summaryrefslogtreecommitdiffstats
path: root/tests/bugs
Commit message (Collapse)AuthorAgeFilesLines
...
* md-cache, afr: Reduce the window of stale readPoornima G2016-10-201-0/+44
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: Consider a replica setup, where one mount writes data to a file and the other mount reads the file. In afr, read operations are not transaction based, a brick(read subvolume) is chosen as a part of lookup or other operations, read is always wound only to the read subvolume, even if there was write from a different client that failed on this brick. This stale read continues until there is a lookup or any write operation from the mount point. Currently, this is not a major issue, as a lookup is issued before every read and it will switch the read subvolume to a correct one. But with the plan of increasing md-cache timeout to 600s, the stale read problem will be more pronounced, i.e. stale read can continue for 600s(or more if cascaded with readdirp), as there will be no lookups. Solution: Afr doesn't have any built-in solution for stale read(without affecting the performance). The solution that came up, was to use upcall. When a file on any brick is marked bad for the first time, upcall sends a notification to all the clients that had recently accessed the file. The solution has 2 parts: - Identifying when a file is marked bad, on any of the bricks, for the first time - Client side actions on recieving the notifications Identifying when a file is marked bad on any of the bricks for the first time: ----------------------------------------------------------------------------- The idea is to track xattrop in upcall. xattrop currently comes with 2 afr xattrs - afr dirty bit and afr pending xattrs. Dirty xattr is set to 1 before every write, and is unset if write succeeds. In certain scenarios, dirty xattr can be 0 and still the file could be bad copy. Hence do not track dirty xattr. Pending xattr is set on the good copy, indicating the other bricks that have bad copy. It is still not as simple as, notifying when any of the pending xattrs change. It could lead to flood of notifcations, in case the other brick is completely down or consistantly failing. Hence it is important to notify only once, the first time a good copy is marked bad. Client side actions on recieving pending xattr change, notification: -------------------------------------------------------------------- md-cache will invalidate the cache of that file, so that further lookup is passed down to afr and hence update the read subvolume. Invalidating only in md-cache is not enough, consider the folling oder of opertaions: - pending xattr invalidation - invalidate md-cache - readdirp on the bad read subvolume - fill md-cache - lookup (served from md-cache) - read - wound to the old read subvol. Hence, along with invalidating md-cache, it is very important to reset the read subvolume for that file, in afr. Design Credit: Anuradha Talur, Ravishankar N 1. xattrop doesn't carry info saying post op/pre op. 2. Pre xattrop will have 0 value for all pending xattrs, the cbk of pre xattrop carries the on-disk xattr value. Non zero indicated healing is required. 3. Post xattrop will have non zero value for any of the pending xattrs, if the fop failed on any of the bricks. Change-Id: I469cbc111714c433984fe1c922be2ef113c25804 BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15398 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>
* glusterd: Revert 368e26f454fe35477e46dc698fa6b8c3c608ea8dN Balachandran2016-09-261-5/+3
| | | | | | | | | | | | | | | | The earlier fix prevented rebalance from starting even if only a single brick of a replica set was down. Change-Id: I8c9a7d4c1fe33f7749568357462f29796e1b832a BUG: 1376671 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/15517 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: Raghavendra G <rgowdapp@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* glusterd: "gluster v heal test statistics heal-count replica" output is not ↵Mohit Agrawal2016-09-261-0/+25
| | | | | | | | | | | | | | | | | | | | correct Problem : "gluster v heal test statistcs heal-count replica" does not show correct output. Solution: After update condition (match brick name) in _select_hxlator_with_matching_brick, it shows correct output. BUG: 1325792 Change-Id: I60cc7c68ea70bce267a747570f91dcddbc1d9016 Signed-off-by: Mohit Agrawal <moagrawa@redhat.com> Reviewed-on: http://review.gluster.org/15494 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: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* socket: pollerr event shouldn't trigger socket_connnect_finishAtin Mukherjee2016-09-192-7/+5
| | | | | | | | | | | | | | | | | | | | | | | | If connect fails with any other error than EINPROGRESS we cannot get the error status using getsockopt (... SO_ERROR ... ). Hence we need to remember the state of connect and take appropriate action in the event_handler for the same. As an added note, a event can come where poll_err is HUP and we have poll_in as well (i.e some status was written to the socket), so for such cases we need to finish the connect, process the data and then the poll_err as is the case in the current code. Special thanks to Kaushal M & Raghavendra G for figuring out the issue. Change-Id: Ic45ad59ff8ab1d0a9d2cab2c924ad940b9d38528 BUG: 1372356 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Signed-off-by: Shyam <srangana@redhat.com> Reviewed-on: http://review.gluster.org/15440 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: Raghavendra G <rgowdapp@redhat.com>
