summaryrefslogtreecommitdiffstats
path: root/xlators
Commit message (Collapse)AuthorAgeFilesLines
* cluster/dht: Reset source file mode bits on migration failureNithya Balachandran2015-08-121-3/+95
| | | | | | | | | | | | | | | DHT rebalance uses the sgid and sticky bits to indicate that a file is being migrated. These were not removed if the file migration failed. The fix resets these bits to the original values. Change-Id: I9801bfc0bd80c0800251ccd66c1c91a51cffd909 BUG: 1236512 Signed-off-by: Nithya Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/11454 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* features/changelog: Porting log messages to new logging frameworkAnusha Rao2015-08-1117-376/+1324
| | | | | | | | | | | Change-Id: Ic7f842acca52908fd88e0796dc90b82650405b25 BUG: 1194640 Signed-off-by: Anusha Rao <anusha91rao@gmail.com> Reviewed-on: http://review.gluster.org/10532 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Venky Shankar <vshankar@redhat.com> Reviewed-by: Kotresh HR <khiremat@redhat.com>
* glusterd: log improvement in glusterd_peer_rpc_notifyAtin Mukherjee2015-08-111-4/+9
| | | | | | | | | | | | | | | If ping time out is enabled glusterd can receive a disconnect event from a peer which has been already deleted resulting into a critical log printed. This patch ensures that critical message is logged only when its a connect event. Change-Id: I67d9aa3f60195e08af7dfc8a42683422aaf90a00 BUG: 1212437 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/10272 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Gaurav Kumar Garg <ggarg@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com>
* features/bit-rot-stub: fail the fop if inode context get failsRaghavendra Bhat2015-08-112-23/+96
| | | | | | | | | | | | | | | In stub, for fops like readv, writev etc, if the the object is bad, then the fop is denied. But for checking if the object is bad inode context should be checked. Now, if the inode context is not there, then the fop is allowed to continue. This patch fixes it and the fop is unwound with an error, if the inode context is not found. Change-Id: I5ea4d4fc1a91387f7f9d13ca8cb43c88429f02b0 BUG: 1243391 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-on: http://review.gluster.org/11449 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Venky Shankar <vshankar@redhat.com>
* glusterd/rebalance: trusted rebalance volfileN Balachandran2015-08-111-9/+11
| | | | | | | | | | | | | | | | | | Creating the client volfiles with GF_CLIENT_OTHER overwrites the trusted rebalance volfile and causes rebalance to fail if auth.allow is set. Now, we always set the value of trusted-client to GF_CLIENT_TRUSTED for rebalance volfiles. Change-Id: I95eb510256d18dfa9048f96a1aeb71cca4811811 BUG: 1248415 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/11819 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Avra Sengupta <asengupt@redhat.com> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* tests: set inode-lru-limit to 1 and check if bit-rot xattrs are wrongy createdRaghavendra Bhat2015-08-101-12/+16
| | | | | | | | | | | | | This test sets the lru limit of the inode table to 1 and checks if inode forgets and resolve cause any problem with bit-rot xattrs (especially bad-file xattr). Change-Id: I1fa25fa2d31dda8d26e8192562e896e5bddd0381 BUG: 1244613 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-on: http://review.gluster.org/11718 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Venky Shankar <vshankar@redhat.com>
* Set nfs.disable to "on" when global NFS-Ganesha key is enabledMeghana M2015-08-101-0/+24
| | | | | | | | | | | | | | | | | | "nfs.disable" gets set to "on" for all the existing volumes, when the command "gluster nfs-ganesha enable" is executed. When a new volume is created,it gets exported via Gluster-NFS on the nodes outside the NFS-Ganesha. To fix this, the "nfs.disable" key is set to "on" before starting the volume, whenever the global option is set to "enable". Change-Id: I7ce58928c36eadb8c122cded5bdcea271a0a4ffa BUG: 1251857 Signed-off-by: Meghana M <mmadhusu@redhat.com> Reviewed-on: http://review.gluster.org/11871 Reviewed-by: jiffin tony Thottan <jthottan@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* quota : volume-reset shouldn't remove quota-deem-statfsManikandan Selvaganesh2015-08-074-2/+56
