summaryrefslogtreecommitdiffstats
path: root/xlators
Commit message (Collapse)AuthorAgeFilesLines
* features/shard: Fix crash during background shard deletion in a specific caseKrutika Dhananjay2019-05-161-3/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Consider the following case - 1. A file gets FALLOCATE'd such that > "shard-lru-limit" number of shards are created. 2. And then it is deleted after that. The unique thing about FALLOCATE is that unlike WRITE, all of the participant shards are resolved and created and fallocated in a single batch. This means, in this case, after the first "shard-lru-limit" number of shards are resolved and added to lru list, as part of resolution of the remaining shards, some of the existing shards in lru list will need to be evicted. So these evicted shards will be inode_unlink()d as part of eviction. Now once the fop gets to the actual FALLOCATE stage, the lru'd-out shards get added to fsync list. 2 things to note at this point: i. the lru'd out shards are only part of fsync list, so each holds 1 ref on base shard ii. and the more recently used shards are part of both fsync and lru list. So each of these shards holds 2 refs on base inode - one for being part of fsync list, and the other for being part of lru list. FALLOCATE completes successfully and then this very file is deleted, and background shard deletion launched. Here's where the ref counts get mismatched. First as part of inode_resolve()s during the deletion, the lru'd-out inodes return NULL, because they are inode_unlink()'d by now. So these inodes need to be freshly looked up. But as part of linking them in lookup_cbk (precisely in shard_link_block_inode()), inode_link() returns the lru'd-out inode object. And its inode ctx is still valid and ctx->base_inode valid from the last time it was added to list. But shard_common_lookup_shards_cbk() passes NULL in the place of base_pointer to __shard_update_shards_inode_list(). This means, as part of adding the lru'd out inode back to lru list, base inode is not ref'd since its NULL. Whereas post unlinking this shard, during shard_unlink_block_inode(), ctx->base_inode is accessible and is unref'd because the shard was found to be part of LRU list, although the matching ref didn't occur. This at some point leads to base_inode refcount becoming 0 and it getting destroyed and released back while some of its associated shards are continuing to be unlinked in parallel and the client crashes whenever it is accessed next. Fix is to pass base shard correctly, if available, in shard_link_block_inode(). Also, the patch fixes the ret value check in tests/bugs/shard/shard-fallocate.c Change-Id: Ibd0bc4c6952367608e10701473cbad3947d7559f Updates: bz#1696136 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
* ec/shd: Cleanup self heal daemon resources during ec finiMohammed Rafi KC2019-05-135-13/+122
| | | | | | | | | | We were not properly cleaning self-heal daemon resources during ec fini. With shd multiplexing, it is absolutely necessary to cleanup all the resources during ec fini. Change-Id: Iae4f1bce7d8c2e1da51ac568700a51088f3cc7f2 fixes: bz#1703948 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* glusterd: Add gluster volume stop operation to glusterd_validate_quorum()Vishal Pandey2019-05-111-1/+1
| | | | | | | | | | | | | | ISSUE: gluster volume stop succeeds even if quorum is not met. Fix: Add GD_OP_STOP_VOLUME to gluster_validate_quorum in glusterd_mgmt_v3_pre_validate (). Since the volume stop command has been ported from synctask to mgmt_v3, the quorum check was missed out. Change-Id: I7a634ad89ec2e286ea262d7952061efad5360042 fixes: bz#1690753 Signed-off-by: Vishal Pandey <vpandey@redhat.com>
* shd/glusterd: Serialize shd manager to prevent race conditionMohammed Rafi KC2019-05-103-0/+18