* dht: "replica.split-brain-status" attribute value is not correctMohit Agrawal2016-09-121-0/+84
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: In a distributed-replicate volume attribute "replica.split-brain-status" value does not display split-brain condition though directory is in split-brain. If directory is in split brain on mutiple replica-pairs it does not show full list of replica pairs. Solution: Update the dht_aggregate code to aggregate the xattr value in this specific condition. Fix: 1) function getChoices returns the choices from split-brain status string. 2) function add_opt adding the choices to local buffer to store in dictionary 3) For the key "replica.split-brain-status" function dht_aggregate call dht_aggregate_split_brain_xattr to prepare the list. Test: To verify the patch followed below steps 1) Create a distributed replica volume and create mount point 2) Stop heal daemon 3) Touch file and directories on mount point mkdir test{1..5};touch tmp{1..5} 4) Down brick process on one of the replica set pkill -9 glusterfsd 5) Change permission of dir on mount point chmod 755 test{1..5} 6) Restart brick process on node with force option 7) kill brick process on other node in same replica set 8) Change permission of dir again on mount point chmod 766 test{1..5} 9) Reexecute same step from 4-9 on other replica set also 10) After check heal status on server it will show dir's are in split brain on all replica sets 11) After check the replica.split-brain-status attr on mount point it will show wrong status of split brain. 12) After apply the patch the attribute shows correct value. BUG: 1368312 Change-Id: Icdfd72005a4aa82337c342762775a3d1761bbe4a Signed-off-by: Mohit Agrawal <moagrawa@redhat.com> Reviewed-on: http://review.gluster.org/15201 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: Raghavendra G <rgowdapp@redhat.com>
* cluster/dht: heal root permission post add-brickSusant Palai2016-09-111-0/+50
| | | | | | | | | | | | | | | | | | | | | | | | | Post add-brick event the new brick will have permission of 755 by default. If the root directory permission was other than 755, that does not get healed to the new brick leading to permission errors/inconsistencies. For choosing source of attr heal we can trust the subvols which have layouts with latest ctime(as part of missing directory heal, we heal the proper attr). In case none of the subvols have layout, return ESTALE to retrigger a fresh lookup. Note: This patch heals the permission of the root directories only. Since, permission healing of directory is not straight forward and required intrusive fix, those are not addressed here. Change-Id: If894e3895d070d46b62d2452e52c1eaafcf56c29 BUG: 1368012 Signed-off-by: Susant Palai <spalai@redhat.com> Reviewed-on: http://review.gluster.org/15195 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>
* tests: fix bug-963541.t spurious failureAtin Mukherjee2016-09-111-1/+2
| | | | | | | | | | | | | wait for remove brick to complete before attempt for a commit. Change-Id: I66ea6c48b6a69fe33d79f9d9080b6f2c1462578e BUG: 1374993 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/15457 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: Vijay Bellur <vbellur@redhat.com>
* cluster/dht: Skip layout overlap maximization on weighted rebalanceN Balachandran2016-09-081-0/+1
| | | | | | | | | | | | | | | | dht_selfheal_layout_maximize_overlap () does not consider chunk sizes while calculating overlaps. Temporarily enabling this operation if only if weighted rebalance is disabled or all bricks are the same size. Change-Id: I5ed16cdff2551b826a1759ca8338921640bfc7b3 BUG: 1366494 Signed-off-by: N Balachandran <nbalacha@redhat.com> Reviewed-on: http://review.gluster.org/15403 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
* tests: Fix one of the md-cache test casesPoornima G2016-09-071-1/+5
| | | | | | | | | | | | | | Verify if the unlink, rename and other ops are reflected both on the current mount and other mounts. Change-Id: I5a296cdd557194dcf487e65ee4a14bbeaf4be690 BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15419 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: Vijay Bellur <vbellur@redhat.com>
* tests: Fix one of the upcall testsPoornima G2016-09-021-2/+3
| | | | | | | | | | | | | | | | | Currently md-cache invalidation feature is enabled by setting "performance.cache-invalidation", but this case was sent when "features.cache-invalidation" was enabling md-cache invalidation. Hence, fix the same. Change-Id: If044f6208179748a120fbe1d63b676367e707f73 BUG: 1372584 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15385 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Raghavendra Talur <rtalur@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* io-stats: Add stats for upcall notificationsv3.10devPoornima G2016-08-311-0/+38