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Volume-reset shouldn't remove quota-deem-statfs, unless explicitly specified, when quota is enabled. 1) glusterd_op_stage_reset_volume () 'gluster volume set/reset <VOLNAME>' features.quota/ features.inode-quota' should not be allowed as it is deprecated. Setting and resetting quota/inode-quota features should be allowed only through 'gluster volume quota <VOLNAME> enable/disable'. 2) glusterd_enable_default_options () Option 'features.quota-deem-statfs' should not be turned off with 'gluster volume reset <VOLNAME>', since quota features can be set/reset only with 'gluster volume quota <VOLNAME> enable/disable'. But, 'gluster volume set features.quota-deem-statfs' can be turned on/off when quota is enabled. Change-Id: Ib5aa00a4d8c82819c08dfc23e2a86f43ebc436c4 BUG: 1250582 Signed-off-by: Manikandan Selvaganesh <mselvaga@redhat.com> Reviewed-on: http://review.gluster.org/11839 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijaikumar Mallikarjuna <vmallika@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* afr: Do not wind statfs to arbiter brickRavishankar N2015-08-073-5/+8
| | | | | | | | | | | | | | | | | | Problem: AFR serves statfs from the brick having the least free space available. Since the size to be allocated to the arbiter brick in a 3 way replica is supposed to be considerably lesser than the other 2 bricks, statfs will be served from this brick which is incorrect. Fix: Don't serve statfs from the arbiter brick. Change-Id: I5af098b9c50626f52cf3d7dbb060bf754c797f05 BUG: 1251346 Reported-by: Fredrik Brandt <fredrikb@denlillaplaneten.se> Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/11857 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* glusterd: Stop/restart/notify to daemons(svcs) during reset/set on a volumeanand2015-08-0614-171/+420
| | | | | | | | | | | | | | | | | | | | problem : Reset/set commands were not working properly. reset command returns success but it not sending notification to svcs if corresponding graph modified. Fix: Whenever reset/set command issued, generate the temp graph and compare with original graph and do the fallowing actions 1.) If both graph are identical nothing to do with svcs. 2.) If any changes in graph topology restart/stop service by calling svc manager. 3) If changes in options send notify signal by calling glusterd_fetchspec_notify. Change-Id: I852c4602eafed1ae6e6a02424814fe3a83e3d4c7 BUG: 1209329 Signed-off-by: anand <anekkunt@redhat.com> Reviewed-on: http://review.gluster.org/10850 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* cluster/ec: Fix tracking of good bricksXavier Hernandez2015-08-0611-258/+122
| | | | | | | | | | | | | | | | | | | The bitmask of good and bad bricks was kept in the context of the corresponding inode or fd. This was problematic when an external process (another client or the self-heal process) did heal the bricks but no one changed the bitmaks of other clients. This patch removes the bitmask stored in the context and calculates which bricks are healthy after locking them and doing the initial xattrop. After that, it's updated using the result of each fop. Change-Id: I225e31cd219a12af4ca58871d8a4bb6f742b223c BUG: 1236065 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/11844 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* dht/tiering : create new dictionary during migrationMohammed Rafi KC2015-08-061-2/+10
| | | | | | | | | | | | | To avoid setting wrong xattr during creating link file Change-Id: Iad8de3521eae17e510035ed42e3e01933d647096 BUG: 1250828 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com> Reviewed-on: http://review.gluster.org/11838 Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* features/shard: Fix excessive logging in readdir(p) callbackKrutika Dhananjay2015-08-051-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | On enabling features.shard on a volume which already has few files, performing operations on the mount was causing excessive logging of messages of the following kind: [2015-08-05 10:57:48.743352] E [shard.c:232:shard_modify_size_and_block_count] 2-dis-shard: Failed to get trusted.glusterfs.shard.file-size for 0b2bd401-c438-4d57-8ae5-8d26105d3396 Turns out this is coming from shard_readdir_cbk() where the shard translator unconditionally looks for the xattr 'trusted.glusterfs.shard.file-size' in every entry's rsp dict and logs this error on not finding it. But files that are not sharded (i.e., the ones that were created before sharding was enabled on the volume) will not (and should not) have this xattr associated with them. So these logs are misleading and must be suppressed in readdir(p). Change-Id: I8d268b4f90a8bf744c7851f1984f5a1b6968fb6a BUG: 1250441 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11843 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* fuse: add "resolve-gids" mount option to overcome 32-groups limitNiels de Vos2015-08-054-39/+93
