summaryrefslogtreecommitdiffstats
path: root/xlators
Commit message (Collapse)AuthorAgeFilesLines
* mgmt/glusterd: Misc fixes to pump / cli / glusterd wrt replace brick.v3.1.0qa30v3.1.0betaPavan Sondur2010-09-238-188/+255
| | | | | | | | | | Patches from Vijay and Shishir have been pulled in into this one big patch. Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235
* distribute: don't update the inode's gfid directlyAmar Tumballi2010-09-235-11/+37
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1680 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1680
* distribute: bring in feature to fix the layout of root inodeAmar Tumballi2010-09-231-1/+143
| | | | | | | | | | | | | | | | | * 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 <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1630 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1630
* fuse-resolve: remove stale codeAmar Tumballi2010-09-231-192/+6
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* mgmt/glusterd: Always use io-stats as the topmost xlator with appropriate ↵Pavan Sondur2010-09-221-14/+103
| | | | | | | | | | volname to be nfs friendly. Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670
* mount/fuse: generate gfid only in case of a fresh lookupVijay Bellur2010-09-221-2/+1
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971
* fuse-resolve: don't resolve fd to new graph for nowAmar Tumballi2010-09-221-1/+5
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1674 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1674
* distribute: in linkfile creation check for valid gfid in inodev3.1.0qa28Amar Tumballi2010-09-221-10/+10
| | | | | | | | | | | * if inode->gfid is not valid (ie, null), take the gfid from the parameter dictionary passed from higher layer Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1565 (deleting files after dht rebalance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1565
* distribute: while selfhealing directory, send proper gfid in dictAmar Tumballi2010-09-223-13/+27
| | | | | | | | | | | | | * 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 <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1629 (files missing during add-brick) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1629
* mgmt/glusterd: skip sending req to disconnected peersPranith Kumar K2010-09-221-0/+8
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1673 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1673
* Restart all bricks which are down when glusterd comes upshishir gowda2010-09-226-5/+150
| | | | | | | | | | This is only done is the volume is started. Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1562 (insufficient consistency check on start of glusterd) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1562
* mgmt/glusterd: replace-brick validationsPranith Kumar K2010-09-224-51/+153
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1657 (validations for replace-brick while stage op) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1657
* nfs, nfs3: Base volume access on CHILD-UP-DOWN eventShehjar Tikoo2010-09-227-105/+418
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* distribute: Propagate CHILD-UP when all subvols are upShehjar Tikoo2010-09-222-3/+18
| | | | | | | | Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* distribute: Return ESTALE when dir selfheal finds no fixShehjar Tikoo2010-09-221-2/+6
| | | | | | | | Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* mgmt/glusterd: opinfo unlock should be done in txn_completePranith Kumar K2010-09-221-1/+0
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1664 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1664
* mgmt/glusterd: Restart src brick and add pump when replace brick cmds are given.Pavan Sondur2010-09-222-15/+129
| | | | | | | | Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1669 (pump xlator should be excluded by default) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1669
* mgmt/glusterd: Enable/disable xlator options support added.Pavan Sondur2010-09-222-60/+268
| | | | | | | | Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1670 (Volume set enable disable support) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1670
* Remove brick for stripe should check for pairs/subvolumesshishir gowda2010-09-221-5/+14
| | | | | | | | Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1658 (removing single brick works) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1658
* performance/quick-read: fix memory leaks.Raghavendra G2010-09-221-3/+1
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1438 (memory leaks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438
* server-helper: check for conf before dereferencingAmar Tumballi2010-09-211-4/+4
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1667 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1667
* unmount the replace brick client irrespective of whether the previous ↵Raghavendra Bhat2010-09-211-10/+31
| | | | | | | | | | commands succeeded or not after the mount Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1661 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1661
* mgmt/glusterd: print critical log for responses from unknown peersPranith Kumar K2010-09-211-4/+8
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1490 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1490
* mount/fuse: By default enable direct-io only for fds not openened with O_RDONLY.v3.1.0qa27Raghavendra G2010-09-211-2/+6
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> 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
* fix the typo in the getxattr of replace-brickRaghavendra Bhat2010-09-211-1/+1
| | | | | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235
* check the private structure of the xlator before accessing itRaghavendra Bhat2010-09-211-0/+8
| | | | | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1651 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1651
* cli, mgmt/glusterd: send errno in case of Peer rejectPranith Kumar K2010-09-213-4/+7
