summaryrefslogtreecommitdiffstats
path: root/xlators/cluster
Commit message (Collapse)AuthorAgeFilesLines
* cluster/dht: Use size to calculate estimatesN Balachandran2017-07-103-24/+188
| | | | | | | | | | | | | | | | | | | The earlier approach of using the number of files to determine when the rebalance would complete did not work well when file sizes differed widely. The new approach now gets the total data size and uses that information to determine how long the rebalance is expected to take. Change-Id: I84e80a0893efab72ff06130e4596fa71c9c8c868 BUG: 1467209 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17668 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: MOHIT AGRAWAL <moagrawa@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/ec : Don't try to heal when no sink is UPAshish Pandey2017-07-071-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: 4 + 2 EC volume configuration. If untar of linux is going on and we kill a brick, indices will be created for the files/dir which need to be healed. ec_shd_index_sweep spawns threads to scan these entries and start heal. If in the middle of this we kill one more brick, we end up in a situation where we can not heal an entry as there are only "ec->fragment" number of bricks are UP. However, the scan will be continued and it will trigger the heal for those entries. Solution: When a heal is triggered for an entry, check if it *CAN* be healed or not. If not come out with ENOTCONN. Change-Id: I305be7701c289f36bd7bde22491b71074771424f BUG: 1464359 Signed-off-by: Ashish Pandey <aspandey@redhat.com> Reviewed-on: https://review.gluster.org/17692 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Sunil Kumar Acharya <sheggodu@redhat.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* cluster/ec: correctly handle end of file for seekXavier Hernandez2017-07-061-0/+18
| | | | | | | | | | | | | | | | | When a SEEK_HOLE was issued near to the end of file, sometimes an offset beyond the end of file was returned. Another problem was that using some offsets greater than the end of file returned successfully instead of failing with ENXIO. Change-Id: I238d2884ba02fd19a78116b0f8f8e8d6338fb3f5 BUG: 1449348 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: https://review.gluster.org/17228 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* core: assorted typos and spelling mistakes from Debian lintianKaleb S. KEITHLEY2017-07-031-1/+1
| | | | | | | | | | | | | | Plus minor readability improvements. Reported-by: pmatthaei@debian.org Change-Id: I5393819a2fc9f240a19811143bb57b127df717cf BUG: 1466785 Signed-off-by: Kaleb S. KEITHLEY <kkeithle@redhat.com> Reviewed-on: https://review.gluster.org/17660 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster:dht Fix crash in dht_rename_lock_cbkN Balachandran2017-06-291-2/+4
| | | | | | | | | | | | | | | | | | Use a local variable to store the call count in the STACK_WIND for loop. Using frame->local is dangerous as it could be freed while the loop is still being processed Change-Id: Ie65cdcfb7868509b4a83bc2a5b5d6304eabfbc8e BUG: 1466110 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17645 Smoke: Gluster Build System <jenkins@build.gluster.org> Tested-by: Nigel Babu <nigelb@redhat.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* cluster/dht: Check if fd is opened on dst subvolN Balachandran2017-06-286-30/+543
| | | | | | | | | | | | | | | | | | | | If an fd is opened on a file, the file is migrated and the cached subvol is updated in the inode_ctx before an fd based fop is sent, the fop is sent to the dst subvol on which the fd is not opened. This causes the FOP to fail with EBADF. Now, every fd based fop will check to see that the fd has been opened on the dst subvol before winding it down. Change-Id: Id92ef5eb7a5b5226688e2d2868b15e383f5f240e BUG: 1465075 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17630 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-by: Susant Palai <spalai@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* ec: Increase notification in all the casesAshish Pandey2017-06-281-31/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: "gluster v heal <volname> info" is taking long time to respond when a brick is down. RCA: Heal info command does virtual mount. EC wait for 10 seconds, before sending UP call to upper xlator, to get notification (DOWN or UP) from all the bricks. Currently, we are increasing ec->xl_notify_count based on the current status of the brick. So, if a DOWN event notification has come and brick is already down, we are not increasing ec->xl_notify_count in ec_handle_down. Solution: Handle DOWN even as notification irrespective of what is the current status of brick. Change-Id: I0acac0db7ec7622d4c0584692e88ad52f45a910f BUG: 1464091 Signed-off-by: Ashish Pandey <aspandey@redhat.com> Reviewed-on: https://review.gluster.org/17606 Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
* cluster/rebalance: Use GF_XATTR_LIST_NODE_UUIDS_KEY to figure out local subvols.Susant Palai2017-06-263-55/+54
| | | | | | | | | | | | | | | | | | | | | | Afr has introduced a new key GF_XATTR_LIST_NODE_UUIDS_KEY, through which rebalance will figure out its local subvolumes.(Reference bugid=1463250) key: GF_XATTR_NODE_UUID_KEY will continue to serve it's old purpose of returning the first afr chiild. test: prove tests/basic/distribute/rebal-all-nodes-migrate.t Change-Id: I4d602feda2a05b29d2210c712a07a4ac6b8bc112 BUG: 1463648 Signed-off-by: Susant Palai <spalai@redhat.com> Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17595 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* cluster/dht: rebalance gets file count periodicallyN Balachandran2017-06-234-30/+97