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a --resolve-gids commandline option to the glusterfs binary. This option gets set when executing "mount -t glusterfs -o resolve-gids ...". This option is most useful in combination with the "acl" mount option. POSIX ACL permission checking is done on the FUSE-client side to improve performance (in addition to the checking on the bricks). The fuse-bridge reads /proc/$PID/status by default, and this file contains maximum 32 groups. Any local (client-side) permission checking that requires more than the first 32 groups will fail. By enabling the "resolve-gids" option, the fuse-bridge will call getgrouplist() to retrieve all the groups from the user accessing the mountpoint. This is comparable to how "nfs.server-aux-gids" works. Note that when a user belongs to more than ~93 groups, the volume option server.manage-gids needs to be enabled too. Without this option, the RPC-layer will need to reduce the number of groups to make them fit in the RPC-header. Change-Id: I7ede90d0e41bcf55755cced5747fa0fb1699edb2 BUG: 1246275 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/11732 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: jiffin tony Thottan <jthottan@redhat.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* SSL improvements: ECDH, DH, CRL, and accessible optionsEmmanuel Dreyfus2015-08-053-77/+90
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Introduce ssl.dh-param option to specify a file containinf DH parameters. If it is provided, EDH ciphers are available. - Introduce ssl.ec-curve option to specify an elliptic curve name. If unspecified, ECDH ciphers are available using the prime256v1 curve. - Introduce ssl.crl-path option to specify the directory where the CRL hash file can be found. Setting to NULL disable CRL checking, just like the default. - Make all ssl.* options accessible through gluster volume set. - In default cipher list, exclude weak ciphers instead of listing the strong ones. - Enforce server cipher preference. - introduce RPC_SET_OPT macro to factor repetitive code in glusterd-volgen.c - Add ssl-ciphers.t test to check all the features touched by this change. Change-Id: I7bfd433df6bbf176f4a58e770e06bcdbe22a101a BUG: 1247152 Signed-off-by: Emmanuel Dreyfus <manu@netbsd.org> Reviewed-on: http://review.gluster.org/11735 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Kaushal M <kaushal@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* client, rpc: make ping-timeout configurable for glusterfs clientsKrishnan Parthasarathi2015-08-051-9/+14
| | | | | | | | | | Change-Id: Idd94adb0457aaffce7330f56f98cebafa2c4dae8 BUG: 1249499 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/11818 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* glusterd: fix op-version bump up flowAtin Mukherjee2015-08-031-10/+16
| | | | | | | | | | | | | | | | | | | | | If a cluster is upgraded from 3.5 to latest version, gluster volume set all cluster.op-version <VERSION> will throw an error message back to the user saying unlocking failed. This is because of trying to release a volume wise lock in unlock phase as the lock was taken cluster wide. The problem surfaced because the op-version is updated in commit phase and unlocking works in the v3 framework where it should have used cluster unlock. Fix is to decide which lock/unlock is to be followed before invoking lock phase Change-Id: Iefb271a058431fe336a493c24d240ed833f279c5 BUG: 1248298 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/11798 Reviewed-by: Avra Sengupta <asengupt@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Anand Nekkunti <anekkunt@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaushal M <kaushal@redhat.com>
* Revert "Add DESTDIR support for pyglupy Makefile"Kaleb KEITHLEY2015-08-032-2/+2
| | | | | | | | | This reverts commit 871000e3ddb457c9cc5757cd94cfc178e3c1be29. Change-Id: I05913151d9cb4c50057e5e72859768085041bdc9 Reviewed-on: http://review.gluster.org/11821 Tested-by: Kaleb KEITHLEY <kkeithle@redhat.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* Add DESTDIR support for pyglupy MakefileMichael Scherer2015-08-032-2/+2
| | | | | | | | | | | | Smoke tests run on a new slave on Fedora 22 fail because make install try to install the python package in /usr/lib/python2.7 without being root, because there is no $DESTDIR support for that part. Change-Id: Ibed17dd091a96fbdf5536ac66b8c876b33a39cd6 Signed-off-by: Michael Scherer <mscherer@redhat.com> Reviewed-on: http://review.gluster.org/11813 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* glusterd: Do not log failure if glusterd_get_txn_opinfo fails in gluster ↵Atin Mukherjee2015-08-022-15/+15
| | | | | | | | | | | | | | | | | | | volume status The first RPC call of gluster volume status fetches the list of the volume names from GlusterD and during that time since no volume name is set in the dictionary gluserd_get_txn_opinfo fails resulting into a failure log which is annoying to the user considering this command is triggered frequently. Fix is to have callers log it depending on the need Change-Id: Ib60a56725208182175513c505c61bcb28148b2d0 BUG: 1238936 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/11520 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Kaushal M <kaushal@redhat.com>