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With this patch, there will be additional entries seen in the profile info: UPCALL : Total number of upcall events that were sent from the brick(in brick profile), and number of upcall notifications recieved by client(in client profile) Cache invalidation events: ------------------------- CI_IATT : Number of upcalls that were cache invalidation and had one of the IATT_UPDATE_FLAGS set. This indicates that one of the iatt value was changed. CI_XATTR : Number of upcalls that were cache invalidation, and had one of the UP_XATTR or UP_XATTR_RM set. This indicates that an xattr was updated or deleted. CI_RENAME : Number of upcalls that were cache invalidation, resulted by the renaming of a file or directory CI_UNLINK : Number of upcalls that were cache invalidation, resulted by the unlink of a file. CI_FORGET : Number of upcalls that were cache invalidation, resulted by the forget of inode on the server side. Lease events: ------------ LEASE_RECALL : Number of lease recalls sent by the brick (in brick profile), and number of lease recalls recieved by client(in client profile) Note that the sum of CI_IATT, CI_XATTR, CI_RENAME, CI_UNLINK, CI_FORGET, LEASE_RECALL may not be equal to UPCALL. This is because, each cache invalidation can carry multiple flags. Eg: - Every CI_XATTR will have CI_IATT - Every CI_UNLINK will also increment CI_IATT as link count is an iatt attribute. Also UP_PARENT_DENTRY_FLAGS is currently not accounted for, as CI_RENAME and CI_UNLINK will always have the flag UP_PARENT_DENTRY_FLAGS Change-Id: Ieb8cd21dde2c4c7618f12d025a5e5156f9cc0fe9 BUG: 1371543 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15193 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* tests: Fix spurious failures because of wrong shd up functionPranith Kumar K2016-08-312-3/+3
| | | | | | | | | | | | | | Fixed the way shd up check is done to prevent self-heal daemon not running error when heal full command is executed. Change-Id: I93c4a0da12316373d62cd4ea74432cd9bf2b090c BUG: 1370053 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/15341 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: Anuradha Talur <atalur@redhat.com>
* upcall: Mark the clients as accessed on readdirp entriesPoornima G2016-08-311-0/+43
| | | | | | | | | | | | | | | | | | | | Currently when a client performs a readdirp it is not stored in upcall, as one of the clients that have accessed the files. Hence, when any other client modifies the file, the client that had performed readdirp will not get any notifications. Fix this by adding the clients to upcall database when they perform readdirp. Change-Id: I7767f1e26bf1bd1f67702a6d01f8aa64526ccc46 BUG: 1369430 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15313 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: soumya k <skoduri@redhat.com> Reviewed-by: Niels de Vos <ndevos@redhat.com>
* md-cache: Process all the cache invalidation flagsPoornima G2016-08-301-0/+45
| | | | | | | | | | | | | | | | Currently, md-cache only processes IATT_UPDATE_FLAGS, UP_XATTR and UP_XATTR_RM. We also need to process UP_RENAME_FLAGS, UP_FORGET, UP_PARENT_DENTRY_FLAGS and UP_NLINK_FLAGS. Otherwise the files unlinked or renamed will not be reflected on other mounts. Change-Id: Icb8b03da51482c3fc2e2a7292d16d56e11a341d9 BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15324 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: Raghavendra G <rgowdapp@redhat.com>
* gfapi: Mark tests/basic/gfapi/1093594.t bad until it is fixedPoornima G2016-08-301-0/+2
| | | | | | | | | | | Change-Id: If88efe3db782a6156614af4c650d53b159ade57f BUG: 1371541 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15354 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Vijay Bellur <vbellur@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* glusterd : Introduce reset brickAnuradha Talur2016-08-291-0/+54
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The command basically allows replace brick with src and dst bricks as same. Usage: gluster v reset-brick <volname> <hostname:brick-path> start This command kills the brick to be reset. Once this command is run, admin can do other manual operations that they need to do, like configuring some options for the brick. Once this is done, resetting the brick can be continued with the following options. gluster v reset-brick <vname> <hostname:brick> <hostname:brick> commit {force} Does the job of resetting the brick. 'force' option should be used when the brick already contains volinfo id. Problem: On doing a disk-replacement of a brick in a replicate volume the following 2 scenarios may occur : a) there is a chance that reads are served from this replaced-disk brick, which leads to empty reads. b) potential data loss if next writes succeed only on replaced brick, and heal is done to other bricks from this one. Solution: After disk-replacement, make sure that reset-brick command is run for that brick so that pending markers are set for the brick and it is not chosen as source for reads and heal. But, as of now replace-brick for the same brick-path is not allowed. In order to fix the above mentioned problem, same brick-path replace-brick is needed. With this patch reset-brick commit {force} will be allowed even when source and destination <hostname:brickpath> are identical as long as 1) destination brick is not alive 2) source and destination brick have the same brick uuid and path. Also, the destination brick after replace-brick will use the same port as the source brick. Change-Id: I440b9e892ffb781ea4b8563688c3f85c7a7c89de BUG: 1266876 Signed-off-by: Anuradha Talur <atalur@redhat.com> Reviewed-on: http://review.gluster.org/12250 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>
* tests: change EXPECT_WITHIN timeoutsAnuradha Talur2016-08-281-1/+1
