summaryrefslogtreecommitdiffstats
path: root/xlators/cluster/dht/src/dht-common.h
Commit message (Collapse)AuthorAgeFilesLines
* cluster/dht: handle EREMOTE in dht lk/flushSusant Palai2016-05-011-0/+2
| | | | | | | | | | | | | | | | With lock-migration, we need to send requests to destination brick post migration. Once, the source brick marks the lock structure to be already migrated, the requests will be redirected to destination brick by dht_lk2/flush2. Change-Id: I50b14011c5ab68c34826fb7ba7f8c8d42a68ad97 BUG: 1326085 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/13493 Smoke: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Niels de Vos <ndevos@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
* glusterd: volume set changes for lock migrationSusant Palai2016-05-011-0/+7
| | | | | | | | | | | Change-Id: I48c6f9cdda47503615ba65882acd5eedf0a70c89 BUG: 1326085 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/14024 Smoke: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Niels de Vos <ndevos@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
* tier/migrator: Fetch the next query file for the next cycleJoseph Fernandes2016-04-301-0/+4
| | | | | | | | | | | | | | | | | | | | | | | Problem: When we spawn promote and demote thread, query files are build. And only query file with index 0 is picked for migration as the first query file. This may not be suitable for scenarios, where the file in the query are too big to move in the first cycle, as a result file in the other query files always get missed. We need to shuffle so that other query files also get a chance. Fix: Remember the previous first query file and shift it by one index, before the migration starts. Change-Id: I704947bcf4bab6b20b1179a6d9ae4a15a3d51bd9 BUG: 1330353 Signed-off-by: Joseph Fernandes <josferna@redhat.com> Reviewed-on: http://review.gluster.org/14068 Tested-by: Joseph Fernandes Smoke: Gluster Build System <jenkins@build.gluster.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
* tier/dht: check for rebalance completion for EIO errorMohammed Rafi KC2016-04-251-1/+3
| | | | | | | | | | | | | | | | | When an ongoing rebalance completion check task been triggered by dht, there is a possibility of a race between afr setting subvol as non-readable and dht updates the cached subvol. In this window a write can fail with EIO. Change-Id: I42638e6d4104c0dbe893d1bc73e1366188458c5d BUG: 1329503 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com> Reviewed-on: http://review.gluster.org/14049 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* dht: Add lease() fopPoornima G2016-04-251-0/+5
| | | | | | | | | | | | | Change-Id: I0bbc2c2ef115c78393f6570815a5b80316e7e4be BUG: 1319992 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/11720 Smoke: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra Talur <rtalur@redhat.com> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* cluster/distribute: detect stale layouts in entry fopsRaghavendra G2016-04-221-1/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | dht_mkdir () { first-hashed-subvol = hashed-subvol for "bname" in in-memory layout of "parent"; inodelk (SETLKW, parent, "LAYOUT_HEAL_DOMAIN", "can be any subvol, but we choose first-hashed-subvol randomly"); { begin: hashed-subvol = hashed-subvol for "bname" in in-memory layout of "parent"; hash-range = extract hashe-range from layout of "parent"; ret = mkdir (parent/bname, hashed-subvol, hash-range); if (ret == "hash-value doesn't fall into layout stored on the brick (this error is returned by posix-mkdir)") { refresh_parent_layout (); goto begin; } } inodelk (UNLCK, parent, "LAYOUT_HEAL_DOMAIN", "first-hashed-subvol"); proceed with other parts of dht_mkdir; } posix_mkdir (parent/bname, client-hash-range) { disk-hash-range = getxattr (parent, "dht-layout-key"); if (disk-hash-range != client-hash-range) { fail-with-error ("hash-value doesn't fall into layout stored on the brick"); return 0; } continue-with-posix-mkdir; } Similar changes need to be done for dentry operations like create, symlink, link, unlink, rmdir, rename. These will be addressed in subsequent patches. This patch addresses only mkdir codepath. This change breaks stripe tests, as on some striped subvols dht layout xattrs are not set for some reason. This results in failure of mkdir. Since striped volumes are always created with dht, some tests associated with stripe also fail. So, I am making following tests changes (since stripe is out of maintainance): * modify ./tests/basic/rpc-coverage.t to not to use striped volumes * mark all (2) tests in tests/bugs/stripe/ as bad tests Change-Id: Idd1ae879f24a48303dc743c1bb4d91f89a629e25 BUG: 1323040 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/13885 Smoke: Gluster Build System <jenkins@build.gluster.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com>
* dht: lock on subvols to prevent lookup vs rmdir raceSakshi2016-04-051-2/+9