| | | | | | | | | | | | | | | | The rebalance used to get the file count in the beginning and not update it. This caused estimates to fail if the number changed during the rebalance. The rebalance now updates the file count periodically. Change-Id: I1667ee69e8a1d7d6bc6bc2f060fad7f989d19ed4 BUG: 1464110 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17607 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/ec: Node uuid xattr support update for ECSunil Kumar Acharya2017-06-232-6/+23
| | | | | | | | | | | | | | | | | | | | | | | | | Problem: The change in EC to return list of node uuids for GF_XATTR_NODE_UUID_KEY was causing problems with geo-rep. Fix: This patch will allow to get the single node uuid as it was doing before with the key "GF_XATTR_NODE_UUID_KEY", and will also allow to get the list of node uuids by using a new key "GF_XATTR_LIST_NODE_UUIDS_KEY". This will solve the problem with geo-rep and any other features which were depending on this. BUG: 1462790 Change-Id: I2d9214a9658d4a41a3d6de08600884d2bda5f3eb Signed-off-by: Sunil Kumar Acharya <sheggodu@redhat.com> Reviewed-on: https://review.gluster.org/17594 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* dht/hardlink : Remove stale linkto file incase of failureJiffin Tony Thottan2017-06-223-1/+81
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a similar issue fixed for rename in https://review.gluster.org/#/c/16016/ For hardlinks, if cached and hashed subvolumes are different, then it will first create linkto file in hashed using root permission, but actually hardlink creation fails with EACESS and stale linkto file is never removed.All the followup hardlink calls with file name will result ESTALE because linktofile creation fails with EEXIST and follow up lookup on linkto file returns gfid-mismatching(old linkto file) and finally fails with ESTALE Steps to produce : (From link/00.t test from posix-testsuite) Steps executed in script * create a file "abc" using root * change the ownership of file to a non root user * create hardlink "link" for "abc" using a non root user, it fails with EACESS * delete "abc" * create directory "abc" using root * again try to create hadrlink "link" for "abc" using non root user, fails with ESTALE Also tried to fix other bugs in dht_linkfile_create_cbk() and posix_lookup. Thanks Susant for the help in debugging the issue and suggestion for this patch. Change-Id: I7a5a1899d3fd1fdb13578b37f9d52a084492e35d BUG: 1452084 Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com> Reviewed-on: https://review.gluster.org/17331 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/afr: Returning single and list of node uuids from AFRkarthik-us2017-06-201-9/+79
| | | | | | | | | | | | | | | | | | | | | | | | Problem: The change in afr to return list of node uuids was causing problems with geo-rep. Fix: This patch will allow to get the single node uuid as it was doing before with the key "GF_XATTR_NODE_UUID_KEY", and will also allow to get the list of node uuids by using a new key "GF_XATTR_LIST_NODE_UUIDS_KEY". This will solve the problem with geo-rep and any other feature which were depending on this. Change-Id: I09885dac6dfca127be94b708470c8c2941356f9a BUG: 1462790 Signed-off-by: karthik-us <ksubrahm@redhat.com> Reviewed-on: https://review.gluster.org/17576 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Kotresh HR <khiremat@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us>
* dht: passing the errno as an argument to gf_msgAnkitRaj2017-06-201-110/+109
| | | | | | | | | | | | | | | | | | | There are many calls in gf_msg where errno is needed to pass as an argument instead of strerrno(error) Change-Id: I15048a5e0b41f9752a2023afe8470eca6f2cd383 Bug: 1454701 Signed-off-by: AnkitRaj <anraj@redhat.com> Reviewed-on: https://review.gluster.org/17464 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: MOHIT AGRAWAL <moagrawa@redhat.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Tested-by: N Balachandran <nbalacha@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Karthik U S <ksubrahm@redhat.com> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us>
* cluster/dht: Additional checks for rebalance estimatesN Balachandran2017-06-201-5/+15
| | | | | | | | | | | | | | | | | | | | | The rebalance estimates calculation was not handling calculations correctly when no files had been processed, i.e., when rate_lookedup was 0. Now, the estimated time is set to 0 in such scenarios as there is no way for rebalance to figure out how long the process will take to complete without knowing the rate at which the files are being processed. Change-Id: I7b6378e297e1ba139852bcb2239adf2477336b5b BUG: 1457985 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17564 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/afr: Implement quorum for lk fopPranith Kumar K2017-06-192-23/+38
| | | | | | | | | | | | | | | | | | | Problem: At the moment when we have replica 3 or arbiter setup, even when lk succeeds on just one brick we give success to application which is wrong Fix: Consider quorum-number of successes as success when quorum is enabled. BUG: 1461792 Change-Id: I5789e6eb5defb68f8a0eb9cd594d316f5cdebaea Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: https://review.gluster.org/17524 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com>