| | | | | | | | | | | | | | | | | Use defined HEAL and PROCESS_UP timeouts rather than hard code them in self-heald.t. Change-Id: I21586811904c8417b7208bb643f14dff20dc4832 BUG: 1370074 Signed-off-by: Anuradha Talur <atalur@redhat.com> Reviewed-on: http://review.gluster.org/15316 Reviewed-by: Ravishankar N <ravishankar@redhat.com> Tested-by: Ravishankar N <ravishankar@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Krutika Dhananjay <kdhananj@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* md-cache: Do not use features.cache-invalidation for both md-cache and upcallPoornima G2016-08-271-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently, the volume set option features.cache-invalidation enables upcall feature on server side and md-cache cache-invalidation on client side. There are multiple problems that can arise from this: 1. The scenario when user wants to, enable upcall for nfs-ganesha setup, but do not want to enable md-cache cache-invalidation, as the nfs-clients have already cached the metadata and upcall is used to to invalidate the nfs-client cache. In this case, users should have a way of disabling md-cache invalidation without disabling upcall. 2. Upcall requires a op-version of GD_OP_VERSION_3_7_0, where as md-cache invalidation requires an op version of GD_OP_VERSION_3_9_0. Consider a setup where the servers are in op-version GD_OP_VERSION_3_7_0, and th clients are in op-version GD_OP_VERSION_3_9_0. if there is one single volume set option, user can enable this feature in this setup. But it can lead to stale xattr cache as the xattr invalidation was introduced in upcall only in release 3.8. Hence, we should not be able to enable md-cache invalidation, if all the servers and clients are not on opversion >= GD_OP_VERSION_3_9_0. To solve the above mentioned issues, we have seperate volume options for enabling md-cache invalidation and upcall. But this can lead to issues when user enable md-cache invalidation and forgets to enable upcall. Probably in the next release, these can be enables by default. Change-Id: Ie70eff97fe12fcb623eec8f4f5861ac065bf483e BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15314 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: soumya k <skoduri@redhat.com> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* glusterd/cli: cli to get local state representation from glusterdSamikshan Bairagya2016-08-261-0/+141
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently there is no existing CLI that can be used to get the local state representation of the cluster as maintained in glusterd in a readable as well as parseable format. The CLI added has the following usage: # gluster get-state [daemon] [odir <path/to/output/dir>] [file <filename>] This would dump data points that reflect the local state representation of the cluster as maintained in glusterd (no other daemons are supported as of now) to a file inside the specified output directory. The default output directory and filename is /var/run/gluster and glusterd_state_<timestamp> respectively. The option for specifying the daemon name leaves room to add support for other daemons in the future. Following are the data points captured as of now to represent the state from the local glusterd pov: * Peer: - Primary hostname - uuid - state - connection status - List of hostnames * Volumes: - name, id, transport type, status - counts: bricks, snap, subvol, stripe, arbiter, disperse, redundancy - snapd status - quorum status - tiering related information - rebalance status - replace bricks status - snapshots * Bricks: - Path, hostname (for all bricks these info will be shown) - port, rdma port, status, mount options, filesystem type and signed in status for bricks running locally. * Services: - name, online status for initialised services * Others: - Base port, last allocated port - op-version - MYUUID Change-Id: I4a45cc5407ab92d8afdbbd2098ece851f7e3d618 BUG: 1353156 Signed-off-by: Samikshan Bairagya <samikshan@gmail.com> Reviewed-on: http://review.gluster.org/14873 Reviewed-by: Avra Sengupta <asengupt@redhat.com> 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: Atin Mukherjee <amukherj@redhat.com>
* cluster/afr: Prevent split-brain when bricks are brought off and on in ↵Krutika Dhananjay2016-08-221-0/+112
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | cyclic order When the bricks are brought offline and then online in cyclic order while writes are in progress on a file, thanks to inode refresh in write txns, AFR will mostly fail the write attempt when the only good copy is offline. However, there is still a remote possibility that the file will run into split-brain if the brick that has the lone good copy goes offline *after* the inode refresh but *before* the write txn completes (I call it in-flight split-brain in the patch for ease of reference), requiring intervention from admin to resolve the split-brain before the IO can resume normally on the file. To get around this, the patch does the following things: i) retains the dirty xattrs on the file ii) avoids marking the last of the good copies as bad (or accused) in case it is the one to go down during the course of a write. iii) fails that particular write with the appropriate errno. This way, we still have one good copy left despite the split-brain situation which when it is back online, will be chosen as source to do the heal. Change-Id: I9ca634b026ac830b172bac076437cc3bf1ae7d8a BUG: 1363721 Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com> Reviewed-on: http://review.gluster.org/15080 Tested-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: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Oleksandr Natalenko <oleksandr@natalenko.name> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