| | | | | | | | | | | | | | | | | | | | | | There is a possibility that while an rmdir is completed on some non-hashed subvol and proceeding to others, a lookup selfheal can recreate the same directory on those subvols for which the rmdir had succeeded. Now the deletion of the parent directory will fail with an ENOTEMPTY. To fix this take blocking inodelk on the subvols before starting rmdir. Selfheal must also take blocking inodelk before creating the entry. Change-Id: I168a195c35ac1230ba7124d3b0ca157755b3df96 BUG: 1245065 Signed-off-by: Sakshi <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/13528 CentOS-regression: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* tier/dht : Attach tier fix layout to run in backgroundJoseph Fernandes2016-03-281-9/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 1. Spawn a thread for background fix-layout for tier process. 2. Once the fix-layout is completed a marker xttr is set on the root of volume to mark the completion of the background fixlayout, so that even if the tier process is spawned again, fixlayout will not be issued, if it was completed last time. 3. Please note that promotion of legacy files will happen eventually as the ctr lookup heal in the fixlayout slowly heals the ctr db for legacy files OR the ctr lookup heal happend due to a name lookup. 4. When a detach tier is successful in evacuation data from hot tier, we remove the marker xattr is removed. So that next attach tier runs the background tier fixlayout. what is remaining ? 1. Instead of clearing the marker xattr of tiering fix layout at the end of detach start clear it during detach commit. But the issue is detach commit is a glusterd operation and the volume is not mounted in glusterd. The reason we want to do it in detach commit is that if the admin wants to attach the same tier again, then a background fixlayout will be triggered, which would not be needed. 2. Clearing the CTR DB of the cold bricks when there is a detach commit, as it will be having entries which will be stale when the volume is used, with ctr off (ctr is switched off only when we have detach commit.) Change-Id: Ibe343572e95865325cd0eef4d0b976b626a3c0c5 BUG: 1313228 Signed-off-by: Joseph Fernandes <josferna@redhat.com> Reviewed-on: http://review.gluster.org/13491 Smoke: Gluster Build System <jenkins@build.gluster.com> Tested-by: Joseph Fernandes NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* dht: report constant directory sizeJeff Darcy2016-03-201-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | Directory size is meaningless. Every filesystem has its own unpredictable way of increasing or decreasing it, based on internal data structures and even transient conditions. Some filesystems (e.g. ext4) never decrease it at all. Others (e.g. btrfs) don't even report it. Very few programs look at it, and those that do are broken. Unfortunately, one such program is GNU tar, which will complain when it sees different values because at different times we got the value from different DHT subvolumes. To avoid such problems, just report a constant value. Change-Id: Id64ce917c75b5f7ff50cb55b6e997f3b3556e7e3 BUG: 1302948 Original-author: Shyam <srangana@redhat.com> Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/13770 Smoke: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/tier: add tunable to migrate files based on sizeDan Lambright2016-03-161-0/+1
| | | | | | | | | | | | | | | | | This fix adds a paramater "tier-max_promote_size" to control wether a file is migrated or not based on its size. By default the value is 0, meaning all files are migrated. If set to a non-zero value, files larger than the parameter won't be moved in tiered volumes. Change-Id: Ia6b88e9b2508935bef500d956f9192e59670fe00 BUG: 1313495 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/13570 Smoke: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Joseph Fernandes
* all: fixes for clang compile warningsKaleb S KEITHLEY2016-02-151-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | cli/src/cli-cmd-parser.c (chenk) cli/src/cli-xml-output.c (spandit) cli/src/cli.c (chenk) libglusterfs/src/common-utils.c (vmallika) libglusterfs/src/gfdb/gfdb_sqlite3.c (jfernand +1) rpc/rpc-transport/socket/src/socket.c (?) xlators/cluster/afr/src/afr-transaction.c (?) xlators/cluster/dht/src/dht-common.h (srangana +2) xlators/cluster/dht/src/dht-selfheal.c (srangana +2) xlators/debug/io-stats/src/io-stats.c (R. Wareing) xlators/features/barrier/src/barrier.c (vshastry) xlators/features/bit-rot/src/bitd/bit-rot-scrub.h (vshankar +1) xlators/features/shard/src/shard.c (kdhananj +1) xlators/mgmt/glusterd/src/glusterd-ganesha.c (skoduri) xlators/mgmt/glusterd/src/glusterd-handler.c (atinmu) xlators/mgmt/glusterd/src/glusterd-op-sm.h (atinmu) xlators/mgmt/glusterd/src/glusterd-snapshot.c (spandit) xlators/mgmt/glusterd/src/glusterd-syncop.c (atinmu) xlators/mgmt/glusterd/src/glusterd-volgen.c (atinmu) xlators/protocol/client/src/client-messages.h (mselvaga +1) xlators/storage/bd/src/bd-helper.c (M. Mohan Kumar) xlators/storage/bd/src/bd.c (M. Mohan Kumar) xlators/storage/posix/src/posix.c (nbalacha +1) Change-Id: I85934fbcaf485932136ef3acd206f6ebecde61dd BUG: 1293133 Signed-off-by: Kaleb S KEITHLEY <kkeithle@redhat.com> Reviewed-on: http://review.gluster.org/13031 CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Smoke: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
* cluster/tier: allow db queries to be interruptableDan Lambright2016-01-071-4/+17
| | | | | | | | | | | | | | | | | | | | A query to the database may take a long time if the database has many entries. The tier daemon also sends IPC calls to the bricks which can run slowly, espcially in RHEL6. While it is possible to track down each such instance, the snapshot feature should not be affected by database operations. It requires no migration be underway. Therefore it is okay to pause tiering at any time except when DHT is moving a file. This fix implements this strategy by monitoring when control passes to DHT to migrate a file using the GF_XATTR_FILE_MIGRATE_KEY trigger. If it is not, the pause operation is successful. Change-Id: I21f168b1bd424077ad5f38cf82f794060a1fabf6 BUG: 1287842 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/13104 Reviewed-by: Joseph Fernandes Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/dht : Ftruncate on migrating file fails with EINVALN Balachandran2015-12-221-4/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | What: If dht_open is called on a migrating file after the inode_ctx is set, subsequent FOPs on that fd do not open the fd on the dst subvol. This is seen when