* cluster/ec: lk shouldn't be a transactionPranith Kumar K2017-06-161-19/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: When application sends a blocking lock, the lk fop actually waits under inodelk. This can lead to a dead-lock. 1) Let's say app-1 takes exculsive-fcntl-lock on the file 2) app-2 attempts an exclusive-fcntl-lock on the file which goes to blocking stage note: app-2 is blocked inside transaction which holds an inode-lock 3) app-1 tries to perform write which needs inode-lock so it gets blocked on app-2 to unlock inodelk and app-2 is blocked on app-1 to unlock fcntl-lock Fix: Correct way to fix this issue and make fcntl locks perform well would be to introduce 2-phase locking for fcntl lock: 1) Implement a try-lock phase where locks xlator will not merge lk call with existing calls until a commit-lock phase. 2) If in try-lock phase we get quorum number of success without any EAGAIN error, then send a commit-lock which will merge locks. 3) In case there are any errors, unlock should just delete the lock-object which was tried earlier and shouldn't touch the committed locks. Unfortunately this is a sizeable feature and need to be thought through for any corner cases. Until then remove transaction from lk call. BUG: 1455049 Change-Id: I18a782903ba0eb43f1e6526fb0cf8c626c460159 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: https://review.gluster.org/17542 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Ashish Pandey <aspandey@redhat.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* dht: reduce duplicate code in tier migrateAmar Tumballi2017-06-141-75/+10
| | | | | | | | | | | | | | | Updates #234 Change-Id: I016f6d4f1e5ad2ea56a611c1bffbd189f10650db Signed-off-by: Amar Tumballi <amarts@redhat.com> Reviewed-on: https://review.gluster.org/17525 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: hari gowtham <hari.gowtham005@gmail.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Susant Palai <spalai@redhat.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: Include dirs in rebalance estimatesN Balachandran2017-06-073-31/+83
| | | | | | | | | | | | | | | | | Empty directories were not being considered while calculating rebalance estimates leading to negative time-left values being displayed as part of the rebalance status. Change-Id: I48d41d702e72db30af10e6b87b628baa605afa98 BUG: 1457985 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17448 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/ec: Update xattr and heal size properlyAshish Pandey2017-06-062-9/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem-1 : Recursive healing of same file is happening when IO is going on even after data heal completes. Solution: RCA: At the end of the write, when ec_update_size_version gets called, we send it only on good bricks and not on healing brick. Due to this, xattr on healing brick will always remain out of sync and when the background heal check source and sink, it finds this brick to be healed and start healing from scratch. That involve ftruncate and writing all of the data again. To solve this, send xattrop on all the good bricks as well as healing bricks. Problem-2: The above fix exposes the data corruption during heal. If the write on a file is going on and heal finishes, we find that the file gets corrupted. RCA: The real problem happens in ec_rebuild_data(). Here we receive the 'size' argument which contains the real file size at the time of starting self-heal and it's assigned to heal->total_size. After that, a sequence of calls to ec_sync_heal_block() are done. Each call ends up calling ec_manager_heal_block(), which does the actual work of healing a block. First a lock on the inode is taken in state EC_STATE_INIT using ec_heal_inodelk(). When the lock is acquired, ec_heal_lock_cbk() is called. This function calls ec_set_inode_size() to store the real size of the inode (it uses heal->total_size). The next step is to read the block to be healed. This is done using a regular ec_readv(). One of the things this call does is to trim the returned size if the file is smaller than the requested size. In our case, when we read the last block of a file whose size was = 512 mod 1024 at the time of starting self-heal, ec_readv() will return only the first 512 bytes, not the whole 1024 bytes. This isn't a problem since the following ec_writev() sent from the heal code only attempts to write the amount of data read, so it shouldn't modify the remaining 512 bytes. However ec_writev() also checks the file size. If we are writing the last block of the file (determined by the size stored on the inode that we have set to heal->total_size), any data beyond the (imposed) end of file will be cleared with 0's. This causes the 512 bytes after the heal->total_size to be cleared. Since the file was written after heal started, the these bytes contained data, so the block written to the damaged brick will be incorrect. Solution: Align heal->total_size to a multiple of the stripe size. Thanks "Xavier Hernandez" <xhernandez@datalab.es> to find out the root cause and to fix the issue. Change-Id: I6c9f37b3ff9dd7f5dc1858ad6f9845c05b4e204e BUG: 1428673 Signed-off-by: Ashish Pandey <aspandey@redhat.com> Reviewed-on: https://review.gluster.org/16985 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* afr: update errno check in afr_inode_refresh_doRavishankar N2017-06-051-1/+1
| | | | | | | | | | | | | Addresses review comment in https://review.gluster.org/#/c/17413 Change-Id: Ic247729e5e92a5bb0148543764e0b30790444004 BUG: 1456582 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/17436 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* core: fix spelling errorsKaleb S. KEITHLEY2017-06-022-3/+2
| | | | | | | | | | | | | | fixes for various minor spelling errors and typos Reported-by: Patrick Matthäi <pmatthaei@debian.org> Change-Id: Ic1be36f82e3d822bbdc9559878bd79520fc0fcd5 BUG: 1457808 Signed-off-by: Kaleb S. KEITHLEY <kkeithle@redhat.com> Reviewed-on: https://review.gluster.org/17442 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Niels de Vos <ndevos@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org>
* cluster/dht: Make optimal usage of buffer provided with readdir(p)Sakshi2017-05-314-54/+62