* tests/cli: Generate SSL certificatesAshish Pandey2016-08-211-0/+17
| | | | | | | | | | | | | | | Generate SSL certificates before enabling management encryption to avoid test failure. Change-Id: Iab23b36703f4653f1d5bb9d14695e4d3fa63ad61 Signed-off-by: Ashish Pandey <aspandey@redhat.com> BUG: 1368349 Signed-off-by: Ashish Pandey <aspandey@redhat.com> Reviewed-on: http://review.gluster.org/15202 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: Atin Mukherjee <amukherj@redhat.com>
* glusterd: Fix volume restart issue upon glusterd restartSamikshan Bairagya2016-08-172-1/+41
| | | | | | | | | | | | | | | | | | | | | | | http://review.gluster.org/#/c/14758/ introduces a check in glusterd_restart_bricks that makes sure that if server quorum is enabled and if the glusterd instance has been restarted, the bricks do not get started. This prevents bricks which have been brought down purposely, say for maintainence, from getting started upon a glusterd restart. However this change introduced regression for a situation that involves multiple volumes. The bricks from the first volume get started, but then for the subsequent volumes the bricks do not get started. This patch fixes that by setting the value of conf->restart_done to _gf_true only after bricks are started correctly for all volumes. Change-Id: I2c685b43207df2a583ca890ec54dcccf109d22c3 BUG: 1367478 Signed-off-by: Samikshan Bairagya <samikshan@gmail.com> Reviewed-on: http://review.gluster.org/15183 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: Atin Mukherjee <amukherj@redhat.com>
* logging: Fix per xl log levelPoornima G2016-08-151-0/+43
| | | | | | | | | | | | | | | | | | | Currently per xlator loglevel setting doesn't work, due to the flaw in loglevel checking. Fix the same. Per xlator logging can be set using the below command: Eg: setfattr -n trusted.glusterfs.patchy-md-cache.set-log-level -v TRACE /mnt/glusterfs/0 Change-Id: I8ff1d15bd5693b6f682d99bee22a4bbb5eee646c BUG: 1362520 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/15071 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: Niels de Vos <ndevos@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* glusterd: Convert volume to replica after adding brick self heal is not ↵Mohit Agrawal2016-08-111-0/+54
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | triggered Problem: After add brick to a distribute volume to convert to replica is not triggering self heal. Solution: Modify the condition in brick_graph_add_index to set trusted.afr.dirty attribute in xlator. Test : To verify the patch followd below steps 1) Create a single node volume gluster volume create <DIS> <IP:/dist1/brick1> 2) Start volume and create mount point mount -t glusterfs <IP>:/DIS /mnt 3) Touch some file and write some data on file 4) Add another brick along with replica 2 gluster volume add-brick DIS replica 2 <IP>:/dist2/brick2 5) Before apply the patch file size is 0 bytes in mount point. BUG: 1365455 Change-Id: Ief0ccbf98ea21b53d0e27edef177db6cabb3397f Signed-off-by: Mohit Agrawal <moagrawa@redhat.com> Reviewed-on: http://review.gluster.org/15118 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Anuradha Talur <atalur@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
* glusterd : skip non directories inside /var/lib/glusterd/volsJiffin Tony Thottan2016-08-081-0/+31
| | | | | | | | | | | | | | | | Right now glusterd won't come up if vols directory contains an invalid entry. Instead of doing that with this change a message will be logged and then skip that entry Change-Id: I665b5c35291b059cf054622da0eec4db44ec5f68 BUG: 1318591 Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com> Reviewed-on: http://review.gluster.org/13764 Reviewed-by: Prashanth Pai <ppai@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> 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>
* posix: Do not move and recreate .glusterfs/unlink directoryAshish Pandey2016-08-081-0/+36
| | | | | | | | | | | | | | | | | | | | | | | | | Problem: At the time of start of a volume, it is checked if .glusterfs/unlink exist or not. If it does, move it to landfill and recreate unlink directory. If a volume is mounted and we write data on it till we face ENOSPC, restart of that volume fails as it will not be able to create unlink dir. mkdir will fail with ENOSPC. This will not allow volume to restart. Solution: If .glusterfs/unlink directory exist, don't move it to landfill. Delete all the entries inside it. Change-Id: Icde3fb36012f2f01aeb119a2da042f761203c11f BUG: 1360679 Signed-off-by: Ashish Pandey <aspandey@redhat.com> Reviewed-on: http://review.gluster.org/15030 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>
* tests: fix spurious failure in tests/bugs/glusterd/bug-1089668.tAtin Mukherjee2016-08-041-2/+1
| | | | | | | | | | | | | | Instead of rebalance stop, its always better to wait for rebalance to complete as the former doesn't have any purpose. Change-Id: Ia1bc2a34d937a0a96543bebd257dcda619f12474 BUG: 1363948 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/15085 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: Jeff Darcy <jdarcy@redhat.com>
* libglusterfs: fix glusterd statedump crashAtin Mukherjee2016-08-041-1/+6