| | | | | | | | | | | At the time of a glusterd restart, while doing a handshake there is a possibility that multiple shd manager might get executed. Because of this, there is a chance that multiple shd get spawned during a glusterd restart Change-Id: Ie20798441e07d7d7a93b7d38dfb924cea178a920 fixes: bz#1707081 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* afr: thin-arbiter lock release fixesRavishankar N2019-05-103-47/+93
| | | | | | | | | | | | | | | | | | | | - pass fop state instead of afr local to afr_ta_dom_lock_check_and_release() - avoid afr_lock_release_synctask() being called simultaneosuly from notify code path and transaction (post-op) code path due to races. - Check if the post-op on TA is valid based on event_gen checks. - Invalidate in-memory information when we get TA child down. Note: Thi patch addresses some pending review comments of commit 053b1309dc8fbc05fcde5223e734da9f694cf5cc (https://review.gluster.org/#/c/glusterfs/+/20095/) fixes: bz#1698449 Change-Id: I2ccd7e1b53362f9f3fed8680aecb23b5011eb18c Signed-off-by: Ravishankar N <ravishankar@redhat.com>
* glusterd: fix inconsistent global option output in volume getAtin Mukherjee2019-05-091-2/+2
| | | | | | | | | | volume get all all | grep <key> & volume get <volname> all | grep <key> dumps two different output value for cluster.brick-multiplex and cluster.server-quorum-ratio Fixes: bz#1707700 Change-Id: Id131734e0502aa514b84768cf67fce3c22364eae Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* glusterd: reduce some work in glusterd-utils.cYaniv Kaul2019-05-091-125/+128
| | | | | | | | | | | | Similar to https://review.gluster.org/#/c/glusterfs/+/22652/ , reduce some of the work by using smaller buffers and less conversion of parameters when snprintf()'ing them. On the way, remove some clang warnings, mainly on dead assignment. Change-Id: Ie51e6d6f14df6b2ccbebba314cf937af08839741 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* glusterd: improve logging in __server_getspec()Sanju Rakonde2019-05-082-2/+15
| | | | | | | updates: bz#1193929 Change-Id: Idad745d5869c92e6bed71842f14bc1a3362ca4bd Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
* afr: log before attempting data self-heal.Ravishankar N2019-05-081-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I was working on a blog about troubleshooting AFR issues and I wanted to copy the messages logged by self-heal for my blog. I then realized that AFR-v2 is not logging *before* attempting data heal while it logs it for metadata and entry heals. I [MSGID: 108026] [afr-self-heal-entry.c:883:afr_selfheal_entry_do] 0-testvol-replicate-0: performing entry selfheal on d120c0cf-6e87-454b-965b-0d83a4c752bb I [MSGID: 108026] [afr-self-heal-common.c:1741:afr_log_selfheal] 0-testvol-replicate-0: Completed entry selfheal on d120c0cf-6e87-454b-965b-0d83a4c752bb. sources=[0] 2 sinks=1 I [MSGID: 108026] [afr-self-heal-common.c:1741:afr_log_selfheal] 0-testvol-replicate-0: Completed data selfheal on a9b5f183-21eb-4fb3-a342-287d3a7dddc5. sources=[0] 2 sinks=1 I [MSGID: 108026] [afr-self-heal-metadata.c:52:__afr_selfheal_metadata_do] 0-testvol-replicate-0: performing metadata selfheal on a9b5f183-21eb-4fb3-a342-287d3a7dddc5 I [MSGID: 108026] [afr-self-heal-common.c:1741:afr_log_selfheal] 0-testvol-replicate-0: Completed metadata selfheal on a9b5f183-21eb-4fb3-a342-287d3a7dddc5. sources=[0] 2 sinks=1 Adding it in this patch. Now there is a 'performing' and a corresponding 'Completed' message for every type of heal. fixes: bz#1707746 Change-Id: I0b954cf1e17b48280aefa76640b5119b92133d61 Signed-off-by: Ravishankar N <ravishankar@redhat.com>
* glusterd/store: store all key-values in one shotYaniv Kaul2019-05-082-323/+292
| | | | | | | | | | | | Instead of saving each key-value separately, which is slow ( especially as we fflush() after each!), store them all as one string and write all together. Implements https://github.com/gluster/glusterfs/issues/629 Change-Id: Ie77a272446b0b6785584b710a4fdd9c613dd9578 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat,.com>
* dht: Custom xattrs are not healed in case of add-brickroot2019-05-081-8/+1