the open-ftruncate-close sequence is repeatedly called on a migrating file. A second call to the sequence described above causes dht_truncate_cbk to call dht_truncate2 as the dht_inode_ctx was already set by the first call. As dht_rebalance_in_progress_check is not called, the fd is not opened on the dst subvol. On a distributed-replicate volume, this causes AFR to open the fd using afr_fix_open, but with the wrong flags, causing posix_ftruncate to fail with EINVAL. The fix: We require fd specific information to make a decision while handling migrating files. Set the fd_ctx to indicate the fd has been opened on the dst subvol and check if it has been set while processing Phase1/Phase2 checks in the FOP callback functions. Change-Id: I43cdcd8017b4a11e18afdd210469de7cd9a5ef14 BUG: 1284823 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/12985 Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Dan Lambright <dlambrig@redhat.com>
* cluster/tier: do not block in synctask created from pause tierDan Lambright2015-12-211-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | We had run sleep() in the pause tier callback. Blocking within a synctask is dangerous. The sleep() call does not inform the synctask scheduler that a thread is no longer running. It therefore believes it is running. If a second synctask already exists, it may not be able to run. This occurs if the thread limit in the pool has been reached. Note the pool size only grows when a synctask is created, not when it is moved from wait state to run state, as is the case when an FOP completes. When the tier is paused during migration, synctasks already exist waiting for responses to FOPs to the server with high probability. The fix is to yield() in the RPC callback, which will place the synctask into the wait queue and free up a thread for the FOP callback. A timer wakes the callback after sufficient time has elapsed for the pause to occur. Change-Id: I6a947ee04c6e5649946cb6d8207ba17263a67fc6 BUG: 1267950 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12987 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com>
* tier:unlink during migrationMohammed Rafi KC2015-12-161-0/+3
| | | | | | | | | | | | | | | | | | | | | | files deleted during promotion were not deleting as the files are moving from hashed to non-hashed. On deleting a file that is undergoing promotion, the unlink call is not sent to the dst file as the hashed subvol == cached subvol. This causes the file to reappear once the migration is complete. This patch also fixes a problem with stale linkfile deleting. Change-Id: I4b02a498218c9d8eeaa4556fa4219e91e7fa71e5 BUG: 1282390 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com> Reviewed-on: http://review.gluster.org/12829 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> Tested-by: Dan Lambright <dlambrig@redhat.com>
* cluster/tier: fix loading tier.so into glusterdN Balachandran2015-12-031-1/+1
| | | | | | | | | | | | | | | | | glusterd occasionally loads shared libraries of translators. This failed for tiering due to a reference to dht_methods which is defined as a global variable which is not necessary. The global variable has been removed and this is now a member of dht_conf and is now initialised in the *_init calls. Change-Id: Ifa0a21e3962b5cd8d9b927ef1d087d3b25312953 BUG: 1287842 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/12863 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> Tested-by: Dan Lambright <dlambrig@redhat.com>
* dht: heal directory path if the directory is not presentMohammed Rafi KC2015-11-081-0/+6
| | | | | | | | | | | | | | | | | | | After a successful nameless lookup if the directory is not present on any of the subvol, then we will get the path of the directory and will recursively send a named lookp on each parent directory. This will help particularly for the scenarios like add brick and attach-tier. Change-Id: I64c2118a5ab03bbaa59b0dfc62babdf4472a92a3 BUG: 1272949 Signed-off-by: Mohammed Rafi KC <rkavunga@redhat.com> Reviewed-on: http://review.gluster.org/12376 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/tier: add pause tier for snapshotsDan Lambright2015-10-211-1/+10
| | | | | | | | | | | | | | | | | | | | Snaps of tiered volumes cannot handle files undergoing migration. We implement a helper mechanism to "pause" migration. Any files undergoing migration are aborted. Clean up is done to remove sticky bits and data at the destination. Migration is restarted after snap completes. For testing an internal switch is added. It is not exposed externally. gluster volume set vol1 tier-pause [true|false] Change-Id: Ia85bbf89ac142e9b7e73fcbef98bb9da86097799 BUG: 1267950 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12304 Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/tier: add watermarks and policy driverDan Lambright2015-10-101-2/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fix introduces infrastructure to support different policies for promotion and demotion. Currently the tier feature automatically promotes and demotes files periodically based on access. This is good for testing but too stringent for most real workloads. It makes it difficult to fully utilize a hot tier- data will be demoted before it is touched- its unlikely a 100GB hot SSD will have all its data touched in a window of time. A new parameter "mode" allows the user to pick promotion/demotion polcies. The "test mode" will be used for *.t and other general testing. This is the current mechanism. The "cache mode" introduces watermarks. The watermarks represent levels of data residing on the hot tier. "cache mode" policy: The % the hot tier is full is called P. Do not promote or demote more than D MB or F files. A random number [0-100] is called R. Rules for migration: if (P < watermark_low) don't demote, always promote. if (P >= watermark_low) && (P < watermark_hi) demote if R < P; promote if R > P. if (P > watermark_hi) always demote, don't promote. gluster volume set {vol} cluster.watermark-hi % gluster volume set {vol} cluster.watermark-low % gluster volume set {vol} cluster.tier-max-mb {D} gluster volume set {vol} cluster.tier-max-files {F} gluster volume set {vol} cluster.tier-mode {test|cache} Change-Id: I157f19667ec95aa1d53406041c1e3b073be127c2 BUG: 1257911 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/12039 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* cluster/tier: Handle FOPs on files being migratedN Balachandran2015-09-221-1/+12