| | | | | | | | | | | | | | | | | | commit 3c04a91 removed setting typeStr to NULL if num_allocs is set to 0, this has caused this regression. Code has been put back like earlier and to avoid statedump printing all the NULL values check is modified to see skip the records if num_allocs is 0 instead of total_allocs Change-Id: Ib8bcc2fba908e88cf52b641c3f6bcba74f5e667c BUG: 1359190 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/14987 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: N Balachandran <nbalacha@redhat.com> Reviewed-by: Prashanth Pai <ppai@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* glusterd: clean up old port and allocate new one on every restartAtin Mukherjee2016-08-032-49/+0
| | | | | | | | | | | | | | | | | | | | | | | | GlusterD as of now was blindly assuming that the brick port which was already allocated would be available to be reused and that assumption is absolutely wrong. Solution : On first attempt, we thought GlusterD should check if the already allocated brick ports are free, if not allocate new port and pass it to the daemon. But with that approach there is a possibility that if PMAP_SIGNOUT is missed out, the stale port will be given back to the clients where connection will keep on failing. Now given the port allocation always start from base_port, if everytime a new port has to be allocated for the daemons, the port range will still be under control. So this fix tries to clean up old port using pmap_registry_remove () if any and then goes for pmap_registry_alloc () Change-Id: If54a055d01ab0cbc06589dc1191d8fc52eb2c84f BUG: 1221623 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/15005 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: Avra Sengupta <asengupt@redhat.com>
* tests: Fix get_pending_heal_count check in ecRavishankar N2016-07-2910-1/+1
| | | | | | | | | | | | | | | | Continuation of http://review.gluster.org/#/c/14985. Also renamed tests/bugs/disperse to tests/bugs/ec for a better correlation to tests/basic/ec and xlators/cluster/ec Change-Id: I662b3477c12af8a0b94597769e8f00f354b1168c BUG: 1332054 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/15006 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: Pranith Kumar Karampuri <pkarampu@redhat.com> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
* io-threads: remove least-rate-limit option and codeJeff Darcy2016-07-281-53/+0
| | | | | | | | | | | | | | This will be unnecessary, and mostly in the way, as real fairness guarantees are implemented. Change-Id: Ic61ec1c9e9add58385f1a4eafcfe2cc554ceefc8 BUG: 1360402 Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-on: http://review.gluster.org/14989 Smoke: Gluster Build System <jenkins@build.gluster.org> Tested-by: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: Gluster Build System <jenkins@build.gluster.org>
* snapshot/snapd: Don't display pid when snapd is offlineAvra Sengupta2016-07-271-0/+6
| | | | | | | | | | | | | | | | We were previously reading the pidfile, and displaying the pid even if snapd daemon is not running. Now to fix it, we re-assign pid value to -1, if snapd is offline. Change-Id: I4baff8d489fe9380061c52aea006db90fa421cd7 BUG: 1358244 Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/14981 Tested-by: Vijay Bellur <vbellur@redhat.com> 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: Jeff Darcy <jdarcy@redhat.com>
* afr: some coverity fixesRavishankar N2016-07-262-4/+4
| | | | | | | | | | | | | | | Thanks to Krutika for a cleaner way to track inode refs in afr_set_split_brain_choice(). Change-Id: I2d968d05b815ad764b7e3f8aa9ad95a792b3c1df BUG: 1355604 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/14895 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>
* tests: Moving ./tests/bugs/snapshot/bug-1316437.t to bad testAvra Sengupta2016-07-251-0/+2
| | | | | | | | | | | | | | | | Moving ./tests/bugs/snapshot/bug-1316437.t to bad test, while mulling over the pros and cons of the fix. Will update the bug, as we go. Sending this patch to unblock master. Change-Id: Ia863312913686b4fa0ee0b63da13aedc0439a835 BUG: 1359717 Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/15001 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-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: Jeff Darcy <jdarcy@redhat.com>
* tests: Fix pending-heal-count checksPranith Kumar K2016-07-221-4/+2
| | | | | | | | | | | | | | | | | | EXPECT_WITHIN takes regular expression to match the count, so even when there are say 10 entries to heal, it would think that the heal is complete. Fixed checking pending heal count with correct regex. Thanks to Xavi for finding this problem. Change-Id: Ic593d22468b2b586bfca864962ffa0eda96b1d1f BUG: 1332054 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/14985 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Xavier Hernandez <xhernandez@datalab.es> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* tests: Enable all gfapi test casesPoornima G2016-07-2015-41/+45
| | | | | | | | | | | Change-Id: I32bfec4af91348d96dc3e81a9d5c9cad599f821b Bug: 1358594 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/14748 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 Talur <rtalur@redhat.com>
* tests: Fix spurious failure of tests/bugs/glusterd/bug-1111041.tAvra Sengupta2016-07-201-6/+2
| | | | | | | | | | | | | | | | | | On a faster machine the ps check was returning two pids, including the glusterfsd process's pid, right after that, process forked. Hence removing that ps, as for the scope of this test, verifying the snapd pid from the status command itself is enough. Change-Id: I8bd8fc4ea406d96e3a47f952cfe44560b615dbe6 BUG: 1358195 Signed-off-by: Avra Sengupta <asengupt@redhat.com> Reviewed-on: http://review.gluster.org/14963 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Rajesh Joseph <rjoseph@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
