summaryrefslogtreecommitdiffstats
path: root/xlators/cluster/ec/src/ec-common.h
Commit message (Collapse)AuthorAgeFilesLines
* cluster/ec: Fix tracking of good bricksXavier Hernandez2015-08-141-8/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | 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> Change-Id: Idbe68b28b865c4b28366703ad1e96ae16ba44b66 BUG: 1235964 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/11867 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>
* cluster/ec: Minimize usage of EIO errorXavier Hernandez2015-08-081-1/+7
| | | | | | | | | | | | | | | | | | >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> Change-Id: Ifd3d63f88a686a2963c5ba2e62110249f84f338d BUG: 1250864 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/11852 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/ec: Handle race between unlock-timer, new lockPranith Kumar K2015-07-231-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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> Change-Id: I9af012e717493684b7cd7d1c63baf2fa401fb542 BUG: 1246121 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11752 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* cluster/ec: wind readlink on good subvol(s)Pranith Kumar K2015-07-211-1/+1
| | | | | | | | | | | | | | | | | >BUG: 1232172 >Change-Id: I3a56e487840d86147dd85bf5fbe79b165eae289f >Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> >Reviewed-on: http://review.gluster.org/11589 >Tested-by: NetBSD Build System <jenkins@build.gluster.org> >Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> >Tested-by: Gluster Build System <jenkins@build.gluster.com> BUG: 1234679 Change-Id: I08560eee095a3921e9c24f16dc2a242a76018a42 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11687 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* cluster/ec: Add throttling in background healingPranith Kumar K2015-07-211-0/+1
| | | | | | | | | | | | | | | | | | | | | - 8 parallel heals can happen. - 128 heals will wait for their turn - Heals will be rejected if 128 heals are already waiting. >Change-Id: I2e99bf064db7bce71838ed9901a59ffd565ac390 >BUG: 1237381 >Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> >Reviewed-on: http://review.gluster.org/11471 >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> BUG: 1238476 Change-Id: Id9625536197c1f5d6c3a9ed53f80bd9e6d14c507 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11679 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* cluster/ec: wind fops on good subvols for access/readdir[p]Pranith Kumar K2015-07-011-1/+2
| | | | | | | | | | | Backport of http://review.gluster.com/11246 BUG: 1234679 Change-Id: I2d774f62740c82e922efab50fc78fa74050ede93 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11357 Tested-by: NetBSD Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/ec: Prevent double unwindPranith Kumar K2015-06-181-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | Backport of http://review.gluster.com/11111 Problem: 1) ec_access/ec_readlink_/ec_readdir[p] _cbks are trying to recover only from ENOTCONN. 2) When the fop succeeds it unwinds right away. But when its ec_fop_manager resumes, if the number of bricks that are up is less than ec->fragments, the the state machine will resume with -EC_STATE_REPORT which unwinds again. This will lead to crashes. Fix: - If fop fails retry on other subvols, as ESTALE/ENOENT/EBADFD etc are also recoverable. - unwind success/failure in _cbks BUG: 1229331 Change-Id: I7510984a237761efba65e872313a8ede8b7543e5 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/11128 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* cluster/ec: Fix all EIO errors in ECPranith Kumar K2015-05-281-13/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Backport of http://review.gluster.org/10770 Backport of http://review.gluster.org/10806 Backport of http://review.gluster.org/10787 Backport of http://review.gluster.org/10868 Backport of http://review.gluster.com/10852 - When a blocking lock is requested, lock request is succeeded even when ec->fragment number of locks are acquired successfully in non-blocking locking phase. This will lead to fop succeeding only on the bricks where the locks are acquired, leading to the necessity of self-heals. To prevent these un-necessary self-heals, if the remaining locks fail with EAGAIN in non-blocking lock phase try blocking locking phase instead. - Handle lookup failures while op in progress - cluster/ec: Correctly cleanup delayed locks When a delayed lock is pending, a graph switch doesn't correctly terminate it. This means that the update of version and size xattrs is lost, causing EIO errors. This patch handles GF_EVENT_PARENT_DOWN event to correctly finish pending udpdates before