| | | | | | | | | | | | | | | | Problem: If any custom xattrs are set on the directory before add a brick, xattrs are not healed on the directory after adding a brick. Solution: xattr are not healed because dht_selfheal_dir_mkdir_lookup_cbk checks the value of MDS and if MDS value is not negative selfheal code path does not take reference of MDS xattrs.Change the condition to take reference of MDS xattr so that custom xattrs are populated on newly added brick Updates: bz#1702299 Change-Id: Id14beedb98cce6928055f294e1594b22132e811c Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* afr : fix Coverity CID 1398627Rinku Kothiya2019-05-071-2/+9
| | | | | | | | | | | Fixed coverity error, "Unchecked return value (CHECKED_RETURN)". Checking return value & logging error message if afr_set_pending_dict fails. updates: bz#789278 Change-Id: Iab7da6b4f3cd0622b95b8e1c412b007a330467e5 Signed-off-by: Rinku Kothiya <rkothiya@redhat.com>
* performance/write-behind: remove request from wip list in wb_writev_cbkRaghavendra G2019-05-061-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a race in the way O_DIRECT writes are handled. Assume two overlapping write requests w1 and w2. * w1 is issued and is in wb_inode->wip queue as the response is still pending from bricks. Also wb_request_unref in wb_do_winds is not yet invoked. list_for_each_entry_safe (req, tmp, tasks, winds) { list_del_init (&req->winds); if (req->op_ret == -1) { call_unwind_error_keep_stub (req->stub, req->op_ret, req->op_errno); } else { call_resume_keep_stub (req->stub); } wb_request_unref (req); } * w2 is issued and wb_process_queue is invoked. w2 is not picked up for winding as w1 is still in wb_inode->wip. w1 is added to todo list and wb_writev for w2 returns. * response to w1 is received and invokes wb_request_unref. Assume wb_request_unref in wb_do_winds (see point 1) is not invoked yet. Since there is one more refcount, wb_request_unref in wb_writev_cbk of w1 doesn't remove w1 from wip. * wb_process_queue is invoked as part of wb_writev_cbk of w1. But, it fails to wind w2 as w1 is still in wip. * wb_requet_unref is invoked on w1 as part of wb_do_winds. w1 is removed from all queues including w1. * After this point there is no invocation of wb_process_queue unless new request is issued from application causing w2 to be hung till the next request. This bug is similar to bz 1626780 and bz 1379655. Change-Id: Iaa47437613591699d4c8ad18bc0b32de6affcc31 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Fixes: bz#1705865
* glusterd: coverity fixAtin Mukherjee2019-05-061-2/+14
| | | | | | | | CID: 1382403 (CHECKED_RETURN) Updates: bz#789278 Change-Id: I4c57b93fd3d14c524ff8519ed876f029834de306 Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* cluster/ec: fix shd healer wait timeoutKinglong Mee2019-05-062-1/+2
| | | | | | | | | Right now, the timeout is written by hard code, fix it by using heal-timeout. fixes: bz#1703020 Change-Id: I0d154e7807f9dba7efc3896805559bbfaa7af2ad Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
* features/shard: Fix integer overflow in block count accountingKrutika Dhananjay2019-05-061-1/+1
| | | | | | | | ... by holding delta_blocks in 64-bit int as opposed to 32-bit int. Change-Id: I2c1ddab17457f45e27428575ad16fa678fd6c0eb updates: bz#1705884 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
* glusterd: prevent use-after-free in glusterd_op_ac_send_brick_op()Niels de Vos2019-05-061-2/+1
| | | | | | | | | Coverity reported that GF_FREE(req_ctx) could be called 2x on req_ctx. Change-Id: I9120686e5920de8c27688e10de0db6aa26292064 CID: 1401115 Updates: bz#789278 Signed-off-by: Niels de Vos <ndevos@redhat.com>
* cluster/ec: Reopen shouldn't happen with O_TRUNCPranith Kumar K2019-05-051-1/+1