| | | | | | | | | | | | | | | | | | | dht_readdirp must unwind with list of entries only after the entire buffer requested by kernel is filled to avoid extra syscalls occuring when returning partially filled buffer. Also wind readdir call to next subvol on reaching EOD for directory on that subvol to avoid extra network call. Change-Id: If2e1a2722f813d95457c7542bff25fef56c7a041 BUG: 1356453 Signed-off-by: Sakshi <sabansal@redhat.com> Signed-off-by: Raghavendra G <rgowdapp@redhat.com> Reviewed-on: https://review.gluster.org/12271 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Susant Palai <spalai@redhat.com>
* afr: add errno to afr_inode_refresh_done()Ravishankar N2017-05-311-7/+16
| | | | | | | | | | | | | | | | | | | | | | | | | Problem: When parellel `rm -rf`s were being done from cifs clients, opendir might fail on some replicas with ENOENT. DHT ignores partial opendir failures in dht_fd_cbk() and winds readdirs on those replicas. Afr inode refresh (as a part of readdirp read_txn) sees in its fd context that the state of the fds is *not* AFR_FD_OPENED and bails out to afr_inode_refresh_done() without doing a refresh. When this happens, the errno is set as EIO due to lack of readable subvols, logging split-brain messages in the logs. Fix: Introduce an errno argument to afr_inode_refresh_do() to bail out with the right error value when inode refresh is not performed. Change-Id: I075707fbb73fd93a923b77b923a96aac79e847f9 BUG: 1456582 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/17413 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* cluster/dht: fix on demand migration files from clientSusant Palai2017-05-304-20/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On demand migration of files i.e. migration done by clients triggered by a setfattr was broken. Dependency on defrag led to crash when migration was triggered from client. Note: This functionality is not available for tiered volumes. Migration from tier served client will fail with ENOTSUP. usage (But refer to the steps mentioned below to avoid any issues) : setfattr -n "trusted.distribute.migrate-data" -v "1" <filename> The purpose of fixing the on-demand client migration was to give a workaround where the user has lots of empty directories compared to files and want to do a remove-brick process. Here are the steps to trigger file migration for remove-brick process from client. (This is highly recommended to follow below steps as is) Let's say it is a replica volume and user want to remove a replica pair named brick1 and brick2. (Make sure healing is completed before you run these steps) Step-1: Start remove-brick process - gluster v remove-brick <volname> brick1 brick2 start Step-2: Kill the rebalance daemon - ps aux | grep glusterfs | grep rebalance\/ | awk '{print $2}' | xargs kill Step-3: Do a fresh mount as mentioned here - glusterfs -s ${localhostname} --volfile-id rebalance/$volume-name /tmp/mount/point Step-4: Go to one of the bricks (among brick1 and brick2) - cd <brick1 path> Step-5: Run the following command. - find . -not \( -path ./.glusterfs -prune \) -type f -not -perm 01000 -exec bash -c 'setfattr -n "distribute.fix.layout" -v "1" ${mountpoint}/$(dirname '{}')' \; -exec setfattr -n "trusted.distribute.migrate-data" -v "1" ${mountpoint}/'{}' \; This command will ignore the linkto files and empty directories. Do a fix-layout of the parent directory. And trigger a migration operation on the files. Step-6: Once this process is completed do "remove-brick force" - gluster v remove-brick <volname> brick1 brick2 force Note: Use the above script only when there are large number of empty directories. Since the script does a crawl on the brick side directly and avoids directories those are empty, the time spent on fixing layout on those directories are eliminated(even if the script does not do fix-layout on empty directories, post remove-brick a fresh layout will be built for the directory, hence not affecting application continuity). Detailing the expectation for hardlink migartion with this patch: Hardlink is migrated only for remove-brick process. It is highly essential to have a new mount(step-3) for the hardlink migration to happen. Why?: setfattr operation is an inode based operation. Since, we are doing setfattr from fuse mount here, inode_path will try to build path from the linked dentries to the inode. For a file without hardlinks the path construction will be correct. But for hardlinks, the inode will have multiple dentries linked. Without fresh mount, inode_path will always get the most recently linked dentry. e.g. if there are three hardlinks named dir1/link1, dir2/link2, dir3/link3, on a client where these hardlinks are looked up, inode_path will always return the path dir3/link3 if dir3/link3 was looked up most recently. Hence, we won't be able to create linkto files for all other hardlinks on destination (read gf_defrag_handle_hardlink for more details on hardlink migration). With a fresh mount, the lookup and setfattr become serialized. e.g. link2 won't be looked up until link1 is looked up and migrated. Hence, inode_path will always have the correct path, in this case link1 dentry is picked up(as this is the most recently looked up inode) and the path is built right. Note: If you run the above script on an existing mount(all entries looked up), hard links may not be migrated, but there should not be any other issue. Please raise a bug, if you find any issue. Tests: Manual Change-Id: I9854cdd4955d9e24494f348fb29ba856ea7ac50a BUG: 1450975 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/17115 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* features/dht: Initialize local hashed_subvolKotresh HR2017-05-251-0/+15