completing the graph switch. - Fix use after free crash ec_heal creates ec_fop_data but doesn't run ec_manager. ec_fop_data_allocate adds this fop to ec->pending_fops, because ec_manager is not run on this heal fop it is never removed from ec->pending_fops. When it is accessed after free it leads to crash. It is better to not to add HEAL fops to ec->pending_fops because we don't want graph switch to hang the mount because of a BIG file/directory heal. - Forced unlock when lock contention is detected EC uses an eager lock mechanism to optimize multiple read/write requests on the same entry or inode. This increases performance but can have adverse results when other clients try to access the same entry/inode. To solve this, this patch adds a functionality to detect when this happens and force an earlier release to not block other clients. The method consists on requesting GF_GLUSTERFS_INODELK_COUNT and GF_GLUSTERFS_ENTRYLK_COUNT for all fops that take a lock. When this count is greater than one, the lock is marked to be released. All fops already waiting for this lock will be executed normally before releasing the lock, but new requests that also require it will be blocked and restarted after the lock has been released and reacquired again. Another problem was that some operations did correctly lock the parent of an entry when needed, but got the size and version xattrs from the entry instead of the parent. This patch solves this problem by binding all queries of size and version to each lock and replacing all entrylk calls by inodelk ones to remove concurrent updates on directory metadata. This also allows rename to correctly update source and destination directories. BUG: 1225279 Change-Id: I02a6084b138dd38e018a462347cd9ce38610c7ef Reviewed-on: http://review.gluster.org/10926 Tested-by: NetBSD Build System Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* ec: Fix failures with missing filesXavier Hernandez2015-05-091-4/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | Backport of http://review.gluster.com/9407 When a file does not exist on a brick but it does on others, there could be problems trying to access it because there was some loc_t structures with null 'pargfid' but 'name' was set. This forced inode resolution based on <pargfid>/name instead of <gfid> which would be the correct one. To solve this problem, 'name' is always set to NULL when 'pargfid' is not present. Another problem was caused by an incorrect management of errors while doing incremental locking. The only allowed error during an incremental locking was ENOTCONN, but missing files on a brick can be returned as ESTALE. This caused an EIO on the operation. This patch doesn't care of errors during an incremental locking. At the end of the operation it will check if there are enough successfully locked bricks to continue or not. BUG: 1220011 Change-Id: I4a1e6235d80e20ef7ef12daba0807b859ee5c435 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/10701 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/ec: data heal implementation for ecPranith Kumar K2015-05-081-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | Data self-heal: 1) Take inode lock in domain 'this->name:self-heal' on 0-0 range (full file), So that no other processes try to do self-heal at the same time. 2) Take inode lock in domain 'this->name' on 0-0 range (full file), 3) perform fxattrop+fstat and get the xattrs on all the bricks 3) Choose the brick with ec->fragment number of same version as source 4) Truncate sinks 5) Unlock lock taken in 2) 5) For each block take full file lock, Read from sources write to the sinks, Unlock 6) Take full file lock and see if the file is still sane copy i.e. File didn't become unusable while the bricks are offline. Update mtime to before healing 7) xattrop with -ve values of 'dirty' and difference of highest and its own version values for version xattr 8) unlock lock acquired in 6) 9) unlock lock acquired in 1) Change-Id: I6f4d42cd5423c767262c9d7bb5ca7767adb3e5fd BUG: 1216303 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/10384 Reviewed-on: http://review.gluster.org/10692 Tested-by: Gluster Build System <jenkins@build.gluster.com>
