files. Since glusterfs uses xattr for storing gfid, and xattr support for symlinks and special files does not exist in solaris. The work around is provided by creating hidden files under export directory on solaris hosts only. the hidden files ares maintained in .glusterfs_xattr_inode directory, and all xattr ops on symlink and special files are redirected to respective inodes. All dir entries with name starting as .glusterfs (GF_HIDDEN_PATH) will not be shown in readdir ops. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2213 (Symlink fails with ENODATA) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2213 commit 0066a093a258bfd1a9130134318c3df3571a091d Author: Amar Tumballi Date: Thu Mar 3 06:22:59 2011 +0000 debug/trace: add logs for 'forget', 'release' and 'releasedir' Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2332 (update 'debug/trace' to log gfid instead of 'ia_ino') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2332 commit 8f132b363d41e7fe94a8712ed297a5f810e8ed56 Author: Amar Tumballi Date: Thu Mar 3 05:47:33 2011 +0000 glusterd: check for the variable before dereferencing it check if 'peerinfo->mgmt' is set (ie, handshake is completed), before sending any request to that peer. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2486 ([glusterfs-3.1.3qa2]: Core generated due to SegFault in glusterd_sm.c) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2486 commit 568d4027033a5cb89d6aaee757d4c71e5369fe25 Author: Amar Tumballi Date: Thu Mar 3 03:43:06 2011 +0000 glusterd: handle a crash in dump_version_cbk (in handshake) reset 'frame->local' to NULL before STACK_DESTROY(), which prevents freeing of valid 'peerctx' pointer. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2485 ([glusterfs-3.1.3qa2]: Core generated due to SegFault in glusterd_rpc_notify) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2485 commit dae57d72a58ff61fe6eda800d386bf83574ef5c2 Author: Pavan T C Date: Fri Mar 4 01:44:22 2011 +0000 Make sure we are looking at the right errno in the fix for bug 2452. Signed-off-by: Pavan T C Signed-off-by: Anand V. Avati BUG: 2452 (Excessive CPU usage /very low throughput while using NFS mounts) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2452 commit 689c1b5044e701e1b695a6e6c80647b9471ba454 Author: Pavan T C Date: Wed Feb 23 06:23:26 2011 +0000 Eliminate syscall tight loop when handling EAGAIN in NFS. Signed-off-by: Pavan T C Signed-off-by: Anand V. Avati BUG: 2452 (Excessive CPU usage /very low throughput while using NFS mounts) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2452 commit 826bf14de9eafe1cb67c45f25a9cfb236649801a Author: Gaurav Date: Thu Mar 3 02:04:51 2011 +0000 NFS : Check for duplicate entries while filling up child_up array. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2483 (Showmount output is not consistent with exported volumes.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2483 commit 77d82df9d5e0047b0f1779130c4031cf3ce8ae1b Author: Rahul Date: Tue Feb 22 04:13:14 2011 +0000 Display correct usage of rebalance command when it is wrongly entered. Signed-off-by: Rahul Signed-off-by: Anand V. Avati BUG: 1922 (Volume not present wrong message displayed on command line) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1922 commit 5166c40af2502d1a26d4c0947378321b9bc3857c Author: Amar Tumballi Date: Tue Mar 1 06:55:03 2011 +0000 gluster rebalance: send the proper 'procnum' to glusterd Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit 4175d3e8e2ca1afc0e9f3404ca04fe29d522c81f Author: Amar Tumballi Date: Tue Mar 1 03:37:12 2011 +0000 gluster rebalance: give option to split the command the 'gluster volume rebalance start' is enhanced with two more options: * 'gluster volume rebalance fix-layout start' (for fixing layout only) * 'gluster volume rebalance migrate-data start' (for migrating data only) Also the old way of running rebalance in one shot will still work fine * 'gluster volume rebalance start' Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2258 (enhance gluster volume rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2258 commit ae578f0c6518afd22cf13c21eebca203352774d3 Author: Amar Tumballi Date: Tue Mar 1 03:36:45 2011 +0000 gluster rebalance: get the proper/exact error msg to cli introduce a new field in XDR structure, and hence change the version of program. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1922 (Volume not present wrong message displayed on command line) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1922 commit d95f28de8482c816c2b718d3cf62b667e7a6953c Author: Gaurav Date: Tue Mar 1 06:02:52 2011 +0000 CLI : NFS disable option through volume set. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2094 (Need option to turn off NFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2094 commit 4d9de810f1cb4211fc59ab5b042771402c998331 Author: Gaurav Date: Tue Mar 1 06:02:39 2011 +0000 CLI : NFS persistent local/global options. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2064 (NFS options are removed upon glusterd restart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2064 commit 63632c7b95d204cb077d999e32690a2cdcba1327 Author: Anand Avati Date: Tue Mar 1 14:49:59 2011 +0000 rpcsvc: safe mem_put of req in nfs_rpcsvc_submit_vectors Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2481 (Crash in NFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2481 commit f8ac2f645716847929f89ed218487f67db3e9f01 Author: Anand Avati Date: Tue Mar 1 14:40:27 2011 +0000 rpcsvc: perform mem_put at the very end for safe unrefs Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2481 (Crash in NFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2481 commit 7e546e16925e50dc33db05c67b8b5cad1b3922ef Author: Kaushik BV Date: Thu Feb 24 00:08:46 2011 +0000 Gsync : Do not expose volume gsync, when geo-replication is disabled Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit a3ab0ad1f1c0a5574ae294f5d72aac4df8f50124 Author: Gaurav Date: Mon Feb 28 22:40:46 2011 +0000 NFS : Send error reply on rpc decoding failure. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2436 (Not able to send error reply in nfs_rpcsvc) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2436 commit 731f07378bc0dce305fd3625e9bd4846096a97e3 Author: Gaurav Date: Mon Feb 28 22:40:30 2011 +0000 RPC : Sending error reply on decodong failure. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2435 (Not able to send error reply in rpcsvc.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2435 commit 972836043ea378cafb9639f2db9f04652955eef1 Author: Amar Tumballi Date: Tue Mar 1 02:10:15 2011 +0000 glusterd: remove rpc code from internals of glusterd Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit bf73fd2d8d6805a9a3b947464c65a9847442bba3 Author: Amar Tumballi Date: Fri Feb 25 08:38:44 2011 +0000 glusterd: separate out cli specific programs and mgmt specific programs Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit 36bd0291118dfee4df9d387eb94681d41a0abcbb Author: Amar Tumballi Date: Fri Feb 25 08:37:21 2011 +0000 glusterd: dependency on 'priv->mgmt' completely removed using 'peerinfo->mgmt' instead. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit 66825f283a28c591af673a9fa752e5f5dd8302db Author: Amar Tumballi Date: Fri Feb 25 08:35:36 2011 +0000 glusterd: keep mgmt program peerinfo specific With different version of glusterd in different machines, its not possible to support using just one mgmt program. Instead each peerinfo structure should have its own mgmt programs, so one glusterd can support multiple versions Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit 204fc1205af14bdd98d9a86b9f7293c5b7f6747a Author: shishir gowda Date: Tue Mar 1 03:16:29 2011 +0000 v2 Prevent removal of trusted.gfid xattr Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2461 (remove xattr of trusted.gfid succeeds) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2461 commit b99e0e06788380e41d6c08ea308a6dd87a7afdfe Author: Kaushik BV Date: Wed Feb 23 03:38:36 2011 +0000 mgmt/Glusterd: while resetting the volume options, the previous data structures w.r.t auth. must be deleted Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2374 ([glusterfs 3.1.2] gluster volume set auth.reject command failure on nfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2374 commit 156e1e26d76d4b62ad1fae15938a1350c9bc892a Author: Raghavendra Bhat Date: Tue Mar 1 00:49:19 2011 +0000 check for inode and path being NULL before copying them Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2463 ([7b07d444a77526f27f860210930bf1d4c7fbea9b]: ./autogen.sh crashes glusterfs in fuse_getattr or fuse_setattr) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2463 commit ba1cea55eedec2f7f9fbbc10e581da2c9bcd8038 Author: Vijay Bellur Date: Mon Feb 28 06:07:40 2011 +0000 Stop building uuid test program Building tst_uuid.c results in a compilation error with -DDEBUG Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2447 (Enable assert () and memory accounting with DEBUG) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2447 commit 46c69ec62db97c52c5e8e42e23cf440f742e033e Author: Raghavendra G Date: Wed Feb 23 09:34:30 2011 +0000 rpcsvc: Handle more than one payload vectors. - fops like write can recieve payload data in more than one vector. This can happen with write-behind being loaded on client side. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2454 (rdma data corruption) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2454 commit c46f85b026a1d0ad90f7be0efa4cd380962a1741 Author: Raghavendra Bhat Date: Wed Feb 23 02:12:50 2011 +0000 if volume created is both of tcp and rdma type show it in volume info Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit 63f00588bbfd477c2f4579fd4392c14679dd7ac0 Author: Pranith K Date: Thu Feb 24 06:16:36 2011 +0000 mgmt/glusterd: prevent spurious cmd unlocks Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2460 ([glusterfs-3.2.0-gsync1]: gluserd crashed trying to access freed request) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2460 commit 8a96aa607b4e3a6c782a0d912b6bf101f82f7c07 Author: Vijay Bellur Date: Mon Feb 28 00:25:05 2011 +0000 performance/io-cache: Whitespace cleanup Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 8d6de6959ad49f413968b562a5963d665dc11488 Author: Vijay Bellur Date: Mon Feb 28 00:24:47 2011 +0000 libglusterfs/dict.c: Whitespace cleanup Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 44020e349649f774021bf65931ee10cf6b6ddd47 Author: Vijay Bellur Date: Mon Feb 28 00:24:27 2011 +0000 cluster/afr: Re-factoring code for alignment Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit b7be90b2674b0c9f1c219479c08b45e424684146 Author: Vijay Bellur Date: Mon Feb 28 00:24:00 2011 +0000 cluster/afr: Whitespace cleanup Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 3e2d1070754cbea8b0ef6c4239ffce9ffe5d856a Author: Vijay Bellur Date: Mon Feb 28 00:23:36 2011 +0000 libglusterfs/xlator.c: whitespace cleanup Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit be002fbdba6c66ea6f04f51e45310faedcba5fd2 Author: Anand Avati Date: Fri Feb 25 13:23:56 2011 +0000 dht: log filename on failed reavalidate The previous log message is pretty much useless without the path Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346 commit 7b07d444a77526f27f860210930bf1d4c7fbea9b Author: Lakshmipathi G Date: Tue Feb 22 08:29:07 2011 +0000 install gluster binaries under /opt/glusterfs/version with sym.link at /usr/bin Signed-off-by: Lakshmipathi G Signed-off-by: Anand V. Avati BUG: 2279 (rpm spec file changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2279 commit 65ad0fb37b4df6ef842235c0ff3981c2611d56c5 Author: shishir gowda Date: Tue Feb 22 06:40:18 2011 +0000 Solaris build fixes. Including compat.h for definitions of IXDR_PUT_U_../IXDR_GET_U.. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2440 (Fix solaris build issues seen on latest git) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2440 commit 4a95f8f3b39f58349ef0935b1746e543408b3080 Author: Amar Tumballi Date: Fri Feb 18 03:10:29 2011 +0000 man pages updated Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2444 (keep man pages upto date with new codebase.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2444 commit 991b61661d74de5b1349050308dbd131e0de607c Author: Raghavendra Bhat Date: Tue Feb 22 05:25:30 2011 +0000 check the op_ret for less than zero in sp_create_cbk since posix can send negative values other than -1 posix can send -ve values other than -1 in create: op_ret = setgid_override (this, real_path, &gid); if (op_ret < 0) { goto out; } In stat-prefetch we check op_ret only for -1 which results in function proceeding and op_ret may become 0 due to other function calls in sp_create_cbk, hence crashes in fuse. Signed-off-by: Raghavendra Bhat Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2409 (crash in stat prefetch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2409 commit 21e4db42468d5bb7ebd9fa6a91461edd11b2a6da Author: Raghavendra G Date: Tue Feb 22 05:25:11 2011 +0000 storage/posix: set op_ret to -1 when setgid_override fails. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2409 (crash in stat prefetch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2409 commit 2a184da3ca83f03dec69fcf0f26ae84c231d2e37 Author: shishir gowda Date: Fri Feb 18 03:37:50 2011 +0000 Solaris: disable cli support rebalance and replace brick Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2440 (Fix solaris build issues seen on latest git) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2440 commit 46279693027230d5454ad98c267d93d5139e19af Author: Amar Tumballi Date: Tue Feb 22 05:00:37 2011 +0000 send the CHILD_DOWN event also to fuse and start the fuse thread in CHILD_DOWN event too. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2005 (Mounting Gluster volume with RO bricks hangs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2005 commit d437dd91bf167675615d7c7c2f99abbed2d899a1 Author: Raghavendra Bhat Date: Mon Feb 21 06:48:23 2011 +0000 log the total replace brick command received Log the full replace brick command which says whether the command is start/pause/status/abort/commit. Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1404 (need a dump of all the op/mgmt commands) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1404 commit 3af42dac5fbea3af8d65799fd50300838f2e1d33 Author: Amar Tumballi Date: Fri Feb 18 03:34:23 2011 +0000 glusterd/cli: option added to create volume with both transports to avail the option, enter the volume create command with arguments 'transport tcp,rdma' and while mounting, on the mountpoints which works on rdma, do, mount -t glusterfs :/-rdma Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294 commit 28bda239100b9eef9b378dac2052a19d7264a51c Author: Amar Tumballi Date: Fri Feb 18 05:18:20 2011 +0000 debug/trace: updated the logs to print gfid instead of 'ino' values Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2332 (update 'debug/trace' to log gfid instead of 'ia_ino') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2332 commit e8aed37adf3f623abd1b05a6926615002987bf17 Author: Amar Tumballi Date: Sat Feb 19 01:52:22 2011 +0000 glusterd: make it more RPC friendly make sure each procedure has a actor associated with it. that way proper versioning can be implemented in modules Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2333 (make glusterd more rpc friendly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2333 commit b2d94417764ca5462cbdcdd634ea45ba12c8877f Author: Amar Tumballi Date: Thu Jan 13 06:55:37 2011 +0000 fuse-resolve: correction in resolve logic * bring in soft (gfid based) and hard (path based) resolving * 'fd' resolving to new graph is not yet done. * fuse-resolve works similar to server-resolve Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2281 (I/O operations exit when add-brick is done) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2281 commit 23d9783a192669b638d42b8dd127ad69ea36f950 Author: Anand Avati Date: Fri Feb 4 21:43:49 2011 +0000 dht: do not send revalidates to all subvols Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2450 (scalability enhancements) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2450 commit a144f2ca40d43a6ee3a50802fe1e8d1eda7a53b7 Author: Anand Avati Date: Fri Feb 4 21:43:19 2011 +0000 core: have framework for GF_EVENT_CHILD_MODIFIED notifcation event If anything changes anywhere in the graph, all xlators know that something has changed. Previously dht and afr would mask certain events from propagating up. Now they forward GF_EVENT_CHILD_MODIFIED event in those situations Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2450 (scalability enhancements) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2450 commit 595e0df48bf387a87eb62a76d437a7ea79a0bc8a Author: Pranith K Date: Mon Feb 21 04:02:24 2011 +0000 mgmt/glusterd: In store-retrieve exit with error message instead of crashing. Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2066 (glusterd crashed while trying to restore volumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2066 commit b00b3d46c226d339a1cfde70ceab101cee2ac865 Author: Raghavendra G Date: Mon Feb 21 08:45:41 2011 +0000 rpc/rpc-clnt: don't use iobref passed from caller to hold iobufs required for building program and rpc headers. - clustering translators like replicate assume iobrefs will be used as read-only by lower layers and there by use the same iobref while winding calls to multiple children. Since iobrefs can hold only limited number of iobufs, this limits the number of children these translators can have without overflowing iobrefs. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2157 (glusterfsd crash) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2157 commit 6312b2fca35b907acf6d29591a608767a2d67781 Author: Raghavendra Bhat Date: Tue Feb 22 01:38:30 2011 +0000 free the tokens obtained from the cli The cli command which is tokenized is not freed leading to a memory leak. Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2113 (cli: memory corruption in add-brick and create volume parsing functions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2113 commit ccee8039720f8253d460384aa6659edd8e75f3db Author: shishir gowda Date: Fri Feb 18 00:06:26 2011 +0000 Fix getcwd size arg to make it work in solaris. glusterfs/d -f path failed if the path was not absolute. If the BUF argument is NULL, then on solaris the size argument has to be passed. On linux, if the size argument passed is 0, then it dynmically allocates a buffer of the required size. The fix is to pass PATH_MAX as the size for consistency. Signed-off-by: Shishir Gowda Signed-off-by: Anand V. Avati BUG: 2443 (starting glusterfs/d -f with relative path crashes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2443 commit 65e5cc0f394e1d2faaab3dc5d097a3f01b03dd41 Author: shishir gowda Date: Thu Feb 17 07:31:18 2011 +0000 Solaris build fixes Disable geosync build for non-linux platforms. And fix solaris related build failures.The symbol getxattr was not available on solaris. The build on linux passed as getxattr symbol was available in the library. The argument was not being used, hence removed it. Make 64 bit build default in CFLAGS option by passing -m64 option Signed-off-by: Shishir Gowda Signed-off-by: Anand V. Avati BUG: 2440 (Fix solaris build issues seen on latest git) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2440 commit 46f0277dfcca246b12700b2c6893abcc14480623 Author: Anand Avati Date: Wed Jan 26 13:28:04 2011 +0000 replicate: set read-child to the subvolume which replied first (fastest) In the old logic read-child was set to the last subvolume which replied. Now it is updated to the first subvolume. This way we can ensure that local servers are preferred for reads _most_ of the times. Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 1172 (ls -lh on NFS mount of 2-mirror replicate gives incorrect file size) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1172 commit d3c622abaa6788e3b62628d2847618713b896cdf Author: Anand Avati Date: Tue Jan 25 15:03:52 2011 +0000 io-threads: use slow/normal/fast classification of fops Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2241 (GlusterFs Stat Actions Degrade During I/O) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2241 commit c3590820ad372fa77c70ebfa37aaa0c4b540dd7a Author: Anand Avati Date: Tue Jan 25 15:03:51 2011 +0000 io-threads: implement bulk and priority queues Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2241 (GlusterFs Stat Actions Degrade During I/O) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2241 commit 8d69845dfdd31b798fb02b08a1eabbc88d31243c Author: Anand Avati Date: Tue Jan 25 15:03:50 2011 +0000 io-threads: whitespace cleanup Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2241 (GlusterFs Stat Actions Degrade During I/O) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2241 commit ea0634bf88dd63294559c2e4542b73b772b7ec56 Author: shishir gowda Date: Fri Feb 18 01:27:31 2011 +0000 Validate peer probe command's hostname/ip address. Note, if an ip octet range exceeds 255, though this fails as a valid ipv4 address, it is still a valid hostname. valid chars are: 'a'-'z', '0' - '9', '-', '.' with a max of 255 chars. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2194 (gluster peer probe on a ip octet value bigger than 255 has no validation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2194 commit 2795f3e03a299daf88e3172b068511d41c493247 Author: Vijay Bellur Date: Mon Feb 21 12:11:59 2011 +0000 libglusterfs: Enable assert() and memory accounting with DEBUG Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2447 (Enable assert () and memory accounting with DEBUG) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2447 commit c47961cc18f7bbc1b46e1cdf5662b8ec409065e5 Author: Raghavendra G Date: Thu Feb 3 01:56:28 2011 +0000 performance/quick-read: disable caching for fds opened with GF_OPEN_NOWB flags. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2240 (Solaris client hangs on file read operations) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2240 commit bf767b85e3e92ec4bad52c6af141299d2afa4480 Author: Amar Tumballi Date: Fri Feb 18 02:55:38 2011 +0000 cluster/dht : implement a fsetxattr() command Thanks to Jeff Darcy for the patch Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2319 (DHT uses wrong subvolume for fsetxattr) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2319 commit 069d7765898ef6f8d1334b23bf8ed9aee017b47a Author: Amar Tumballi Date: Fri Feb 18 02:54:49 2011 +0000 rpc/xdr: update .x files * now, 'rpcgen $filename-xdr.x' file will result in $filename-xdr.h Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2153 (glusterfs3.x does not match "generated" source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2153 commit 52cf9e992749a7cd5b2411581eff4c052d055ea9 Author: Pranith K Date: Tue Feb 8 02:22:52 2011 +0000 cluster/afr: stop spawning self-heal loops when the self-heal fails With the current model of self-heal, any loop wont resume if a self-heal failure happens. I have added the fix to stop spawning the initial loops on self-heal failure. Fixed the invalid read shown in valgrind in diff-self-heal. Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1174 (Replicate spawns read loops even after destination fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1174 commit e77eae0f04b90ad9722ce82d59fd552cae63c347 Author: Vikas Gorur Date: Thu Feb 17 19:18:12 2011 +0000 libglusterfs/dict: memcpy() data_t in unserialize. This fixes a race in dht_getxattr() where the xattr dictionary returned by one of the subvolumes can get free'd before STACK_UNWIND, leading to applications seeing junk values. Signed-off-by: Vikas Gorur Signed-off-by: Anand V. Avati BUG: 2442 (getxattr() on a directory sometimes returns junk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2442 commit fc63f24904b14aaad338aa44107cbda7e547e6b1 Author: Sachidananda Date: Fri Feb 11 02:08:55 2011 +0000 Check correct variable after function call. And some white space cleanups. Signed-off-by: Sachidananda Urs Signed-off-by: Anand V. Avati BUG: 2410 (Wrong variable checked after a function call) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2410 commit de44838d514e1f83a81dcff9438adbbb268ef981 Author: Sachidananda Date: Thu Jan 27 00:29:21 2011 +0000 Typo fixes in log and cli messages. Signed-off-by: Sachidananda Urs Signed-off-by: Anand V. Avati BUG: 2321 (Typo in logs and cli messages) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2321 commit 26cedae57d5b7cb8d50ed077ce29c92e30d6e260 Author: Amar Tumballi Date: Wed Feb 16 01:48:03 2011 +0000 glusterd-volgen: fix a issue of wrongly closing '0' fd. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2421 ([glusterfs-3.1.2gsync10]: epoll_create returning 0) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2421 commit 3f0525e65e7eb1d48610f13152b676dd6d9208f5 Author: Anand Avati Date: Wed Feb 16 01:41:44 2011 +0000 volgen: avoid fclose() on cosed FILE * It can so happen that a previously freed up FILE * structure has 0'ed out memory and a second fclose() on it can result in close(0). This results in bad bad things happening. Signed-off-by: Anand Avati Signed-off-by: Anand V. Avati BUG: 2421 ([glusterfs-3.1.2gsync10]: epoll_create returning 0) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2421 commit 43b68bb25c9ee16c10342ef643a6ecb82a345e16 Author: Csaba Henk Date: Tue Feb 15 18:01:54 2011 +0000 syncdaemon: fix RePCe version query RepceClient.repce_version fetched its own RePCe version, instead of querying peer, so lame. Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2381 (RePCe versioning) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2381 commit 8ce08eb78165c9107925f23ac3057ee2cc01ff2f Author: Mohammed Junaid Ahmed Date: Tue Feb 15 11:34:51 2011 +0000 syncdaemon: Checking for the existence of gsyncd by trying to aquire a lock on the pidfile. If the locking succeeds then gsyncd is not running and if it fails then it means that gsyncd is running. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 1569424d1425a2f81c428d3968cd103ab2cad49e Author: Csaba Henk Date: Tue Feb 15 10:52:32 2011 +0000 syncdaemon: change pidfile handling approach Signal handling of the python interpreter is a bit messy, so we cannot rely on executing a final clause upon termination. Switch over fcntl lock based pidfile handling which can provide reliable info about status of the process. (Due to aforementioned reason, pidfile as such is not guaranteed to be cleaned up, but lock acquisition is a reliable measure.) Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit a68b4ad416970ec0ca710f650f54b87c3b92428e Author: Mohammed Junaid Ahmed Date: Tue Feb 15 08:58:05 2011 +0000 syncdaemon: Check for ctx context in the glusterd_op_stage_gsyc_set(). Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 647d599f86f5577a94800607ff95b3e3636c4782 Author: Kaushik BV Date: Tue Feb 15 03:08:44 2011 +0000 syncdaemon: set the default value of timeout to 120sec Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 5a6720f1ee4ad6d96dae23742315c8ef35555a3b Author: Mohammed Junaid Ahmed Date: Mon Feb 14 19:27:34 2011 +0000 syncdaemon: Moved the gsync start code to cli. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 98cfaa15d8c51728ea4d3555667328b94ef497c1 Author: Vijay Bellur Date: Mon Feb 14 16:43:36 2011 +0000 Changes to include geo-sync in spec Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 30504941ea36ed40bbb628e8144ec2413e6fe765 Author: Csaba Henk Date: Mon Feb 14 16:42:05 2011 +0000 syncdaemon: fix some pidfile issues Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 8c801cfd05eb533ae64ea9f06e49e632955cf0c0 Author: Csaba Henk Date: Mon Feb 14 16:42:04 2011 +0000 syncdaemon: make /usr/libexec/gsyncd the default remote gsyncd (incomplete hacky quickfix) Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2427 (set a proper default for remote syncdaemon) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2427 commit 248a1b7d387832dd97f43eb74b8b9d168292f3a0 Author: Csaba Henk Date: Mon Feb 14 16:42:03 2011 +0000 syncdaemon: use "ping" message instead of "__version__" to wait for remote to come up Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2424 (Starting gsyncd with --debug : AttributeError: type object 'FILEServer' has no attribute '__version__') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2424 commit 741ce91b89cf221f8be94168e1d04916cc2f3204 Author: Vikas Gorur Date: Mon Feb 14 13:33:00 2011 +0000 cluster/dht: Send removexattr() to all subvolumes. Signed-off-by: Vikas Gorur Signed-off-by: Anand V. Avati BUG: 2426 (removexattr is not sent to all subvolumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2426 commit d6f065b350a72a34b9a435a89d9b7cb59081bb44 Author: Mohammed Junaid Ahmed Date: Mon Feb 14 01:01:19 2011 +0000 syncdaemon: config-get-all option add to gsync cli. Signed-off-by: Mohammed Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 0cc73c92734acc86cb559fc2d3b3ee8c834e5f63 Author: Csaba Henk Date: Mon Feb 14 11:19:25 2011 +0000 syncdaemon: fix KeyError Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 653a46850d765ca00a76452c76950ed60ab967d3 Author: Csaba Henk Date: Mon Feb 14 10:57:59 2011 +0000 syncdaemon: make configparser code work with all supported python versions Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 1b04647157079d35851e206b8e9572960b2de214 Author: Mohammed Junaid Ahmed Date: Sun Feb 13 03:46:56 2011 +0000 syncdaemon: Using /usr/local/libexec/python/syncdaemon as the default directory where the python scripts are installed. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 76cbd26728a491fef0c7e2d657a931910ba3f8d1 Author: Kaushik BV Date: Sun Feb 13 02:01:30 2011 +0000 syncdaemon: conf file to be read properly Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 38ae1720be39b62a4f199aa5be4ac85948bc23f0 Author: Kaushik BV Date: Sun Feb 13 01:58:09 2011 +0000 syncdaemon: Create conf directory if not preset Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit f0831feae02a0c248b674c9cf9e9cc282e0e4854 Author: Raghavendra Bhat Date: Fri Feb 11 07:19:05 2011 +0000 fix a typo in xdr_gf1_cli_gsync_set_req function Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2418 ([glusterfs-3.1.2qa7]: crash in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2418 commit 206b11705f36d4cc74d80465e77ecc9d74c69405 Author: Raghavendra Bhat Date: Fri Feb 11 07:06:52 2011 +0000 initialize the cli_req structure before sending it to xdr Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2418 ([glusterfs-3.1.2qa7]: crash in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2418 commit bee672e5f70b3c6712280130aeb61da0674add11 Author: Kaushik BV Date: Wed Feb 9 08:15:59 2011 +0000 syncdaemon: Handling of deleted symlinks (of directories). When a symlink of a directory of master is deleted. The corresponding delete in slave is handled as rmdir() of the symlink assuming the file to be directory Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2377 (gsyncd.py RepceClient: call (symlink) failed on peer with instance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2377 commit 7b16a08989e804e857589c8a34881140150dc11c Author: Mohammed Junaid Ahmed Date: Fri Feb 11 01:06:55 2011 +0000 syncdaemon: configinterface.py file moved under xlators/features/marker/utils/syncdaemon/ directory. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit d6407c59a4fd262749edd11ecb457b1e5be7a77a Author: Kaushik BV Date: Wed Feb 9 02:12:59 2011 +0000 syncdaemon: Syncdaemon should not crash on ENOENT while performing setxattr() Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2342 ([glusterfs-3.1.2geosyncqa4]: crash in gsyncd script) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2342 commit 6248ead2ab0481a40d91b824fb249e4bc4f943ba Author: Gaurav Date: Wed Feb 9 00:39:55 2011 +0000 NFS : Fail Nfs init if volume-id not found. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2124 (NFS crashes when volume-id option is not given with dynamic-volume option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2124 commit 2e81c881f036d90323fd07d7df07d881723d7a28 Author: Mohammed Junaid Ahmed Date: Thu Feb 10 05:29:34 2011 +0000 gsync: cli support for gsyncd. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 08ca1d3c7801d22f1de452f098b0a5df251ca5e7 Author: Amar Tumballi Date: Wed Feb 9 06:11:02 2011 +0000 removed some of the stale scripts Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2393 ('gluster-volgen' and 'gluster-defrag' scripts are stale, but present in AMI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2393 commit 07402f590e12b097e8267e924e0ae69d9b8964fb Author: Csaba Henk Date: Mon Feb 7 20:42:24 2011 +0000 syncdaemon: config revamp #3: implement command line get/set/del interface to configuration The INI style config file has following type of sections: - [global] - [peers ] - [peers ] Option dispatch to sections is derived from command line (ie., [global] if no arg given, [peers ] with being the only arg, [peers ] if and args are provided). So this all happens under the hood, gsyncd users need not to specify sections. New command line options: - query options: --config-get-all --config-get OPT - modify options: --config-set OPT VAL --config-del OPT Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit ebd7e1771c69a056f0456ff2dccac4319806f63b Author: Csaba Henk Date: Mon Feb 7 20:42:23 2011 +0000 syncdaemon: config revamp #2: implement canonicalized urls, use them in config file sections Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit d6363c595ace12a1bf9060dcd76a9e88e58d3db0 Author: Csaba Henk Date: Mon Feb 7 20:42:22 2011 +0000 syncdaemon: config revamp #1: drop simplecfg, switch to stdlib's ConfigParser Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit 71888401e2b959db316a9a296580d1e1c0c3a882 Author: Mohammed Junaid Ahmed Date: Tue Feb 8 06:33:38 2011 +0000 syncdaemon: Removing the simplecfg.py entry from the Makefile.am, since it is removed. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570 commit e045741f2bb75344a557cd618e1c7b1691238703 Author: Kaushik BV Date: Tue Feb 8 04:05:21 2011 +0000 features/marker: Use touch TimeStamp file instead of futimens, to avoid the dependency of newer libc Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2354 (handling futimens with older glibc) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2354 commit ff7a493428e011f961d541e59e52ddb53c331d9c Author: Csaba Henk Date: Mon Feb 7 20:28:48 2011 +0000 syncdaemon: refine RePCe version check to tolerate difference in minor Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2381 (RePCe versioning) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2381 commit b6fcde94b37ba6d669ef24e4537846f33ac8ef41 Author: Csaba Henk Date: Fri Jan 28 03:34:05 2011 +0000 volgen: specify a mode argument for open(2) Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 44773417bcaafeb6b7a8c44b5dc22bc7969e3102 Author: Pranith K Date: Thu Feb 3 21:23:15 2011 +0000 cluster/dht: Perform self-heal as root Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2370 (cluster/afr: Perform self-heal as root) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2370 commit 9f2e9fc465361e7821627a8c3a22863bb25b0810 Author: Pranith K Date: Thu Feb 3 21:22:44 2011 +0000 cluster/afr: Perform self-heal as root Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2370 (cluster/afr: Perform self-heal as root) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2370 commit 9cfa22f828f69c9f1f48b5e8994a4dff48d283a6 Author: Pranith K Date: Mon Feb 7 05:42:18 2011 +0000 protocol/client: decrement reopen fd count in cases of re-open errors In post-client-handshake client tries to re-open files, dirs, but if those files/dirs are already deleted when the brick is down the reopens won't even get triggered. In those cases the re-open fd count needs to be decremented to make sure the child up is triggered. I have also made similar changes in all the error cases of re-open/re-open-dir cbks. Lock recovery is already handling all these errors. Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1761 (incorrect self-heal behaviour when files are deleted) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1761 commit 3a467b62babad8d44605db34601927025227f90e Author: Pranith K Date: Fri Feb 4 01:12:31 2011 +0000 cluster/dht: restore attrs of dirs in self-heal Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2371 (dht: Set owners of directories after performing self-heal as root) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2371 commit ffbbb6a17075714865820a2f9722edcd70a4436f Author: Raghavendra G Date: Mon Jan 31 03:29:13 2011 +0000 rpc/rpc-clnt: don't access rpcreq after putting the struct back into mem-pool. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2335 (Segmentation fault in saved_frames_unwind) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2335 commit 3bad56d0d39e132b43d0122a570ba1b59a9a7caa Author: Amar Tumballi Date: Fri Feb 4 01:29:08 2011 +0000 gluster rebalance: fix the permission issue of rebalanced files Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2369 (Rebalanced files written as root:root on any brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2369 commit 31efe81b13d6761cf153e71f7ac150751b2d4090 Author: Csaba Henk Date: Mon Feb 7 01:32:57 2011 +0000 syncdaemon: add "setattr" server method, needed to synchronize metadata of links/dirs Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2318 (gsyncd.py :chmod on directory not working) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2318 commit d376253d1e91b9fc29f6a23253021647e139c2c1 Author: Csaba Henk Date: Mon Feb 7 01:32:56 2011 +0000 syncdaemon: fix broken symlink handling in "purge" call Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2340 ([glusterfs-3.1.2geosyncqa4]: crash in gsyncd script while posix compliance test was running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2340 commit 4b96f79fa19191344ddeeafd40df8b6d18ef7cc9 Author: Csaba Henk Date: Mon Feb 7 01:32:55 2011 +0000 syncdaemon: version the rpc Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2381 (RePCe versioning) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2381 commit 67f842aa406a05fd701f9dbdcd373516fa529087 Author: Csaba Henk Date: Mon Feb 7 01:32:54 2011 +0000 syncdaemon: improve program termination - get rid of annoying "TypeError: 'str' object is not callable" message with python 2.4 - don't leave program hanging dead when failure is hit Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2380 (TypeError: 'str' object is not callable) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2380 commit 681928ddc750c28b12ec5097aff0dc694a5275d6 Author: Csaba Henk Date: Mon Feb 7 01:32:53 2011 +0000 syncdaemon: display slave role in log output Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2379 (master and slave log should be easier to distinguish) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2379 commit e266833e72749368019b7dcae32dc206d180acdd Author: Anand V. Avati Date: Fri Feb 4 11:22:55 2011 -0800 Revert "distribute: Return ESTALE when dir selfheal finds no fix" This reverts commit a4c948aca6058049523e31acf33ce5770f8693ad. commit ed743d89affe8be2d9d7da87479a498af40e12b0 Author: Shehjar Tikoo Date: Fri Feb 4 03:14:37 2011 +0000 mount3: Do not return error when mount list is empty An exports list can be empty when no subvolumes have come up. No point returning error and confusing the user. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2345 (Taking distribute brick down returns 10006 error on mount command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2345 commit 44e68cbf833cc176d589780d47ffdbe5b4c3ab7c Author: Shehjar Tikoo Date: Fri Feb 4 02:04:08 2011 +0000 nfs: Set volume started after root lookup succeeds Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2345 (Taking distribute brick down returns 10006 error on mount command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2345 commit a139e43f484d1b434c9120f9fb99bf5ff33fb51d Author: Mohammed Junaid Ahmed Date: Fri Feb 4 02:12:19 2011 +0000 marker: Updating the xtime marks on both the paths in rename fop. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 2372 (marker: time stamp not updated with rename) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2372 commit 5f8e2cab86eab7f5ee5b4bb9b649376e476c740c Author: Gaurav Date: Mon Jan 31 04:25:38 2011 +0000 Logging : Use of uuid_utoa and uuid_utoa_r. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2308 (Threadsafe uuid to string conversion function) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2308 commit f3648c88ebc6d58a10854d564d3fc2c82290ce13 Author: Gaurav Date: Mon Jan 31 04:25:23 2011 +0000 Logging : New uuid to string conversion functions. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2308 (Threadsafe uuid to string conversion function) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2308 commit ba40a3ece0a0b5b381e7d05c74d09cdd1818b817 Author: Kaushik BV Date: Thu Feb 3 23:16:03 2011 +0000 libxlator: New policy for aggregation of xtime: -Try to salvage errors like ENOENT/ENOTCONN/ENODATA, -Propogate back any other error from any brick -EINVAL if some assertion of the aggregation logic is broken Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2341 ([glusterfs-3.1.2gsyncqa4]: crash in gsyncd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2341 commit 7f59d855bb160a14a517e82b71e4f387b50cbf63 Author: Kaushik BV Date: Thu Feb 3 23:15:17 2011 +0000 libxlator: memdup the data that is required for aggregation of attributes Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2339 ([glusterfs-3.1.2geosyncqa4]: crash in gsyncd script) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2339 commit df9122f70deb6dbd0d950219ad1876e0a1ccd940 Author: Pranith K Date: Wed Feb 2 01:46:15 2011 +0000 cluster/afr: fix races in self-heal Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1188 (3.0.5 client crash - afr_set_split_brain) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1188 commit cbd61752ffefab6b42d29057e0f5b5e59191d51d Author: Raghavendra G Date: Thu Jan 27 02:50:38 2011 +0000 performance/io-cache: disable caching if indicated by NFS. - wbflags - which contain flags to disable caching - passed by NFS were not stored in local by ioc_open, there by causing failure of io-cache to honour these flags. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2289 ([3.1.2qa3] EIO while reading & writing from a file concurrently) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2289 commit 066b1809876ba156d925edcb8fb470ee90319d3c Author: Sachidananda Date: Tue Jan 25 05:32:01 2011 +0000 Move hostname, ip address validating functions to libglusterfs. hostname and ip address validation functions are duplicated in several source files. Move them to libglusterfs. Signed-off-by: Sachidananda Urs Signed-off-by: Anand V. Avati BUG: 2249 (Problems with hostname validation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2249 commit 7691550a5bd281e9d21771b37066d44434e92934 Author: Amar Tumballi Date: Mon Jan 24 22:55:07 2011 +0000 use rpc_clnt_{new,start} (), instead of rpc_clnt_init(); to prevent a race between getting a CONNECT/DISCONNECT event before registering a notify function Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2314 (notify function registration in CLI) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2314 commit efda1b98f5ef5449687cf9ded8d0b2c82d948885 Author: Raghavendra Bhat Date: Wed Jan 19 02:08:48 2011 +0000 free GF_CALLOCed memory by GF_FREE instead of FREE Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 329 (Replacing memory allocation functions with mem-type functions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=329 commit 89f556574552abe80d9afe155eb366634375846c Author: Amar Tumballi Date: Mon Jan 17 10:51:17 2011 +0000 glusterfsd-mgmt: handle the RPC_DISCONNECT event properly This patch solves the issue of hanging mount point in case of wrong server name is given during mount command Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1453 (mount command didn't give error message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1453 commit 0e651882a9aadcb35ea764ea65c05c3661175e00 Author: Raghavendra Bhat Date: Mon Jan 17 00:44:39 2011 +0000 remove op_errstr from glusterd_handle_rpc_msg as op_errstr is not used in that function Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1598 ([glusterfs-3.1.0qa22]: crash in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1598 commit bd8f7b95972abdbaba0b4ec067b6cb7968ad7e56 Author: Gaurav Date: Thu Jan 13 07:29:08 2011 +0000 cli: Show 'commit' option in replace-brick. Signed-off-by: Gaurav Signed-off-by: Anand V. Avati BUG: 2273 (replace-brick help does not show commit option) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2273 commit 85300e25f2d47e33b169d14fa9eb0b7cfe39011b Author: Csaba Henk Date: Thu Jan 27 05:23:35 2011 +0000 adding syncdaemon Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 7d883898c5225df3f7c38e67274b74ff8ac396c0 Author: Kaushik BV Date: Thu Jan 27 05:23:34 2011 +0000 mgmt/glusterd: restart bricks when syncdaemon is enabled Signed-off-by: Kaushik BV Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 66808736b7af00a868e98464282b1118fc80a612 Author: Csaba Henk Date: Thu Jan 27 05:23:33 2011 +0000 volgen: add marker to brick volfiles Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 482d77b85d84bf5c2b48e4717f8d186967e42e63 Author: Csaba Henk Date: Thu Jan 27 05:23:32 2011 +0000 implement "--client-pid" option which can forcibly set the pid value in messages to a predefined value Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit a2a92b99fc031544ff8a87861d34b2bbbdd2753c Author: Junaid Date: Thu Jan 27 05:23:31 2011 +0000 adding marker translator Signed-off-by: Junaid Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 73bce15b61755509de23d32646135254d369a2f6 Author: Kaushik BV Date: Thu Jan 27 05:23:30 2011 +0000 adding libxlator, to ensure proper client side aggregation of marks by clustering translators Signed-off-by: Kaushik BV Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2310 (georeplication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2310 commit 11dd59b788334fe2de1653ae85395986ba531606 Author: Amar Tumballi Date: Mon Jan 24 20:35:44 2011 +0000 rpc: handle proper 'ref', 'unref' of transport from rpc-clnt Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2250 ([glusterfs-3.1.2qa2]: SegFault in rpc-clnt.c) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2250 commit 40cdb88962cff1d32cd46cb089ad8bcd9be3d62d Author: Pranith K Date: Mon Jan 24 01:49:23 2011 +0000 features/access-control: skip access-tests if the call is from fuse Fuse cant send aux gids. So access-control checks treat non-primary-group membership of user as "other". So skip access-control checks if the call is from fuse. We added a hack to treat all calls with pid set to 1 as calls from nfs. So for calls with pid not 1 we skip the access-control checks on all fops. Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2296 (svn / subversion fails on gluster volume (replicated and non-replicated)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2296 commit 945ac04532d5efeeef324be485dcf2bade41708e Author: Pranith K Date: Wed Jan 19 01:49:05 2011 +0000 mgmt/glusterd: error out if remove-brick comes for final bricks Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2298 (removing the last pair of bricks from a volume results in inconsistency) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2298 commit 26e1bfc68a6b4dff95d5fb244076116896add68d Author: Pranith K Date: Thu Jan 13 01:25:09 2011 +0000 cli: return error when cmd execution fails Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2287 (Gluster CLI returns wrong return code.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2287 commit 5fd43d28ff12ac1c4e4d60e77a38659013b1ab3a Author: Mohammed Junaid Ahmed Date: Mon Jan 3 00:37:22 2011 +0000 protocol/server: Distinguishing the locks based on the type of fop like inodelk and entrylk. Currently, the protocol server considers entrylk to be held only on directories and inodelk on files and thus when a client unmounts itself while holding locks, it fails to free entrylk locks held on files and inodelk locks held on directories. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 2221 (Failed to free Inodlk locks on directories when the client holding the locks was unmounted before releasing the locks held.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2221 commit df6d34d0042421bb87f30bcf5e03d4ba0de7501c Author: Pranith K Date: Fri Dec 17 02:53:15 2010 +0000 glusterd: de-register nfs rpcs when it is stopped Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1783 (kill glusterd and stop the cluster and start again - check nfs process) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1783 commit f2a067c4fe92f7aefc5f64ea1e5b000c16af0946 Author: Shehjar Tikoo Date: Thu Jan 13 03:38:51 2011 +0000 nfs3: Handle root resolution failures ..to prevent a second reply to the client which results in accessing a call state structure that gets freed on the first reply. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2286 ([glusterfs 3.1.2qa3]: Crash due to corruption in gf_dirent_free) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2286 commit 5368b898fad7264405275adc2092859e3c87c14e Author: Raghavendra G Date: Tue Jan 11 23:31:40 2011 +0000 performance/quick-read: Fix unwinding of same frame twice when qr_loc_fill fails. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2274 (crash in fd_unref) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2274 commit 29b664f062795614417b9348f40503360f9f9c56 Author: Kaushik BV Date: Tue Jan 11 04:47:00 2011 +0000 mgmt/Glusterd: make nfs.mem-factor settable through CLI Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 2277 (Regression in Gluster NFS re-read performance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2277 commit 89cbbee063243d84dc64b15b2e2f403be1ca226b Author: Shehjar Tikoo Date: Tue Jan 11 01:40:16 2011 +0000 nfs: Introduce tunable for memory consumption NFS has used a common define called the mem-factor to determine how much memory is allocated for the following items: o inode table o local structures used by nfs for storing fop state o local structures used by nfs3 for storing nfs op state These are all allocated through the mem-pool. The factor is multiplied by a multiple that is specific to each data structure. For eg. define GF_NFS_CONCURRENT_OPS_MULT 15 define GF_NFS_INODE_LRU_MULT 6000 The first value is used for allocating a mem-pool for storing state for each fop or nfs op that is currently being handled. Knowing that linux allows at most 128 in-flight requests, this multiple combined with the default mem-factor of 15 gives us 225 slots in the mem-pool for the local structures. Similarly, 6000*15 gives us a space of 90k inodes in the lru. That means, increasing the common mem-factor will allow increasing the perf under some conditions. This patch introduces the mem-factor as a configurable option. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2277 (Regression in Gluster NFS re-read performance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2277 commit e344d58762e12aa1edd1d4b133e1c1f77229b370 Author: Raghavendra Bhat Date: Tue Jan 11 01:24:02 2011 +0000 exit if the key or the value is null while retrieving the peer information in glusterd_restore Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2271 ([glusterfs-3.1.2qa3]: entry->hostname in glusterd_friend_find_by_hostname is 0x0) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2271 commit f5934192a32a76baa12b7a22035187e63b7fdc1d Author: Sachidananda Date: Fri Jan 7 06:11:34 2011 +0000 Add corresponding va_end. Signed-off-by: Sachidananda Urs Signed-off-by: Anand V. Avati BUG: 2247 (Add corresponding va_end) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2247 commit 985f87517b7d00afd626f2cc85ca2ab02d33e613 Author: Raghavendra G Date: Fri Jan 7 00:45:48 2011 +0000 cluster/replicate: update st_nlink count of stat sent to application after completion of entry-self-heal. - certain applications like 'find' use st_nlink count to optimize searches. Hence an incorrect hard link count can result in non-healing of some of the newly created subdirectories. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2187 (Self heal errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2187 commit 38d0824031f445620fa0d704043cd5dedadea721 Author: Shehjar Tikoo Date: Wed Jan 5 07:02:14 2011 +0000 nfs3: Ignore requests for volumes without a single CHILD-UP NFS ignores the requests for subvolumes on which child-up has never been received. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2200 (cp dies with "Invalid argument" after failover) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2200 commit de6936a022e34a22eca39e189da368c03b46481f Author: Raghavendra Bhat Date: Tue Jan 4 03:15:35 2011 +0000 check the value of op_ret pointer not the address Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 221 (stat prefetch implementation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221 commit 2e81e4b828d53068e291100f4024d628d9a59443 Author: Amar Tumballi Date: Fri Jan 7 03:49:24 2011 +0000 storage/posix: in opendir, allocate proper size for fd ctx pointer Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2280 (wrong size allocated for posix_fd in posix.c:posix_opendir()) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2280 commit 879dc2f04f2bd35362bee214618f78ec4d688949 Author: Anand Avati Date: Tue Jan 4 14:00:28 2011 +0000 logging: reintroduce build warning for mismatching format strings and parameters Signed-off-by: Anand V. Avati Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit cfc387b0af174dfe303cdb3ef3ccfba979ef75ac Author: Amar Tumballi Date: Tue Jan 4 13:59:52 2011 +0000 logging: fix format warnings Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit cbba1c3f55a7f73791310085b5d9bc65008f0b9b Author: Shehjar Tikoo Date: Wed Dec 29 05:42:02 2010 +0000 nfs3: Force root lookup before starting fh resolution Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2200 (cp dies with "Invalid argument" after failover) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2200 commit 165efc45ab5518033612a58c1ac51243eb6bcef8 Author: Mohammed Junaid Ahmed Date: Tue Dec 28 01:14:19 2010 +0000 nfs/server: unrefing inodes on error in nfs_loc_copy (). Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 2252 (unreffing of inodes not done when memory allocation fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2252 commit 010394ee5e237606023f455955e005e111b9fa5b Author: Mohammed Junaid Ahmed Date: Tue Dec 28 01:13:45 2010 +0000 xlator.c: Unrefing inode's on error in loc_copy. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 2252 (unreffing of inodes not done when memory allocation fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2252 commit 03c791e2d699574dae077d05a171a768bfb28ec3 Author: Shehjar Tikoo Date: Thu Dec 23 04:28:26 2010 +0000 nfs: Support subdirectory exports Enable exporting directories as separate exports. Even though the directories wont show up in showmount output, they'll still be mount'able. The new option: nfs.export-dirs is enabled by default so that users dont have to wait till this option is incorporated into the gluster command line. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit f0eeffe7b658164fb060a9805aa6cc422aba213b Author: shishir gowda Date: Thu Dec 23 04:08:43 2010 +0000 afr_lookup_done: Propogate the same inode number as sent in first lookup If only one subvolume was up, we used to unwind, without updating the ino Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2144 (errors removing directories when one subvolume is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2144 commit 818a4d128048721d70be2d6c8eafd2f41034b260 Author: Anand Avati Date: Wed Dec 29 12:23:08 2010 +0000 stripe: fix memory leak destroy the frame copied and clean the local structure in stripe to avoid memory leak Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2253 (Memory leak in glusterfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2253 commit 98a1f381ba15dfc9c19ea3f9d778e8efb9e6be8e Author: Amar Tumballi Date: Mon Nov 8 03:43:20 2010 +0000 quiesce: bring in feature to re-transmit the frames there was a corner case of 'fops' failing if they were in transit during a disconnection, if the failure is due to 'ENOTCONN' re-transmit the frame. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1500 (Mount point should not be in-accessible between reconnect to server) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1500 commit 0cc2b35734224f44dda2fbd853506e04d889eb07 Author: Raghavendra Bhat Date: Wed Dec 22 04:56:37 2010 +0000 change the log level from warning to debug while getting pending matrix Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1080 (clang errors in the file afr-self-heal-common.c) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1080 commit 2bf223a5d31cc82ffa7a06371fde6615ced3b68f Author: shishir gowda Date: Wed Dec 22 04:35:10 2010 +0000 send_fuse_iov: check args to prevent possible NULL dereferencing Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2223 (Crash in send_fuse_err) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2223 commit 2e317d2d35a50a6440865de5445008fd814cd298 Author: Amar Tumballi Date: Mon Dec 20 03:59:02 2010 +0000 rdma : prevent confusing logs when both 'poll_in' and 'poll_err' are received. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 48f3faaa492b7a6f93e1f3d79cb66b34fd080468 Author: Shehjar Tikoo Date: Mon Dec 20 00:24:33 2010 +0000 nfs3: Access cbk must account for auxgids on group access checks Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2045 (Write permission denied for non-primary group membership) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2045 commit d0fff8965875ed7e7cee223bd2c7b12df10cb6d7 Author: Shehjar Tikoo Date: Mon Dec 20 00:24:32 2010 +0000 nfs: Do not touch iatt on failed fops Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2169 (NFS crash in nfs-fops due to failed fop from subvolume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2169 commit 953f89d82f2c444719ba3150c9890c072a2e7fb3 Author: Pranith K Date: Thu Dec 16 01:24:33 2010 +0000 glusterd,cli: print single error message on failure Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1922 (Volume not present wrong message displayed on command line) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1922 commit e7512cbb171856a925b7db938da423b493339b00 Author: Harshavardhana Date: Wed Dec 15 19:46:49 2010 +0000 Add volume key to select data-self-heal-algorithm Signed-off-by: Harshavardhana Signed-off-by: Anand V. Avati BUG: 2218 (Replicate self-heal causes servers to go 100% cpu and unresponsive.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2218 commit e89a57733381b5fc70128eefc3184c03004b994a Author: Raghavendra Bhat Date: Wed Dec 15 06:00:28 2010 +0000 log the total rebalance command recieved into the logfile Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2231 (log the total rebalance command recieved, in the logfile to avoid confusion) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2231 commit 8ba141e5e5d6616f05f69bb958b4a879198c1de5 Author: Pranith K Date: Wed Dec 15 00:37:22 2010 +0000 libglusterfs: data_copy needs to init the lock Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2226 (data_copy needs to init the data lock) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2226 commit 70f29baa5d45f765903d1547c57640e578836e7f Author: shishir gowda Date: Mon Dec 13 05:53:54 2010 +0000 Make STRIPE_STACK_UNWIND and STRIPE_STACK_DESTROY default calls in stripe Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2134 (inode leaks on stripe) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2134 commit b4218f679113b3b0a6e08a0dd9482ec99ee77a38 Author: shishir gowda Date: Mon Dec 13 13:40:34 2010 +0000 Implement STRIPE_STACK_UNWIND and STRIPE_STACK_DESTROY Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2134 (inode leaks on stripe) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2134 commit ef27058512773a76853e3c6c715465f87da2b13a Author: shishir gowda Date: Mon Dec 13 05:31:28 2010 +0000 Remove check for path in stripe_local_wipe The check for path is done in loc_wipe. During loc_copy, inode ref is taken before path set succeeds or fails. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2134 (inode leaks on stripe) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2134 commit f190be2ea2793b6a9be51fef1043224b477986dd Author: Raghavendra G Date: Mon Dec 13 23:03:37 2010 +0000 performance/io-threads: implement rchecksum fop. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2220 (Implement rchecksum fop) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2220 commit 4e2b53708e0ca3f740815dbe7741f276069235ab Author: shishir gowda Date: Tue Dec 14 01:03:38 2010 +0000 setsockopt should be called with solaris specific arguments for solaris server ----- Original Message ----- From: "Raghavendra Bhat" To: glusterfs@dev.gluster.com Sent: Tuesday, December 14, 2010 11:56:43 AM Subject: [PATCH BUG:2205 v4] setsockopt should be called with solaris specific arguments for solaris server Looks fine to me. Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2205 ([glusterfs-3.1.2qa1]: error while setting the keepalive time interval) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2205 commit 1637eabfd3e953a609cd5c82f58a7daa9d88b243 Author: Pranith K Date: Mon Dec 13 06:06:20 2010 +0000 cli: remove duplication of cmd help Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2089 (Documentation bug in replace-brick options) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2089 commit b754e531b48113596fddcd7d0b433ebcbf016c27 Author: Raghavendra G Date: Mon Dec 13 03:34:21 2010 +0000 mgmt: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 361c804e9d70bd5a1c38eae1944635ca127c9ed9 Author: Raghavendra G Date: Mon Dec 13 03:34:05 2010 +0000 nfs: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit f9b61e81eb6ffbfcd25e43191797570b07412ef4 Author: Raghavendra G Date: Mon Dec 13 03:33:52 2010 +0000 features/quota: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 5ef77ec5a06d2fddb37c313fbee316da06002b82 Author: Raghavendra G Date: Mon Dec 13 03:33:38 2010 +0000 cluster/distribute: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 3fd60a81d3a536cfd005e7fe3171d397d1019067 Author: Raghavendra G Date: Mon Dec 13 03:33:21 2010 +0000 cluster/replicate: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 04fe9457923ff74e9fc396ed13c6a5eef4810493 Author: Raghavendra G Date: Mon Dec 13 00:14:25 2010 +0000 libglusterfs: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 5f708e77242b0658f1619cca16e3e679163fb570 Author: Raghavendra G Date: Mon Dec 13 00:14:12 2010 +0000 performance/quick-read: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit cc0c857ceba2bec066cb4167f4c84dfea925546b Author: Raghavendra G Date: Mon Dec 13 00:13:59 2010 +0000 performance/io-cache: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 11b1c0735d7709d37ef775ff036e473a1b60801d Author: Raghavendra G Date: Mon Dec 13 00:13:41 2010 +0000 performance/io-threads: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 9b87966e12fa53f59e383f701e9e391916a7860a Author: Raghavendra G Date: Mon Dec 13 00:13:28 2010 +0000 performance/write-behind: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit 26caaeae10414f9888a438ad8559692a7f74f918 Author: Raghavendra G Date: Mon Dec 13 00:13:15 2010 +0000 protocol: fix warnings due to format string mismatches during invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit aaad9c6f6ebe4bff3307e532cd802fafaed4a67f Author: Raghavendra G Date: Mon Dec 13 00:12:54 2010 +0000 rpc: fix format string mismatches in invocation of gf_log. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2211 ((re)introduce warnings for format string/parameter mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2211 commit df5f71b401decfb32006d7564db1a13bcd5e8be2 Author: Amar Tumballi Date: Fri Dec 10 12:24:16 2010 +0000 client-reopen-cbk: fix a gf_log() crash due to wrong argument list Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit c40ce6beac9c3d9d006bcbd91bdac5e96055a00e Author: Raghavendra G Date: Thu Dec 9 01:03:57 2010 +0000 rpc-transport/rdma: QP configuration changes. - set send and recv count to 4K. - set max_send_sge of QP to 2 since for msgs of type RDMA_NOMSG, there can be two vectors - rpc header and message from program. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2197 (applications running on large number of clients simultaneously result in ibv_post_send errors on server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2197 commit ef8feeb8608728c738543b854f7f0795e80780e2 Author: Raghavendra G Date: Thu Dec 9 01:03:39 2010 +0000 rpc-transport/rdma: add informative debug messages when posting of send requests fail. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2197 (applications running on large number of clients simultaneously result in ibv_post_send errors on server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2197 commit 625fb341b14acc704c588344ab5390c05b387179 Author: Raghavendra Bhat Date: Wed Dec 8 23:20:14 2010 +0000 set the return value to -1 intitially which may be returned as success in validate_or_goto Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 9d4ba49cd3f8055d4305d85c6149311e36d78bdd Author: Raghavendra Bhat Date: Wed Dec 8 23:14:04 2010 +0000 check the return value after setting the fd context in afr Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 48d6fe293a487727d4686f64ef410a3df569f6a8 Author: Raghavendra Bhat Date: Wed Dec 8 22:55:24 2010 +0000 check the return value properly after calling inode_path Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2203 ([glusterfs 3.1.1]: Core generated with Segmentation fault in afr-open.c) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2203 commit 40e1d364161b45299fcefd50879d532a01f4d2b5 Author: Raghavendra G Date: Fri Dec 10 04:48:49 2010 +0000 rpcsvc: while handling transport-cleanup event look for listener with transport trans->listener instead of trans. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2208 (transport cleanup event is not sent to programs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2208 commit 9f480be0333863a2cb30088504d233fd6eb46ebf Author: Anand Avati Date: Thu Dec 9 02:06:52 2010 +0000 protocol: avoid repetitive disconnect logs Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 353fb2e97bfc3a44cc5301fa8dfb015406565048 Author: Anand Avati Date: Wed Dec 8 09:58:27 2010 +0000 replicate: propagate CHILD_DOWN upwards properly During initialization if one subvolume returns CHILD_DOWN, then do not consider the other subvolume as down if we still haven't heard from it yet This causes DHT (on top) to prematurely (and wrongly) send CHILD_UP/DOWN upwards Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2200 (cp dies with "Invalid argument" after failover) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2200 commit 147b20c4a485ddb4b31b1811be4bf90610c91f7f Author: Anand Avati Date: Tue Dec 7 05:36:54 2010 +0000 nfs: cleanup inode_ref/inode_unref to fix inode leaks and extra unrefs Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2195 (Crash in __inode_retire on NFS failover) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2195 commit 64cdcbe39bcb8d52d0c6aa88ce5cd5f3d6062a9e Author: Vijay Bellur Date: Tue Dec 7 06:53:49 2010 +0000 mgmt/glusterd: Use a static buffer to perform ioctl with SIOCGIFCONF Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2163 (Can't create volume using 3.1.1qa11 on OpenSolaris 2009.6) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2163 commit e3232db35a20e5cfd68ab3fb0b7d0931c4cfb67d Author: Anand Avati Date: Tue Dec 7 00:19:30 2010 +0000 gfid: disable setting/getting of gfid from higher level translators Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2196 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2196 commit f783ecfbfd8c873d97644b8b6b0d95e3f878b992 Author: Anand Avati Date: Tue Dec 7 00:02:10 2010 +0000 rpc-clnt: show disconnect messages in log file by default Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit fceef36419503f332ffd1fccdcb03da86cf9cdb3 Author: Anand Avati Date: Mon Dec 6 23:28:19 2010 +0000 inode: fix crash in logging during cyclic loop detection Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2196 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2196 commit caa77054005ea9ca9b806006103cd3f7eed10c7d Author: Raghavendra Bhat Date: Mon Dec 6 07:55:56 2010 +0000 check whether the file is a symlink while doing utimes Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 881 (GlusterFS daemon hangs on replication of symlink (3.0.4)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=881 commit 574d938adcfe74f912fb2de8f77fc7a9d18c689b Author: Raghavendra G Date: Thu Dec 2 00:34:09 2010 +0000 mount.glusterfs: use option --direct-io-mode instead of --disable-direct-io-mode Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2173 (enabling/disabling direct-io mode is not possible when glusterfs is mounted using mount command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2173 commit ae6e73f4d2a9fba6ccef42d49d70d8bbd7cba84a Author: Shehjar Tikoo Date: Fri Nov 26 00:45:50 2010 +0000 nfs: Start nfs process even if portmap registration fails It helps to have the process be listed in ps ax|grep output so that user can get the path to the log from the listed command line and check what the problem is. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2093 (volumes cannot start when one node in a replicated setup is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2093 commit 773c9688bc8d3190eab3797190bd06d7acf275aa Author: Anand Avati Date: Mon Nov 29 06:24:15 2010 +0000 fuse-bridge: construct fa->rdev properly Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2145 ([3.1.1qa9] mknod does not work properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2145 commit 69a62d2a6d8ad127787aad2215c2130a03f58090 Author: Anand V. Avati Date: Mon Nov 29 09:01:41 2010 -0800 rpm: glusterfs.spec.in fixes for upgrade via rpm -Uvh commit c0be54cfcd4491ca212226ed5687740813a4aeb6 Author: Anand Avati Date: Thu Nov 25 23:35:18 2010 +0000 stat-prefetch: changes to incorporate gfid Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2136 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2136 commit 47548f09f005998598edd8183804cd93c35a12f3 Author: Vijay Bellur Date: Wed Nov 24 12:42:56 2010 +0000 mgmt/glusterd: Enable stat-prefetch for fuse Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2136 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2136 commit b605865986f19cf5e376a16b963f68f28d4aea44 Author: Shehjar Tikoo Date: Thu Nov 25 04:11:11 2010 +0000 nfs3: Prevent second lookup on a fresh entry lookup Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 50e5c72fd63c44119b272435e715a712d848476a Author: Shehjar Tikoo Date: Thu Nov 25 04:11:10 2010 +0000 nfsrpc: Add new macro nfs_rpcsvc_request_procnum Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 6623055696e1b28267305ac45087497f4c6a884a Author: Shehjar Tikoo Date: Thu Nov 25 04:11:09 2010 +0000 nfs: Export subvolumes on per-subvolume CHILD-UP ..so that nfs clients can mount an UP subvolume even if other subvolumes havent come up yet. This was a problem because nfs was waiting for all children to receive CHILD-UP before exporting any subvolume. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2093 (volumes cannot start when one node in a replicated setup is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2093 commit 26a8202550593232f941cd2251cfbeb304991808 Author: Shehjar Tikoo Date: Thu Nov 25 00:17:08 2010 +0000 nfs3: Fresh inode lookup on failed revalidation Brings in changes that were earlier introduced in commit: f5afcc47f9f00472d6c2b3f48127e02332cd457a but reverted because the patch was buggy and caused a seg-fault due to extra inode_unrefs. It fixes that extra inode_unref and cleans up the revalidation logic. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit ac5e34ec840889bc3eaf07d2f7091432ff698fe2 Author: Shehjar Tikoo Date: Thu Nov 25 00:17:07 2010 +0000 nfs: Undo selective changes in inode revalidation Those changes were brought in by commit 161850285ff06e90f2c990989bab9513dd4a4289: "nfs: re-implement logic to perform fresh lookups when lookup revalidates fail" Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 9e67fd90e0df32b9a450632566855339b133d3a6 Author: Vijay Bellur Date: Thu Nov 25 02:26:26 2010 +0000 mgmt/glusterd: Move .cmd_log_history to log directory Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2154 (Move .cmd_log_history to log directory) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2154 commit c56b9967a33b8bb106d37df0cf6979b340dbf950 Author: Raghavendra G Date: Wed Nov 24 07:35:26 2010 +0000 rpc-transport: don't merge payload iobuf and iobuf which holds program header into single iobref. - io-cache holds a reference on iobref passed from transport layer. Hence, two iobufs are accounted instead of one in calculated used cache size. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2135 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2135 commit b7ca86e7614c61f8bf0b1e4bea47b4bc0a7fe080 Author: Sachidananda Date: Thu Nov 25 01:05:08 2010 +0000 rpc-coverage.sh: Make error messages explicit. Make failure explicit, with `set -e' script exits silently and we have no way to know where it failed unless run by set -x. Signed-off-by: Sachidananda Urs Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit f7436a82bc0d02639efaa8e4fdf922a9849d0713 Author: Vijay Bellur Date: Thu Nov 25 02:04:43 2010 +0000 mgmt/glusterd: Temporary fix for a crash seen in replace-brick Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 commit 5725f33e314c2fca6a4b9c2b102fc66361145301 Author: Vijay Bellur Date: Thu Nov 25 02:11:45 2010 +0000 cli: Enhance message shown upon successful volume creation Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2034 (Why not start a volume after it has been created?) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2034 commit 43a039789cbbdb50d67c960c7a6f4d0ac1858e48 Author: Anand Avati Date: Wed Nov 24 07:24:33 2010 +0000 resolver: include par_idx access within the conditional section Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 9f8edf2b2576a235526087f4fbc5769940f019ad Author: Anand Avati Date: Wed Nov 24 07:15:19 2010 +0000 iatt: fix bug in ia_makedev the wrong binary operator was resulting in lookup/stat showing wrong major/minor numbers for device files Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2145 ([3.1.1qa9] mknod does not work properly) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2145 commit ab5c5610bb37e5f4fbcc4722abf21de3dc2c9679 Author: Csaba Henk Date: Sat Nov 20 05:52:24 2010 +0000 volgen: put back an amended form of check erased in 96f44835 ("do not error out if brick count is less than sub count...") Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2054 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2054 commit cef1669d5fdf43e1df38189759345170b90a1455 Author: Csaba Henk Date: Tue Nov 16 19:35:12 2010 +0000 volgen: clean up 0fbf226c (... add nfs.enable-ino32 as an option ...) Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1972 (xcs get doesn't work with gNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1972 commit 8b1aac46732c871c6b97c1f2bbb7fcc5b79d52bd Author: Raghavendra Bhat Date: Tue Nov 23 07:13:27 2010 +0000 display the error to the user if volume stop is given on a volume which does not exist Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2140 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2140 commit 0ccd9f4f2ddf83d35cfa9bbc872ca84f6fb9c8a9 Author: Anand Avati Date: Tue Nov 23 10:35:56 2010 +0000 inode: catch loop formation during inode_link() and fail linking - explores all parent branches - performs loop formation check only if the operation is resulting in relinking of an inode already existing in the table Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 7f68e386132af9e02bf37a3b4d0653de000bdefe Author: Anand Avati Date: Mon Nov 22 10:52:51 2010 +0000 resolver: handle corner cases of handling root inode better - changes in deep resolution and simple resolution of pure paths to handle resolution of "/" - warn on pure path resolution Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit f1205225417b3e0d5cf27f5ba85ccdfe0ef6b246 Author: Raghavendra Bhat Date: Mon Nov 22 00:55:44 2010 +0000 display the error message to the user if a volume with the name is tried to be created Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1209 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1209 commit c509e7f185d4f76be9f5ddbd61839239198a0b1d Author: Anand Avati Date: Fri Nov 19 06:25:40 2010 +0000 rpc-coverage.sh: enhancements for more extensive testing Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit f6785d2b4999db7d42e8c1cd054fd7ec174e8136 Author: Anand Avati Date: Thu Nov 18 08:35:24 2010 +0000 nfs: treat GF_EVENT_CHILD_CONNECTING as subvolume up status GF_EVENT_CHILD_CONNECTING is sent as a status from underlying subvolumes after a sufficient margin of time (tcp connect() timeout) if the subvolumes are not reachable. This should avoid the problem of NFS not being reachable if any volume is down Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2093 (volumes cannot start when one node in a replicated setup is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2093 commit e098653b73c7b379b2ad6bf7878bac65147f7ebe Author: Pavan Sondur Date: Thu Nov 18 05:38:59 2010 +0000 features/locks: Send prelock unlock only if it is not grantable and is a blocking lock call. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Anand V. Avati BUG: 1017 (Locking deadlock when upgrading lock) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1017 commit e111591585c8e5f3c8404b72ad13b5f5580c25c4 Author: shishir gowda Date: Wed Nov 17 23:36:06 2010 +0000 Remove spurious inode_ref call on parent dir in fuse_create_cbk The additional ref caused leaks. The ref is taken in __dentry_create called from inode_link Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2117 ([glusterfs-3.1.1qa7]: memleak in glusterfsd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2117 commit 001a44f7dc6cec6fb5ce555ce583af4428cc471d Author: Raghavendra Bhat Date: Thu Nov 18 02:32:38 2010 +0000 error out if the data-self-heal-window-size is less than 1 Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2120 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2120 commit 99134d33f85e38e5c37227ecb8fdfbe03bd521d0 Author: Vijay Bellur Date: Thu Nov 18 06:26:26 2010 +0000 mgmt/glusterd: Avoid creating multiple destination brickinfo during replace-brick Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 commit f0cdfd03051cee8d25f03103ed467438c6479e47 Author: Amar Tumballi Date: Thu Nov 18 06:31:01 2010 +0000 cluster/pump: send PARENT_UP to dst_child after init is successful Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2122 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2122 commit 61a8945649eced6c490a92e6533c5fb3a9d9a1d3 Author: Amar Tumballi Date: Thu Nov 18 06:21:55 2010 +0000 rpc-clnt: add check for NULL argument for rpc_clnt_start prevents crash when rpc_clnt_start is called before init Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2122 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2122 commit 9c80f63d8264718c5855f1f6cca9e5a801392ed3 Author: shishir gowda Date: Tue Nov 16 03:52:17 2010 +0000 protocol/client: skip notify if query portmap is successful Mount point does not hang, though stale handle error on / till the downed brick is online again Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1905 (Mounting volume is not working when any one server is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1905 commit ce9f328aa93892ea79057c41c70836eb49fae8b5 Author: Anand Avati Date: Tue Nov 16 08:17:07 2010 +0000 protocol/client: use the new rpc_clnt initialization methods This way of initializing an rpc_clnt object by splitting into a passive rpc_clnt_new and a delayed rpc_clnt_start between which registration of callback programs and notify methods are performed provides a race-free way to avoid the missing of connect notifications Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2078 (Volume Migration is not working) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2078 commit 8faf940c00e3722a2322ee70ba1e18d9b9bc8c9c Author: Anand Avati Date: Tue Nov 16 08:16:42 2010 +0000 rpc-clnt: introduce new way of creating rpc-clnt objects rpc_clnt_new() creates a new passive rpc clnt object. rpc_clnt_start() triggers the connection/reconnection from the object. rpc_clnt_init() - the old way - still works. Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2078 (Volume Migration is not working) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2078 commit 15d56782ae560aa556d6af64896c4c879c6c46e6 Author: Anand Avati Date: Tue Nov 16 08:15:48 2010 +0000 rpc-clnt: move rpc_clnt_reconnect() call to rpc_clnt_init Previously rpc_clnt_reconnect() was called inside rpc_clnt_connection_init which in turn was called from rpc_clnt_init. This change makes rpc_clnt_connection_init re-usable for the next patch Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2078 (Volume Migration is not working) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2078 commit b985dce6c4415a9d67fefabdbf2e5fe287e1dc62 Author: Shehjar Tikoo Date: Tue Nov 16 04:56:38 2010 +0000 nfsrpc: Fail auth-unix if more than 16 gids found Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2045 (Write permission denied for non-primary group membership) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2045 commit 015b08d64dfea093d8fcd0a30b655469b18bbc2e Author: Shehjar Tikoo Date: Tue Nov 16 04:56:37 2010 +0000 rpc-lib: Fail auth-unix if more than 16 gids found Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2045 (Write permission denied for non-primary group membership) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2045 commit 36f696c7dbc785be464acae737f4c25ed3af861a Author: Shehjar Tikoo Date: Tue Nov 16 03:44:37 2010 +0000 rpc-lib: Copy auxiliary GIDs into request from de-XDRed buffer Fixes a problem where secondary groups are not accounted for in permission checks. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2045 (Write permission denied for non-primary group membership) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2045 commit 4cfd6e1b45da64429c3e10886e2ceb4e9c9deb5d Author: shishir gowda Date: Tue Nov 16 01:07:20 2010 +0000 Stripe I/O exits when graph changes Adding event CONNECTING to be handled like CHILDUP in notify. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2111 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2111 commit 66c768a4845482c42a77e458ecbc73488998fb13 Author: Amar Tumballi Date: Tue Nov 16 01:21:54 2010 +0000 protocol/client: fix ping timeout checks in reconfigure() Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2104 ([3.1.1qa5]: network.ping-timeout set failed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2104 commit eb13791c229b011b41e63099ce097a4271ae0451 Author: Pranith K Date: Tue Nov 16 01:26:00 2010 +0000 cli: fix memory corruption in create volume and add-brick Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2113 (cli: memory corruption in add-brick and create volume parsing functions) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2113 commit bc3cad79cd0cf48318e723fd3377af979673374e Author: Amar Tumballi Date: Tue Nov 16 01:26:45 2010 +0000 fuse: dentry create time inode resolution fixes treat successful 'inode' resolution as stale entries in case of entry creation fops, instead of continueing with an error log with old entry. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1240 (DVM: after graph change, inodes should resolve to new inode-table) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1240 commit e10f1ec908139d9778406d07274dd390b7f56bc8 Author: shishir gowda Date: Tue Nov 16 00:12:58 2010 +0000 Solaris: df -h returned invalid size The reason seems to have been multiplying fields with f_bsize, while they are in f_frsize units. On linux both f_bize and f_frbsize seems to have been the same Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1021 (NFS: df -h shows incorrect out put) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1021 commit 961fc917e8e9f13b8cab69b1ba11767d5c41a8ce Author: shishir gowda Date: Mon Nov 15 06:44:44 2010 +0000 Remove symlnk of log dir to /etc/glusterd Hence forth the default log dir will be /usr/local/var/log/glusterfs Missed out on log locate changes Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2109 (Remove symbolic link of log directory from /etc/glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2109 commit b552465ca4a8d65650cb1d0beb4ccfe5eaf93c26 Author: shishir gowda Date: Mon Nov 15 02:55:38 2010 +0000 Remove symlnk of default log dir to /etc/glusterd Hence forth the default log dir will be /usr/local/var/log/glusterfs Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2109 (Remove symbolic link of log directory from /etc/glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2109 commit 6d42bc03d0ebe6100d9f3815f06637cb1b44c2ac Author: Amar Tumballi Date: Mon Nov 15 03:46:30 2010 +0000 glusterd rebalance: update the status in failure cases Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1999 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1999 commit 553c15160e4e3b063f4b689ee762b6d14be9953b Author: Shehjar Tikoo Date: Mon Nov 15 05:57:46 2010 +0000 Revert "nfs: Use only 38467 as default port instead of 3846[567]" This reverts commit be5c02a81c19336a6b922b1e1f28293c90955e7f. By default, continue to register the three original port numbers so that an upgrade to future version from 3.1 release does not break mount requests against portmap, which may have old port numbers registered. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit 78654d270cde028c5d7f9da29b2790b90c19e11f Author: Anand Avati Date: Mon Nov 15 05:34:00 2010 +0000 nfs: opendir/closedir for every readdir Revert "nfs3: Unref & unbind dir fd with inode lock on EOF" This reverts commit 4e6fb304ce41acbaf7c9ba67c06bf443e65082e8. The above commit (which unbinds fds at EOF) does not fix the original bug (1619) because a readdir from a second app could have already started before the readdir_cbk of the first app's readdir reaches NFS code. Hence the race still exists. Performing extra unrefs when EOF is received is not a reliable way of detecting that a client has performed a closedir (and to close the fd ourselves). Neither is interpreting a 0 cookies a new opendir. Clients can always use telldir/seekdir and hit EOFs twice. Due to the way NFS3 protocol is designed, it is just not possible for the server to reliably detect opendirs/closedirs performed by the client and map the corresponding readdirs to the same dir fd on the server side. The only reliable way of fixing this is to perform opendir/closedir at the cost of performance. Any optimization towards keeping dir fds open attempting to map them with application's opendir/closedir will either result in fd leaks or extra fd unrefs. Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2061 (NFS server crashes in readdir_fstat_cbk due to extra fd unref) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2061 commit 7d48999c13b885d034528cfca61a8b63ade8a365 Author: Raghavendra G Date: Mon Nov 15 04:02:45 2010 +0000 cluster/replicate: Fix memory leak in afr_fd_ctx_cleanup. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1438 (memory leaks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438 commit 415f7f6a29b361dfccc197a6b67add1733c7f617 Author: Raghavendra Bhat Date: Sat Nov 13 02:06:12 2010 +0000 check for dict also while setting the port for source brick while doing replace brick Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 commit ec43d07c3ab758e0e8cfa427d914ab9c653068a4 Author: Pranith K Date: Sun Nov 14 00:13:25 2010 +0000 cli: remove special behavior for help commands without readline Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2091 (Gluster CLI exits after issuing volume help) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2091 commit 22aa43c16357811f8218215d2f2f830005860c96 Author: Vijay Bellur Date: Sun Nov 14 12:08:23 2010 +0000 mgmt/glusterd: fixes for uninterrupted replace-brick with nfs Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 commit 479393858a1744adf7c9f56216ca228b188a7398 Author: Vijay Bellur Date: Sun Nov 14 12:07:30 2010 +0000 cluster/pump: Reset saved path upon pump completion Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 commit d6f1f04ef0db60bcc0f4963dbd1b76ce73c36779 Author: Raghavendra G Date: Thu Nov 11 23:00:19 2010 +0000 performance/quick-read: handle the errors in qr_loc_fill properly when an fop needs to do open before continuing. - without need_unwind set, 'goto out' will result in infinite loop. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2075 (inode_from_path silently consumes 99% CPU causing nfs client disconnects) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2075 commit 20fb15dc02a4d1a4b38335a988c0c1abafee7355 Author: Pranith K Date: Fri Nov 12 04:01:01 2010 +0000 mgmt/glusterd: "peer probe new-hostname" should replace old-hostname of friend Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1995 (Gluster Peer probe command keeps ip address instead of server name in the destination server) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1995 commit fe349e42baa47dd7c010707bddbd114946f4d95b Author: Amar Tumballi Date: Fri Nov 12 05:23:42 2010 +0000 stripe: allow lookup on an entry if other than first subvolume is down Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2099 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2099 commit e48f8e62e0d7d68ca8b45402a6b9a79352fd8063 Author: Shehjar Tikoo Date: Thu Nov 11 00:19:54 2010 +0000 nfsrpc: Change log levels for RPC program search messages Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2072 (NFS server crash in __nfs_rpcsvc_program_actor) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2072 commit c364d4114c0f0ec888e03c909266f521dd6dc87c Author: Amar Tumballi Date: Thu Nov 11 01:54:50 2010 +0000 cli: fix issues with running command over ssh Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2081 (gluster CLI does not work over ssh) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2081 commit b43ef598abec07cff6090dd507419347621b473c Author: Pranith K Date: Fri Nov 12 00:55:02 2010 +0000 mgmt/glusterd: set the transport type correctly in create volume Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2095 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2095 commit ed8499c728df609a3d09743ee60f85f6ecea9d16 Author: Amar Tumballi Date: Fri Nov 12 04:05:22 2010 +0000 distribute: handle a case of 'local->key' being free'd twice. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2097 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2097 commit 26db1945888a4c85d55c3c5c75beb49e09c19588 Author: shishir gowda Date: Fri Nov 12 04:15:08 2010 +0000 Solaris: vasprint fix for %llu crash vasprint now inturn call gf_vasprintf, which calls vsnprintf. vsnprintf allocates buffer of required size, and hence prevents the sigsegv seen in vasprintf w.r.t %llu Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1058 (vasprintf dumps core when %llu is involved) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1058 commit 0bd8ecda6554e20336112febf1ade9e1d66bea8e Author: shishir gowda Date: Fri Nov 12 04:15:38 2010 +0000 Solaris: Fix crash seen in rpc_clnt_reconnect rpc_clnt_set_connected was being called from mgmt_rpc_notify with incorrect argument. The crash was only seen on solaris. Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2013 (Gluster 3.1 should be supported on the current versions of Solaris and OpenSolaris) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2013 commit 7b8015edf8ac2fc33e486d2ef66b01c53c200d60 Author: Shehjar Tikoo Date: Wed Nov 10 07:56:45 2010 +0000 rpcsvc: Fix crash in program search after portmap registration failure Failure to register with portmap was leaving the registered programs list in inconsistent state. This was causing a crash. portmap registration can fail if there is an NFS server already running. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2072 (NFS server crash in __nfs_rpcsvc_program_actor) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2072 commit 681d7d3aa926e0959ad3f66e53282cb4e55d6202 Author: Raghavendra G Date: Wed Nov 10 02:59:10 2010 +0000 rpc/rpc-lib: don't build libgfrpc as a module. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1427 (libgfrpc.so is not portable) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1427 commit f406a2e2754a5aa44736f25459e33ef068b6b14a Author: Amar Tumballi Date: Tue Nov 9 06:51:31 2010 +0000 rpmspec: add glusterfs-core dependency for glusterfs-fuse package also add dependency for rdma package Thanks to Bernard Li for the patch Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 2019 (glusterfs-fuse should require glusterfs-core (RPM spec file)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2019 commit eaf0618e47b4e575180a9cbdbeda6ff5995fb144 Author: Anand Avati Date: Tue Nov 9 05:38:12 2010 +0000 protocol/server: fix log level of message in server-resolver.c Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 1092 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1092 commit 6fb49f18a9bbfd1266b4773e757e459519c6719c Author: Anand Avati Date: Tue Nov 9 05:27:02 2010 +0000 replicate: optimistic changelog The standard way of maintaining changelog in replicate has been to write out pending flags and to unset the pending flag post the actual operation. This new optimization kicks in only when all subvolumes are up. The optimization is that, during pre-op, no changelog is written for METADATA and ENTRY/RENAME operations. If during the operation nothing failed, no changelog is updated in post-op either. If however, something does fail during an operation, then, pending flags get written during post op pointing only towards the failed nodes. DATA transactions continue to work the way they are. If one subvolume is down, pending flags are written in pre-op changelog itself as before. The impact of this optimization is only in the case when both servers die or the client dies while the 'FOP' stage of the transaction is in progress. By nature of METADATA and ENTRY operations, detecting a mismatch later is not dependent on the presence of changelog. Changelog only determines the direction in which self-heal happens for these types of transactions. For the direction too this optimization does not have a major impact because in the cases of failure (both servers dieing or client dieing) the final state (direction of self-heal) would be arbitrary anyways as the syscall wouldn't have completed. Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 2068 (performance enhancements) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2068 commit 667c5e22467cbecd371bfc052e7f65b6b6b41e2d Author: Vijay Bellur Date: Tue Nov 9 05:14:22 2010 +0000 libglusterfs: Memory accounting changes This patch disables memory accounting by default and provides better alignemnt for faster fetch. Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2068 (performance enhancements) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2068 commit 16eb9f73a5a7699d5c51d8139b4f1bc77ee3deda Author: Pranith K Date: Tue Nov 9 04:08:33 2010 +0000 glusterd test-script change in add/remove-brick syntax Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1436 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1436 commit 891216e186b436444bc5368a96318df7364ce30a Author: Pranith K Date: Tue Nov 9 03:17:31 2010 +0000 cli: remove volume type from add-brick and remove-brick cmds Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1983 ("type" in add-brick is completely redundant) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1983 commit 1badd4511f1cd7ea7c3187b121f793cabb414f3a Author: Shehjar Tikoo Date: Tue Nov 9 02:48:31 2010 +0000 client: Return correct pre/post iatt for dst during rename Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2050 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2050 commit 030393152fe6e7660cc4464be8b65ec1d6ecbbc5 Author: Shehjar Tikoo Date: Tue Nov 9 00:36:24 2010 +0000 mnt3: Fail mount requests for disallowed clients Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1385 (showmount says no access though it can be mounted.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1385 commit 19aa7b6923f84ffb8a558263e2dede4661862342 Author: Raghavendra G Date: Tue Nov 9 00:05:31 2010 +0000 rpc-transport/rdma: set the default quota of recv buffers to 128. - since quota is returned once the reply is recieved, 32 is too less value. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 2060 (Infiniteband errors on large file find) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2060 commit 8205e939178ba2253117869024a306442b30d3d1 Author: Raghavendra Bhat Date: Mon Nov 8 06:40:21 2010 +0000 check if the brick being added is the destination brick of replace brick Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2033 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2033 commit e3808ac86f8ff5baebea59e610a791cef5f5f2c9 Author: Shehjar Tikoo Date: Mon Nov 8 06:25:18 2010 +0000 nfs: Support nfs.port to allow changing nfs port numbers Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit be5c02a81c19336a6b922b1e1f28293c90955e7f Author: Shehjar Tikoo Date: Mon Nov 8 06:25:17 2010 +0000 nfs: Use only 38467 as default port instead of 3846[567] Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit 0f9ec3dec9d51ac5a8f692896d0724b3e87e9ae2 Author: Shehjar Tikoo Date: Mon Nov 8 06:25:16 2010 +0000 nfsrpc: Decouple TCP connections from programs ..so that multiple programs can be served from the same connection or multiple ports can be bound to the same port number. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit 13c4f8d0f9114a9f8324d0dec8bd926c04a5dfc5 Author: Amar Tumballi Date: Mon Nov 8 05:02:06 2010 +0000 glusterfsd.c: cleanup_and_exit() doesn't call all the 'fini()' calling 'fini()' of each xlator needs more synchronization work to be done. We will be doing a direct 'exit()' as of now. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1879 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1879 commit 96d16edec3dda4cd565b9d4106411c36bebe6dd5 Author: Amar Tumballi Date: Mon Nov 8 02:53:16 2010 +0000 protocol/server: array declarations changed to alloca() This is to make sure we don't spend CPU cycles in memset(0) on the array, instead do a 'alloca()' on size of the request. Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit bdfaaf42b643e2e51b85dd9ff5f7da91db3e0710 Author: Shehjar Tikoo Date: Mon Nov 8 00:54:27 2010 +0000 access-control: Allow Writes/Reads to proceed without perm checks a. We expect that when the fds are opened through FUSE, thats when the perm checks happen, depending on the read/write mode used. b. In case of nfs clients, we expect the nfs clients to perform the checks based on getattr/access nfs requests. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2058 (posix permission compliance error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2058 commit 96f44835ea31b6d432337013b0b70191f6fa903a Author: Raghavendra Bhat Date: Thu Nov 4 02:44:02 2010 +0000 do not error out if brick count is less than sub count which is valid in the case of replicate Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2054 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2054 commit 7d4b708b7d2180045793677534e9fedd47da794c Author: Vijay Bellur Date: Fri Nov 5 03:54:39 2010 +0000 fuse: init entry timeout Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2059 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2059 commit 8f16c5ed15e3c0cfbef396c63dbc45778ea84475 Author: Kaushik BV Date: Thu Nov 4 05:11:50 2010 +0000 Remove the hard-coded thread-count option in volgen Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 9c4777534bdcce46f2391852933336bc73309f93 Author: Raghavendra G Date: Thu Nov 4 02:34:26 2010 +0000 rpc-transport/rdma: create request_context only if message contains read chunks or write chunks. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1992 (glusterd crashed while submitting a callback.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1992 commit d19a72024c8cd5e40dc48df27c21fda701e76c54 Author: Raghavendra G Date: Thu Nov 4 02:33:19 2010 +0000 rpc-transport/rdma: Fix 2KB as threshold size for msgs that can be transferred inline. - Any fop/mop that can result a reply whose size is greater than this threshold allocates and submits a buffer along with the request to receive reply. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513 commit 56450b818756a762c925c76f8c6218ea1c5f7efe Author: Raghavendra G Date: Mon Nov 1 01:25:03 2010 +0000 rpc-transport/rdma: increment post->ctx.count in a loop doint rdma_read. - incrementing by the number of read chunks even before doing rdma read will cause issues since post->ctx.count is used while posting rdma read. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1877 (data corruption while running arequal.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1877 commit 86a1ef81527da5b9eb11ba3dc361c1c4ca291ca8 Author: Shehjar Tikoo Date: Wed Nov 3 06:35:29 2010 +0000 nfs: Introduce rpc.register-with-portmap to disable portmap registration For systems that need to run multiple nfs servers, we need to prevent more than one from registering with portmap service. Use this option to turn off portmap registration for Gluster NFS. Portmap registration is on by default. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit b16c0784da56fc2e7d660753882ec63587e2049e Author: Shehjar Tikoo Date: Wed Nov 3 06:35:28 2010 +0000 nfs: Remove conn_destroy/init callbacks NFS is transport-independent, so no point emulating knowledge of transportin software. Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1743 (XenServer is not compatible with GlusterNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1743 commit d6d7a85487d8ec8017d1d13aa36642ad0355b3e4 Author: Shehjar Tikoo Date: Wed Nov 3 06:35:27 2010 +0000 nfs3: More robust root gfid checks Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 2051 (find fails with loop detected error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2051 commit 5afc77d585c480f185dd7b24b753a6924218bb86 Author: Shehjar Tikoo Date: Wed Nov 3 00:34:10 2010 +0000 mnt3: Fix UMNTALL crash with Windows clients Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1666 (GlustNFS is incompatible with Windows 7 NFS client.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1666 commit 428b6edc2e141ec701e4a8b0f2964bf251e0014b Author: Mohammed Junaid Ahmed Date: Tue Nov 2 05:29:05 2010 +0000 Throwing an error while mounting glusterfs when fuse is not installed. Signed-off-by: Junaid Signed-off-by: Anand V. Avati BUG: 2002 (Mount fails, but gives no error) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2002 commit 0fbf226cdeb970f4b5829f92c6d27523f3ef4f04 Author: Kaushik BV Date: Wed Nov 3 05:29:49 2010 +0000 mgmt/Glusterd: add nfs.enable-ino32 as an option to set from CLI Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1972 (xcs get doesn't work with gNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1972 commit ba1d55c083a39f56077305037de0b619316b2717 Author: shishir gowda Date: Wed Nov 3 02:13:31 2010 +0000 Fix DHT getxattr for directories When a heal on the directory or layout changes, the user xattrs do not get healed in dht. The current fix sends the getxattr call n all the subvolumes, aggregates it and sends the response Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1991 (distribute directory self-heal does not copy user extended attributes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1991 commit 8ca96737a92a032334b745ffb6f4b872b8359fb0 Author: shishir gowda Date: Tue Nov 2 04:05:07 2010 +0000 Cli memory leak fix for tmp_list in cli_cmd_volume_add_brick_parse Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2047 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2047 commit c4ef206dd37a9e6c547caae5bf10b19d336dde8d Author: Raghavendra Bhat Date: Tue Nov 2 00:45:27 2010 +0000 use uuid_copy instead of memcpy Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 0fe40b1f74a4b070ce2e8928adab52524b86e273 Author: shishir gowda Date: Tue Nov 2 01:39:00 2010 +0000 Fix crash while freeing tmp_list in cli_cmd_volume_create_parse Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 2047 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2047 commit 33ce70b6fb7f3e268bcb166477c1e79e19b48a11 Author: Vijay Bellur Date: Tue Nov 2 01:27:56 2010 +0000 socket: avoid check on lowlat for enabling nodelay Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2040 (Using 'du' and 'ls' command, it got slow performance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2040 commit de001e8659d78dd16ba8515228c70fd2986e56df Author: Vijay Bellur Date: Sat Oct 30 13:09:08 2010 +0000 cli: Fix memory leaks Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 1198 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1198 commit 961d5fb6025f4901d63be8cfc8062bd8e2093021 Author: Vijay Bellur Date: Sat Oct 30 12:11:36 2010 +0000 mgmt/glusterd: Honor log filename set during add-brick Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2042 (No volume log files found in the specified directory for the newly added bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2042 commit 586000144be8919a234939ad43b04394d5f2636e Author: Pavan Sondur Date: Fri Oct 29 07:03:38 2010 +0000 mgmt/glusterd: Start nfs before killing source brick in replace brick commit. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Anand V. Avati BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 1b4613936e2d176df8e5a8548af2d59116bd9531 Author: Raghavendra Bhat Date: Fri Oct 29 07:23:54 2010 +0000 copy the gfid of root to the iatt structure of root Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit c65be2d304c67e57447d6d4a2e53fae07e31ff5c Author: Shehjar Tikoo Date: Fri Oct 29 05:38:13 2010 +0000 nfs: Introduce nfs.enable-ino32 to support legacy 32-bit only apps Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1972 (xcs get doesn't work with gNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1972 commit 413b2a5f9b77fd3d7f3b26c848482ec7b914102f Author: Anand Avati Date: Fri Oct 29 04:32:18 2010 +0000 protocol/client: add check for changed gfids to fail revalidates Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit ffbe9470cd189b7921509c08c9b2d308b8ac390e Author: Raghavendra G Date: Fri Oct 29 03:13:22 2010 +0000 rpc-transport: fix race-condition between rdma-read completion and updating the count of number of vectors to be passed to rpc. - If rdma read completes before incrementing the vector count, the count value sent to rpc will be improper. For fops like write, this may result in missing out a vector to be written, thereby causing data corruption. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1877 (data corruption while running arequal.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1877 commit 9c29312628af743f16badb4bc820cbd31f2a9488 Author: Pranith K Date: Fri Oct 29 03:39:56 2010 +0000 cli,mgmt/glusterd: fsm log implementation Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1966 (Unnecessarily verbose logs at the default log level) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1966 commit c1b80f0f590e2d7448b890b57e80f4a1b2e39a03 Author: Anand V. Avati Date: Fri Oct 29 03:32:44 2010 -0700 Revert "rpc-transport/rdma: create request_context only if message contains read chunks or write chunks." This reverts commit b66f4598f4dafb6479232b20c5c521ab0da4e84a. commit 8ea6882c424afd3f18ad1273ec31d34f5d74e47e Author: Raghavendra Bhat Date: Thu Oct 28 07:02:44 2010 +0000 script for testing glusterd sanity Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1436 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1436 commit d654c29d20f24802e6c5aa24a9206377428b9359 Author: Vijay Bellur Date: Thu Oct 28 13:15:54 2010 +0000 performance/quick-read: white space cleanup Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2027 (Updates not happening with replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2027 commit 82ad7b3be8478628ef448c97a702f4c6f1298329 Author: Vijay Bellur Date: Thu Oct 28 13:15:26 2010 +0000 performance/quick-read: set right validation checks Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 2027 (Updates not happening with replication) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2027 commit d615015ef4707d0df476547cbf7b6f83a29d804b Author: Anand Avati Date: Thu Oct 28 00:52:50 2010 +0000 replicate: attempt re-open of files before performing openfd selfheal in cases where subvolume state gets swapped between open and write opening file on the remaining subvolumes is necessary before attempting a self-heal. previously files were opened after self heal. Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 918 (AFR write fails when subvolumes' state is swapped) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918 commit 00b0a53bae2a5e39f197359581a3850a32970e54 Author: Anand Avati Date: Thu Oct 28 00:52:30 2010 +0000 replicate: fix hang/missing frame during locking nonblocking style locking would result in a missing frame when all subvolumes are down or when no subvolume on which fd was opened is up. Check for this condition and unlock gracefully Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati BUG: 918 (AFR write fails when subvolumes' state is swapped) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918 commit 87c0e8fba2d0be4496ec4085136fca459f62c00c Author: shishir gowda Date: Wed Oct 27 23:57:55 2010 +0000 Solaris build fixes: Patch for 64bit build This will fix build failures when -m64 option is used to build gluster Signed-off-by: Super-User Signed-off-by: Anand V. Avati BUG: 1990 (Gluster mainline build on solaris fails with errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1990 commit e93b270e8d09fc9d36a39b22987d3a172197e73b Author: Pranith K Date: Wed Oct 27 10:33:23 2010 +0000 cli: gluster --version implementation Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2006 (Add gluster version command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2006 commit b2f195720b27d9e69f7b851478515781e5786469 Author: Vijay Bellur Date: Wed Oct 27 05:36:32 2010 +0000 socket: Reduce keepalive idle and interval time Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 1956 (NFS client hangs after failover) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1956 commit 6ac081eccaa4f034874aa6687d87fb8b30207ebf Author: shishir gowda Date: Fri Oct 8 01:49:25 2010 +0000 Remove libglusterfsclient option from gld-dm benchmarking tool Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 968 (gluster client encountered out of memory very quickly when running glfs-bm) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=968 commit 7efad96683f605d5a0eb21b0377a6e14b89cd910 Author: Pranith K Date: Wed Oct 27 05:10:19 2010 +0000 mgmt/glusterd: update brick-count as soon as it is added in add-brick Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 2023 (add-brick fails in regression) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2023 commit 0e1bead7b77adab9115b2af977bc78273a34a70d Author: Pranith K Date: Wed Oct 27 04:55:03 2010 +0000 mgmt/glusterd: glusterd_is_local_addr implementation Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1855 (Initial server in a cluster not a friend) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1855 commit e4a43cf475f5a2d908cffdb518028ba74dc9f8b1 Author: Amar Tumballi Date: Thu Oct 21 04:51:47 2010 +0000 added a test script to test rpc procedures Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 1bafcd847a2bdaea7aebdb212bbb480eaeee7ede Author: Csaba Henk Date: Wed Oct 27 04:33:15 2010 +0000 libglusterfs: fix buffer overflow in gf_string2int() Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 2022 (gf_string2int() overflows target pointer) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2022 commit 38c91384861f29f97c3f564a36ee799f1eb57cc1 Author: Vijay Bellur Date: Wed Oct 27 03:07:29 2010 +0000 mgmt/glusterd: Unlock upon a cli request failure Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 1873 (Stop volume gluster command execution failed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1873 commit c02cd37866ae22e3a433d737f3c80395bb72f002 Author: Amar Tumballi Date: Wed Oct 6 05:23:44 2010 +0000 distribute: bring in statfs normalization We had normalization of statvfs structure in 'cluster/unify' translator, with distribute, we had this section as 'TODO:'. Now, the same code is migrated to distribute. Thanks to for sending the patches Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1035 (The distribute translator does not handle differently sized block sizes and/or fragment sizes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1035 commit 40dd9e9e18c5de009baf9e437d3222fa6b473237 Author: Raghavendra Bhat Date: Sat Oct 9 07:34:52 2010 +0000 log locate should check if the export directory is valid Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1871 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1871 commit 78bccc25b7c1b54c46c6aab9e34c7c455486d1fd Author: Csaba Henk Date: Fri Oct 8 07:36:55 2010 +0000 fuse: retire the faked-FLUSH-upon-RELEASE hack Now the code has lived up to the glorious state of not relying on getting the FLUSH whenever a file is released. So we don't need to forge one in release for the cases when the kernel doesn't send it. Undo commits: - 155ffe5c - c50bc710 - b8779318 (partly, just release related parts) Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 223 (flush not sent) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=223 commit a7d41a64fb11451e622db19813738c3ee3942c92 Author: Raghavendra Bhat Date: Tue Oct 26 05:20:34 2010 +0000 report the error if a volume not in the started state is tried to be stopped Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 2010 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2010 commit a53d14d5f5be431279c5e56963b495bf164cf453 Author: Csaba Henk Date: Tue Oct 26 04:00:30 2010 +0000 volgen: macro cleanup Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit db94ed06a688fb596aba4deafdf59a5af2fd6bbe Author: Csaba Henk Date: Tue Oct 26 04:00:29 2010 +0000 libglusterfs, glusterfsd: add shortname resolution + optname hinting support to VOLUME SET Trie code used for hinting is contributed by Avati. Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 9f14b0a0ef26b6d41b61222dcf34fe7cdf46cb46 Author: Csaba Henk Date: Tue Oct 26 04:00:28 2010 +0000 libglusterfs: fix graph mem types Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 3b70ff915a7451911dd35733171b97d7073df2c4 Author: Pavan Vilas Sondur Date: Tue Oct 26 03:58:59 2010 +0000 glusterd-volgen: Fix division by zero clang warning. Also clean up surrounding calculations a little bit. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Csaba Henk Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1089 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1089 commit 1a2463cefac2cd9faf80ce7041b2fa1d9cfff36c Author: Shehjar Tikoo Date: Tue Oct 26 06:39:08 2010 +0000 nfs3: Translate ENOTCONN into IO error for client Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1923 (Unknown error 526 when one of the subvolumes for distribute is down) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1923 commit 29dc176fa7832699b34a3a3e2f1a5f14ae55274a Author: Shehjar Tikoo Date: Tue Oct 26 06:39:07 2010 +0000 nfs-rpc: Fix log message for unsupported program Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1973 (Unnecessary log message "RPC program not available") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1973 commit bd890a0f53142e60e70e6cad8363738d607fbdb4 Author: Shehjar Tikoo Date: Tue Oct 26 06:39:06 2010 +0000 core: Use lru_limit as count for inode and dentry mempool Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1948 (For each subvolume started, glusterfs process takes up around 30-35MB more memory) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1948 commit c9c411b48aa0477cd44c18cbdf83d14389d27221 Author: noah williamsson Date: Mon Sep 27 07:47:11 2010 +0000 OS X: fnctl() flag FNM_EXTMATCH is not supported under Mac OS X Signed-off-by: Noah Williamsson Signed-off-by: Anand V. Avati BUG: 361 (GlusterFS 3.0 should work on Mac OS/X) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=361 commit 7ca61c1082b6c7554ea7b615ca3f2d3c8ab4b090 Author: noah williamsson Date: Mon Sep 27 07:47:10 2010 +0000 OS X: Include rpc/types.h Signed-off-by: Noah Williamsson Signed-off-by: Anand V. Avati BUG: 361 (GlusterFS 3.0 should work on Mac OS/X) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=361 commit d6a34a08d5a583c4f0f2264511286ed39a071e1b Author: noah williamsson Date: Mon Sep 27 07:43:49 2010 +0000 Correct enum declaration of gf_dump_procnum, fixing duplicate symbol error when linking on Mac OS X Signed-off-by: Noah Williamsson Signed-off-by: Anand V. Avati BUG: 361 (GlusterFS 3.0 should work on Mac OS/X) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=361 commit 9272cce5feb55c6526078f2d1440bb0d0591d651 Author: Csaba Henk Date: Tue Oct 26 03:56:32 2010 +0000 fuse: "terminating upon EBADF" log message is confusing, set its level to DEBUG Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1887 (logging mess) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1887 commit 81e718ab513e2cdf1b1e22b268c5798752d79cc1 Author: Csaba Henk Date: Sat Oct 9 15:46:40 2010 +0000 server: parse more precisely when validating auth options Signed-off-by: Csaba Henk Signed-off-by: Anand V. Avati BUG: 1885 (auth validator in server parses too sloppily) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1885 commit b66f4598f4dafb6479232b20c5c521ab0da4e84a Author: Raghavendra G Date: Sun Oct 24 23:44:34 2010 +0000 rpc-transport/rdma: create request_context only if message contains read chunks or write chunks. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1992 (glusterd crashed while submitting a callback.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1992 commit 7c479d61681d3ddb7fcc325752384eac89ae809d Author: Amar Tumballi Date: Thu Oct 21 02:25:49 2010 +0000 rpcsvc: handle NULL deref in case of program mismatch Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1982 (rpc: crash on progver mismatch) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1982 commit 93de6e1f8106220d1c41f2ca9fdc207c76dd0560 Author: Raghavendra Bhat Date: Thu Oct 14 05:56:53 2010 +0000 NULL checks in the fops of io-cache Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1757 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1757 commit 29377452062b07b6487105ebe65a717898e19e2a Author: Amar Tumballi Date: Thu Oct 14 05:12:12 2010 +0000 io-stats: handle the case of 'cleanup_and_exit()' properly Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 1933 (Segfault while expansion of volume from distributed mirror) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1933 commit 0d11145c0c2a9bac61398bff2fbab14820f0764a Author: Mohammed Junaid Date: Thu Oct 14 04:14:47 2010 +0000 takes either 'y' or 'yes' and 'n' or 'no' for stop volume, delete volume and remove-brick Signed-off-by: Mohammed Junaid Signed-off-by: Anand V. Avati BUG: 1942 (cli: loose parsing of confirmation answer) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1942 commit 2ec661c0729370f0acd966fab0ae644f7e62bd71 Author: Vijay Bellur Date: Wed Oct 13 04:09:15 2010 +0000 extras: Do not check_config() for glusterd in Debian init Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 681bfd7ff32202314a5cdf8a8e13478c6c45acdb Author: Raghavendra G Date: Wed Oct 13 01:38:20 2010 +0000 server: Don't free conf in fini. - This will fix race condition between handling DISCONNECT event and doing fini. Though conf need to be freed, this will be done in future where finis of all translators are properly implemented to make sure no corruptions. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1758 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1758 commit a8212606e23312fabd5c2068ade05efacae9c086 Author: Raghavendra G Date: Tue Oct 12 04:13:19 2010 +0000 rpc-transport/rdma: associate mem-pools with device instead of transport. - this will help to reduce memory usage of glusterfs process. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513 commit 959f051b0c39f114d54b5bb303dd2241603d7607 Author: Vijay Bellur Date: Wed Oct 13 03:05:09 2010 +0000 Correct location of git repository Signed-off-by: Vijay Bellur Signed-off-by: Anand V. Avati BUG: 1941 (wrong git url) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1941 commit 5ca019f339d76187f26757222084319cd1b28ad6 Author: shishir gowda Date: Tue Oct 19 03:02:10 2010 +0000 Propogate rebalance already started error to cli Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1882 (starting rebalance while previous rebalance is still running) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1882 commit 54219ecf2ad344a55e974ff4b86a02408c9c17f2 Author: Raghavendra G Date: Mon Oct 25 00:11:51 2010 +0000 xlator.c/option-validation: change the log level to warning when given value is out of range. Signed-off-by: Raghavendra G Signed-off-by: Anand V. Avati BUG: 1214 (When cache-size is given out of range, error is logged but GlusterFS starts) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1214 commit 1e1f97a89cdd454bcfbf158ae7520932bacb1aa1 Author: Amar Tumballi Date: Thu Oct 14 02:34:31 2010 +0000 client: move reopen{,dir} code to handshake file and minor log level changes Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 44b27f7ec27173c5d12c12aa3947cc1f409d8c1f Author: Amar Tumballi Date: Thu Oct 14 02:34:01 2010 +0000 client: decrement the 'openfd' count in case of opendir_cbk too Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 14d2ed37a966a10d8553e8b5a5283d35f9addc7e Author: Amar Tumballi Date: Mon Oct 18 04:22:47 2010 +0000 server: print information about disconnected client Signed-off-by: Amar Tumballi Signed-off-by: Anand V. Avati BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 41b14258c08a0065c573a2ec9f39fb3354fd9be3 Author: Kaushik BV Date: Mon Oct 18 05:02:11 2010 +0000 debug/io-stats: init() should also set loglevel Signed-off-by: Kaushik BV Signed-off-by: Anand V. Avati BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit cfad660310978ffda6263d44ab2445d42c2621b2 Author: shishir gowda Date: Mon Oct 18 08:15:30 2010 +0000 Log level mess clean up Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1886 (log-level mess) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1886 commit f014877f37488d6f9d4c505f0675ad45cd770546 Author: shishir gowda Date: Tue Oct 19 07:50:05 2010 +0000 Remove additional failure cli msg for peer detach Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1955 (Redundant log messages when "peer detach" fails) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1955 commit a9187b9609dacb017aff171c317cd5332ef64bd5 Author: Pranith K Date: Wed Oct 20 01:20:59 2010 +0000 mgmt/glusterd: resolve the bricks before comparing uuid Signed-off-by: Pranith Kumar K Signed-off-by: Anand V. Avati BUG: 1985 (peer detach fails if bricks are not resolved) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1985 commit db61075a123008ebd94ab8ff00b984e484155654 Author: shishir gowda Date: Thu Oct 21 03:38:30 2010 +0000 Solaris build: Fix linux only features Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1990 (Gluster mainline build on solaris fails with errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1990 commit cd9a247906924106c722ecf4611b7be4b5408ad9 Author: shishir gowda Date: Thu Oct 21 03:37:52 2010 +0000 Solaris build: Handle namespace clash for rpc-clnt.h Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1990 (Gluster mainline build on solaris fails with errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1990 commit f3737b2ee75bda6cd05744f2fbd13cb92ecab655 Author: shishir gowda Date: Thu Oct 21 03:37:27 2010 +0000 Solaris build: Remove sigtimewaitd This part of code was stale as a result of fixes for volume start force changes. Removing the unwanted code Signed-off-by: shishir gowda Signed-off-by: Anand V. Avati BUG: 1990 (Gluster mainline build on solaris fails with errors) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1990 commit 559055ebfebe8d58c8607c521661c1f1c1d3a2d5 Author: Shehjar Tikoo Date: Thu Oct 21 04:06:49 2010 +0000 nfs3: Correctly funge solaris root lookup FH for DVM Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1997 (Solaris mount fails with "RPC program not registered") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1997 commit 46b7ce29e1b300044e03841a1a70325f190416c1 Author: Shehjar Tikoo Date: Thu Oct 21 04:06:48 2010 +0000 nfs: Fix volume-id option declaration Signed-off-by: Shehjar Tikoo Signed-off-by: Anand V. Avati BUG: 1972 (xcs get doesn't work with gNFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1972 commit 8ce807dd811e32b704a7beec1bbbcbb2625a7219 Author: Raghavendra Bhat Date: Thu Oct 21 04:33:44 2010 +0000 do not hardcode the replace brick remote port to 34034 Signed-off-by: Raghavendra Bhat Signed-off-by: Anand V. Avati BUG: 1998 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1998 commit 51ddf878b1d74369434c6b95b49a76bce32fd4b1 Author: Amar Tumballi Date: Wed Oct 13 00:12:49 2010 +0000 glusterd-rebalance: if file is open, don't do rebalance Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1934 (Server segfault with 3.1 platform ISO during volume expansion) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1934 commit e788e2dec0c90c77a88b561636df569d94c8e638 Author: Vijay Bellur Date: Tue Oct 19 06:20:24 2010 -0700 Revert "glusterd-rebalance: if file is open, don't do rebalance" This reverts commit 6e6b4b4fd002347ca08691f73e10b961f693d754. commit 6e6b4b4fd002347ca08691f73e10b961f693d754 Author: Amar Tumballi Date: Tue Oct 12 04:09:35 2010 +0000 glusterd-rebalance: if file is open, don't do rebalance Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit b9d6e0c879feb9d86cdadf4072a7ebeb5eb29798 Author: Raghavendra G Date: Tue Oct 12 03:54:31 2010 +0000 rpc-transport/socket: initialize fragcurrent pointer in correct state while reading vectored replies. - If fragcurrent is initialized in the same state which reads payload data, there is a possibility of it getting reset during partial reads from socket. Hence it should be initialized just before entering the state which reads payload data. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1929 (different value is logged for read header size for multiple reads) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1929 commit a6304aec8c366ad7853f95348aa6c73a0b873678 Author: Pranith K Date: Tue Oct 12 03:08:46 2010 +0000 mgmt/glusterd: create brick path if does not exist Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 9bad9d59f0f19fe20f90c6ed80e25c7db08b3371 Author: Vijay Bellur Date: Tue Oct 12 03:06:30 2010 +0000 Change assert to GF_ASSERT Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit f637330995eab92a1d0b9f4ad9c43acfaad35037 Author: Raghavendra G Date: Tue Oct 12 02:21:16 2010 +0000 rpcsvc: calculate dump response length instead of hard coding it. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 15c9f6789fe41afdda12052c9ce6d538e0c2f5e6 Author: Raghavendra G Date: Tue Oct 12 02:26:34 2010 +0000 rpc-transport/rdma: by default use infiniband port 1 Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513 commit ed4975b13db3220d461b8ea2a764efd6572e156a Author: Anand Avati Date: Tue Oct 12 02:25:46 2010 +0000 nfs: avoid assignment of structure pointer into serialized buffer With the introduction of variable sized file handle feature in NFS, on-wire lengths of file handles can be lesser than file handle structure of code. Direct pointer assignment into the offsetted buffer and dereference and result in reads beyond the end of buffer and crashes. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 999 (Crash in nfs3_fh_resolve_and_resume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=999 commit 48672d26a01f3ce443479b19820e2822a6c650f6 Author: Raghavendra Bhat Date: Fri Oct 8 00:25:30 2010 +0000 check if fd is NULL before accessing it in fuse_open_resume Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1858 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1858 commit fab78b45f7e99ea2e41a4ef3603a56e9eac5b776 Author: Harshavardhana Date: Fri Oct 8 17:43:36 2010 +0000 Add mount.glusterfs to fuse since its only needed for native client Signed-off-by: Harshavardhana Signed-off-by: Vijay Bellur BUG: 1770 (Cleanup rpmbuild) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1770 commit 161850285ff06e90f2c990989bab9513dd4a4289 Author: Anand Avati Date: Tue Oct 12 01:22:28 2010 +0000 nfs: re-implement logic to perform fresh lookups when lookup revalidates fail - implement lookup to pass via inode layer so that looked up entries make it to inode cache - implement lookup revalidation failure check in the fop layer Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit efa94a4237bc98c629671e6fbb58948789604fe5 Author: Anand Avati Date: Tue Oct 12 01:22:11 2010 +0000 Revert "nfs3: Revalidate inode on receiving ESTALE on lookup" This reverts commit f5afcc47f9f00472d6c2b3f48127e02332cd457a. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit c3b6df1a8e27c66a5c17cc1d6a92fdc37354ae6f Author: Anand Avati Date: Tue Oct 12 01:21:51 2010 +0000 protocol/client: prevent propagation of CHILD_DOWN after pmap query pmap query results in a new port to which the rpc client reconnects. This involves disconnection of current connection to pmap which was propagating CHILD_DOWN upwards prematurely Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 91580140b3df01838c5c5a6dac301efb87c4bd93 Author: Anand Avati Date: Tue Oct 12 01:21:32 2010 +0000 protocol/server: be consistent in setting rsp.dict_len and rsp.dict in cases where op_ret was -1 and dict was not NULL, the code was setting a dictionary length but not the serialized dictionary. This would cause crashes in the xdr serialization function Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 2478d21c8d7c0e4d66990f7da7323f2c750a9d82 Author: Raghavendra Bhat Date: Mon Oct 11 15:17:18 2010 +0000 unwind if layout is NULL in getxattr for dht Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1917 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1917 commit f182151cf338cad36d1d503f33b65ca40785b797 Author: Vijay Bellur Date: Mon Oct 11 12:32:04 2010 -0700 Revert "nfs: re-implement logic to perform fresh lookups when lookup revalidates fail" This reverts commit 563ef3d12f8d7a927b403d04c279d9fc702faad0. commit 61308de7645f1df462bef50e9c22237899218c65 Author: Vijay Bellur Date: Mon Oct 11 12:31:26 2010 -0700 Revert "Revert "nfs3: Revalidate inode on receiving ESTALE on lookup"" This reverts commit 6dd3b7fa3bc7acf9281cc17f08010675e2297089. commit d31e97336aac057510203f0942856b66baf4a91b Author: Kaushik BV Date: Mon Oct 11 12:13:51 2010 +0000 mgmt/Glusterd: fixes in volume reset Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 27c8b7a36972db1a80d51764f9dfc6d3deb10a80 Author: Vijay Bellur Date: Mon Oct 11 09:13:27 2010 +0000 Remove references to COPYING.* files Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit d6978803395fb1d1635dd454894e26d9feb806d9 Author: Anand Avati Date: Mon Oct 11 07:30:55 2010 +0000 dht: change behaviour CHILD_UP/DOWN/CONNECTING event propagation The first CHILD_UP/DOWN/CONNECTING event to pass dht upwards should be only after all subvols have reported their status atleast once. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit 4868116c1ca08868abe69c271dc108f1d0b5a227 Author: Anand Avati Date: Mon Oct 11 07:30:30 2010 +0000 Revert "distribute: Propagate CHILD-UP when all subvols are up" This reverts commit 6b2e2fb0903fc56105c267881f202a4865a8b6c7. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit 563ef3d12f8d7a927b403d04c279d9fc702faad0 Author: Anand Avati Date: Mon Oct 11 06:43:35 2010 +0000 nfs: re-implement logic to perform fresh lookups when lookup revalidates fail - implement lookup to pass via inode layer so that looked up entries make it to inode cache - implement lookup revalidation failure check in the fop layer Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 6dd3b7fa3bc7acf9281cc17f08010675e2297089 Author: Anand Avati Date: Mon Oct 11 06:42:39 2010 +0000 Revert "nfs3: Revalidate inode on receiving ESTALE on lookup" This reverts commit f5afcc47f9f00472d6c2b3f48127e02332cd457a. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit bf68324270f7e15f140ccb74ab355f8179cce92f Author: Pranith K Date: Mon Oct 11 06:42:32 2010 +0000 Set correct logging level for log messages Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1887 (logging mess) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1887 commit 47a87215e30d3ea2dc6ec9ae178f5a9e3eae9e96 Author: Raghavendra G Date: Mon Oct 11 06:03:40 2010 +0000 features/locks: free fdctx in release. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1438 (memory leaks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438 commit 2854c559340d33473750fac65aace58506951276 Author: Vijay Bellur Date: Mon Oct 11 08:38:19 2010 +0000 Copyright changes Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 5d4800fa35d3a9ca08175fe2bbdd78c2b0b5e184 Author: Vijay Bellur Date: Mon Oct 11 06:18:07 2010 +0000 Do graph init after topology change Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit ab42cb8d75985e33fb27e9fc5da0bc37c1024804 Author: Amar Tumballi Date: Mon Oct 11 00:04:57 2010 +0000 fuse_loc_fill(): handle a case of NULL dereference Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1889 (gluster FUSE client crashes on irregularity) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1889 commit 74dabe95193a0bc76c3ba149431a9110149a8e9e Author: Raghavendra Bhat Date: Mon Oct 11 04:28:30 2010 +0000 get the remote-host option from the dictionary in reconfigure Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1898 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1898 commit 81b6fa2b813d6913dd6329ef6a463669d282ebb6 Author: shishir gowda Date: Mon Oct 11 03:49:45 2010 +0000 Add log-level validation for volume set command Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1886 (log-level mess) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1886 commit 3dc782527482d2c62c9344669ccaa2dc42481a58 Author: Pranith K Date: Mon Oct 11 03:26:00 2010 +0000 mgmt/glusterd: handle reqs from unknown peers for friend sm Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1838 (handle peer detach gracefully in case of lost frames) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1838 commit eb99bee0246d5a43bbee7383b3809a360aa70018 Author: shishir gowda Date: Mon Oct 11 02:23:18 2010 +0000 Add confirmation to volume delete command Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 2eb9861cbc0387b1054bfeb7864c255a42b475f5 Author: Kaushik BV Date: Sat Oct 9 06:58:00 2010 +0000 mgmt/Glusterd: Memory leak fixes, minor CLI changes Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1852 (Usage message of volume set printed twice) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1852 commit afb6997fe74af257c7e687e33fe88a292f7a4a00 Author: Csaba Henk Date: Fri Oct 8 09:52:52 2010 +0000 io-stats, volgen: make the distinction between client and brick loglevel in volgen's scope Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1789 (add log-level options to volume set) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1789 commit d1f938c16e309431382ab9aaa32d50bf0ccd3260 Author: Raghavendra G Date: Fri Oct 8 20:21:59 2010 +0000 rpc-transport/rdma: fix the bug which was causing an ioq-entry being mem_put twice. - in case of failure to send message, ioq-entry would be freed, but it used to get added to the ioq-list. Failure in sending a message (for reasons other than insufficient quota), would result in transport being disconnected. In the process of handling pollerr, when ioq-list is flushed, the same ioq-entry which would've already been freed, would be freed for second time. - this patch also fixes spurious disconnects happening when quota was not available while sending a request. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1854 (GlusterFS 3.1 beta crashes over Infiniband with rdma issue) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1854 commit 0ccb63dbc52f66975205baf8452d2b57418da4aa Author: Raghavendra Bhat Date: Sat Oct 9 07:41:14 2010 +0000 set keepalive for client connections Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1802 (Gluster volume creation failed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1802 commit 13f1fff6da4b2b9ee30f43346cb382abfc1bc304 Author: Kaushik BV Date: Fri Oct 8 10:34:18 2010 +0000 mgmt/Glusterd : Volume info fixes Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1872 (gluster volume info is not working with qa42-) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1872 commit e0cdcbf68ab1dc1cc1af874cd84579d89a3e3747 Author: Amar Tumballi Date: Fri Oct 8 10:17:55 2010 +0000 rpc-clnt: do rpc_transport_destroy() in rpc_clnt_destroy() handles the case of peer detach properly Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit cd5c9df4b67073089a5502d5e4c2e2e7d2141e4a Author: Pavan Sondur Date: Fri Oct 8 07:06:57 2010 +0000 mgmt/glusterd: Fix replace brick to pass src-brick and dst-brick port nos properly. Fix also contains patch from shishir ng for maintaining replace-brick states in glusterd. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 09914c02f24b4cc74cb6aad9994ae590cf8b76bf Author: Raghavendra G Date: Fri Oct 8 07:01:42 2010 +0000 rpc/clnt: allocate a new cbk_program before registering it. - Refer Bug 1836 for more details. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1862 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1862 commit 2e43696eb90dc835d0aa8000e19b6f207760309c Author: Amar Tumballi Date: Fri Oct 8 06:58:51 2010 +0000 migrate from port 69* to 24007 Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1870 (Change the port from 69* to some other ports.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1870 commit 98e1ea0f178bdb8d26037edda9aae7bc2339bac4 Author: shishir gowda Date: Thu Oct 7 03:20:59 2010 +0000 Possible race condition between cleanup and dereferencing Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1760 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1760 commit d4b0360c8c4c5dab692f827972ccea0e728af688 Author: Pranith K Date: Fri Oct 8 01:37:54 2010 +0000 mgmt/glusterd: memory leak fixes Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit ce616c5fa08722044ee311f5f6c7c4e3ccb684c4 Author: Pranith K Date: Fri Oct 8 00:19:17 2010 +0000 mgmt/glusterd: print state, event names for numbers in friend sm Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1847 (print event names, state names instead of numbers for FSMs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1847 commit 99b04920189df06cfd8704a773c51cdb995b7ae0 Author: Vijay Bellur Date: Fri Oct 8 04:54:36 2010 +0000 support for configuring keepalive idle time Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1802 (Gluster volume creation failed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1802 commit 95d595d9cbe727401021cf1caf0d59b3ab12d454 Author: Pranith K Date: Thu Oct 7 10:15:18 2010 +0000 mgmt/glusterd: Always kill nfs with SIGKILL Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1853 (kill nfs process with SIGKILL while restarting) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1853 commit e7178b0646d1542faea6d6acab0291ca0d176b35 Author: Kaushik BV Date: Thu Oct 7 07:26:14 2010 +0000 Glusterfsd Crash in server_link_cbk Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit c7b518ab85f6fbcbdbae64c8fa092e998a14d1e9 Author: Kaushik BV Date: Thu Oct 7 06:37:12 2010 +0000 mgmt/Glusterd: Volume set enhancements - performance.flush-behind, transport.keepalive added - volume info to display the options reconfigured Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit f62484f42230db9d240c9b0eaadac48d845053b1 Author: Pranith K Date: Thu Oct 7 04:41:28 2010 +0000 mgmt/glusterd: Change event, state numbers to names for op-sm Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1847 (print event names, state names instead of numbers for FSMs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1847 commit 5979bc3b964adcb8a536dc354e4eca08acaff03e Author: Amar Tumballi Date: Thu Oct 7 05:56:22 2010 +0000 protocol/rpc/transport: bring in one more event for 'TRANSPORT-DESTROY' needed because, a RPC disconnect doesn't mean that a RPC transport/listener is dead. With this, the race in server protocol cleaning up the lock table / fd table when some frames are in transit will be handled properly. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1843 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1843 commit 3c0a7fb86eef1eecada77a6f040f96e1fd9e0536 Author: Shehjar Tikoo Date: Thu Oct 7 05:50:53 2010 +0000 nfs3: Fix gfid to ino conversion Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1724 (kernel untar fails during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1724 commit 58ce5f46af7e08db3d786c597ec5144294fbd099 Author: Shehjar Tikoo Date: Thu Oct 7 05:23:59 2010 +0000 nfs: Revert downed-subvolume changes For the record these are the patches committed as: 1. "nfs, nfs3: Base volume access on CHILD-UP-DOWN event" http://git.gluster.com/?p=glusterfs.git;a=commit;h=f47b0c55de9941823fbefe4b3a7e37179d6d4329 2. "nfs: Fix multiple subvolume CHILD-UP support" http://git.gluster.com/?p=glusterfs.git;a=commit;h=336e2df7b74be7ad4c9ed403ca10b9f7f7ef9a58 3. "nfs,nfs3: Disable subvolume on ENOTCONN" http://git.gluster.com/?p=glusterfs.git;a=commit;h=8c6e27cdaf895e3031c3256efb9472a6c0bf61f3 Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1724 (kernel untar fails during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1724 commit 32b62dd42fc479d19211a3c223b665d28d2207f2 Author: Anand Avati Date: Thu Oct 7 05:58:06 2010 +0000 lock recovery: temporarily disable lock healing Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 0c0c82729b947256beefcd3999d230302faef1fd Author: Raghavendra G Date: Wed Oct 6 08:00:18 2010 +0000 rpcsvc: allocate a new program structure before registering it. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1836 (server is hung in infinite loop while trying to search for an actor during request processing) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1836 commit 96155f065e229f6123cc90b9ca37df9cbd7598c7 Author: Amar Tumballi Date: Wed Oct 6 04:44:14 2010 +0000 transport: set 'trans->options' before calling 'trans->init()' Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 7c7cf68b798ac6ff1d4727c288cdcba15589e456 Author: Raghavendra Bhat Date: Wed Oct 6 07:32:07 2010 +0000 changes for the sanity script Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1436 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1436 commit 4880761284daf6da623322e1d3f7152486c5770f Author: Pranith K Date: Wed Oct 6 02:04:01 2010 +0000 mgmt/glusterd: set the return value in case of failure Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1823 (add-brick fails first time but works in next attempt) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1823 commit 05727129fd08e237d2b4f5daf4726438ebc6efb6 Author: Pranith K Date: Tue Oct 5 08:02:41 2010 +0000 mgmt/glusterd: dont access req after reply Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit ef13a1046f72c993b8e053e5fc5f671e9bd2579b Author: Amar Tumballi Date: Tue Oct 5 07:48:21 2010 +0000 cli: fix Number of bricks output Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1815 (gluster volume info - Number of Bricks field) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1815 commit 4c7ca7ec15760681703450dc9279a8c3cf8b98c0 Author: Pranith K Date: Tue Oct 5 07:34:45 2010 +0000 mgmt/glusterd: send volume options to friend Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1816 (send volume options in friend add) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1816 commit 6b74f3ec7b6e0fed2e253df456b067fc27049117 Author: Kaushik BV Date: Tue Oct 5 07:02:07 2010 +0000 Reply back to CLI on error, by validating each xlator's opts Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 7aec50bdad06665243a16f1ce83a03037bcd5d56 Author: Kaushik BV Date: Tue Oct 5 07:01:52 2010 +0000 mgmt/Glusterd : Reply to CLI error: graph construction Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 79db3aced2ffca84a696192343d5b811833eb671 Author: Pavan Sondur Date: Tue Oct 5 06:40:32 2010 +0000 features/locks: Handle lock upgrade and downgrade properly in locks. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1017 (Locking deadlock when upgrading lock) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1017 commit 99ac72b988f0ccd0bf876cf3e2326b8406f71461 Author: Anand Avati Date: Tue Oct 5 05:07:37 2010 +0000 replicate: use the new rmdir prototype for cleaner entry self-healing Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1761 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1761 commit f62ff8a8df7ab7c0c551b650f9bd2f1a87b8dc71 Author: Pavan Sondur Date: Tue Oct 5 04:48:27 2010 +0000 features/locks: cluster/afr: Misc fixes for lock recovery. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 79342c436fb994e6a41e3c7b69c962af37e8946a Author: Amar Tumballi Date: Tue Oct 5 03:50:06 2010 +0000 glusterfsd: '-f' option help update Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1809 (glusterd help text for -f is wrong) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1809 commit b5c5a7fa141e77a5d688647c753b2d59d6330f83 Author: Amar Tumballi Date: Tue Oct 5 03:49:39 2010 +0000 rpm spec file: add proper Obselete keys Thanks to Bernard Li Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1808 (Allow RPM upgrade from glusterfs 3.0.x to 3.1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1808 commit fe2777ccaff5d2660af65472962bbef8d10b1814 Author: Shehjar Tikoo Date: Tue Oct 5 01:58:46 2010 +0000 nfs3: Convert gfid to ino only for non-root Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1724 (kernel untar fails during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1724 commit 25c2e7e18a07f76a8e2168eb9c3d8f87c558069e Author: shishir gowda Date: Tue Oct 5 00:24:40 2010 +0000 Do not exit to shell after gluster help if readline mode is not enabled Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1709 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1709 commit 3f89342de32f214cdb9d641c402954ae9345af71 Author: Csaba Henk Date: Mon Oct 4 17:57:59 2010 +0000 volgen: add interface to complete option names from specifier (after-dot) part Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 6658fdde8f6e328e232d9d40067df8ae4b16e8b2 Author: Amar Tumballi Date: Mon Oct 4 22:15:57 2010 +0000 distribute: check for 'conf' before dereferencing it Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1806 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1806 commit 372ed08f25da2eb7e09f27685cb1773b88c62173 Author: Harshavardhana Date: Mon Oct 4 17:54:12 2010 +0000 init.d: Path not resolved during compilation to actual prefix Signed-off-by: Harshavardhana Signed-off-by: Vijay Bellur BUG: 1810 (qa 40 glusterd path is hardcoded, won't start by default.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1810 commit 2136876274690bc7377b97ca0ed812a6befafee2 Author: Amar Tumballi Date: Mon Oct 4 13:51:29 2010 +0000 glusterd: more sanity checks during restart * check for validity of pid file before doing pmap search, as in few cases, pmap_signin() may take more time. * remove stale code from 'init()' * update pmap->last_alloc during restore itself to handle glusterd restarts more agnostics to port collisions Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 0d31e7e4239d4765198ea6f46b98ba680038f7ad Author: Amar Tumballi Date: Mon Oct 4 13:28:00 2010 +0000 fuse: handle the case of NULL dereference Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1798 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1798 commit 4c28d069b5be71bb2136d85e7a9b9fe0d07e04a1 Author: Amar Tumballi Date: Mon Oct 4 13:27:43 2010 +0000 glusterd-volgen: fix the auth.allow/auth.reject keys Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1798 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1798 commit dc1113c4a02b1b1186bf37e09685631891d85537 Author: Pavan Sondur Date: Mon Oct 4 12:15:34 2010 +0000 cli: mgmt/glusterd: Add commit force op to replace-brick Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 841ee8d5021980d836c834792b581475b05b0e6b Author: Csaba Henk Date: Mon Oct 4 11:24:43 2010 +0000 volgen: revise option list for VOLUME SET Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit ca8615173f495a906520c3a1b238ed8266a932bf Author: Pranith K Date: Mon Oct 4 11:20:38 2010 +0000 mgmt/glusterd: dont change ret val in cmd handlers if fails Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit 846383acb963b9c74a386192bb5050a9366a8036 Author: Vijay Bellur Date: Mon Oct 4 11:19:23 2010 +0000 mgmt/glusterd: cleanup during detach Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1765 (peer probe on removed-detached bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1765 commit bde5cb81e251032594e2bba57fb4a72c10e32207 Author: Amar Tumballi Date: Mon Oct 4 11:01:14 2010 +0000 rpc: don't refer to 'req' after calling 'prog->actor()' there are chances that a error reply is sent to client from actor, in which case, 'req' would be free'd and accessing it would result in error. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1790 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1790 commit 98d51842863d52bab2674258c3ec12d668139539 Author: Raghavendra Bhat Date: Mon Oct 4 10:59:08 2010 +0000 initialize the list earlier while handling create volume and add brick Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit b6fea1abc756c31d93244263a654b56f2f8b7894 Author: Shehjar Tikoo Date: Mon Oct 4 10:06:08 2010 +0000 nfs3: Convert gfid into inode number ..avoids stale file handle errors at the client when client detects changing inode numbers from the server. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1724 (kernel untar fails during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1724 commit 8c6e27cdaf895e3031c3256efb9472a6c0bf61f3 Author: Shehjar Tikoo Date: Mon Oct 4 10:06:07 2010 +0000 nfs,nfs3: Disable subvolume on ENOTCONN ..so that nfs does not return an error to the client, instead the subvolume gets disabled till it comes back up again. The client is expected to keep retransmitting requests in the mean time. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1724 (kernel untar fails during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1724 commit 64609b65c2ffc34577b342dab12595b13a52d8a2 Author: Pranith K Date: Mon Oct 4 08:54:55 2010 +0000 mgmt/glusterd: added new brick validation functionality Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit 85c013f3accfc409c1a520d0ad529a2c1c16c653 Author: Pranith K Date: Mon Oct 4 08:44:11 2010 +0000 Change GNU GPL to GNU AGPL Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1388 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1388 commit 6a244f2e95b09603507782061ac08b7e0c28fd64 Author: Pavan Sondur Date: Mon Oct 4 08:18:19 2010 +0000 cluster/pump: mgmt/glusterd: Misc fixes for replace-brick Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 14d6a7023fc1abc985675e9ee3e5fee4cd519210 Author: Csaba Henk Date: Mon Oct 4 08:11:27 2010 +0000 implement volume level address allow/reject setting Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit ef0c7384299e6104a2d4a967847b8c9cea1e79b8 Author: Amar Tumballi Date: Mon Oct 4 08:02:29 2010 +0000 stat-prefetch: reduce the stat-prefetch mem-pool size because we are not calling 'fini()' on old graph, after every graph change, we are leaking lot of memory. Hence reduce the foot-print for now, bring in changes to call 'fini()' later. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit c2e93bf6e391657c23a16b6536f7976136c32ce5 Author: shishir gowda Date: Mon Oct 4 07:45:08 2010 +0000 Additional status check for rebalance in progress Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1791 (remove-brick during rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1791 commit 63281f698908897218bb6ca427e280217a4b38c2 Author: Amar Tumballi Date: Mon Oct 4 07:38:11 2010 +0000 /etc/init.d/glusterd (for RPM based distros), fix output format Thanks to Bernard Li for the patch Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1677 (Fix output formatting for Red Hat init script) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1677 commit f02499e16624f29ac2be5531f1c4c298a12f33a8 Author: shishir gowda Date: Mon Oct 4 06:47:35 2010 +0000 Add log-level option to command volume set log-level option to set brick's log-level client-log-level to set client's log-level Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1789 (add log-level options to volume set) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1789 commit 408c164d0adf67d0ab636d3f617fc48c896d33a6 Author: Amar Tumballi Date: Mon Oct 4 06:32:47 2010 +0000 cli: add more type for volumes Added 'Distributed-Replicate', 'Distributed-Stripe' as types Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit e2438fdde0458b70b0cd201b4950b676188d0824 Author: Harshavardhana Date: Mon Oct 4 04:50:53 2010 +0000 Some cleanup in rpm specification file Thanks to Bernard Li for rdma 'BuildRequires' fix Signed-off-by: Harshavardhana Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1770 (Cleanup rpmbuild) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1770 commit 2420fd1f0cc5c357776d3766884b86859f3c3781 Author: Pranith K Date: Mon Oct 4 02:50:55 2010 +0000 mgmt/glusterd: update volumes on friend update Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur commit ebc40051898881fa3d49946046448ee34e356338 Author: Pranith K Date: Mon Oct 4 02:17:09 2010 +0000 mgmt/glusterd: update volumes from friend Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1784 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1784 commit 73f8e094495a71f6a6a4c90495874396f2614567 Author: Anand Avati Date: Mon Oct 4 00:29:17 2010 +0000 rpcsvc: bump log level of message for missing transport type Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 6d9bcd67e99ad638ca260f04cff401e7d9ebe3c5 Author: Csaba Henk Date: Sun Oct 3 14:57:11 2010 +0000 volgen: impemlent dynamic (pattern-based) option matching So now auth.addr.*.allow can be a basic option, without any specific support code! Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 609a89ceace25a0a81d0a9cafde3a4d1afd1b916 Author: Kaushik BV Date: Sun Oct 3 02:41:29 2010 +0000 mgmt/Glusterd: new command volume reset , volume set enhancements - Write the reconfigured options in 'info' file to make it persistant - Implementation of volume set history - Implementation of volume reset Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 53b8c7470f9e40c60c5eebd1fbad5c6d274f7ee5 Author: Vijay Bellur Date: Sun Oct 3 04:14:19 2010 +0000 mgmt/glusterd: changes for detach everywhere Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1765 (peer probe on removed-detached bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1765 commit c0c419a3572307e71026144b8907a33b464f6066 Author: Csaba Henk Date: Sat Oct 2 18:44:16 2010 +0000 volgen: add a precise getter function which considers default values as well Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit ff7f17da9e1817c6d02da3e98163fce834b429f6 Author: Csaba Henk Date: Sat Oct 2 18:44:15 2010 +0000 volgen: add support for auth.addr.%s.{allow, reject} options Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit e463cb64d99cf741fabf9e46f7511554607e250e Author: Csaba Henk Date: Sat Oct 2 18:44:14 2010 +0000 volgen: fix up replace-brick + pump generation Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit a3bf2a40fbd0b1b7478e0fbf87dd5a1a9c42e5ab Author: Csaba Henk Date: Sat Oct 2 18:44:13 2010 +0000 volgen: some refactor to make frequent invocations more handy Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 99caede76b0ef312d622b2387bf9524724e7c6df Author: Anand V. Avati Date: Sat Oct 2 11:25:05 2010 +0000 rmdir: introduce extra flags parameter in FOP prototype Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 5a4e1e69b2ec65dcefa6b37b8ac7d058f3a2c29f Author: Anand V. Avati Date: Sat Oct 2 11:25:04 2010 +0000 xdr: introduce extra flag in rmdir request Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 77085451a88878728e703215f9bf871a74df92ba Author: Pavan Sondur Date: Sat Oct 2 08:29:38 2010 +0000 Set the lock owner properly for lock self heal. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 8d70c0dd0a9346d75469634777daa362ec8f89f6 Author: Pavan Sondur Date: Sat Oct 2 08:03:44 2010 +0000 cluster/pump: Do not do lookup if it is "." and ".." in pump. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 33d7a49bd55d6810d87811c109c7445e27b04c17 Author: Raghavendra G Date: Sat Oct 2 07:36:33 2010 +0000 rpc-transport/rdma: send disconnect event only if the transport is already connected. - A disconnect event can be sent before a connect event to rpc, if some error happens during rdma handshake. - Also call rdma_quota_put only if peer is not NULL. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513 commit 1b7a997a7b368aa459dcd57ec23532fe4cdd6e0c Author: Pranith K Date: Sat Oct 2 04:12:51 2010 +0000 mgmt/glusterd: print peer state names instead of state numbers Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1779 (print peer state names instead of state numbers) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1779 commit ef44323b4ba58fa8c1eb89105851983f828dd91b Author: Csaba Henk Date: Sat Oct 2 07:30:39 2010 +0000 volgen: reimplement volgen Generating a volfile occurs in two steps: - Build a graph (ie, glusterfs_graph_t instance) by graph manipulation primitives - Write out the graph to a file by the the graph printing API. Graph builder routines can optionally make use of a "modifier dict", which can contain overrides wrt. volume options. This can be used for a "dry-run" graph generation. Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 067d0e476abe42f1e290039cb903928080e90d8d Author: Csaba Henk Date: Sat Oct 2 07:30:38 2010 +0000 implemented graph printing Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 1cc15f9b0057cd6c8843c8b9cbb36c02d334ec6f Author: Csaba Henk Date: Sat Oct 2 07:30:37 2010 +0000 xlator: make it possible to do type setting and dynamic loading separately Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1750 (clean up volgen) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1750 commit 73c6b2f21a67bed186a279adacb4eb28eafcd853 Author: Pavan Sondur Date: Sat Oct 2 06:14:33 2010 +0000 protocol/client: Fix dumping of locks in client. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 99ff5f22db3404abbbab6e7d7edabe930762118d Author: Pranith K Date: Sat Oct 2 05:31:55 2010 +0000 mgmt/glusterd: destroy frames in callback Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit 0ac18907614886fa00858b6a1abfeb099b49348a Author: shishir gowda Date: Sat Oct 2 02:14:07 2010 +0000 Replace assert in mem_put with gf_log_callingfn Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1759 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1759 commit 365c814f7ba4cc8e04959927c3ded9cdd5b2ab24 Author: Pranith K Date: Sat Oct 2 01:36:16 2010 +0000 mgmt/glusterd: handle peer not connected in peer detach Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1762 (peer detach/peer status ,created glusterd crash) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1762 commit c5714ce6e6fe20575159220bbdf178ebf33ca0ad Author: Raghavendra G Date: Sat Oct 2 00:23:31 2010 +0000 debug/trace: print more information while logging inodelk and finodelk. Signed-off-by: Vijay Bellur commit 26b259476421b89e2df76572c101f5a628ae1bbe Author: shishir gowda Date: Sat Oct 2 01:21:35 2010 +0000 get server xattr only if name is not NULL Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit 17295c37f9ad12163f7c449dbe6f76aff90b493f Author: Amar Tumballi Date: Fri Oct 1 13:04:57 2010 +0000 rebalance: bring in two stages step 1: fix layout (quick pass, so the newly added brick can participate in distribute's entry creations) step 2: migrate data (do the actual rebalance) Its advised to run rebalance after add-brick, and let it complete at-least 'step 1', so things will be smooth with distribute. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 4afbc4e1c44d5da4d4cd6141fb2b693e7baeabe4 Author: Amar Tumballi Date: Fri Oct 1 13:03:58 2010 +0000 glusterd: put all the code related to 'rebalance' in new file Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit b656bff2dd912bcd5caf5bf9303bdef17f753ce1 Author: Raghavendra Bhat Date: Fri Oct 1 09:23:40 2010 +0000 changes for replace-brick status message Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1767 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1767 commit 24ec0fbc4bd145b93b80afa480d5cb4cf785717e Author: Amar Tumballi Date: Fri Oct 1 08:01:14 2010 +0000 stat enhancements * dht to send 'setxattr' to all subvolumes in the layout * server dumps info on total bytes read/written for 'trusted.io.stat.dump' key * server dumps all the mount point IP for 'trusted.list.mount.point' key. * io-stats dumps latency information only if measured Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit a3f90eeb0ad97e4f86aef603f95b0562ab18f36d Author: Pranith K Date: Fri Oct 1 08:00:12 2010 +0000 mgmt/glusterd: handle glusterfs crashes for start/stop of bricks Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1741 (gluster volume stop after one process crashed.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1741 commit fd2e7d007e5362f0738cd9a825349abcf5d27d8f Author: Pavan Sondur Date: Fri Oct 1 05:45:12 2010 +0000 Changes to replace flock with gf_flock across GlusterFS. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 55c6e672503a2451186e17b9c1b7daf6e3ae5463 Author: Csaba Henk Date: Thu Sep 30 12:44:26 2010 +0000 contrib/fuse: update from upstream [555d6b50 in git://fuse.git.sourceforge.net/fuse/fuse] """ commit 555d6b504308eac6b976321ce938ee4bec62c354 Author: Miklos Szeredi Date: Tue Sep 28 10:13:24 2010 +0200 Fix option escaping for fusermount. If the "fsname=" option contained a comma then the option parser in fusermount was confused (Novell bugzilla #641480). Fix by escaping commas when passing them over to fusermount. Reported by Jan Engelhardt """ Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1752 (sync with upstream for "Fix option escaping for fusermount.") URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1752 commit 828829a9cf7b925709f9a1f289d9a6cb94b74dd8 Author: Pavan Sondur Date: Fri Oct 1 04:33:49 2010 +0000 cluster/pump: Initiailize pthread mutex and saved fds list. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 3009bc7b585ae9973c6b50ce464a52f20182c63f Author: Amar Tumballi Date: Fri Oct 1 04:21:17 2010 +0000 remove 'gfs_id' field from all protocol xdr structures It was kept as a debugging requirement/placeholder. Because RPC is mostly bug free with regard to basic xdr structures, it doesn't make sense to carry this forward in release. Saves 8bytes in each request. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 1af483d3716d6b520c1b4fd984ccecee638b2886 Author: Raghavendra Bhat Date: Fri Oct 1 02:22:08 2010 +0000 check if the table is NULL before accessing it Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1757 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1757 commit f5afcc47f9f00472d6c2b3f48127e02332cd457a Author: Shehjar Tikoo Date: Fri Oct 1 01:58:05 2010 +0000 nfs3: Revalidate inode on receiving ESTALE on lookup Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1756 (NFS must revalidate inode on first ESTALE on lookup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1756 commit 9555e5ee7dd2c3a2c98cf505bb198e453ea747d1 Author: Pavan Sondur Date: Fri Oct 1 01:42:46 2010 +0000 cluster/afr: Recover locks on child_up from source to sink. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit d355ecd89427871d8d3f20a99acd284baccef6e1 Author: Vijay Bellur Date: Fri Oct 1 01:41:46 2010 +0000 mgmt/glusterd: Make replace-brick atomic Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 4ec7688091f9d6ee2a6886d53055b94f284c1f7a Author: Raghavendra Bhat Date: Fri Oct 1 01:35:22 2010 +0000 changes for the gluster sanity script Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1436 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1436 commit 64437e01d920597140b35bfeb46591966584e7fc Author: shishir gowda Date: Fri Oct 1 01:12:39 2010 +0000 Allow graph processing even if reconfigure fails Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1730 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1730 commit da74288339563759f568aa5052fdce4c45ebcd22 Author: Vijay Bellur Date: Thu Sep 30 11:41:07 2010 +0000 glusterfsd: perform init new graph if re-configure fails Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit af18c636c44b1ea56296850e55afe0e4b2ce845c Author: Pavan Sondur Date: Thu Sep 30 02:25:31 2010 +0000 protocol/client: cluster/afr: Support lock recovery and self heal. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 865 (Add locks recovery support in GlusterFS) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=865 commit 760daf28898cbb8b5072551735bebee16450ba08 Author: Amar Tumballi Date: Thu Sep 30 09:00:14 2010 +0000 glusterd: fix in log filename and log rotate Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1731 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1731 commit 5a5a7f939c830d8e4a542c8fff00138b83ddd4fc Author: Pranith K Date: Thu Sep 30 08:46:03 2010 +0000 mgmt/glusterd: memory leak fixes Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit bf152d98cee31a2346f3aec32301ca4a4bbfcea1 Author: shishir gowda Date: Thu Sep 30 03:41:04 2010 +0000 Block add, remove and replace brick ops when rebalance is in progress Also fixing msg, changing defrag to rebalance Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit d39ed89765a8d0a1f767b864fd6826d29de7ad1f Author: Amar Tumballi Date: Thu Sep 30 02:18:11 2010 +0000 start the per brick process with 'glusterfsd' instead of 'glusterfs' for users, it becomes easy to differenciate which process is exporting bricks, and which is used as a client process. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit f63e4b6e9aada6f96c71513bcf7f501f613a30fe Author: Amar Tumballi Date: Thu Sep 30 01:49:52 2010 +0000 rpc: in rpc_clnt_destroy(), destroy the memory pool also Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1727 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1727 commit b7aed950dbeba2fdc952f734ca2f713acee2345d Author: Pranith K Date: Thu Sep 30 02:22:52 2010 +0000 mgmt/glusterd: remove debug messages in cleanup_and_exit Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1746 (volume delete fails after volume stop) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1746 commit 65c704747809e126edde164cd0ce9f98ea7f6dc8 Author: Amar Tumballi Date: Thu Sep 30 02:31:47 2010 +0000 protocol/client: handle more NULL dereference Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1745 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1745 commit 76b0e35e7809c38e62f33b5068c61623a6914d5f Author: Amar Tumballi Date: Wed Sep 29 10:47:58 2010 +0000 protocol/server: set 'this->private' only if 'init()' is successful If volume file is fetched (due to HUP or volume file changes) and server init is called again, server protocol init fails with 'bind to port failed' error. If 'this->private' is set to new 'conf' before successful init, the whole process goes to corrupted state. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 0dc7064bd6047e9283d873f418d2e0a4e0ba29e6 Author: Anand Avati Date: Wed Sep 29 06:53:35 2010 +0000 replicate: remove checks which prevented self-heal when open fds were present this check is not needed anymore since the introduction of changelog piggybacking as the optimization technique instead of first-write-to-flush technique some of the self-healing issues with NFS mounts should be resolved Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit b8c42e5cef817bdd0270b1991c0a365aa321f7cc Author: Anand Avati Date: Wed Sep 29 06:53:03 2010 +0000 replicate: keep read_child in inode ctx as up-to-date as possible In every transaction check if the currently set read child in the inode context failed in the fop and set it to another subvol on which the latest fop has passed. This will prevent read fops landing on subvols which have witnessed a failure. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1172 (ls -lh on NFS mount of 2-mirror replicate gives incorrect file size) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1172 commit 87697e7ed88ca650fe70e26d59b67254ed2393f9 Author: Anand Avati Date: Wed Sep 29 05:41:34 2010 +0000 pump: skip "." and ".." entries while traversing dir tree Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 723c57faa30e102732aa29c8c4608703081970f3 Author: Pranith K Date: Wed Sep 29 05:08:34 2010 +0000 mgmt/glusterd: resolve uuid if null Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1734 (replace brick should accept both ipaddress and hostname for bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1734 commit 528dde957c809014aee40737d01cb667e858e0c9 Author: Kaushik BV Date: Wed Sep 29 04:49:53 2010 +0000 glusterd: make sure init is not called when there is no topology change Signed-off-by: Kaushik BV Signed-off-by: Vijay Bellur BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159 commit 2ce4be96bf1c3d08381cbdeb8d57800635702f37 Author: Pranith K Date: Wed Sep 29 04:48:18 2010 +0000 mgmt/glusterd: set the error before starting checks Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1734 (replace brick should accept both ipaddress and hostname for bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1734 commit 6689104ce7eed29c7878c124fa13caecaa1245ef Author: Pranith K Date: Wed Sep 29 03:59:19 2010 +0000 mgmt/glusterd: volume start force Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1736 (implement volume start force) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1736 commit 95dd4ae4dc2a8a3b3673e60c1fa6cbdbb9409d2c Author: Anand Avati Date: Wed Sep 29 03:22:24 2010 +0000 storage/posix: prevent chmod() from getting called on symlinks symlinks, if at all their mode can be changed (on non-linux platforms) can only be done via lchmod(). Attempting chmod on a symlink can be disastrous. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 881 (GlusterFS daemon hangs on replication of symlink (3.0.4)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=881 commit 9406c06522f9e8ef8ee73f6da55937cb1fa04d22 Author: Amar Tumballi Date: Tue Sep 28 06:11:07 2010 +0000 features/quiesce: new translator 'Quiesce' is used to describe pausing or altering the state of running processes on a computer In GlusterFS context, this translator looks for CHILD_DOWN/CHILD_UP events, and will hold the requests for some time if the child node is in disconnected state current timeout is 20seconds, will be made tunable soon Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1500 (Mount point should not be in-accessible between reconnect to server) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1500 commit 3702814c02c0789d8b65b4f096cd0d37947eef3f Author: Amar Tumballi Date: Tue Sep 28 02:58:20 2010 +0000 defaults.{c,h}: _resume functions added * cleaned up whitespace * untabify Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1500 (Mount point should not be in-accessible between reconnect to server) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1500 commit 95d45c7479db322028ab186f4f565c30cbdfba69 Author: Anand Avati Date: Wed Sep 29 01:11:07 2010 +0000 replicate: clear pre_op_done/piggyback values after open fd self-heal Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 34a635c43fa4e33df29be2141348b6c360fcacc9 Author: Anand Avati Date: Wed Sep 29 01:08:05 2010 +0000 replicate: use new style (un)locking in self heal of missing entries Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 960 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=960 commit aee339605337916aaa1e38a0e9ed2422f0f0dcfb Author: Anand V. Avati Date: Wed Sep 29 00:28:07 2010 +0000 replicate: replace first-write-to-flush optimization use a changelog piggybacking optimization instead of first-write-to-flush optimization and do other cleanups (removal of post-post-op hook etc.) Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 25e4eefc40de8fc47260c1d8209679269686c162 Author: Anand V. Avati Date: Wed Sep 29 00:28:06 2010 +0000 whitespace cleanup Signed-off-by: Anand V. Avati Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 28980e69cf720a614fdd6666da5021524bc1f071 Author: Pranith K Date: Tue Sep 28 23:28:28 2010 +0000 mgmt/glusterd: brick info get should compare uuid instead of hostname Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1734 (replace brick should accept both ipaddress and hostname for bricks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1734 commit 4e72e3ac439bab76880236a87558fc54009c007c Author: Amar Tumballi Date: Tue Sep 28 11:01:38 2010 +0000 rpc-clnt: handle NULL dereferences Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1723 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1723 commit 2e8f8e85e9f5ccbefe834498d4cf665728c70303 Author: Amar Tumballi Date: Tue Sep 28 11:01:10 2010 +0000 client-handshake: prevent NULL dereference Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1720 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1720 commit 7fa2a88a28578dce36d88436776c05aee65165fd Author: Anand Avati Date: Tue Sep 28 23:04:24 2010 +0000 resolver: set safer conditionals during path creation when client would send just the path as part of a transaction, path reconstruction would create parent directory's path instead of actual path at the time of resolution. Signed-off-by: Anand V. Avati Signed-off-by: Vijay Bellur BUG: 935 (Directories change mode from 0755 to 0644 automatically) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=935 commit 6686ddc22785fba5ea488fcaafa598161469085b Author: Vijay Bellur Date: Tue Sep 28 09:30:27 2010 +0000 mgmt/glusterd: Fix incorrect state machine transition Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 981970098a68ae222805ae77a0ea53eb1f95fd21 Author: Vijay Bellur Date: Tue Sep 28 09:29:52 2010 +0000 mgmt/glusterd: compute cksum upon volume retrieval Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit d7e694ad7049cd819f8dbc26ec1e7d35b4d1a6fe Author: Pranith K Date: Tue Sep 28 09:27:23 2010 +0000 mgmt/glusterd: prevent cleanup_and_exit if its already started Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1706 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1706 commit 84952d98750165f211d632940fbbd95059553dc2 Author: shishir gowda Date: Tue Sep 28 06:21:44 2010 +0000 Changing readdir calls to readdirp calls in DHT Changing readdir calls to readdirp calls to handle layout issues seen in dht. Also, changing posix readdir call to do stat after dir read for readdirp. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1690 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1690 commit 387f4d385e1d2c29af54c4f87eef7a07acfcfdf9 Author: Amar Tumballi Date: Tue Sep 28 05:37:02 2010 +0000 more proper error returns in case of graph topology validation Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 5ea64d983b31c6882d4582af71a339b6a4fcccf2 Author: Shehjar Tikoo Date: Tue Sep 28 04:30:39 2010 +0000 nfs: Free inodes layer fop locals to fix memory leak Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1259 (Memory leaks to 5.7g usage in gnfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1259 commit 9c8a9bd96733dc3ccde4d76786fe0ad009b3bf6e Author: Raghavendra Bhat Date: Tue Sep 28 06:03:59 2010 +0000 change the loglevel from error to debug while reconfiguring Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1729 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1729 commit fd3662166f8d7e8247bc535f0816bb3abea01889 Author: Shehjar Tikoo Date: Tue Sep 28 04:30:38 2010 +0000 distribute: Propagate -1 op_ret on failed fop Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1717 (dht_attr_cbk does not propagate op_ret on failed fop causing nfs crash) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1717 commit 059c05561e1df6e24229e7adf613f868fa0275b9 Author: Raghavendra Bhat Date: Mon Sep 27 08:13:19 2010 +0000 do not allow remove brick if the total bricks given is less than the sub_count Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1713 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1713 commit c3bf3b45a7cf612833c14fc701f751ffc04a7e73 Author: Amar Tumballi Date: Mon Sep 27 01:57:15 2010 +0000 access-control: report possible errors in graph during 'init()' Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1712 (Error is not logged for a dangling volume) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1712 commit a381d3a29fc149d78aecba22fdb285314aa9b711 Author: Amar Tumballi Date: Tue Sep 28 05:17:27 2010 +0000 glusterd: logs is a symlink to default var log dir Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1728 (glusterd log file location) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1728 commit a89ec9419758b420ce11dddac27327ec34141da6 Author: Raghavendra Bhat Date: Tue Sep 28 04:31:51 2010 +0000 unref the dict allocated in set_volume, remove_brick Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1726 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1726 commit 1fd7b1c4fcfd4041c2a9cb89dcc3874f70324cde Author: shishir gowda Date: Tue Sep 28 03:47:40 2010 +0000 Starting/stoppin glusterd changes brick pairs the problem was the pair information was not maintained anywhere. When glusterd re-starts, it reads the brick dir entries and populates the brick list. adding brick info to volume info file to fix this issue Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1714 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1714 commit 65a84c9d0d691ac4f7a5f33374140e50746a96af Author: Pranith K Date: Tue Sep 28 02:47:08 2010 +0000 mgmt/glusterd: prevent detach of peer with its bricks existing in cluster Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1681 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1681 commit dbbec1261eae8440726b001df8fe4c06837d6f3d Author: Amar Tumballi Date: Mon Sep 27 09:26:17 2010 +0000 distribute: don't check for inode's gfid in _cbk * in dht_lookup_dir_cbk(), at the entry itself we are dereferencing local->inode, which can be NULL in many cases. Hence no need to check/dereference that variable. Just check 'local->gfid'. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1696 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1696 commit efd1f08b57a3175cab9bb543833bc3c9192b527d Author: Pavan Sondur Date: Mon Sep 27 16:20:19 2010 +0000 replace brick fixes Reviewed ok. Just like commit, maybe we can move 'pause' also to the commit op of replace brick since it can be performed only when replace brick has been started. I'll send in a patch for that soon. ----- Original Message ----- From: "Vijay Bellur" To: glusterfs@dev.gluster.com Sent: Monday, September 27, 2010 7:59:25 PM Subject: [PATCH BUG:1235] replace brick fixes Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 4a9c36ea9df9dada0d16c5fdb9fe149b360d9150 Author: Amar Tumballi Date: Mon Sep 27 08:57:05 2010 +0000 glusterfsd: after volume fetch, return proper values from functions Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit edf5b0b4b89b46a566607d159b282c57298679db Author: Amar Tumballi Date: Mon Sep 27 08:55:55 2010 +0000 io-threads: fix NULL dereference in 'reconfigure()' Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1715 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1715 commit f4ff82641baf75cf534531a4dc2eb588db1218cb Author: Pranith K Date: Mon Sep 27 05:57:51 2010 +0000 mgmt/glusterd: delay probe till connection happens Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1607 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1607 commit 542476b4bcf248c02ad087381c03c49c2b4c8014 Author: Amar Tumballi Date: Mon Sep 27 02:06:26 2010 +0000 access-control: handle a case of wrong error handling in rename_src_stat_cbk(), we were checking the return value as '-1', but the function can return '-EFAULT' (ie, -14 in few cases). Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1691 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1691 commit c0cd0637bb8c28db5d3de0a89f312cad96ba2347 Author: Amar Tumballi Date: Mon Sep 27 01:22:57 2010 +0000 fix a build warning about stack overflow Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1710 (build warning) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1710 commit acd2c4dc93381df9806243b6d367a36301e5eb66 Author: Pranith K Date: Sun Sep 26 23:55:41 2010 +0000 mgmt/glusterd: perform post operations of volume set Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1708 (update store, re-compute checksum, restart nfs for volume set) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1708 commit 4725bd37787fe1c02213ab63316abb234077990f Author: Vijay Bellur Date: Sat Sep 25 07:52:18 2010 +0000 protocol/server: Check before de-referencing conf Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 1698 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1698 commit 336e2df7b74be7ad4c9ed403ca10b9f7f7ef9a58 Author: Shehjar Tikoo Date: Sat Sep 25 04:42:30 2010 +0000 nfs: Fix multiple subvolume CHILD-UP support Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit cb1c1d78a3aededcc1d1f77f6e91e23fda83a631 Author: Vijay Bellur Date: Sat Sep 25 04:40:33 2010 +0000 mgmt/glusterd: Do not look into brick when logfile is being set for volume Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 0b68f788a8ff0579f70e546bcd365ee0c3a49a12 Author: Vijay Bellur Date: Fri Sep 24 13:37:32 2010 +0000 mgmt/glusterd: resolve brick before doing uuid compare Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit bd73298410ac6814ed2f45acf2beafee21dc0af1 Author: Amar Tumballi Date: Fri Sep 24 10:16:23 2010 +0000 glusterd: add new stats related options for 'volume set' * 'gluster volume set latency-measurement ' * 'gluster volume set dump-fd-stats ' Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit dca5c02cf31e373e6e4ff376a5f35684cd43e081 Author: Amar Tumballi Date: Fri Sep 24 10:18:31 2010 +0000 glusterd-volgen: add 'io-stats' xlator on server volfile too Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit f91dad3f618b2d981e69ecd5000974db712f9188 Author: Amar Tumballi Date: Fri Sep 24 10:14:37 2010 +0000 io-stats: bring in latency measurement feature Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit 96846cb2aaac582323a5f7347581dad2f5f2cd31 Author: Amar Tumballi Date: Fri Sep 24 10:14:23 2010 +0000 stack.h: remove the time/latency measurement code Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1701 (better statistics gathering in glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1701 commit 25e868b571bc394dd65b54849f369e1a0c29caab Author: Raghavendra Bhat Date: Fri Sep 24 08:50:24 2010 +0000 check if the bricks provided are the same and are alredy being used Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1682 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1682 commit 6e952607f17dd5ea6e3748f2bbc26234f4b1e553 Author: Raghavendra G Date: Fri Sep 24 07:51:53 2010 +0000 rpc/rpc-transport: fix frame-loss during rdma-reads. - total no of rdma reads in progress was tracked using refcount of post (refcount = total rdma reads + 1). However doing rdma_post_unref _after_ rdma_do_reads, can result in race condition between execution of rdma_post_unref and procedure handling rdma read completion. This makes it impossible to find out whether the current rdma read was the last rdma-read being done in procedure handling rdma read-completion. The fix to this should either do rdma_post_unref before posting an rdma read or use another variable to track the number of rdma-reads. This patch implements second method. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1700 (write fops are bailing out on a distribute setup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1700 commit f2c5894f254d9b3d17b058adce7c7b4152da2f5e Author: Pranith Kumar K Date: Fri Sep 24 04:38:36 2010 +0000 mgmt/glusterd: add option to force kill gnfs process Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1517 (gluster volume stop - starts a new nfs server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1517 commit 0cf88c1d35bbc86fdfc1b8035222b248d6725807 Author: Pranith Kumar K Date: Fri Sep 24 04:09:03 2010 +0000 mgmt/glusterd: initialize addrinfo variables Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1695 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1695 commit e9880384632d8ae489a1f6cdc5429ba6e378ce40 Author: Amar Tumballi Date: Fri Sep 24 03:17:36 2010 +0000 glusterd: fetch-spec now allows NFS like '/' To make mount options similar, so less confusion Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 6965560fe9f9291093e9d91c5787ce0374371eb8 Author: Raghavendra G Date: Fri Sep 24 01:40:34 2010 +0000 rpc-clnt: print frame-sent time till microsecond resolution in call_bail. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 0209aab58c56e06fd86487be76312d04fd8f5593 Author: Amar Tumballi Date: Fri Sep 24 00:29:29 2010 +0000 glusterfsd: handle relative path for '--volfile/-f' option Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit ad9c5f801ebffb0993d5f764b27e12b01beba2ce Author: Csaba Henk Date: Thu Sep 23 08:29:15 2010 +0000 mgmt/glusterd: cleanup generate_perf_xlator_list () Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670 commit 7e1b8bb370b4082e66ebe6e458fc45aa653ab3f1 Author: Csaba Henk Date: Thu Sep 23 08:29:14 2010 +0000 dict: add dict_get_str_boolean() function handily query string-boolean values Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670 commit 406bcbb443aaca1655be9dcb9101a717eafdc061 Author: shishir gowda Date: Thu Sep 23 02:09:25 2010 +0000 Check for possible fd/ctx NULL in afr Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1636 (Replicate crashed in afr_nonblocking_inodelk on deref of NULL fd_ctx) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1636 commit c5a5fea9e6a1f1709e6826c1eea89dfd25cc496b Author: Pavan Sondur Date: Thu Sep 23 09:18:37 2010 +0000 mgmt/glusterd: Misc fixes to pump / cli / glusterd wrt replace brick. Patches from Vijay and Shishir have been pulled in into this one big patch. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit fa3ca3c61fbd7ad95f57f0522624396b8f05ecf6 Author: Amar Tumballi Date: Thu Sep 23 06:30:43 2010 +0000 distribute: don't update the inode's gfid directly Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1680 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1680 commit a2e35ea0166c42435f860990c9476dda470843c8 Author: Amar Tumballi Date: Thu Sep 23 05:14:05 2010 +0000 distribute: bring in feature to fix the layout of root inode * If the errno is ESTALE for root, fuse doesn't send fresh lookup on the path (it does for all other inodes). Earlier layout mismatch for root never used to happen inside codebase, and if noticed, it was serious issue. Now with DVM, after a add-brick or a remove-brick, layout can be changed even for 'root' inode. Needed to fix this issue inside distribute itself, instead of fuse sending 'fresh' lookup on root. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1630 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1630 commit 279d46c1068761ffd6349db2913f06c4bb692e17 Author: Amar Tumballi Date: Thu Sep 23 03:52:57 2010 +0000 fuse-resolve: remove stale code Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1240 (DVM: after graph change, inodes should resolve to new inode-table) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1240 commit 7f645c3ac3678bab9b74c62b33951450841af967 Author: Amar Tumballi Date: Thu Sep 23 00:45:53 2010 +0000 gluster cli: handle case of no brick given in log locate/rotate Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1679 (gluster volume log locate/rotate segfault) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1679 commit 2b0299da40ec4d35106d1caaadf936387a54fcce Author: Vijay Bellur Date: Wed Sep 22 23:42:11 2010 +0000 cli: Make volume rename hidden Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 26228ccddc85ab575e4508a03297af57713a5b28 Author: Pranith Kumar K Date: Wed Sep 22 22:42:51 2010 +0000 glusterfsd: destroy mgmt in cleanup Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1517 (gluster volume stop - starts a new nfs server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1517 commit 22560c7faf95157c8ff4df9953d83147e153d3d7 Author: Pavan Sondur Date: Wed Sep 22 15:05:22 2010 +0000 mgmt/glusterd: Always use io-stats as the topmost xlator with appropriate volname to be nfs friendly. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670 commit 37b4a747f5741dda0a24b97420460734452a4b1d Author: Vijay Bellur Date: Wed Sep 22 13:27:04 2010 +0000 cli: Avoid exposing volume set-transport Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit b89e9348aed56c40fec1f8401230dd5a1965f235 Author: Vijay Bellur Date: Wed Sep 22 13:26:41 2010 +0000 mount/fuse: generate gfid only in case of a fresh lookup Signed-off-by: Vijay Bellur Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit 5c4ac19e88f5d7954770aceed930ee193c4138b5 Author: Amar Tumballi Date: Wed Sep 22 10:03:17 2010 +0000 fuse-resolve: don't resolve fd to new graph for now Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1674 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1674 commit 435603caeb651dc1050c85281e3838df9d37ce64 Author: Amar Tumballi Date: Wed Sep 22 09:43:45 2010 +0000 distribute: in linkfile creation check for valid gfid in inode * if inode->gfid is not valid (ie, null), take the gfid from the parameter dictionary passed from higher layer Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1565 (deleting files after dht rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1565 commit 66b1613efdae3ba2740241ee325e5f0b0634424d Author: Amar Tumballi Date: Wed Sep 22 08:50:23 2010 +0000 distribute: while selfhealing directory, send proper gfid in dict * this was the root cause for having layout mismatches in case of add-brick, because the gfid of directories on newly added brick was always mismatching, which caused many operation on that particular brick fail. Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1629 (files missing during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1629 commit 0a14d255dcd6fa3e9d575bae1fecd164763104bb Author: Raghavendra G Date: Wed Sep 22 08:14:02 2010 +0000 rpc/rpcsvc: add debug messages when rpc-messages are handed over to/from transport. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 679395dc7ed5b716f3fb37886f7ec8e59ab02659 Author: Pranith Kumar K Date: Wed Sep 22 06:17:32 2010 +0000 mgmt/glusterd: skip sending req to disconnected peers Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1673 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1673 commit 2915e10dd0ffe529ddf747451051cf9924c708f3 Author: shishir gowda Date: Wed Sep 22 05:21:28 2010 +0000 Restart all bricks which are down when glusterd comes up This is only done is the volume is started. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1562 (insufficient consistency check on start of glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1562 commit 3225d7ccf599e726012fb2d32fe3cc68b979e0ea Author: Amar Tumballi Date: Wed Sep 22 04:23:45 2010 +0000 rpmspec file: add option for '--without rdma' Thanks to Bernard Li for the patch Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1650 (Add '--without rdma' rpmbuild argument) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1650 commit d42f248c58b2ca73fb56a3e091c8e967e2435546 Author: Pranith Kumar K Date: Wed Sep 22 04:21:02 2010 +0000 mgmt/glusterd: replace-brick validations Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1657 (validations for replace-brick while stage op) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1657 commit f47b0c55de9941823fbefe4b3a7e37179d6d4329 Author: Shehjar Tikoo Date: Wed Sep 22 03:32:17 2010 +0000 nfs, nfs3: Base volume access on CHILD-UP-DOWN event Overall, the aim of this patch is to change the result of an nfs op depending on whether the underlying volume is up or down as notified by CHILD_UP and CHILD_DOWN events. This patch contains three intertwined changes: o Only when the lookup on the root of a volume is successful does gnfs now export the subvolume. Till now the result of the lookup was not used to determine whether we should export that volume. Not accounting for root lookup failure resulted in ESTALEs on first access because some children of distribute were down at the time of the root lookup. o Only when lookups on all the subvolumes have succeeded are these exports enabled through NFS. o When a child of say distribute goes down, on CHILD_DOWN event nfs will ignore all incoming requests from the client because ignoring these will prevent ESTALEs for those requests and in the hope that ignoring the requests will make the client retransmit. There are risks in this approach absent the DRC but we're willing to live with that for now. When a child goes down, the mount exports list will continue to show it but mount requests will be denied. Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit 6b2e2fb0903fc56105c267881f202a4865a8b6c7 Author: Shehjar Tikoo Date: Wed Sep 22 03:32:16 2010 +0000 distribute: Propagate CHILD-UP when all subvols are up Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit a4c948aca6058049523e31acf33ce5770f8693ad Author: Shehjar Tikoo Date: Wed Sep 22 03:32:15 2010 +0000 distribute: Return ESTALE when dir selfheal finds no fix Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1641 (Distribute must return error when dir selfheal has no fix) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1641 commit 151c120908fbd8e18072a6e64a641911c307a51c Author: Shehjar Tikoo Date: Wed Sep 22 03:32:14 2010 +0000 core: Introduce string representation of GF_EVENTS Signed-off-by: Shehjar Tikoo Signed-off-by: Vijay Bellur BUG: 1643 (Initial requests after mount ESTALE if DHT subvolumes connect after nfs startup) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1643 commit b6121c62717c89ddc38b72ef18ba110c944cde70 Author: Pranith Kumar K Date: Wed Sep 22 02:29:12 2010 +0000 mgmt/glusterd: opinfo unlock should be done in txn_complete Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1664 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1664 commit 05fd7d004a307a1aba158df82a868e3d271fe966 Author: Pavan Sondur Date: Wed Sep 22 02:01:36 2010 +0000 mgmt/glusterd: Restart src brick and add pump when replace brick cmds are given. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1669 (pump xlator should be excluded by default) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1669 commit e6bdd4f642d5f4d0afbe76b21fdd644c326edb0e Author: Pavan Sondur Date: Wed Sep 22 02:01:10 2010 +0000 mgmt/glusterd: Enable/disable xlator options support added. Signed-off-by: Pavan Vilas Sondur Signed-off-by: Vijay Bellur BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670 commit 14bd64ad53409fb093c499eca45cb23fe9f96772 Author: shishir gowda Date: Wed Sep 22 01:40:45 2010 +0000 Remove brick for stripe should check for pairs/subvolumes Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 1658 (removing single brick works) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1658 commit 8432caca68b9006061226998648c0dd0ff5ebbd3 Author: Raghavendra G Date: Wed Sep 22 00:10:28 2010 +0000 performance/quick-read: fix memory leaks. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 1438 (memory leaks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438 commit 7655ccebd46936a42a6edb62184455077a6505fd Author: Amar Tumballi Date: Tue Sep 21 22:22:45 2010 +0000 server-helper: check for conf before dereferencing Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1667 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1667 commit a2688982b7694f18d6a1d7e20ab36274cca9cc27 Author: Raghavendra Bhat Date: Tue Sep 21 08:12:36 2010 +0000 unmount the replace brick client irrespective of whether the previous commands succeeded or not after the mount Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1661 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1661 commit 78a09306fe1bd955616b8dd56e85f3af954c96b0 Author: Csaba Henk Date: Tue Sep 21 09:12:31 2010 +0000 libglusterfs: handle failure properly in gf_system() - Child must be terminated if execve(2) fails, otherwise it will deadlock parent - Status, as of given by waitpid(2), is aggregated data, should not be returned as is. In fact, there is not much point in threading up the exitvalue: callers usually return gf_system result as is, and according to glusterfs conventions, they should return -1 on failure. Therefore now we check only for success/fail, and return 0/-1. Signed-off-by: Csaba Henk Signed-off-by: Vijay Bellur BUG: 1665 (glusterd hangs if spawning a child is failed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1665 commit eb8561e302bd83305fb093eb8cca42b4f9f62b22 Author: Pranith Kumar K Date: Tue Sep 21 10:49:49 2010 +0000 cli: remove trailing slashes from brick paths Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1659 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1659 commit bd1fa94c8e26cb34566ad460092c2089597e2b17 Author: Pranith Kumar K Date: Tue Sep 21 05:37:10 2010 +0000 mgmt/glusterd: print critical log for responses from unknown peers Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1490 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1490 commit 6dbd6185483591fc2f83beee9d2766d1ea0c61a4 Author: Raghavendra G Date: Wed Aug 25 04:37:44 2010 +0000 mount/fuse: By default enable direct-io only for fds not openened with O_RDONLY. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 801 (Direct io-mode support and related changes in caching translators.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=801 commit 7547953e3a7a458d60f8bbfef8e141aff087bfa3 Author: Raghavendra Bhat Date: Tue Sep 21 05:12:08 2010 +0000 fix the typo in the getxattr of replace-brick Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 commit 7e4d13b56022dfe57fc1512e247eb030edec17fb Author: Raghavendra Bhat Date: Tue Sep 21 03:51:57 2010 +0000 check the private structure of the xlator before accessing it Signed-off-by: Raghavendra Bhat Signed-off-by: Vijay Bellur BUG: 1651 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1651 commit 0484b5768da303998549e8153d08899e58edab68 Author: Pranith Kumar K Date: Tue Sep 21 02:02:48 2010 +0000 cli, mgmt/glusterd: send errno in case of Peer reject Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1653 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1653 commit ae376259304b654206c50b095dabf172fc355438 Author: shishir gowda Date: Mon Sep 20 23:55:55 2010 +0000 Friend find should handle hostname/ip Regardless of friend being added(probe) using hostname or ip address, friend find should succeed if any of the above pair is provided. Signed-off-by: shishir gowda Signed-off-by: Vijay Bellur BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 commit ad234382336a6f2dafb4cb698dfabbf7957b498b Author: Pranith Kumar K Date: Mon Sep 20 09:54:12 2010 +0000 cli, mgmt/glusterd: volume sync command Signed-off-by: Pranith Kumar K Signed-off-by: Vijay Bellur BUG: 1310 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1310 commit e71b50e49612af4e76510b0c2a6f0519adfd852d Author: Raghavendra G Date: Mon Sep 20 08:09:09 2010 +0000 rpc-transport/socket: set keepalive socket option. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875 commit 1473491b576700bb3891abb8adb49e0c31cef8bc Author: Raghavendra G Date: Mon Sep 20 07:28:30 2010 +0000 cluster/afr: print correct offset in debug message during diff self-heal. Signed-off-by: Raghavendra G Signed-off-by: Vijay Bellur BUG: 960 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=960 commit abbfbe2461511183a983f5c97f08f2653f40d47b Author: Amar Tumballi Date: Mon Sep 20 02:29:14 2010 +0000 build glusterfs with '-O0' flag by default Signed-off-by: Amar Tumballi Signed-off-by: Vijay Bellur BUG: 1599 (can we build glusterfs with -O0 -g by default) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1599 commit 5c297be9612f76dad6f970092fb6762b4ee4844a Author: Kaushik BV Date: Sat Sep 18 03:31:56 2010 +0000 Glusterd: gluster volume set