| | | | | | | | | | | | | | | | | | Self heal directory code path doesn't always have local->hashed_subvol populated. Populating the same which otherwise would fail the self heal. Change-Id: I03b64709fd7a68e28f9e7438243e817c53c6ef5d BUG: 1455104 Signed-off-by: Kotresh HR <khiremat@redhat.com> Reviewed-on: https://review.gluster.org/17381 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/ec: Implement FALLOCATE FOP for ECSunil Kumar Acharya2017-05-233-3/+209
| | | | | | | | | | | | | | | FALLOCATE file operations is not implemented in the existing EC code. This change set implements it for EC. BUG: 1448293 Change-Id: Id9ed914db984c327c16878a5b2304a0ea461b623 Signed-off-by: Sunil Kumar Acharya <sheggodu@redhat.com> Reviewed-on: https://review.gluster.org/15200 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/dht: Fix crash in dht_selfheal_dir_setattrN Balachandran2017-05-191-2/+6
| | | | | | | | | | | | | | | Use a local variable to store the call cnt used in the for loop for the STACK_WIND so as not to access local which may be freed by STACK_UNWIND after all fops return. Change-Id: I24f49b6dbd29a2b706e388e2f6d5196c0f80afc5 BUG: 1452102 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17343 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/afr: Remove debug logs in fix_quorum_options()Vijay Bellur2017-05-191-5/+0
| | | | | | | | | | | Change-Id: Id019b0c6425849eece8a9aba7acec9a521dfb10b BUG: 1452378 Signed-off-by: Vijay Bellur <vbellur@redhat.com> Reviewed-on: https://review.gluster.org/17335 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/dht: initialize throttle option "normal" to same in init and reconfigureSusant Palai2017-05-181-77/+52
| | | | | | | | | | | | | | | | Normal value were different in dht_init and dht_reconfigure. Initialization/reconfigure of throttle option are carved out to a separate function (dht_configure_throttle) now. Normal value will be "2". Change-Id: Ie323eae019af41d6bef0a136e3d284dc82bab9a1 BUG: 1451162 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/17303 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Zhou Zhengping <johnzzpcrystal@gmail.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/afr: Return the list of node_uuids for the subvolumekarthik-us2017-05-173-50/+145
| | | | | | | | | | | | | | | | | | | | | | | | Problem: AFR was returning the node uuid of the first node for every file if the replica set was healthy, which was resulting in only one node migrating all the files. Fix: With this patch AFR returns the list of node_uuids to the upper layer, so that they can decide on which node to migrate which files, resulting in improved performance. Ordering of node uuids will be maintained based on the ordering of the bricks. If a brick is down, then the node uuid for that will be set to all zeros. Change-Id: I73ee0f9898ae473584fdf487a2980d7a6db22f31 BUG: 1366817 Signed-off-by: karthik-us <ksubrahm@redhat.com> Reviewed-on: https://review.gluster.org/17084 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/ec: return all node uuids from all subvolumesXavier Hernandez2017-05-172-105/+141
| | | | | | | | | | | | | | | | | | | | | | | | EC was retuning the UUID of the brick with smaller value. This had the side effect of not evenly balancing the load between bricks on rebalance operations. This patch modifies the common functions that combine multiple subvolume values into a single result to take into account the subvolume order and, optionally, other subvolumes that could be damaged. This makes easier to add future features where brick order is important. It also makes possible to easily identify the originating brick of each answer, in case some brick will have an special meaning in the future. Change-Id: Iee0a4da710b41224a6dc8e13fa8dcddb36c73a2f BUG: 1366817 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: https://review.gluster.org/17297 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Ashish Pandey <aspandey@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* cluster/dht: Rebalance on all nodes should migrate filesN Balachandran2017-05-166-16/+211
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Rebalance compares the node-uuid of a file against its own to and migrates a file only if they match. However, the current behaviour in both AFR and EC is to return the node-uuid of the first brick in a replica set for all files. This means a single node ends up migrating all the files if the first brick of every replica set is on the same node. Fix: AFR and EC will return all node-uuids for the replica set. The rebalance process will divide the files to be migrated among all the nodes by hashing the gfid of the file and using that value to select a node to perform the migration. This patch makes the required DHT and tiering changes. Some tests in rebal-all-nodes-migrate.t will need to be uncommented once the AFR and EC changes are merged. Change-Id: I5ce41600f5ba0e244ddfd986e2ba8fa23329ff0c BUG: 1366817 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17239 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* cluster/dht: Fix crash in dht rmdirN Balachandran2017-05-161-4/+10
| | | | | | | | | | | | | | | | | | | | Using local->call_cnt to check STACK_WINDs can cause dht_rmdir_do to be called erroneously if dht_rmdir_readdirp_cbk unwinds before we check if local->call_cnt is zero in dht_rmdir_opendir_cbk. This can cause frame corruptions and crashes. Thanks to Shyam (srangana@redhat.com) for the analysis. Change-Id: I5362cf78f97f21b3fade0b9e94d492002a8d4a11 BUG: 1451083 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17305 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>
* afr: propagate correct errno for fop failures in arbiterRavishankar N2017-05-154-15/+12