* quota/marker: set log-level to debug for ESTALE/ENOENT for marker txnvmallika2015-07-311-58/+33
| | | | | | | | | | | | | | | For all marker txn, it is possible that while the txn in progress file can be removed. So log all ENOENT/ESTALE error in debug level Change-Id: I776ba3cda33fe992f9dcc7baede7206c4ce19553 BUG: 1245544 Signed-off-by: vmallika <vmallika@redhat.com> Reviewed-on: http://review.gluster.org/11736 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* rebalance/glusterd: Refactor rebalance volfileMohammed Rafi KC2015-07-301-24/+74
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | performance xlator loaded in rebalance xlators are dummy translators, since all fops are starting with dht level. Removing the performance xlators from rebalance volfile will help to minimize the chance for a graph switch. The new rebalance xlators will look like->>> (io-stats) || || || (----DHT----) // \\ // \\ // \\ (replica-1) ... (replica-n) // \\ // \\ // \\ // \\ // \\ // \\ client client client client Change-Id: I3808e3b48fd0cb3e60ef386b8ac9fd994e2831e3 BUG: 1240621 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com> Reviewed-on: http://review.gluster.org/11565 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* features/shard: Create /.shard with 0777 permissions (for now)Krutika Dhananjay2015-07-301-1/+1
| | | | | | | | | | Change-Id: I4e5692f06a189230825f0aeb6487b103bfb66fe1 BUG: 1247108 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11791 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* quota: fix parents caching during build ancestryvmallika2015-07-293-79/+82
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In build ancestry, we get the list of parents for a file, these parents are cached in inode ctx. This caching is not happening because posix is not setting d_stat information in the leaf node entry This patch fixes the issue Inode-ctx is not updated with new parent when rename performed on same directory. This patch fixes the issue There is a possibility of caching stale entries, consider below example: 1) build_ancestry invoked on a file 2) rename is invoked on the same file 3) buils_ancestry prepared entries of old parent 4) rename completed and in cbk old parent is replaced with new parent in inode ctx 5) now build_ancestry cbk adds old parent to inode ctx In this patch we also remove stale entries in writev and fallocate Change-Id: Ib1854a41b47b14eb775326588352015c83d034de BUG: 1240949 Signed-off-by: vmallika <vmallika@redhat.com> Reviewed-on: http://review.gluster.org/11574 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* tiering: Error message change for detach-tier non tier volumeHari Gowtham2015-07-291-5/+13
| | | | | | | | | | | Change-Id: Ib350b201df14b105e475426d2ec20ff5da39a8a1 BUG: 1245935 Signed-off-by: Hari Gowtham <hgowtham@redhat.com> Reviewed-on: http://review.gluster.org/11745 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: mohammed rafi kc <rkavunga@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* features/shard: Fix block size get from xdataPranith Kumar K2015-07-291-2/+3
| | | | | | | | | | | | | | Instead of using dict_get_ptr, dict_get_uint64 was used. If the first byte of the value is '\0' then size is returned as 0 because strtoull is used in data_to_uint64. This will make it seem like the file is not sharded at all. BUG: 1247108 Change-Id: Id1fc291198ac94b20ae645c04a51db78bab51993 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11778 Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* rpc: fix concurrency bug in gf_authenticateJeff Darcy2015-07-281-47/+31
| | | | | | | | | | | | | | | | | | | | | The basic problem is that gf_authenticate abused global variables to pass info through dict_foreach. This is not thread-safe, but it wasn't affecting most people until multi-threaded epoll came along. Now, if two threads get into this code at the same time - and there's nothing to prevent it - one of them could free one of the dicts involved while the other is still using it. The fix is to pass this same information using a temporary structure instead of globals. This makes the code smaller and more efficient too. Change-Id: I72cccc440bb40d5f7ff695250dd014762c7efb73 BUG: 1247765 Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-on: http://review.gluster.org/11780 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Niels de Vos <ndevos@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* features/shard: (Re)initialize local->call_count before winding lookupKrutika Dhananjay2015-07-281-2/+4
| | | | | | | | | | Change-Id: I616409c38b86c0acf1817b3472a1fed73db293f8 BUG: 1247108 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11770 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/ec: Minimize usage of EIO errorXavier Hernandez2015-07-2815-1892/+1203