| | | | | | | | | | | | | Problem: Doing re-open with O_TRUNC will truncate the fragment even when it is not needed needing extra heals Fix: At the time of re-open don't use O_TRUNC. fixes bz#1706603 Change-Id: Idc6408968efaad897b95a5a52481c66e843d3fb8 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* glusterd-utils.c: reduce work in glusterd_add_volume_to_dict()Yaniv Kaul2019-05-031-58/+59
| | | | | | | | | | | 1. Use small arrays, 32 or 64 bytes should suffice. 2. Do not repeat the pattern of snprintf '%s.%d', prefix, count over and over. Change-Id: Ief6de78b766d9a07acb6256fc4830f4f3cfba7c9 updates: bz#1193929 Signed-off-by: Yaniv Kaul <ykaul@redhat.com>
* glusterd: Fix coverity defects & put coverity annotationsAtin Mukherjee2019-05-0214-33/+65
| | | | | | | | | | | Along with fixing few defect, put the required annotations for the defects which are marked ignore/false positive/intentional as per the coverity defect sheet. This should avoid the per component graph showing many defects as open in the coverity glusterfs web page. Updates: bz#789278 Change-Id: I19461dc3603a3bd8f88866a1ab3db43d783af8e4 Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* glusterd: Fix bulkvoldict thread logic in brick multiplexingMohit Agrawal2019-04-301-6/+18
| | | | | | | | | | | | | | | Problem: Currently glusterd spawn bulkvoldict in brick_mux environment while no. of volumes are less than configured glusterd.vol_count_per_thread Solution: Correct the logic to spawn bulkvoldict thread 1) Calculate endindex only while total thread is non zero 2) Update end index correctly to pass index for bulkvoldict thread Fixes: bz#1704252 Change-Id: I1def847fbdd6a605e7687bfc4e42b706bf0eb70b Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* cloudsync/plugin: coverity fixesSusant Palai2019-04-301-6/+6
| | | | | | | | | CID 1401087: Null pointer dereferences (REVERSE_INULL) CID 1401088: Null pointer dereferences (FORWARD_NULL) Change-Id: I71bf67af80e1b22bcd2eb997b01a1a5ef0b4d80b Updates: bz#789278 Signed-off-by: Susant Palai <spalai@redhat.com>
* storage/posix: fix fresh file detection delayXavier Hernandez2019-04-291-4/+20
| | | | | | | | | | | Current implementation made it possible to consider that a file was not fresh even if it was created less than a second ago. This patch fixes the way in which the delay is computed to ensure that at least one second has elapsed. Change-Id: I05f7b99e7e8dd97e31f7ebaaec6c39eecf98b00f Updates: bz#1193929 Signed-off-by: Xavier Hernandez <jahernan@redhat.com>
* protocol: remove compound fopAmar Tumballi2019-04-299-7483/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | Compound fops are kept on wire as a backward compatibility with older AFR modules. The AFR module used beyond 4.x releases are not using compound fops. Hence removing the compound fop in the protocol code. Note that, compound-fops was already an 'option' in AFR, and completely removed since 4.1.x releases. So, point to note is, with this change, we have 2 ways to upgrade when clients of 3.x series are present. i) set 'use-compound-fops' option to 'false' on any volume which is of replica type. And then upgrade the servers. ii) Do a two step upgrade. First from current version (which will already be EOL if it's using compound) to a 4.1..6.x version, and then an upgrade to 7.x. Consider the overall code which we are removing for the option seems quite high, I believe it is worth it. updates: bz#1693692 Signed-off-by: Amar Tumballi <amarts@redhat.com> Change-Id: I0a8876d0367a15e1410ec845f251d5d3097ee593
* performance/decompounder: remove the translator as the feature is not used ↵Amar Tumballi2019-04-298-1014/+3
| | | | | | | | anymore updates: bz#1693692 Change-Id: Id5932b11e115ca6da1c2bfff7ae1460787109e06 Signed-off-by: Amar Tumballi <amarts@redhat.com>
* glusterd: define dumpops in the xlator_api of glusterdSanju Rakonde2019-04-271-0/+1