| | | | | | | | | | | | | | | | Determine which DHT level is responsible for handling fops on a file undergoing migration based on the name of the the linkto xattr set on the file being migrated and process accordingly. Change-Id: I82772e39314d4fe7f2ba0dcf22de0c6a374ee139 BUG: 1254428 Signed-off-by: N Balachandran <nbalacha@redhat.com> Signed-off-by: Nithya Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/12090 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>
* dht: reverting changes that takes lock on all subvols to prevent rmdir vs ↵Sakshi2015-09-141-11/+3
| | | | | | | | | | | | | | | lookup selfheal race Locking on all subvols before an rmdir is unable to remove all directory entries. Hence reverting the patch for now. Change-Id: I31baf2b2fa2f62c57429cd44f3f229c35eff1939 BUG: 1245065 Signed-off-by: Sakshi <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/12125 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>
* dht : lock on subvols to prevent lookup vs rmdir raceSakshi2015-08-271-3/+11
| | | | | | | | | | | | | | | | | There is a possibility that while an rmdir is completed on some non-hashed subvol and proceeding to others. A lookup selfheal can recreate the same directory on those subvols for which the rmdir had succeeded. The fix is to take a blocking inodelk on the subvols before starting rmdir. Since selfheal requires lock on all subvols, if an rmdir is in progess acquiring locks will fail and vice versa. Change-Id: I841a44758c3b88f5e04d1cb73ad36e0cac9fdabb BUG: 1245065 Signed-off-by: Sakshi <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/11725 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: avoid mknod on decommissioned brickSusant Palai2015-08-251-0/+5
| | | | | | | | | | Change-Id: I8c39ce38e257758e27e11ccaaff4798138203e0c BUG: 1256243 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/11998 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>
* dht: block/handle create op falling to decommissioned brickSusant Palai2015-08-231-0/+11
| | | | | | | | | | | | | | | | | | | | | | | Problem: Post remove-brick start till commit phase, the client layout may not be in sync with disk layout because of lack of lookup. Hence,a create call may fall on the decommissioned brick. Solution: Will acquire a lock on hashed subvol. So that a fix-layout or selfheal can not step on layout while reading the layout. Even if we read a layout before remove-brick fix-layout and the file falls on the decommissioned brick, the file should be migrated to a new brick as per the fix-layout. Change-Id: If84a12ec34f981adb2b9b224e80f535cfe5bf9f2 BUG: 1232378 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/11260 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/dht: use refcount to manage memory used to store migrationRaghavendra G2015-07-011-0/+2
| | | | | | | | | | | | | | | | information. Without refcounting, we might free up memory while other fops are still accessing it. BUG: 1235927 Change-Id: Ia4fa4a651cd6fe2394a0c20cef83c8d2cbc8750f Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/11418 Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
* features/changelog: Avoid setattr fop logging during renameSaravanakumar Arumugam2015-06-111-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: When a file is renamed and the (renamed)file's Hashing falls into a different brick, DHT creates a special file(linkto file) in the brick(Hashed subvolume) and carries out setattr operation on that file. Currently, Changelog records this(setattr) operation in Hashed subvolume. glusterfind in turn records this operation as MODIFY operation. So, there is a NEW entry in Cached subvolume and MODIFY entry in Hashed subvolume for the same file. Solution: Avoid logging setattr operation carried out, by marking the operation as internal fop using xdata. In changelog translator, check whether setattr is set as internal fop and skip accordingly. Change-Id: I21b09afb5a638b88a4ccb822442216680b7b74fd BUG: 1230007 Signed-off-by: Saravanakumar Arumugam <sarumuga@redhat.com> Reviewed-on: http://review.gluster.org/11137 Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: fix incorrect dst subvol info in inode_ctxNithya Balachandran2015-06-021-1/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Stashing additional information in the inode_ctx to help decide whether the migration information is stale, which could happen if a file was migrated several times but FOPs only detected the P1 migration phase. If no FOP detects the P2 phase, the inode ctx1 is never reset. We now save the src subvol as well as the dst subvol in the inode ctx. The src subvol is the subvol on which the FOP was sent when the mig info was set in the inode ctx. This information is considered stale if: 1. The subvol on which the current FOP is sent is the same as the dst subvol in the ctx 2. The subvol on which the current FOP is sent is not the same as the src subvol in the ctx This does not handle the case where the same file might have been renamed such that the src subvol is the same but the dst subvol is different. However, that is unlikely to happen very often. Change-Id: I05a2e9b107ee64750c7ca629aee03b03a02ef75f BUG: 1142423 Signed-off-by: Nithya Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/10834 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: pass a destination subvol to fop2 variants to avoid races.Raghavendra G2015-06-021-3/+3