| | | | | | | | | | Change-Id: I82e245615419c2006a2d1b5e94ff0908d2f5e891 BUG: 1245276 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/11741 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* features/bit-rot-stub: handle REOPEN_WAIT on forgotten inodesRaghavendra Bhat2015-07-281-1/+43
| | | | | | | | | | Change-Id: Ia8706ec9b66d78c4e33e7b7faf69f0d113ba68a4 BUG: 1245981 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-on: http://review.gluster.org/11729 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Venky Shankar <vshankar@redhat.com>
* glusterd: getting txn_id from frame->cookie in op_sm call backanand2015-07-271-16/+61
| | | | | | | | | | | | | | | | | RCA: If rebalance start is triggered from one node and one of other nodes in the cluster goes down simultaneously we might end up in a case where callback will use the txn_id from priv->global_txn_id which is always zeros and this means injecting an event with an incorrect txn_id will result into op-sm getting stuck. fix: set txn_id in frame->cookie during sumbit_and_request, so that we can get txn_id in call back functions. Change-Id: I519176c259ea9d37897791a77a7c92eb96d10052 BUG: 1245142 Signed-off-by: anand <anekkunt@redhat.com> Reviewed-on: http://review.gluster.org/11728 Reviewed-by: Atin Mukherjee <amukherj@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* features/shard: Handle unlink of files with holes appropriately in unlink() ↵Krutika Dhananjay2015-07-271-2/+30
| | | | | | | | | | | | and rename(). Change-Id: I25a02386dc95580c2e76a13fdd8e11a0df234d56 BUG: 1245547 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11737 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* glusterd: initialize the daemon services on demandAtin Mukherjee2015-07-2720-147/+190
| | | | | | | | | | | | | | | | | | | | | | As of now all the daemon services are initialized at glusterD init path. Since socket file path of per node daemon demands the uuid of the node, MY_UUID macro is invoked as part of the initialization. The above flow breaks the usecases where a gluster image is built following a template could be Dockerfile, Vagrantfile or any kind of virtualization environment. This means bringing instances of this image would have same UUIDs for the node resulting in peer probe failure. Solution is to lazily initialize the services on demand. Change-Id: If7caa533026c83e98c7c7678bded67085d0bbc1e BUG: 1238135 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/11488 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Gaurav Kumar Garg <ggarg@redhat.com> Reviewed-by: Kaushal M <kaushal@redhat.com>
* posix,shard: Fill in ia_size and ia_blocks before unwinding (f)setattrKrutika Dhananjay2015-07-262-19/+155
| | | | | | | | | | | | | | The shard xlator will request for size xattrs in its request and posix will perform xattr_fill of requested keys before unwinding (f)setattr. Change-Id: I4ec4779568be6f805724b875b1b4215787112e7f BUG: 1246082 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11754 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* cluster/afr: Fix incorrect logging in read transactionsKrutika Dhananjay2015-07-261-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | afr_read_txn_refresh_done() at its entry point can fail for reasons like ENOENT/ESTALE but seldom due to EIO, which is something _AFR_ would internally generate and not receive in response from a child translator. AFR is reporting "split-brain" for _any_ kind of failure in read txn, of the following kind: [2015-07-07 18:04:34.787612] E [MSGID: 108008] [afr-read-txn.c:76:afr_read_txn_refresh_done] 0-vol3-replicate-3: Failing STAT on gfid 18a973c4-73d3-48b8-942c-33a6f1a8e6b4: split-brain observed. [Input/output error] This patch fixes such misleading errors. To-Do: Avoid logging EIO if/when split-brain choice is set. Will do that as part of a separate commit. Change-Id: Ib513c75168f7026118ad5b3f0b35e9dd498cfe1e BUG: 1246052 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/11756 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Anuradha Talur <atalur@redhat.com> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* logging: client3_3_removexattr_cbk should not log expected ENODATANiels de Vos2015-07-261-1/+1
| | | | | | | | | | | | | | | | Commit 379dbbfd changed the log level of an expected error message from GF_LOG_DEBUG to '0'. This causes the message to always get logged. It is intended to log the warning when the xattr could not be removed (but exists), removing a non-existing xattr is sufficient as debug. BUG: 1246736 Change-Id: If11d15d699e8152cc32e0c0c1d65b587c5c48892 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/11759 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Joe Julian <me@joejulian.name> Tested-by: Joe Julian <me@joejulian.name> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* dict: dict_set_bin() should never free the pointer on errorNiels de Vos2015-07-2414-37/+70
