summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* mgmt/glusterd: send unlock upon commit failurev3.1.0qa13Vijay Bellur2010-08-312-1/+13
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1476 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1476
* cluster/afr: Break STACK_WIND loop when the call count is reached.Pavan Sondur2010-08-312-1/+30
| | | | | | | | | | | Fix also has a check for self heal relevant to pump. Tested with dbench with AFR client and pump on server. Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1443 (Crash in afr_nonblocking_entrylk_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1443
* mgmt/glusterd: memory leak fixesPranith Kumar K2010-08-3116-148/+280
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1186 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1186
* rpc-transport/socket: use xdr_sizeof instead of sizeof when trying to read ↵Raghavendra G2010-08-311-2/+21
| | | | | | | | | | vectored request/reply Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* mgmt/glusterd: prevent a double reply for the same request.Amar Tumballi2010-08-311-2/+10
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1401 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1401
* fixes in 'gluster volume rebalance'Amar Tumballi2010-08-315-18/+56
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1481 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1481
* check if the export directory is present only on the correct hostRaghavendra Bhat2010-08-311-6/+31
| | | | | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1489 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1489
* 'gluster volume log' feature addedAmar Tumballi2010-08-3126-142/+1372
| | | | | | | | | * 'gluster volume log filename <VOLNAME> [BRICK] <path>' * 'gluster volume log locate <VOLNAME> [BRICK]' * 'gluster volume log rotate <VOLUME> [BRICK]' Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>
* nfs, mount3: Fix assumptions of this being child xlShehjar Tikoo2010-08-312-6/+9
| | | | | | | | | | | This is plain wrong. this must always be the xlator that receives the callback. Use cookie to access the child subvolume on which the fop was issued. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1410 (nfs uses this for child translator during frame creation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1410
* nfs: Create frames with frame->root as nfsxShehjar Tikoo2010-08-311-58/+58
| | | | | | | | | | | | | frame root was being set to the subvol on which the fop was to be performed. Apart from just being totally wrong behaviour, this also messes up mem-accouting because there THIS points to the wrong xlator resulting in crap addresses being dereferenced through the mem type index. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1410 (nfs uses this for child translator during frame creation) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1410
* nfs: Set actorxl to enable setting THIS to nfsxShehjar Tikoo2010-08-311-0/+1
| | | | | | | | | | ..for fixing mem-accounting for NFS in mainline. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1280 (gf_mem_set_acct_info goes into spinlock busyloop, never returns) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1280
* nfsrpc: Introduce THIS-setting support to fix mem-accountingShehjar Tikoo2010-08-312-0/+10
| | | | | | | | | | | | | Not setting THIS in nfs/rpc has been a blocker for NFS on mainline because without THIS set correctly to nfsx, mem-accounting goes looking into translators other than nfsx for nfs memory allocations, resulting in dereferencing bad addresses. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1280 (gf_mem_set_acct_info goes into spinlock busyloop, never returns) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1280
* nfs3: Close dst cached fd & unref inode on renameShehjar Tikoo2010-08-311-0/+19
| | | | | | | | | | | | If the src file is over-writing an existing file and if the destination file is open, then close the cached fd on the destination file and unref the inode for it. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1464 (fd leak after rename) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1464
* nfs: Free fop local only after inode checksShehjar Tikoo2010-08-312-53/+52
| | | | | | | | | | | | | | Fixes a crash that occurs because the nfs-fops code accesses a fop local after it has been returned to the mem pool. Generally seen when nfs load is so high that the mem-pool runs out of memory and starts CALLOCing. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1449 (NFS crash in nfs_fop_fsync_cbk) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1449
* nfs3: Return ESTALE when going beyond fh-hashcount or max-hashesShehjar Tikoo2010-08-311-7/+40
| | | | | | | | | | | | During fh resolution, if we go beyond the max hashes support by gnfs or if we go beyond the dir depth specified in the filehandle, then return ESTALE. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1378 (Deep directory creation crashes gnfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1378
* nfs3: Logging and comments made more accurateShehjar Tikoo2010-08-312-11/+24
| | | | | | | | Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1378 (Deep directory creation crashes gnfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1378
* nfs3: Support hashcounts larger than hash array sizeShehjar Tikoo2010-08-312-5/+26
| | | | | | | | Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1378 (Deep directory creation crashes gnfs) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1378
* nfs3: Unref dir fd once usage ends in hard fh resolutionShehjar Tikoo2010-08-311-3/+29
| | | | | | | | | | | | | | | | | | There are three conditions when a dir fd_t needs to be unrefed when: a. the inode being searched is found as the candidate entry, b. we have exhausted all the entries in the current dir, c. we decide to step into a child directory because of a hash match. This decision is made in nfs3_fh_resolve_check_response. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1397 (Cached dir fd_ts are a leakin') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1397
* nfs3: Dont ref dir fd_t used in hard fh resolutionShehjar Tikoo2010-08-312-11/+11
| | | | | | | | | | | | ..because the extra ref was under the mistaken assumption that directory fd_t will be cached even during hard fh resolution and that is not the case. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1397 (Cached dir fd_ts are a leakin') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1397
* nfs3: Dont ref cached fd after fd_lookupShehjar Tikoo2010-08-311-1/+1
| | | | | | | | | | ..because fd_lookup returns a ref'd fd_t. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1397 (Cached dir fd_ts are a leakin') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1397
* Add fuse.glusterfs to PRUNEFS variable in updatedb.conf(5)Sachidananda2010-08-311-19/+32
| | | | | | | | | | | | | | Append fuse.glusterfs to PRUNEFS variable in updatedb.conf(5). updatedb(8) should not index files under GlusterFS, indexing will slow down GlusteFS if the filesystem is several TB in size. Plus some whitespace cleanup. Signed-off-by: Sachidananda Urs <sac@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 538 (disable glusterfs mount from updatedb.conf) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=538
* Log all commands from glusterdshishir gowda2010-08-311-0/+142
| | | | | | | | | | | | | Logging all commands processed by glusterd which causes some change. the log file is @ /etc/glusterd/.cmd_log_history. gf_cmd_log() is used to write to this log Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1404 (need a dump of all the op/mgmt commands) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1404
* Add command logging facility for glusterdshishir gowda2010-08-313-1/+114
| | | | | | | | | | | | | | | Added new command logging facility to gf_cmd_log() which can be used to log all commands to a .cmd_log_history file situated in the glusterd working directory. Accepts 1 st argument a domain string (e.g: volume, peer..) followed by msg string (similar to gf_log) Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1404 (need a dump of all the op/mgmt commands) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1404
* rpc-transport/rdma: By default, enable building of rdma only if libibverbs ↵Raghavendra G2010-08-312-2/+5
| | | | | | | | | | is installed. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* rpc-transport/rdma: free ioq entry even when churning of message fails.Raghavendra G2010-08-311-1/+1
| | | | | | | | | | | - An ioq entry is added to ioq-list only when it is not processed due to lack of quota. For all other cases, it should be freed to avoid memory leak. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* fix a crash in cleanup_and_exit ()v3.1.0qa12Amar Tumballi2010-08-311-8/+12
| | | | | | | | | | | | * fini() was being called without proper 'THIS' being set. * in protocol/client, a frame was getting created after frame pool was destroyed Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1030 (mount directory is not unmounted after killing glusterfs process) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1030
* fix typo in commandline help messageCsaba Henk2010-08-311-3/+2
| | | | | | | | Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1482 (typo in help message) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1482
* mgmt/glusterd: Update store on start/stop volumeVijay Bellur2010-08-303-6/+17
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1480 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1480
* fuse: have the fsname passed to mount(2) include the volfile idCsaba Henk2010-08-301-3/+26
| | | | | | | | Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1478 (show volfile id in mount(8) output) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1478
* mgmt/glusterd: Return replace-brick statusPavan Sondur2010-08-302-18/+62
| | | | | | | | Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1322 (Replace brick should show status of paused and abort states) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1322
* mgmt/glusterd: fixed volgen creation problemsPranith Kumar K2010-08-302-19/+5
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1454 (Remove brick unsuccessful - wrong volume info) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1454