| | | | | | | | | | | | | | | | | | | The destination subvol used in the fop2 variants is either stored in inode-ctx1 or local->cached_subvol. However, it is not guaranteed that a value stored in these locations before invocation of fop2 is still present after the invocation as these locations are shared among different concurrent operations. So, to preserve the atomicity of "check dst-subvol and invoke fop2 variant if dst-subvol found", we pass down the dst-subvol to fop2 variant. This patch also fixes error handling in some fop2 variants. Change-Id: Icc226228a246d3f223e3463519736c4495b364d2 BUG: 1142423 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/10943 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com>
* dht: Add lookup-optimize configuration option for DHTShyam2015-06-021-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently with commit 4eaaf5 a mixed version cluster would have issues if lookup-uhashed is set to auto, as older clients would fail to validate the layouts if newer clients (i.e 3.7 or upwards) create directories. Also, in a mixed version cluster rebalance daemon would set commit hash for some subvolumes and not for the others. This commit fixes this problem by moving the enabling of the functionality introduced in the above mentioned commit to a new dht option. This option also has a op_version of 3_7_1 thereby preventing it from being set in a mixed version cluster. It brings in the following changes, - Option can be set only if min version of the cluster is 3.7.1 or more - Rebalance and mkdir update the layout with the commit hashes only if this option is set, hence ensuring rebalance works in a mixed version cluster, and also directories created by newer clients do not cause layout errors when read by older clients - This option also supersedes lookup-unhased, to enable the optimization for lookups more deterministic and not conflict with lookup-unhashed settings. Option added is cluster.lookup-optimize, which is a boolean. Usage: # gluster volume set VOLNAME cluster.lookup-optimize on Change-Id: Ifd1d4ce3f6438fcbcd60ffbfdbfb647355ea1ae0 BUG: 1222126 Signed-off-by: Shyam <srangana@redhat.com> Reviewed-on: http://review.gluster.org/10797 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Kaushal M <kaushal@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* build: do not #include "config.h" in each fileNiels de Vos2015-05-291-5/+0
| | | | | | | | | | | | | | | | | | Instead of including config.h in each file, and have the additional config.h included from the compiler commandline (-include option). When a .c file tests for a certain #define, and config.h was not included, incorrect assumtions were made. With this change, it can not happen again. BUG: 1222319 Change-Id: I4f9097b8740b81ecfe8b218d52ca50361f74cb64 Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/10808 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* dht: make lookup-unhashed=auto do something actually usefulJeff Darcy2015-05-101-1/+28
| | | | | | | | | | | | | | | | | | | | | | | | The key concept here is to determine whether a directory is "clean" by comparing its last-known-good topology to the current one for the volume. These are stored as "commit hashes" on the directory and the volume root respectively. The volume's commit hash changes whenever a brick is added or removed, and a fix-layout is done. A directory's commit hash changes only when a full rebalance (not just fix-layout) is done on it. If all bricks are present and have a directory commit hash that matches the volume commit hash, then we can assume that every file is in its "proper" place. Therefore, if we look for a file in that proper place and don't find it, we can assume it's not on any other subvolume and *safely* skip the global (broadcast to all) lookup. Change-Id: Id6ce4593ba1f7daffa74cfab591cb45960629ae3 BUG: 1219637 Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Signed-off-by: Shyam <srangana@redhat.com> Reviewed-on: http://review.gluster.org/7702 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* dht/rebalance: Throttle rebalanceSusant Palai2015-05-071-0/+8
| | | | | | | | | | | | Throttle value will be "normal" by default. For throttling down, a thread will be put in to sleep. And for throttling up, gf_defrag_process_dir will wake up the sleeping threads. Change-Id: I74d530e3effd6e60e6eec81ccc8ff65789fa9c13 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/10526 Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* dht/tier/rebalancer: Fix reset of tiering client pidJoseph Fernandes2015-05-051-0/+1
| | | | | | | | | | | | | | | | In the patch http://review.gluster.org/#/c/9657 the client pid set by tiering migration was getting over- written in dht_start_rebalance_task(). Just corrected it in dht_setxattr() before calling dht_start_rebalance_task() and removed it from dht_start_rebalance_task(). Change-Id: I37cfa111f83a4e5d498042575c93799f60b49870 BUG: 1217937 Signed-off-by: Joseph Fernandes <josferna@redhat.com> Reviewed-on: http://review.gluster.org/10502 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Susant Palai <spalai@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* rebalance: Introducing local crawl and parallel migrationSusant Palai2015-04-291-0/+47