| | | | | | | | | | | | | | | | | | | | | | dict_set_bin() is handling the pointer that it passed inconsistently. Depending on the errors that can occur, the pointer passed to the dict can be free'd, but there is no guarantee. It is cleaner to have the caller free the pointer that allocated it and dict_set_bin() returned an error. When dict_set_bin() returned success, the given pointer will be free'd when dict_unref() calls data_destroy(). Many callers of dict_set_bin() already take care of free'ing the pointer on error. The ones that did not, are corrected with this change too. Change-Id: I39a4f7ebc0cae6d403baba99307d7ce408f25966 BUG: 1242280 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/11638 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: jiffin tony Thottan <jthottan@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* rpc,server,glusterd: Init transport list for accepted transportKaushal M2015-07-242-0/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | GlusterD or a brick would crash when encrypted transport was enabled and an unencrypted client tried to connect to them. The crash occured when GlusterD/server tried to remove the transport from their xprt_list due to a DISCONNECT event. But as the client transport's list head wasn't inited, the process would crash when list_del was performed. Initing the client transports list head during acceptence, prevents this crash. Also, an extra check has been added to the GlusterD and Server notification handlers for client DISCONNECT events. The handlers will now first check if the client transport is a member of any list. GlusterD and Server DISCONNECT event handlers could be called without the ACCEPT handler, which adds the transport to the list, being called. This situation also occurs when an unencrypted client tries to establish a connection with an encrypted server. Change-Id: Icc24a08d60e978aaa1d3322e0cbed680dcbda2b4 BUG: 1243774 Signed-off-by: Kaushal M <kaushal@redhat.com> Reviewed-on: http://review.gluster.org/11692 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/ec: Handle race between unlock-timer, new lockPranith Kumar K2015-07-233-50/+17
| | | | | | | | | | | | | | | | | | | | | | | | Problem: New lock could come at the time timer is on the way to unlock. This was leading to crash in timer thread because thread executing new lock can free up the timer_link->fop and then timer thread will try to access structures already freed. Fix: If the timer event is fired, set lock->release to true and wait for unlock to complete. Thanks to Xavi and Bhaskar for helping in confirming that this race is the RC. Thanks to Kritika for pointing out and explaining how Avati's patch can be used to fix this bug. Change-Id: I45fa5470bbc1f03b5f3d133e26d1e0ab24303378 BUG: 1243187 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11670 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* dht: send lookup even for fd based operations during rebalanceRavishankar N2015-07-221-23/+30
| | | | | | | | | | | | | | | | | | | | | Problem: dht_rebalance_inprogress_task() was not sending lookups to the destination subvolume for a file undergoing writes during rebalance. Due to this, afr was not able to populate the read_subvol and failed the write with EIO. Fix: Send lookup for fd based operations as well. Thanks to Raghavendra G for helping with the RCA. Change-Id: I638c203abfaa45b29aa5902ffd76e692a8212a19 BUG: 1244165 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/11713 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* libglusterfs: Even anonymous fds must have fd->flags setRaghavendra Talur2015-07-201-5/+13
| | | | | | | | | | | | | | | | | | | | | | We do not set the same flags to anonymous fd that posix uses to open an anonymous fd in the backend. If there are any xlators which rely on these flags for their operation they may not work well. Add proper flags to anonymous fds at the time of their creation and refer to them for subsequent operations. Change-Id: Ia99b7ea7d38839f099c7b4aae3c7ead123bc8c67 BUG: 1211221 Signed-off-by: Raghavendra Talur <rtalur@redhat.com> Reviewed-on: http://review.gluster.org/10219 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: soumya k <skoduri@redhat.com> Reviewed-by: Poornima G <pgurusid@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com> Reviewed-by: Niels de Vos <ndevos@redhat.com> Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* quota/marker: contribution with list_del can cause mem corruptionvmallika2015-07-192-9/+9
| | | | | | | | | | | | | | | | There is a possibility that contribution is removed twice from list during unlink operation (with hard links) or during rename operation Use list_del_init for a thread safe deltion of member from list Change-Id: Iff5e0c03cc8f0ed85da0db1739b84b695abf9ea6 BUG: 1244109 Signed-off-by: vmallika <vmallika@redhat.com> Reviewed-on: http://review.gluster.org/11706 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* nfs: log disabled export/netgroups feature as INFOJiffin Tony Thottan2015-07-191-1/+1