* cluster/ec: metadata/name/entry heal implementation for ecPranith Kumar K2015-05-081-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Metadata self-heal: 1) Take inode lock in domain 'this->name' on 0-0 range (full file) 2) perform lookup and get the xattrs on all the bricks 3) Choose the brick with highest version as source 4) Setattr uid/gid/permissions 5) removexattr stale xattrs 6) Setxattr existing/new xattrs 7) xattrop with -ve values of 'dirty' and difference of highest and its own version values for version xattr 8) unlock lock acquired in 1) Entry self-heal: 1) take directory lock in domain 'this->name:self-heal' on 'NULL' to prevent more than one self-heal 2) we take directory lock in domain 'this->name' on 'NULL' 3) Perform lookup on version, dirty and remember the values 4) unlock lock acquired in 2) 5) readdir on all the bricks and trigger name heals 6) xattrop with -ve values of 'dirty' and difference of highest and its own version values for version xattr 7) unlock lock acquired in 1) Name heal: 1) Take 'name' lock in 'this->name' on 'NULL' 2) Perform lookup on 'name' and get stat and xattr structures 3) Build gfid_db where for each gfid we know what subvolumes/bricks have a file with 'name' 4) Delete all the stale files i.e. the file does not exist on more than ec->redundancy number of bricks 5) On all the subvolumes/bricks with missing entry create 'name' with same type,gfid,permissions etc. 6) Unlock lock acquired in 1) Known limitation: At the moment with present design, it conservatively preserves the 'name' in case it can not decide whether to delete it. this can happen in the following scenario: 1) we have 3=2+1 (bricks: A, B, C) ec volume and 1 brick is down (Lets say A) 2) rename d1/f1 -> d2/f2 is performed but the rename is successful only on one of the bricks (Lets say B) 3) Now name self-heal on d1 and d2 would re-create the file on both d1 and d2 resulting in d1/f1 and d2/f2. Because we wanted to prevent data loss in the case above, the following scenario is not healable, i.e. it needs manual intervention: 1) we have 3=2+1 (bricks: A, B, C) ec volume and 1 brick is down (Lets say A) 2) We have two hard links: d1/a, d2/b and another file d3/c even before the brick went down 3) rename d3/c -> d2/b is performed 4) Now name self-heal on d2/b doesn't heal because d2/b with older gfid will not be deleted. One could think why not delete the link if there is more than 1 hardlink, but that leads to similar data loss issue I described earlier: Scenario: 1) we have 3=2+1 (bricks: A, B, C) ec volume and 1 brick is down (Lets say A) 2) We have two hard links: d1/a, d2/b 3) rename d1/a -> d3/c, d2/b -> d4/d is performed and both the operations are successful only on one of the bricks (Lets say B) 4) Now name self-heal on the 'names' above which can happen in parallel can decide to delete the file thinking it has 2 links but after all the self-heals do unlinks we are left with data loss. Change-Id: I3a68218a47bb726bd684604efea63cf11cfd11be BUG: 1216303 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/10298 Reviewed-on: http://review.gluster.org/10691 Tested-by: Gluster Build System <jenkins@build.gluster.com> Tested-by: NetBSD Build System
* ec: Add trusted.ec.dirty xattrXavier Hernandez2015-02-231-0/+1
| | | | | | | | | | | | | | | | | This xattr will be incremented before each data modifying operation and decremented after it. This will add the possibility to detect partially updated writes and refuse them on reads. It will also be useful for interacting with index xlator and have a way to heal dispersed files from the self-heal daemon. Change-Id: Ie644a8dd074ae0f254c809c5863bdb030be5486a BUG: 1190581 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9607 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix posix compliance failuresXavier Hernandez2015-01-281-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch solves some problems that caused dispersed volumes to not pass posix smoke tests: * Problems in open/create with O_WRONLY Opening files with -w- permissions using O_WRONLY returned an EACCES error because internally O_WRONLY was replaced with O_RDWR. * Problems with entrylk on renames. When source and destination were the same, ec tried to acquire the same entrylk twice, causing a deadlock. * Overwrite of a variable when reordering locks. On a rename, if the second lock needed to be placed at the beggining of the list, the 'lock' variable was overwritten and later its timer was cancelled, cancelling the incorrect one. * Handle O_TRUNC in open. When O_TRUNC was received in an open call, it was blindly propagated to child subvolumes. This caused a discrepancy between real file size and the size stored into trusted.ec.size xattr. This has been solved by removing O_TRUNC from open and later calling ftruncate. Change-Id: I20c3d6e1c11be314be86879be54b728e01013798 BUG: 1161886 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9420 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* ec: Change licenseXavier Hernandez2014-12-031-16/+6