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current patch address two part of the design proposed. 1. Rebalance multiple files in parallel 2. Crawl only bricks that belong to the current node Brief design explanation for the above two points. 1. Rebalance multiple files in parallel: ------------------------------------- The existing rebalance engine is single threaded. Hence, introduced multiple threads which will be running parallel to the crawler. The current rebalance migration is converted to a "Producer-Consumer" frame work. Where Producer is : Crawler Consumer is : Migrating Threads Crawler: Crawler is the main thread. The job of the crawler is now limited to fix-layout of each directory and add the files which are eligible for the migration to a global queue in a round robin manner so that we will use all the disk resources efficiently. Hence, the crawler will not be "blocked" by migration process. Producer: Producer will monitor the global queue. If any file is added to this queue, it will dqueue that entry and migrate the file. Currently 20 migration threads are spawned at the beginning of the rebalance process. Hence, multiple file migration happens in parallel. 2. Crawl only bricks that belong to the current node: -------------------------------------------------- As rebalance process is spawned per node, it migrates only the files that belongs to it's own node for the sake of load balancing. But it also reads entries from the whole cluster, which is not necessary as readdir hits other nodes. New Design: As part of the new design the rebalancer decides the subvols that are local to the rebalancer node by checking the node-uuid of root directory prior to the crawler starts. Hence, readdir won't hit the whole cluster as it has already the context of local subvols and also node-uuid request for each file can be avoided. This makes the rebalance process "more scalable". Change-Id: I73ed6ff807adea15086eabbb8d9883e88571ebc1 BUG: 1171954 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/9657 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* glusterd: support for tier volumes 'detach start' and 'detach commit'Dan Lambright2015-04-221-0/+6
| | | | | | | | | | | | | | | | | | | | | These commands work in a manner analagous to rebalancing when removing a brick. The existing migration daemon detects "detach start" and switches to moving data off the hot tier. While in this state all lookups are directed to the cold tier. gluster v detach-tier <vol> start gluster v detach-tier <vol> commit The status and stop cli commands shall be submitted separately. Change-Id: I24fda5cc3ba74f5fb8aa9a3234ad51f18b80a8a0 BUG: 1205540 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Signed-off-by: root <root@localhost.localdomain> Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/10108 Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Tested-by: NetBSD Build System
* Xlators : Fixed typosManikandan Selvaganesh2015-04-021-1/+1
| | | | | | | | | | | Change-Id: I948f85cb369206ee8ce8b8cd5e48cae9adb971c9 BUG: 1075417 Signed-off-by: Manikandan Selvaganesh <mselvaga@redhat.com> Reviewed-on: http://review.gluster.org/9529 Reviewed-by: Niels de Vos <ndevos@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Reviewed-by: Humble Devassy Chirammal <humble.devassy@gmail.com>
* libxlator: Change marker xattr handling interfacePranith Kumar K2015-03-251-3/+0
| | | | | | | | | | | | | | | | | | | | | - Changed the implementation of marker xattr handling to take just a function which populates important data that is different from default 'gauge' values and subvolumes where the call needs to be wound. - Removed duplicate code I found while reading the code and moved it to cluster_marker_unwind. Removed unused structure members. - Changed dht/afr/stripe implementations to follow the new implementation - Implemented marker xattr handling for ec. Change-Id: Ib0c3626fe31eb7c8aae841eabb694945bf23abd4 BUG: 1200372 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/9892 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Add tier translator.Dan Lambright2015-03-211-0/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The tier translator shares most of DHT's code. It differs in how subvolumes are chosen for I/Os, and how file migration (cache promotion and demotion) is managed. That different functionality is split to either DHT or tier logic according to the "tier_methods" structure. A cache promotion and demotion thread is created in a manner similar to the rebalance daemon. The thread operates a timing wheel which periodically checks for promotion and demotion candidates (files). Candidates are queued and then migrated. Candidates must exist on the same node as the daemon and meet other critera per caching policies. This patch has two authors (Dan Lambright and Joseph Fernandes). Dan did the DHT changes and Joe wrote the cache policies. The fix depends on DHT readidr changes and the database library which have been submitted separately. Header files in libglusterfs/src/gfdb should be reviewed in patch 9683. For more background and design see the feature page [1]. [1] http://www.gluster.org/community/documentation/index.php/Features/data-classification Change-Id: Icc26c517ccecf5c42aef039f5b9c6f7afe83e46c BUG: 1194753 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/9724 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Change the subvolume encoding in d_off to be a "global"Dan Lambright2015-03-181-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | position in the graph rather than relative (local) to a particular translator. Encoding the volume in this way allows a single translator to manage which brick is currently being scanned for directory entries. Using a single translator minimizes allocated bits in the d_off. It also allows multiple DHT translators in the same graph to have a common frame of reference (the graph position) for which brick is being read. Multiple DHT translators