| | | | | | | | | | | | | | Problem: statedump is not capturing information related to glusterd Solution: statdump is not capturing glusterd info because trav->dumpops is null in gf_proc_dump_single_xlator_info () where trav is glusterd xlator object. trav->dumpops is null because we missed to define dumpops in xlator_api of glusterd. defining dumpops in xlator_api of glusterd fixes the issue. fixes: bz#1703629 Change-Id: If85429ecb1ef580aced8d5b88d09fc15258bfc4c Signed-off-by: Sanju Rakonde <srakonde@redhat.com>
* cloudsync: Fix bug in cloudsync-fops-c.pyAnuradha Talur2019-04-261-3/+21
| | | | | | | | | | | | | | | | In some of the fops generated by generator.py, xdata request was not being wound to the child xlator correctly. This was happening because when though the logic in cloudsync-fops-c.py was correct, generator.py was generating a resultant code that omits this logic. Made changes in cloudsync-fops-c.py so that correct code is produced. Change-Id: I6f25bdb36ede06fd03be32c04087a75639d79150 updates: bz#1642168 Signed-off-by: Anuradha Talur <atalur@commvault.com>
* cloudsync/cvlt: Cloudsync plugin for commvault storeAnuradha Talur2019-04-2611-3/+1213
| | | | | | Change-Id: Icbe53e78e9c4f6699c7a26a806ef4b14b39f5019 updates: bz#1642168 Signed-off-by: Anuradha Talur <atalur@commvault.com>
* glusterd: coverity fixesAtin Mukherjee2019-04-265-8/+9
| | | | | | | | | | | | | | | | 1400775 - USE_AFTER_FREE 1400742 - Missing Unlock 1400736 - CHECKED_RETURN 1398470 - Missing Unlock Missing unlock is the tricky one, we have had annotation added, but coverity still continued to complaint. Added pthread_mutex_unlock to clean up the lock before destroying it to see if it makes coverity happy. Updates: bz#789278 Change-Id: I1d892612a17f805144d96c1b15004a85a1639414 Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* glusterd: enable fips-mode-rchecksum for new volumesRavishankar N2019-04-261-0/+13
| | | | | | | | | | | | | ...during volume create if the cluster op-version is >=GD_OP_VERSION_7_0. This option itself was introduced in GD_OP_VERSION_4_0_0 via commit 6daa65356. We missed enabling it by default for new volume creates in that commit. If we are to do it now safely, we need to use op version GD_OP_VERSION_7_0 and target it for release-7. fixes: bz#1702303 Change-Id: I7c6d4a8abe0816367e7069cb5cad01744f04858f Signed-off-by: Ravishankar N <ravishankar@redhat.com>
* features/locks: error-out {inode,entry}lk fops with all-zero lk-ownerPranith Kumar K2019-04-265-15/+53
| | | | | | | | | | | | | | | | | Problem: Sometimes we find that developers forget to assign lk-owner for an inodelk/entrylk/lk before writing code to wind these fops. locks xlator at the moment allows this operation. This leads to multiple threads in the same client being able to get locks on the inode because lk-owner is same and transport is same. So isolation with locks can't be achieved. Fix: Disallow locks with lk-owner zero. fixes bz#1624701 Change-Id: I1aadcfbaaa4d49308f7c819505857e201809b3bc Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* cloudsync: Make readdirp return stat info of all the direntsAnuradha Talur2019-04-253-1/+38
| | | | | | | | | | | | | | | This change got missed while the initial changes were sent. Should have been a part of : https://review.gluster.org/#/c/glusterfs/+/21757/ Gist of the change: Function that fills in stat info for dirents is invoked in readdirp in posix when cloudsync populates xdata request with GF_CS_OBJECT_STATUS. Change-Id: Ide0c4e80afb74cd2120f74ba934ed40123152d69 updates: bz#1642168 Signed-off-by: Anuradha Talur <atalur@commvault.com>
* glusterd: coverity fixesAtin Mukherjee2019-04-255-13/+50