| | | | | | | | | | Change-Id: Iae90ade2421898417b53dec0417a610cf306c44b BUG: 1168167 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/9201 Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Fix self-heal issuesXavier Hernandez2014-10-211-12/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Doing an 'ls' of a directory that has been modified while one of the bricks was down, sometimes returns the old directory contents. Cause: Directories are not marked when they are modified as files are. The ec xlator balances requests amongst available and healthy bricks. Since there is no way to detect that a directory is out of date in one of the bricks, it is used from time to time to return the directory contents. Solution: Basically the solution consists in use versioning information also for directories, however some additional changes have been necessary. Changes: * Use directory versioning: This required to lock full directory instead of a single entry for all requests that add or remove entries from it. This is needed to allow atomic version update. This affects the following fops: create, mkdir, mknod, link, symlink, rename, unlink, rmdir Another side effect is that opendir requires to do a previous lookup to get versioning information and discard out of date bricks for subsequent readdir(p) calls. * Restrict directory self-heal: Till now, when one discrepancy was found in lookup, a self-heal was automatically started. This caused the versioning information of a bad directory to be healed instantly, making the original problem to reapear again. To solve this, when a missing directory is detected in one or more bricks on lookup or opendir fops, only a partial self-heal is performed on it. A partial self-heal basically creates the directory but does not restore any additional information. This avoids that an 'ls' could repair the directory and cause the problem to happen again. With this change, output of 'ls' is always consistent. However, since the directory has been created in the brick, this allows any other operation on it (create new files, for example) to succeed on all bricks and not add additional work to the self-heal process. To force a self-heal of a directory, any other operation must be done on it. For example a getxattr. With these changes, the correct healing procedure that would avoid inconsistent directory browsing consists on a post-order traversal of directoriesi being healed. This way, the directory contents will be healed before healing the directory itslef. * Additional changes to fix self-heal errors - Don't use fop->fd to decide between fd/loc. open, opendir and create have an fd, but the correct data is in loc. - Fix incorrect management of bad bricks per inode/fd. - Fix incorrect selection of fop's target bricks when there are bad bricks involved. - Improved ec_loc_parent() to always return a parent loc as complete as possible. Change-Id: Iaf3df174d7857da57d4a87b4a8740a7048b366ad BUG: 1149726 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8916 Reviewed-by: Dan Lambright <dlambrig@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
* ec: Add config information in an xattrXavier Hernandez2014-09-231-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | To simplify backward compatibility of the ec xlator when some parameter or the implementation itself is changed, a new xattr is added to each file with the configuration needed to recover it. The new attribute is called 'trusted.ec.config', and it's a 64-bit value containing the following information: 8 bits: version of the config information (currently always 0) 8 bits: algorithm used to encode the file (currently always 0) 8 bits: size of the galois field (currently always 8) 8 bits: number of bricks 8 bits: redundancy 24 bits: chunk size (currently 512) This new xattr could allow, in a future version, to have different configurations per file. Change-Id: I8c12d40ff546cc201fc66caa367484be3d48aeb4 BUG: 1140861 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8770 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
* ec: Optimize read/write performanceXavier Hernandez2014-09-151-8/+9
| | | | | | | | | | | | | | | | | | This patch significantly improves performance of read/write operations on a dispersed volume by reusing previous inodelk/ entrylk operations on the same inode/entry. This reduces the latency of each individual operation considerably. Inode version and size are also updated when needed instead of on each request. This gives an additional boost. Change-Id: I4b98d5508c86b53032e16e295f72a3f83fd8fcac BUG: 1122586 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/8369 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
* cluster/ec: Added erasure code translatorXavier Hernandez2014-07-111-0/+105
Change-Id: I293917501d5c2ca4cdc6303df30cf0b568cea361 BUG: 1118629 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: http://review.gluster.org/7749 Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-21 22:22:38 +0000