| | | | | | | | | | | | | | | | | | | | | | | Problem: If quorum is not met in fop cbk, arbiter sends an ENOTCONN error to the upper xlators. In a VM workload with sharding enabled, this was leading to the VM pausing when replace-brick was performed as described in the BZ. Fix: Move the fop cbk arbitration logic to afr_handle_quorum() because in normal replica volumes, that is the function that has the quorum and errno checks in the fop cbk path before doing a post-op. Thanks to Pranith for suggesting this approach. Change-Id: Ie6315db30c5e36326b71b90a01da824109e86796 BUG: 1449610 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/17235 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/tier: Don't update cached subvolN Balachandran2017-05-121-15/+3
| | | | | | | | | | | | | | | | | | | tier_readdirp_cbk updates the cached subvol to the hot tier if it finds a linkto file. However, if no lookup has been sent to the hot tier, lower layers will not have updated the inode-ctx causing later fops to fail. Change-Id: Ib8a5e58a6e7fd7750cf6a0ea85da611aa24c7512 BUG: 1402406 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/16163 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Dan Lambright <dlambrig@gmail.com> Tested-by: Dan Lambright <dlambrig@gmail.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
* afr: send the correct iatt values in fsync cbkRavishankar N2017-05-111-25/+43
| | | | | | | | | | | | | | | | | | | | | | | | Problem: afr unwinds the fsync fop with an iatt buffer from one of its children on whom fsync was successful. But that child might not be a valid read subvolume for that inode because of pending heals or because it happens to be the arbiter brick etc. Thus we end up sending the wrong iatt to mdcache which will in turn serve it to the application on a subsequent stat call as reported in the BZ. Fix: Pick a child on whom the fsync was successful *and* that is readable as indicated in the inode context. Change-Id: Ie8647289219cebe02dde4727e19a729b3353ebcf BUG: 1449329 RCA'ed-by: Miklós Fokin <miklos.fokin@appeartv.com> Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/17227 CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org>
* afr: fixes to quorum-type in afr_priv_dump()Ravishankar N2017-05-101-0/+2
| | | | | | | | | | | | | | | | | | Include the 'none' option as well in the output. This fixes the bug in commit 335555d256d444f4952ce239168f72b393370f01. Also added a test-case. This is a Signed-off-by: Ravishankar N <ravishankar@redhat.com> Change-Id: I479a14ae69ecae5a03e85e73ed50c19b483df603 BUG: 1448804 Reviewed-on: https://review.gluster.org/17215 Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/ec: fix incorrect answer check in seek fopXavier Hernandez2017-05-091-15/+8
| | | | | | | | | | | | | | | A bad check in the answer of a seek request caused a segmentation fault when seek reported an error. Change-Id: Ifb25ae8bf7cc4019d46171c431f7b09b376960e8 BUG: 1439068 Signed-off-by: Xavier Hernandez <xhernandez@datalab.es> Reviewed-on: https://review.gluster.org/16998 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* afr: include quorum type and count when dumping afr privRavishankar N2017-05-081-0/+6
| | | | | | | | | | | | | | | | Dump the client quorum type ('auto' or 'fixed'). If it is 'fixed', also dump the quorum-count. This information will be available in the client statedump and in /<fuse_mount>/.meta/graphs/active/testvol-replicate-X/private. Change-Id: Idbd6e2acbd622d4e6cfabf511e649a6da0e42384 BUG: 1448804 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/17196 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* cluster/dht: Fix ret checkN Balachandran2017-05-081-1/+1
| | | | | | | | | | | | | | Fixed an incorrect return code check in the rebalance code. Change-Id: I60804ff121cec7a2f0419e2ee70dd22ea7533c0c BUG: 1448640 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17197 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* coreutils: use coreutils instead of duplicate codeZhou Zhengping2017-05-051-3/+1
| | | | | | | | | | | | | Change-Id: I0e442331d2bbb22ec18c37af87ab2a8852737c43 BUG: 1448265 Signed-off-by: Zhou Zhengping <johnzzpcrystal@gmail.com> Reviewed-on: https://review.gluster.org/16975 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Prashanth Pai <ppai@redhat.com> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us>
* Fix wrong operatorsMichael Scherer2017-05-042-4/+3
| | | | | | | | | | | | | | | | | | | | | | Coverty rightfully note that if we verify that A =! C or A != B, it will always be true. In one case, that prevent healing from continuing. In the other, that trigger useless logs. Fixing this bug also show that ENOSPC shouldn't abort the rebalance operation, as seen during the review of the first patch on https://review.gluster.org/#/c/16676/1/xlators/cluster/dht/src/dht-rebalance.c Change-Id: I93c4df43b880b211da202a7e49cef6b1ce7ab68f BUG: 1424817 Signed-off-by: Michael Scherer <misc@redhat.com> Reviewed-on: https://review.gluster.org/16676 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Jeff Darcy <jeff@pl.atyp.us> Tested-by: Jeff Darcy <jeff@pl.atyp.us> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com>
* Halo Replication feature for AFR translatorKevin Vigor2017-05-025-58/+422