| | | | | | | | | | | | | | | | | | | | | | | | Addresses the following: * CID 1124776: Resource leaks (RESOURCE_LEAK) - Variable "aa" going out of scope leaks the storage it points to in glusterd-volgen.c * Bunch of CHECKED_RETURN defects in the callers of synctask_barrier_init * CID 1400755: Error handling issues (CHECKED_RETURN) - Calling "gf_is_service_running" without checking return value in xlators/mgmt/glusterd/src/glusterd-shd-svc.c: 671 in glusterd_shdsvc_stop() * CID 1400745: Memory - illegal accesses (USE_AFTER_FREE) - Dereferencing freed pointer "volinfo" in /xlators/mgmt/glusterd/src/glusterd-shd-svc.c: 460 in glusterd_shdsvc_start() * CID 1400742: Program hangs (LOCK) - adding annotation to fix this false positive Updates: bz#789278 Change-Id: I02f16e7eeb8c5cf72f7d0b29d00df4f03b3718b3 Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* features/bit-rot: Unconditionally sign the files during oneshot crawlRaghavendra Bhat2019-04-251-1/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently bit-rot feature has an issue with disabling and reenabling it on the same volume. Consider enabling bit-rot detection which goes on to crawl and sign all the files present in the volume. Then some files are modified and the bit-rot daemon goes on to sign the modified files with the correct signature. Now, disable bit-rot feature. While, signing and scrubbing are not happening, previous checksums of the files continue to exist as extended attributes. Now, if some files with checksum xattrs get modified, they are not signed with new signature as the feature is off. At this point, if the feature is enabled again, the bit rot daemon will go and sign those files which does not have any bit-rot specific xattrs (i.e. those files which were created after bit-rot was disabled). Whereas the files with bit-rot xattrs wont get signed with proper new checksum. At this point if scrubber runs, it finds the on disk checksum and the actual checksum of the file to be different (because the file got modified) and marks the file as corrupted. FIX: The fix is to unconditionally sign the files when the bit-rot daemon comes up (instead of skipping the files with bit-rot xattrs). Change-Id: Iadfb47dd39f7e2e77f22d549a4a07a385284f4f5 fixes: bz#1700078 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>
* cluster/dht: Refactor dht lookup functionsN Balachandran2019-04-251-74/+30
| | | | | | | | | | Part 2: Modify dht_revalidate_cbk to call dht_selfheal_directory instead of separate calls to heal attrs and xattrs. Change-Id: Id41ac6c4220c2c35484812bbfc6157fc3c86b142 updates: bz#1590385 Signed-off-by: N Balachandran <nbalacha@redhat.com>
* ctime: Fix log repeated logging during openKotresh HR2019-04-241-10/+5
| | | | | | | | | | | | The log "posix set mdata failed, No ctime" logged repeatedly after the fix [1]. Those could be internal fops. This patch fixes the same. [1] https://review.gluster.org/22540 fixes: bz#1701457 Change-Id: I42799a90b976982cedb0ca11fa224d555eb05650 Signed-off-by: Kotresh HR <khiremat@redhat.com>
* core: avoid dynamic TLS allocation when possibleXavi Hernandez2019-04-243-54/+6
| | | | | | | | | | | | | | | | | | | Some interdependencies between logging and memory management functions make it impossible to use the logging framework before initializing memory subsystem because they both depend on Thread Local Storage allocated through pthread_key_create() during initialization. This causes a crash when we try to log something very early in the initialization phase. To prevent this, several dynamically allocated TLS structures have been replaced by static TLS reserved at compile time using '__thread' keyword. This also reduces the number of error sources, making initialization simpler. Updates: bz#1193929 Change-Id: I8ea2e072411e30790d50084b6b7e909c7bb01d50 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* glusterd/shd: Keep a ref on volinfo until attach rpc execute cbkMohammed Rafi KC2019-04-242-0/+7
| | | | | | | | | | | When svc attach execute for multiplexing a daemon, we have to keep a ref on volinfo until it finish the execution. Because, if the attach is an aysnc call, then a parallel volume delete can lead to free the volinfo Change-Id: Ibc02b89557baaed2f63db63d7fb1a7480444ae0d fixes: bz#1702185 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com>
* cluster/ec: fix fd reopenXavi Hernandez2019-04-2314-274/+328