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1653 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1653
* Friend find should handle hostname/ipshishir gowda2010-09-211-1/+54
| | | | | | | | | | | 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 <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971
* cli, mgmt/glusterd: volume sync commandPranith Kumar K2010-09-208-216/+583
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1310 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1310
* cluster/afr: print correct offset in debug message during diff self-heal.Raghavendra G2010-09-201-2/+2
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 960 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=960
* Glusterd: gluster volume set <volume> <option> <value>Kaushik BV2010-09-1817-36/+1333
| | | | | | | | Signed-off-by: Kaushik BV <kaushikbv@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1159 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1159
* mgmt/glusterd: detach peer properly when msg submission failsVijay Bellur2010-09-182-1/+4
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971
* change stat structure to iattAnush Shetty2010-09-181-1/+1
| | | | | | | | Signed-off-by: Anush Shetty <anush@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1642 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1642
* cluster/afr: allocate memory big enough to hold iatt structures.Raghavendra G2010-09-182-3/+3
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 927 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=927
* cluster/replicate: stack_wind into read_child only if it is up.Raghavendra G2010-09-181-6/+6
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1637 (replicate should wind reads into read-child only if it is up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1637
* check for 'link_inode' in server protocolAmar Tumballi2010-09-181-0/+7
| | | | | | | | | | * also log and return in case of 'fd_bind' getting fd with NULL inode. Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1635 (running mixed tests glusterfs crashed) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1635
* mgmt/glusterd: Proceed state machine when cli response failsVijay Bellur2010-09-181-0/+8
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1530 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1530
* server-resolve: check for variables before dereferencingAmar Tumballi2010-09-171-7/+14
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1628 (glusterfs crash) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1628
* glusterd: refactor service terminationCsaba Henk2010-09-173-133/+67
| | | | | | | | Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570
* reorganize /etc/glusterd/logs, add nfs log tooCsaba Henk2010-09-173-4/+17
| | | | | | | | Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1319 (gnfs support in gluster command line) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1319
* nfs3: Unref & unbind dir fd with inode lock on EOFv3.1.0qa26Shehjar Tikoo2010-09-171-6/+12
| | | | | | | | | | | | | | ..so that when EOF is reached on this fd, any further requests on the same inode do not get handled through this fd but result in a new fd being opened. Unbinding results in the fd getting deleted from the inode's fd list. Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1619 (glusterfs nfs server crashed on dht+replica(2x2)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1619
* mount/fuse: Perform malloc for appropriate lengthVijay Bellur2010-09-171-1/+1
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1631 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1631
* free the dict_val to avoid memory leakRaghavendra Bhat2010-09-171-0/+2
| | | | | | | | Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1621 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1621
* Fix crash in dht_pathinfo_getxattr_cbkshishir gowda2010-09-171-4/+11
| | | | | | | | | | The crash happened due to NULL dereferencing. Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1626 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1626
* Fix transalator indent for optionshishir gowda2010-09-171-2/+2
| | | | | | | | Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1626 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1626
* portmap: add support for registering multiple bricks on one portCsaba Henk2010-09-161-7/+23
| | | | | | | | | | | | | | | | Rationale: if a brick serves multiple volumes, all of them need to be registered for the port the brick server listens on. Implementation: to register volumes "foo" and "bar" for port 6543, you have to send a SIGNUP for brick: "foo bar", port: 6543. Upon a pmap lookup, we match the search term to whitespace tokenized bricknames on server side. Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570
* portmap: make grounds for typed service mappingCsaba Henk2010-09-164-25/+33
| | | | | | | | Signed-off-by: Csaba Henk <csaba@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1570 (geosync related changes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1570
* server: Check gfid presence using uuid_is_nullv3.1.0qa25Shehjar Tikoo2010-09-161-2/+2
| | | | | | | | | Signed-off-by: Shehjar Tikoo <shehjart@gluster.com> Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1608 (stat fop on dir returns ENOENT from server-resolution path) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1608
* distribute: send proper 'gfid' in calls originated from lookup/mkdirAmar Tumballi2010-09-161-0/+9
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1608 (stat fop on dir returns ENOENT from server-resolution path) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1608
* performance/write-behind: dump contents of wb-fileRaghavendra G2010-09-162-9/+155
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1059 (enhancements for getting statistics from performance translators) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1059