| | | | | | | | | | | | | If export/netgroups feature is disabled for gluster/nfs, then the "nfs.log" contains a Warning message which is deceiving for the users. Logging the message as Info is sufficient. Change-Id: I3d07e8bc4f09f3eb32014f5a10390d0484b838cf BUG: 1243805 Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com> Reviewed-on: http://review.gluster.org/11695 Reviewed-by: Niels de Vos <ndevos@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* storage/posix: Check xdata for NULL before dict_getRaghavendra Talur2015-07-181-4/+4
| | | | | | | | | | | | | | Performing a dict_get on xdata can lead to frequent logging if xdata is NULL. Change-Id: I1666f0cc958c639ccd816e3738dd4a1efebbff82 BUG: 1235921 Signed-off-by: Raghavendra Talur <rtalur@redhat.com> Reviewed-on: http://review.gluster.org/11390 Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* glusterd: Porting the left out gf_log_callingfns to new frameworkNandaja Varma2015-07-185-15/+52
| | | | | | | | | | Change-Id: I1b0ad54238895475ddbacc4fffacac8dc6e887fe BUG: 1235538 Signed-off-by: Nandaja Varma <nandaja.varma@gmail.com> Reviewed-on: http://review.gluster.org/11590 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* features/marker: Fixing dereference after null checkarao2015-07-171-1/+1
| | | | | | | | | | | | | | CID: 1124494 The variable was sent as a parameter to the function without the null check, hence added a check on null and error log accordingly. Change-Id: I11a649fc9a1bedad17422aeddb8dd8fa225d404e BUG: 789278 Signed-off-by: arao <arao@redhat.com> Reviewed-on: http://review.gluster.org/9641 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* glusterd: rebalance support for cluster.rc frameworkanand2015-07-161-1/+20
| | | | | | | | | | | | | | | | | | | Issue:Rebalance is failing in cluster framework (any simulated cluster environment in same node ). RCA: 1. we are passing always "localhost" as volfile server for rebalance xlator . 2. Rebalance daemons are overwriting unix socket and log files each other. (All rebalance processes are creating socket with same name) . Fix: set vol_file_server, unix socket and log files properly. Change-Id: I6654461e00c2a164b2f1f1db24a316c4180dd8d5 BUG: 1231437 Signed-off-by: anand <anekkunt@redhat.com> Reviewed-on: http://review.gluster.org/11210 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* posix: fix mem-leak in posix xattropvmallika2015-07-161-2/+4
| | | | | | | | | | Change-Id: I1dd70f74a98c5875eb316f3c3e560047f128685b BUG: 1243890 Signed-off-by: vmallika <vmallika@redhat.com> Reviewed-on: http://review.gluster.org/11700 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* glusterd: use 2 epoll worker threads by defaultKrishnan Parthasarathi2015-07-162-0/+22
| | | | | | | | | | | | | | | The no. of epoll worker threads can be configured by adding the following option into glusterd.vol. option event-threads <NUM-OF-EPOLL_WORKERS> BUG: 1242421 Change-Id: I2a9e2d81c64beaf54872081f9ce45355cf4dfca7 Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-on: http://review.gluster.org/11630 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* protocol/server: use different dict for resolvingRaghavendra Bhat2015-07-151-2/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | protocol/server has to resolve the inode before continuing with any fop coming from the clients. For resolving it, server xlator was using the same dict associated with the fop. It causes problems in some situations. If a directory's inode was forgotten because of lru limit being exceeded, then when a create fop comes for an entry within that directory, server tries to resolve it. But since the parent directory's inode is not found in the inode table, it tries to do a hard resolve by doing a lookup on the parent gfid. If any xlator below server wants to get some extended attributes whenever lookup comes, then they set the new keys in the same dict that came along with the create fop. Now, the lookup of the parent succeeds and the create fop proceeds with the same dict (with extra keys present). posix xlaror creates those xattrs that are present in the dict. Thus the xattrs which were not to be present by default are also set as part of create. (Ex: bit-rot related xattrs such as bad-file, version and sign xattrs) Change-Id: I4bdad175a1d7a04a3aa36073667c556d6c260263 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com> Reviewed-on: http://review.gluster.org/11661 Reviewed-by: Vijaikumar Mallikarjuna <vmallika@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
generated by cgit (git 2.34.1) at 2024-11-19 23:44:55 +0000