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently EC tries to reopen fd's that have been opened while a brick was down. This is done as part of regular write operations, just after having acquired the locks, and it's sent as a sub-fop of the main write fop. There were two problems: 1. The reopen was attempted on all UP bricks, even if a previous lock didn't succeed. This is incorrect because most probably the open will fail. 2. If reopen is sent and fails, the error is propagated to the main operation, causing it to fail when it shouldn't. To fix this, we only attempt reopens on bricks where the current fop owns a lock, and we prevent any error to be propagated to the main fop. To implement this behaviour an argument used to indicate the minimum number of required answers has overloaded to also include some flags. To make the change consistent, it has been necessary to rename the argument, which means that a lot of files have been changed. However there are no functional changes. This change has also uncovered a problem in discard code, which didn't correctely process requests of small sizes because no real discard fop was being processed, only a write of 0's on some region. In this case some fields of the fop remained uninitialized or with incorrect values. To fix this, a new function has been created to simulate success on a fop and it's used in the discard case. Thanks to Pranith for providing a test script that has also detected an issue in this patch. This patch includes a small modification of this script to force data to be written into bricks before stopping them. Change-Id: If272343873369186c2fb8f43c1d9c52c3ea304ec Fixes: bz#1699866 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* features/sdfs: Assign unique lk-owner for entrylk fopPranith Kumar K2019-04-221-0/+6
| | | | | | | | | | | | | sdfs is supposed to serialize entry fops by doing entrylk, but all the locks are being done with all-zero lk-owner. In essence sdfs doesn't achieve its goal of mutual exclusion when conflicting operations are executed by same client because two locks on same entry with same all-zero-owner will get locks. Fixed this up by assigning lk-owner before taking entrylk updates bz#1624701 Change-Id: Ifabfc998c9f1724915d38e90ed8287e05797d769 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* cluster/afr: Set lk-owner before inodelk/entrylk/lkPranith Kumar K2019-04-222-19/+23
| | | | | | Updates: bz#1624701 Change-Id: I7152c28ad85925abccdcc4cd6de8cb2a2b847a51 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* GlusterD:Checking for null value to void explicit dereferencing of null pointerrishubhjain2019-04-221-0/+14
| | | | | | | | | | | | Before calling strtok_r a check for null pointer is necessary to avoid dereferencing of null pointer CID:1398617 CID:1274074 Change-Id: I34956c6e04af1faa22d550e6474909ecd36f5d6c updates: bz#789278 Signed-off-by: rishubhjain <rishubhjain47@gmail.com>
* features/locks: fix coverity issuesXavi Hernandez2019-04-192-1/+6
| | | | | | | | | | | | | | This patch fixes the following NULL dereferences identified by Coverity: * CID 1398619 * CID 1398621 * CID 1398623 * CID 1398625 * CID 1398626 Change-Id: Id6af0d7cba0bb3346005376bc27180e8476255a4 Updates: bz#789278 Signed-off-by: Xavi Hernandez <xhernandez@redhat.com>
* glusterd: fix loading ctime in client graph logicAtin Mukherjee2019-04-171-3/+9
| | | | | | | | | Commit efbf8ab wasn't handling all the scenarios of toggling ctime option correctly and more over a ! had completely tossed up the logic. Fixes: bz#1697907 Change-Id: If12e2f69045e59878992ee2cd0518cc0eabcce0d Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* Revert "features/locks: error-out {inode,entry}lk fops with all-zero lk-owner"Atin Mukherjee2019-04-175-53/+15
| | | | | | | | | This reverts commit 3883887427a7f2dc458a9773e05f7c8ce8e62301 as it has broken sdfs-sanity.t. Updates: bz#1624701 Change-Id: Icb2b0d6bfcce4d556f1cd0f11695c03ffc138736 Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* features/bit-rot-stub: clean the mutex after cancelling the signer threadRaghavendra Bhat2019-04-172-7/+59