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: Halo Geo-replication is a feature which allows Gluster or NFS clients to write locally to their region (as defined by a latency "halo" or threshold if you like), and have their writes asynchronously propagate from their origin to the rest of the cluster. Clients can also write synchronously to the cluster simply by specifying a halo-latency which is very large (e.g. 10seconds) which will include all bricks. In other words, it allows clients to decide at mount time if they desire synchronous or asynchronous IO into a cluster and the cluster can support both of these modes to any number of clients simultaneously. There are a few new volume options due to this feature: halo-shd-latency: The threshold below which self-heal daemons will consider children (bricks) connected. halo-nfsd-latency: The threshold below which NFS daemons will consider children (bricks) connected. halo-latency: The threshold below which all other clients will consider children (bricks) connected. halo-min-replicas: The minimum number of replicas which are to be enforced regardless of latency specified in the above 3 options. If the number of children falls below this threshold the next best (chosen by latency) shall be swapped in. New FUSE mount options: halo-latency & halo-min-replicas: As descripted above. This feature combined with multi-threaded SHD support (D1271745) results in some pretty cool geo-replication possibilities. Operational Notes: - Global consistency is gaurenteed for synchronous clients, this is provided by the existing entry-locking mechanism. - Asynchronous clients on the other hand and merely consistent to their region. Writes & deletes will be protected via entry-locks as usual preventing concurrent writes into files which are undergoing replication. Read operations on the other hand should never block. - Writes are allowed from _any_ region and propagated from the origin to all other regions. The take away from this is care should be taken to ensure multiple writers do not write the same files resulting in a gfid split-brain which will require resolution via split-brain policies (majority, mtime & size). Recommended method for preventing this is using the nfs-auth feature to define which region for each share has RW permissions, tiers not in the origin region should have RO perms. TODO: - Synchronous clients (including the SHD) should choose clients from their own region as preferred sources for reads. Most of the plumbing is in place for this via the child_latency array. - Better GFID split brain handling & better dent type split brain handling (i.e. create a trash can and move the offending files into it). - Tagging in addition to latency as a means of defining which children you wish to synchronously write to Test Plan: - The usual suspects, clang, gcc w/ address sanitizer & valgrind - Prove tests Reviewers: jackl, dph, cjh, meyering Reviewed By: meyering Subscribers: ethanr Differential Revision: https://phabricator.fb.com/D1272053 Tasks: 4117827 Change-Id: I694a9ab429722da538da171ec528406e77b5e6d1 BUG: 1428061 Signed-off-by: Kevin Vigor <kvigor@fb.com> Reviewed-on: http://review.gluster.org/16099 Reviewed-on: https://review.gluster.org/16177 Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* cluster/dht: Make rebalance throttle option tuned by numberSusant Palai2017-04-293-26/+110
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Current rebalance throttle options: lazy/normal/aggressive may not always be sufficient for the purpose of throttling. In our recent test, we observed for certain setups, normal and aggressive modes behaved similarly consuming full disk bandwidth. So in cases like this admin should be able to tune it down(or vice versa) depending on the need. Along with old throttle configurations, thread counts are tuned based on number. e.g. gluster v set vol-name cluster-rebal.throttle 5. Admin can tune up/down between 0 and the number of cores available. Note: For heterogenous servers, validation will fail on the old server if "number" is given for throttle configuration. The message looks something like this: "volume set: failed: Staging failed on vm2. Error: cluster.rebal-throttle should be {lazy|normal|aggressive}" Test: Manual test by logging active thread number after reconfiguring throttle option. testcase: tests/basic/distribute/throttle-rebal.t Change-Id: I46e3cde546900307831028b344ecf601fd9b02c3 BUG: 1438370 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/16980 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* dht: send lookup on old name inside rename with bname and pargfidSusant Palai2017-04-291-9/+58
| | | | | | | | | | | | | | | | | | | | | | | | | | | Inside rename, a lookup is done on the source name to make sure that the file is there. But we used to do a gfid based lookup and hence, even if the source name was renamed to a new name from some other client, lookup will be successful as server3_3_lookup will fetch the new path based on the gfid. So even if the source file does not exist any more rename will carry on, and as server3_3_link(destination is hashed to a different brick other than source cached scenario) also does gfid based resolve, it wont detect that the source name does not exist and hardlink creation will be successful (since gfid based resolve will get the new dentry). To solve this problem, do a name based lookup inside rename. So that rename will fail right away if the source does not exist. Change-Id: Ieba8bdd6675088dbf18de90ed4622df043d163bd BUG: 1412135 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/16375 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: rebalance perf enhancementSusant Palai2017-04-292-108/+246