* Add rdma as valid transport type for client and server protocol.Raghavendra G2010-08-302-2/+2
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* changes to client to make use of the rdma functionality.Raghavendra G2010-08-309-129/+367
| | | | | | | | | | | - preallocate buffers in client and pass them to transport layer whenever a large response is expected. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* Bring in new transport rdma.Raghavendra G2010-08-3010-2/+5984
| | | | | | | | | | | | - rdma is new transport and improvement over current ib-verbs. It uses rdma-read and rdma-write for efficiently transferring large buffers. For more details please refer to rfc-5666 and rfc-5667. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* Only admin should be able to run gluster commandshishir gowda2010-08-301-0/+29
| | | | | | | | | | | Checking for port number to fail any requests coming in from client. if port is >1024, then fail the requests Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1403 (only admin (uid 0) should be able to run 'gluster' command) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1403
* glusterfsd: call fini of fuse and all active xlators in cleanup_and_exit()Amar Tumballi2010-08-301-1/+17
| | | | | | | | | | * handles the case of stale mount point in case of killing glusterfs process Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1030 (mount directory is not unmounted after killing glusterfs process) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1030
* Volume Add-brick validation for exportsshishir gowda2010-08-303-52/+83
| | | | | | | | | | | | Added checks for export already in use, duplicate exports in command, and check whether exports are valid. Also, cleaned up error handling in glusterd_handle_add_bricks Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1457 (volume add brick validation for export) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1457
* mgmt/glusterd: remove volfile, brick file upon remove-brickPranith Kumar K2010-08-304-0/+28
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1475 (glusterd should delete brick related files upon remove brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1475
* Provides the ability to filter the output of state dumpKaushik BV2010-08-303-27/+228
| | | | | | | | Signed-off-by: Kaushik BV <kaushikbv@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 828 (glusterdump filled up the /) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=828
* mgmt/glusterd: handle port allocation so ports are reused for same brickv3.1.0qa11Amar Tumballi2010-08-292-9/+11
| | | | | | | | | | | * if 'brickinfo->port' exists use it instead of pmap_registry_alloc(), hence a brick after stop/start starts on same port Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1473 (reuse the ports while starting 'glusterfsd') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1473
* gluster{d,fs,fsd}: add logrorate functionality to SIGHUPAmar Tumballi2010-08-292-6/+14
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1472 (SIGHUP should do 'logrotate') URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1472
* cli, mgmt/glusterd: added volume stop <VOLNAME> force functionalityPranith Kumar K2010-08-289-52/+161
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1361 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1361
* mgmt/glusterd: Fix some more options in volgen.Pavan Sondur2010-08-281-6/+6
| | | | | | | | Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1455 (df command hangs before showing the gluster mount) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1455
* dump the volume file details in log file if graph init succeedsAmar Tumballi2010-08-281-0/+2
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1468 (after dvm changes, volfile info is not dumped in logfile) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1468
* afr: enable metadata self-heal by defaultAmar Tumballi2010-08-281-1/+1
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1467 (enable the metadata-change-log by default) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1467
* change the path to brickpath while creating the pidfileRaghavendra Bhat2010-08-281-1/+1
| | | | | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1409 (Gluster add brick fails if all the bricks are local) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1409
* performance/stat-prefetch: while removing an entry from cache, remove it ↵Raghavendra G2010-08-283-142/+110
| | | | | | | | | | from caches stored in all opened fds. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1414 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1414
* mgmt/glusterd: look for local hostname in is_local_addr()v3.1.0qa10Vijay Bellur2010-08-272-17/+29
| | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>
* check for ENOENT after unlink system call in stop volume functionRaghavendra Bhat2010-08-271-1/+2
| | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>
* change the shell to bash form shRaghavendra Bhat2010-08-271-1/+1
| | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>
generated by cgit (git 2.34.1) at 2024-05-21 23:46:01 +0000