* md-cache: Add cache invalidation support to invalidate the meta data cachePoornima G2016-07-201-7/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: md-cache currently updates its stat in cbks of selected fops. The default cache time is 1 second, if this is increasd to reap the benefits of caching, we may end up with stale cache for long time, as there is no logic yet to notify md-cache of backend changes by another client. Solution: Use the existing upcall mechanism to invalidate the cache. For this feature to work, "features.cache-invalidation" volume option should be enabled. This patch as is doesn't improve any performance, the benifit of the patch is that it provides coherency for stat cache, hence the cache timeout can be quite longer which in turn can improve the performance. Change-Id: I2dbb0afa7b5e4a5a248f910188e0918e02f18692 BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/12951 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>
* xlator/trash : append '/' at the end in trash_notify_lookup_cbkJiffin Tony Thottan2016-07-191-0/+29
| | | | | | | | | | | | | | | | | | In the notify function in trash xlator, a lookup is performed to obtain path of old trash directory. The result usually contains path without '/' at the end. The trash xlator maintains expects '/' at the end for the values such as 'old trash dir' and 'new trash dir'. Otherwise certian checks in the code will fail. Change-Id: I89e02e4b249314fb6536297f959865feee182c83 BUG: 1357397 Signed-off-by: Jiffin Tony Thottan <jthottan@redhat.com> Reviewed-on: http://review.gluster.org/14938 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Anoop C S <anoopcs@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
* Revert "tests: remove tests for clear-locks"Pranith Kumar K2016-07-183-0/+114
| | | | | | | | | | | | | | | | | | This reverts commit 0086a55bb7de1ef5dc7a24583f5fc2b560e835fd. As part of Richard's patch for lock-revocation feature this bug is completely fixed (I think at least ;-) ). So bringing these back so that we will find out if there are anymore things we need to address in this code path. BUG: 1350867 Change-Id: If1440fc83b376576ae1a77b1156188a6bf53fe3a Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/14817 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: Jeff Darcy <jdarcy@redhat.com>
* tests: fix rebalance timing issueSakshi Bansal2016-07-111-0/+2
| | | | | | | | | | | | | | | | With a start and stop rebalance, the stop command may fail as by that time the rebalance process may not come up. Using the rebalance status commmand to ensure that the rebalance process is up before stoping rebalance. Change-Id: I3d5123cd5dfabde2720428455b257d11b980ce21 BUG: 1354372 Signed-off-by: Sakshi Bansal <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/14885 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: Jeff Darcy <jdarcy@redhat.com>
* glusterd: Don't start bricks if server quorum is not metSamikshan Bairagya2016-07-051-0/+62
| | | | | | | | | | | | | | | | | | | | | Upon glusterd restart if it is observered that the server quorum isn't met anymore due to changes to the "server-quorum-ratio" global option, the bricks should be stopped if they are running. Also if glusterd has been restarted, and if server quorum is not applicable for a volume, do not restart the bricks corresponding to the volume to make sure that bricks that have been brought down purposely, say for maintenance, are not brought up. This commit moves this check that was previously inside "glusterd_spawn_daemons" to "glusterd_restart_bricks" instead. Change-Id: I0a44a2e7cad0739ed7d56d2d67ab58058716de6b BUG: 1345727 Signed-off-by: Samikshan Bairagya <samikshan@gmail.com> Reviewed-on: http://review.gluster.org/14758 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: Jeff Darcy <jdarcy@redhat.com>
* glusterd: spawn daemons from init() on a single or two node setupAtin Mukherjee2016-07-051-0/+37
| | | | | | | | | | | | | | | | | Allow glusterd to spawn the daemons at the time of initialization when peer count is less than 2. This is required if user wants to set up a two node cluster with out server side quorum and want the bricks to come up on a node where the other node is down, however the behaviour will be overriden when server side quorum is enabled. Change-Id: I21118e996655822467eaf329f638eb9a8bf8b7d5 BUG: 1352277 Signed-off-by: Atin Mukherjee <amukherj@redhat.com> Reviewed-on: http://review.gluster.org/14848 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: Jeff Darcy <jdarcy@redhat.com>
* md-cache: Cache gluster-samba metadataPoornima G2016-07-051-0/+22
| | | | | | | | | | | | Change-Id: I0a95f4897440c5bf6f54612d9c232e015c8bf983 BUG: 1211863 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/14824 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Prashanth Pai <ppai@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
* glusterd: glusterd must store all rebalance related informationSakshi Bansal2016-07-041-0/+59
| | | | | | | | | | | Change-Id: I8404b864a405411e3af2fbee46ca20330e656045 BUG: 1351021 Signed-off-by: Sakshi Bansal <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/14827 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: Atin Mukherjee <amukherj@redhat.com>
* cli: different status output for rebalance fix-layoutSakshi2016-07-033-4/+4