are needed for the Tiering feature. The fix builds off a previous change (9332) which removed subvolume encoding from AFR. The fix makes an equivalent change to the EC translator. More background can be found in fix 9332 and gluster-dev discussions [1]. DHT and AFR/EC are responsibile (as before) for choosing which brick to enumerate directory entries in over the readdir lifecycle. The client translator receiving the readdir fop encodes the dht_t. It is referred to as the "leaf node" in the graph and corresponds to the brick being scanned. When DHT decodes the d_off, it translates the leaf node to a local subvolume, which represents the next node in the graph leading to the brick. Tracking of leaf nodes is done in common utility functions. Leaf nodes counts and positional information are updated on a graph switch. [1] www.gluster.org/pipermail/gluster-devel/2015-January/043592.html Change-Id: Iaf0ea86d7046b1ceadbad69d88707b243077ebc8 BUG: 1190734 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/9688 Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: fixes to should_layout_fix logicRaghavendra G2015-03-051-0/+5
| | | | | | | | | | | | | | * Don't consider "dir-spread-count" option. This option is not supported. * Consider transition to weighted to equal distribution or vice-versa a valid case for fixing the layout. Change-Id: I0dcfe555dae9269ce20a41611cfdaa4f96c9e98b BUG: 1196615 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/9809 Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* dht: fix for dht_lock_count() compile errorNiels de Vos2015-02-261-1/+1
| | | | | | | | | | | | | | | dht-common.h includes a function definition with "inline", but the function is not declared in the header. Dropping the "inline" compile directive so that linking against .o files works correctly. BUG: 1196650 Change-Id: I105be591125b29cd455769b0c4ff22d6e139227d Signed-off-by: Niels de Vos <ndevos@redhat.com> Reviewed-on: http://review.gluster.org/9760 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: synchronize with other concurrent healers while healing layout.Raghavendra G2015-02-201-6/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | Current layout heal code assumes layout setting is idempotent. This allowed multiple concurrent healers to set the layout without any synchronization. However, this is not the case as different healers can come up with different layout for same directory and making layout setting non-idempotent. So, we bring in synchronization among healers to 1. Not to overwrite an ondisk well-formed layout. 2. Refresh the in-memory layout with the ondisk layout if in-memory layout needs healing and ondisk layout is well formed. This patch can synchronize 1. among multiple healers. 2. among multiple fix-layouts (which extends layout to consider added or removed brick) 3. (but) not between healers and fix-layouts. So, the problem of in-memory stale layouts (not matching with layout ondisk), is not _completely_ fixed by this patch. Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Change-Id: Ia285f25e8d043bb3175c61468d0d11090acee539 BUG: 1176008 Reviewed-on: http://review.gluster.org/9302 Reviewed-by: N Balachandran <nbalacha@redhat.com>
* cluster/dht: Modify dht-rebalance.c to use trusted.distribute.migrate-dataDan Lambright2015-02-131-1/+1
| | | | | | | | | | | | | | | rather than distribute.migrate-data and work with CLI. The change makes this work both when it is internally driven and from the shell. The problem is further described in bugzilla # 1147107. Change-Id: I4fe04cae661dca25432530ddf5ac6ff2c957d6b3 BUG: 1147107 Signed-off-by: Dan Lambright <dlambrig@redhat.com> Reviewed-on: http://review.gluster.org/9284 Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* cluster/dht: Fix incorrect updates to parent timesKrutika Dhananjay2015-01-191-6/+5
| | | | | | | | | | | | | | | | | | | | | In directory write FOPs, as far as updates to timestamps associated with parent by DHT is concerned, there are three possibilities: a) time (in sec) gotten from child of DHT < time (in sec) in inode ctx b) time (in sec) gotten from child of DHT = time (in sec) in inode ctx c) time (in sec) gotten from child of DHT > time (in sec) in inode ctx In case (c), for time in nsecs, it is the value returned by DHT's child that must be selected. But what DHT_UPDATE_TIME ends up doing is to choose the maximum of (time in nsec gotten from DHT's child, time in nsec in inode ctx). Change-Id: I535a600b9f89b8d9b6714a73476e63ce60e169a8 BUG: 1179169 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/9457 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Tested-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: Rename should not fail post hardlink creationShyam2014-09-021-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | In the rename path, we wind the creation of newname hardlink and linkto file in dst hashed a the same time. If the linkto creation fails, but the link creation succeeds, we enter the failure code and cleanup the created newname hardlink. In the interim if another client looks up newname and finds it as a hardlink from FUSE, it could send an unlink for oldname instead of a rename. This combined with the above cleanup code could end up losing all the files copies, and thereby losing data. This fix separates these steps into 2 parts, creating the linkto first and then the link file, so that post link file creation no failures would cleanup the newname file. If linkto fails then link is not attempted, thereby not polluting the name space with newname. Change-Id: I61da8e906060da16a31ea1076eec2f01fd617f44 BUG: 1130888 Signed-off-by: Shyam <srangana@redhat.com> Reviewed-on: http://review.gluster.org/8570 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: synchronize rename and file-migrationRaghavendra G2014-08-281-0/+4