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Throttle settings "normal" and "aggressive" for rebalance did not have performance difference. normal mode spawns $(no. of cores - 4)/2 threads and aggressive spawns $(no. of cores - 4) threads. Though aggressive mode has twice the number of threads compared to that of normal mode, there was no performance gain when switched to aggressive mode from normal mode. RCA: During the course of debugging the above problem, we tried assigning migration job to migration threads spawned by rebalance, rather than synctasks(as there is more overhead associated to manage the task queue and threads). This gave us a significant improvement over rebalance under synctasks. This patch does not really gurantee that there will be a clear performance difference between normal and aggressive mode, but this patch certainly maximized the disk utilization for 1GBfiles run. Results: Test enviroment: Gluster Config: Number of Bricks: 2 (one brick per disk(RAID-6 12 disk)) Bricks: Brick1: server1:/brick/test1/1 Brick2: server2:/brick/test1/1 Options Reconfigured: performance.readdir-ahead: on server.event-threads: 4 client.event-threads: 4 1000 files with 1GB each were created/renamed such that all files will have server1 as cached and server2 as hashed, so that all files will be migrated. Test machines had 24 cores each. Results with/without synctask based migration: ----------------------------------------------- mode normal(10threads) aggressive(20threads) timetaken 0:55:30 (h:m:s) 0:56:3 (h:m:s) withsynctask timetaken with migrator 0:38:3 (h:m:s) 0:23:41 (h:m:s) threads From above table it can be seen that, there is a clear 2x perf gain between rebalance with synctask vs rebalance with migrator threads. Additionally this patch modifies the code so that caller will have the exact error number returned by dht_migrate_file(earlier the errno meaning was overloaded). This will help avoiding scenarios where migration failure due to ENOENT, can result in rebalance abort/failure. Change-Id: I8904e2fb147419d4a51c1267be11a08ffd52168e BUG: 1420166 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/16427 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* cluster/dht: Pass the correct xdata in fremovexattr fopKrutika Dhananjay2017-04-281-8/+4
| | | | | | | | | | | Change-Id: Id84bc87e48f435573eba3b24d3fb3c411fd2445d BUG: 1440051 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: https://review.gluster.org/17126 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht Remove redundant logs in dht rmdirN Balachandran2017-04-261-8/+7
| | | | | | | | | | | | | | | Removing redundant logs were introduced in https://review.gluster.org/#/c/17065/ Change-Id: I0d6055488b51a13c91d2121e87f653cdb94888b0 BUG: 1445590 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: https://review.gluster.org/17118 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Susant Palai <spalai@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* feature/dht: Directory synchronizationKotresh HR2017-04-2610-1141/+1897
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Design doc: https://review.gluster.org/16876 Directory creation is now synchronized with blocking inodelk of the parent on the hashed subvolume followed by the entrylk on the hashed subvolume between dht_mkdir, dht_rmdir, dht_rename_dir and lookup selfheal mkdir. To maintain internal consistency of directories across all subvols of dht, we need locks. Specifically we are interested in: 1. Consistency of layout of a directory. Only one writer should modify the layout at a time. A writer (layout setting during directory heal as part of lookup) shouldn't modify the layout while there are readers (all other fops like create, mkdir etc., which consume layout) and readers shouldn't read the layout while a writer is in progress. Readers can read the layout simultaneously. Writer takes a WRITE inodelk on the directory (whose layout is being modified) across ALL subvols. Reader takes a READ inodelk on the directory (whose layout is being read) on ANY subvol. 2. Consistency of directory namespace across subvols. The path and associated gfid should be same on all subvols. A gfid should not be associated with more than one path on any subvol. All fops that can change directory names (mkdir, rmdir, renamedir, directory creation phase in lookup-heal) takes an entrylk on hashed subvol of the directory. NOTE1: In point 2 above, since dht takes entrylk on hashed subvol of a directory, the transaction itself is a consumer of layout on parent directory. So, the transaction is a reader of parent layout and does an inodelk on parent directory just like any other layout reader. So a mkdir (dir/subdir) would: > Acquire a READ inodelk on "dir" on any subvol. > Acquire an entrylk (dir, "subdir") on hashed subvol of "subdir". > creates directory on hashed subvol and possibly on non-hashed subvols. > UNLOCK (entrylk) > UNLOCK (inodelk) NOTE2: mkdir fop while setting the layout of the directory being created is considered as a reader, but NOT a writer. The reason is for a fop which can consume the layout of a directory to come either of the following conditions has to be true: > mkdir syscall from application has to complete. In this case no need of synchronization. > A lookup issued on the directory racing with mkdir has to complete. Since layout setting by a lookup is considered as a writer, only one of either mkdir or lookup will set the layout. Code re-organization: All the lock related routines are moved to "dht-lock.c" file. New wrapper function is introduced to take blocking inodelk followed by entrylk 'dht_protect_namespace' Updates #191 Change-Id: I01569094dfbe1852de6f586475be79c1ba965a31 Signed-off-by: Kotresh HR <khiremat@redhat.com> BUG: 1443373 Reviewed-on: https://review.gluster.org/15472 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org>
* cluster/dht: correct space check for rebalanceSusant Palai2017-04-251-1/+1
| | | | | | | | | | | | | | | | | | | | With rebalance doing fallocate on destination, we don't need to add file size to the "destination available space" to decide whether to migrate the file or not. Notes: Fallocate would have already occupied the file size space on destination Change-Id: If7f6a6654e6257726680cf20d618482a6e9095a6 BUG: 1441508 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: https://review.gluster.org/17104 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: N Balachandran <nbalacha@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-13 05:40:17 +0000