| | | | | | | | | | | Change-Id: I6ded40a1b1cff5c72e5b61fd353db3d8c688efd8 BUG: 1225718 Signed-off-by: Sakshi <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/10956 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: Raghavendra G <rgowdapp@redhat.com>
* afr:Don't wind reads for files in metadata split-brainRavishankar N2016-06-242-1/+43
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem: For a read on a file in metadata split-brain: 1.lookup_done resets event_generation to zero. 2. readv is issued, goes to inode refresh due to mismatching event_gen. 3. After refresh is successful, we update event_generation, data and metdata readable. 3. We then call afr_read_txn_refresh_done() which in turn calls afr_inode_get_readable() but doesn't check for EIO. So afr_readv_wind is called with local->readable (which is populated with data_readable), thus winding the read to a brick. 4. Also, further parallel reads that come directly go to the wind path because there is no inode_refresh needed. Fix: 1.For any afr_read_txn(), readable must be an intersection of data and metadata readable. 2.Check for EIO in afr_read_txn_refresh_done(). Change-Id: I22dd221fdfaf96d7aced2f474e28ed1337d69f0e BUG: 1305031 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: http://review.gluster.org/13389 Reviewed-by: Ashish Pandey <aspandey@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>
* Fix opRet value for volume info --xml call on non-existent volumeSamikshan Bairagya2016-06-211-0/+24
| | | | | | | | | | | | | | | | | | The opRet field was being assigned to 0 in the XML output when a gluster volume info --xml call is made on a non-existent volume. This change assigns a value of -1 to opRet for volume info calls for non-existent volumes. Other fields like opErrno and opErrstr are also assigned relevant values Change-Id: I3920c602328f74252c87bb521f5a43d4bdc7d44d BUG: 1321836 Signed-off-by: Samikshan Bairagya <samikshan@gmail.com> Reviewed-on: http://review.gluster.org/13843 Smoke: Gluster Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: darshan n <dnarayan@redhat.com> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
* gfapi: Fix IO error caused when there is consecutive graph switchesPoornima G2016-06-164-0/+185
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Issue: Consider a simple situation, where glfs_init() is done, i.e. initial graph is up. Now perform 2 volume sets that results in 2 client side graph changes. After this perform some IO, the IO fails with ENOTCON. The only way to recover this client is i guess another graph switch or restart. What actually is happening from code perspective: Initial graph lets say A, followed by 2 consecutive graph switches to B and C without any IO those two switches. - graph_setup (A) as a result of GF_EVENT_CHILD_UP, and fs->next_subvol = A - glfs_init() results in fs->active_subvol = A, fs->next_subvol = NULL - graph_setup (B) as a result of GF_EVENT_CHILD_UP, and fs->next_subvol = B - graph_setup (C) as a result of GF_EVENT_CHILD_UP, and fs->next_subvol = C. It also sees that the previous graph B was never set as fs->active_subvol, i.e. no IO or anything happened on B, so can safely send GF_EVENT_PARENT_DOWN (by calling glfs_subvol_done(B)). This parent down on B, results in child_down(B), which is fine. But child_down also triggers graph_setup(B). - graph_setup(B) as a result of GF_EVENT_CHILD_DOWN, and fs->next_subvol = B, and GF_EVENT_PARENT_DOWN on C as explained above. This again leads to GF_EVENT_CHILD_DOWN on C. - graph_setup(C) as a result of GF_EVENT_CHILD_DOWN, and fs->next_subvol = C, and GF_EVENT_PARENT_DOWN on B as explained above. Thus both the graphs B and C are disconnected, and hence the ENOTCON Solution: Remove the call to graph_setup() when the event is GF_EVENT_CHILD_DOWN. It don't see any reason why graph_setup should be called when there is child_down. Not sure what the original reason was, to have graph_setup in child_down. git hostory shows the first patch itself had this call. Change-Id: I9de86555f66cc94a05649ac863b40ed3426ffd4b BUG: 1343038 Signed-off-by: Poornima G <pgurusid@redhat.com> Reviewed-on: http://review.gluster.org/14656 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: Jeff Darcy <jdarcy@redhat.com>
* io-stats: Fix io-stat dump to dump at all levelsShyam2016-06-151-5/+56
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previous commit to fix the bug, where io-stat-dump was overwriting the dump file when the client and a brick was on the same host, failed to consider the existing behaviour where io-stats can help generate closely correlated set of stats across clients and bricks, by triggering the dump using the same command. This was introduced in commit: 0facb11220aea20a6573b656785922219c9650cf Further, by limiting the first io-stat to unwind the dump request, there is no way to trigger other io-stat xlators in the stack to dump their stat information. This bug hence is being fixed by this commit keeping the following in mind, - We need to trigger io-stat-dump for all instances in the graph when this attr is set - We need to write the output to different files, so that they do not overwrite each others data - We need to prevent this xattr from being set on the path that is used to trigger the io-stat-dump information Change-Id: I31ec380f0d85e10313a9d7b977da0e1ec74638a6 BUG: 1322825 Signed-off-by: Shyam <srangana@redhat.com> Reviewed-on: http://review.gluster.org/14552 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Ravishankar N <ravishankar@redhat.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Jeff Darcy <jdarcy@redhat.com>