| | | | | | | | | Change-Id: I4f243c946f76d440680b651235f925e3d0ebf0fd BUG: 1130888 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/8523 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: introduce locking api.Raghavendra G2014-08-261-0/+56
| | | | | | | | | | Change-Id: I41389ba91951d3e63e617aa32cd0bee848261c72 BUG: 1130888 Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: http://review.gluster.org/8521 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Modified logic of linkto file deletion on non-hashedVenkatesh Somyajulu2014-07-311-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently whenever dht_lookup_everywhere gets called, if in dht_lookup_everywhere_cbk, a linkto file is found on non-hashed subvolume, file is unlinked. But there are cases when this file is under migration. Under such condition, we should avoid deletion of file. When some other rebalance process changes the layout of parent such that dst_file (w.r.t. migration) falls on non-hashed node, then may be lookup could have found it as linkto file but just before unlink, file is under migration or already migrated In such cased unlink can be avoided. Race: ------- If we have two bricks (brick-1 and brick-2) with initial file "a" under BaseDir which is hashed as well as cached on (brick-1). Assume "a" hashing gives 44. Brick-1 Brick-2 Initial Setup: BaseDir/a BaseDir [1-50] [51-100] Now add new-brick Brick-3. 1. Rebalance-1 on node Node-1 (Brick-1 node) will reset the BaseDir Layout. 2. After that it will perform a) Create linkto file on new-hashed (brick-2) b) Perform file migration. 1.Rebalance-1 Fixes the base-layout: Brick-1 Brick-2 Brick-3 --------- ---------- ------------ BaseDir/a BaseDir BaseDir [1-33] [34-66] [67-100] 2. Only a) is BaseDir/a BaseDir/a(linkto) BaseDir performed Create linktofile Now rebalance 2 on node-2 jumped in and it will perform step 1 and 2-a. After (rebal-2, step-1), it changes the layout of the BaseDir. BaseDir/a BaseDir/a(link) BaseDir [67-100] [1-33] [34-66] For (rebale-2, step-2), It will perform lookup at Brick-3 as w.r.t new layout 44 falls for brick-3. But lookup will fail. So dht_lookup_everywhere gets called. NOTE: On brick-2 by rebalance-1, a linkto file was created. Currently that linkto files gets deleted by rebalance-2 lookup as it is considered as stale linkto file. But with patch if rebalance is already in progress or rebalance is over, linkto file will not be unlinked. If rebalance is in progress fd will be open and if rebalance is over then linkto file wont be set. Change-Id: I3fee0d28de3c76197325536a9e30099d2413f079 BUG: 1116150 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/8345 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Fix races to avoid deletion of linkto fileVenkatesh Somyajulu2014-07-181-0/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Explanation of Race between rebalance processes: https://bugzilla.redhat.com/show_bug.cgi?id=1110694#c4 STATE 1: BRICK-1 only one brick Cached File in the system STATE 2: Add brick-2 BRICK-1 BRICK-2 STATE 3: Lookup of File on brick-2 by this node's rebalance will fail because hashed file is not created yet. So dht_lookup_everywhere is about to get called. STATE 4: As part of lookup link file at brick-2 will be created. STATE 5: getxattr to check that cached file belongs to this node is done STATE 6: dht_lookup_everywhere_cbk detects the link created by rebalance-1. It will unlink it. STATE 7: getxattr at the link file with "pathinfo" key will be called will fail as the link file is deleted by rebalance on node-2 Fix: So in the STATE 6, we should avoid the deletion of link file. Every time dht_lookup_everywhere gets called, lookup will be performed on all the nodes. So to avoid STATE 6, if linkto file is found, it is not deleted until valid case is found in dht_lookup_everywhere_done. Case 1: if linkto file points to cached node, and cached file exists, uwind with success. Case 2: if linkto does not point to current cached node, and cached file exists: a) Unlink stale link file b) Create new link file Case 3: Only linkto file exists: Delete linkto file Case 4: Only cached file Create link file (Handled event without patch) Case 5: Neither cached nor hashed file is present Return with ENOENT (handled even without patch) Change-Id: Ibf53671410d8d613b8e2e7e5d0ec30fc7dcc0298 BUG: 1116150 Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com> Reviewed-on: http://review.gluster.org/8231 Reviewed-by: Vijay Bellur <vbellur@redhat.com> Tested-by: Vijay Bellur <vbellur@redhat.com>
* dht: fix rename raceJeff Darcy2014-07-171-0/+1
| | | | | | | | | | | | | | | | | | | | | | | If two clients try to rename the same file at the same time, we sometimes end up with *no file at all* in either the old or new location. That's kind of bad. The culprit seems to be some overly aggressive cleanup code. AFAICT, based on today's study of the code, the intent of the changed section is to remove any linkfile we might have created before the actual rename. However, what we're removing might not be our extra link. If we're racing with another client that's also doing a rename, it might be the only remaining link to the user's data. The solution, which is good enough to pass this test but almost certainly still not complete, is to be more selective about when we do this unlink. Now, we only do it if we know that, at some point, we did in fact create the link without error (notably ENOENT on the source or EEXIST on the destination) ourselves. Change-Id: I8d8cce150b6f8b372c9fb813c90be58d69f8eb7b BUG: 1117851 Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-on: http://review.gluster.org/8269 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-05 05:05:19 +0000