| | | | | | | | | | | | | | | | | | When bit-rot feature is disabled, the signer thread from the bit-rot-stub xlator (the thread which performs the setxattr of the signature on to the disk) is cancelled. But, if the cancelled signer thread had already held the mutex (&priv->lock) which it uses to monitor the queue of files to be signed, then the mutex is never released. This creates problems in future when the feature is enabled again. Both the new instance of the signer thread and the regular thread which enqueues the files to be signed will be blocked on this mutex. So, as part of cancelling the signer thread, unlock the mutex associated with it as well using pthread_cleanup_push and pthread_cleanup_pop. Change-Id: Ib761910caed90b268e69794ddeb108165487af40 updates: bz#1700078 Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>
* glusterd: fix op-version of glusterd.vol_count_per_threadAtin Mukherjee2019-04-161-1/+1
| | | | | | | | It was hardcoded and with a wrong value. Fixes: bz#1699339 Change-Id: Ibabe2424a0d35e172a9259bd8849c9bb7cebff1e Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
* features/locks: error-out {inode,entry}lk fops with all-zero lk-ownerPranith Kumar K2019-04-165-15/+53
| | | | | | | | | | | | | | | | | Problem: Sometimes we find that developers forget to assign lk-owner for an inodelk/entrylk/lk before writing code to wind these fops. locks xlator at the moment allows this operation. This leads to multiple threads in the same client being able to get locks on the inode because lk-owner is same and transport is same. So isolation with locks can't be achieved. Fix: Disallow locks with lk-owner zero. fixes bz#1624701 Change-Id: I1c816280cffd150ebb392e3dcd4d21007cdd767f Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
* glusterd: Optimize glusterd handshaking code pathMohit Agrawal2019-04-155-48/+290
| | | | | | | | | | | | | | | | | | | | Problem: At the time of handshaking glusterd populate volume data in a dictionary.While no. of volumes are configured more than 1500 glusterd takes more than 10 min to generated the data.Due to taking more time rpc request times out and rpc start bailing of call frames. Solution: To optimize the code done below changes 1) Spawn multiple threads to populate volumes data in bulk in separate dictionary and introduce an option glusterd.brick-dict-thread-count to configure no. of threads to populate volume data. 2) Populate tier data only while volume type is tier 3) Compare snap data only while snap_count is non zero Fixes: bz#1699339 Change-Id: I38dc71970c049217f9d1a06fc0aaf4c26eab18f5 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
* libgfchangelog : use find_library to locate shared librarySunny Kumar2019-04-151-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Issue: libgfchangelog.so: cannot open shared object file Due to hardcoded shared library name runtime loader looks for particular version of a shared library. Solution: Using find_library to locate shared library at runtime solves this issue. Traceback (most recent call last): File "/usr/libexec/glusterfs/python/syncdaemon/gsyncd.py", line 323, in main func(args) File "/usr/libexec/glusterfs/python/syncdaemon/subcmds.py", line 82, in subcmd_worker local.service_loop(remote) File "/usr/libexec/glusterfs/python/syncdaemon/resource.py", line 1261, in service_loop changelog_agent.init() File "/usr/libexec/glusterfs/python/syncdaemon/repce.py", line 233, in __call__ return self.ins(self.meth, *a) File "/usr/libexec/glusterfs/python/syncdaemon/repce.py", line 215, in __call__ raise res OSError: libgfchangelog.so: cannot open shared object file: No such file or directory Change-Id: I3dd013d701ed1cd99ba7ef20d1898f343e1db8f5 fixes: bz#1699394 Signed-off-by: Sunny Kumar <sunkumar@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-06 02:18:30 +0000