glusterfs.git/tests/basic/afr, branch v3.7.2

afr: honour selfheal enable/disable volume set options

2015-06-04T02:11:56+00:00

afr-v1 had the following volume set options that are used to enable/ disable
self-heals from happening in AFR xlator when loaded in the client graph:
cluster.metadata-self-heal
cluster.data-self-heal
cluster.entry-self-heal

In afr-v2, these 3 heals can happen from the client if there is an inode
refresh. This patch allows such heals to proceed only if the corresponding
volume set options are set to true.

Change-Id: I8d97d6020611152e73a269f3fdb607652c66cc86
BUG: 1227674
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/11012
Tested-by: NetBSD Build System 
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
(cherry picked from commit da111ae21429d33179cd11409bc171fae9d55194)
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/11062

tests: data-self-heal.t fixes

2015-05-28T08:37:08+00:00

Backport of http://review.gluster.org/10530 and http://review.gluster.org/10875
Signed-off-by: Ravishankar N 

Change-Id: Ib4ea340bb7e05facbbd0ab6a03eec556770a0c9f
BUG: 1225077
Reviewed-on: http://review.gluster.org/10924
Tested-by: NetBSD Build System
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri

tests: arbiter.t fix

2015-05-27T07:52:04+00:00

Backport of http://review.gluster.org/10833

Wait for AFR's children to be up in glustershd process before attempting heal.

Also, grep (version 2.21) is detecting statedump files as binary, causing tests
to succeed incorrectly. Hence adding the -a switch to force it to treat it as a
text file. Thanks to Vijay Bellur for identifying the issue
(http://lists.gnu.org/archive/html/bug-grep/2015-05/msg00000.html) and the
workaround.

Change-Id: Ie3d9591ffaf44baa0cd8c2baa327aed24378e3df
BUG: 1225077
BUG:
Reviewed-on: http://review.gluster.org/10833
Tested-by: Niels de Vos 
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
(cherry picked from commit b51ee5f8d1f80d66effffc06c1e49099c04014a4)
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/10923
Tested-by: NetBSD Build System
Reviewed-by: Vijay Bellur

tests: Fix entry-self-heal.t

2015-05-27T07:51:21+00:00

        Backport of: http://review.gluster.org/10916

Because both bricks in the replica pair of patchy are in the same node,
both full healer threads within the same shd try and fail to acquire
non-blocking locks when each one gets lock on one of the bricks,
causing heal to fail occasionally.

Now heals are triggered from the mount as part of inode refresh.
And because the AFR on the mount graph
a. does not treat presence of dirty xattrs as something that needs
   a heal (this is true for dirs fool_heal and fool_me) and
b. does not recursively heal the entire hierarchy of subdirs and their
   entries in one shot (this is true with source_creations_heal/dir1),

index heal is used to heal fool_heal, fool_me and
source_creations_heal/dir1 wherein only one brick (which is the brick that
contains the good copy of source_creations_heal/dir_1: brick-1) has all
the gfids to be healed copied into its indices/xattrop directory.

Change-Id: Ibafccfb04967c66066cc58110b767bf118755f90
BUG: 1225077
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/10922
Tested-by: NetBSD Build System
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/afr : Prevent inode-evict during split-brain resolution

2015-05-09T08:54:56+00:00

        Backport of: http://review.gluster.org/#/c/10134/

1) Provided setfattr command to set timeout for split-brain
choice.

2) If split-brain inspection/resolution is being done
from the mount for a file, ref the inode when
split-brain-choice is set.
This inode will be unconditionally unref-ed after timeout
seconds set by the user/default otherwise.

3) Updated the doc and testcase to reflect the changes.

Change-Id: I15c9037dee28855f21e680e7e3632e1f48dba4e1
BUG: 1219388
Reviewed-on: http://review.gluster.org/10134
Reviewed-by: Krutika Dhananjay 
Reviewed-by: Ravishankar N 
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Signed-off-by: Anuradha 
Reviewed-on: http://review.gluster.org/10679

afr: add arbitration support

2015-05-05T09:30:41+00:00

Backport of http://review.gluster.org/#/c/10258/

Add logic in afr to work in conjunction with the arbiter xlator when a
replica 3 arbiter volume is created. More specifically, this patch:

* Enables full locks for afr data transaction for such volumes.
* Removes the upfront marking of pending xattrs at the time of pre-op
  and defer it to post-op. (This is an arbiter independent change and is made for all afr transactions.)
* After pre-op stage, check if we can proceed with the fop stage without
  ending up in split-brain by examining the changelog xattrs.
* Unwinds the fop with failure if only one source was available at the
   time of pre-op and the fop happened to fail on particular source brick.
* Skips data self-heal if arbiter brick is the only source available.
* Adds the arbiter-count option to the shd graph.

This patch is a part of the arbiter logic implementation for 3 way AFR
details of which can be found at http://review.gluster.org/#/c/9656/

Change-Id: I9603db9d04de5626eb2f4d8d959ef5b46113561d
BUG: 1217689
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/10514
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri

tests: Replace getxattr with getfattr

2015-04-08T06:06:25+00:00

Change-Id: Ibbe97dae51a81c8d5142c53a57fd9c630dfb6f46
BUG: 1191396
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/10153
Reviewed-by: Anuradha Talur 
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Pranith Kumar Karampuri 
Tested-by: Gluster Build System

cluster/afr : enable inspection & resolution of files in split-brain

2015-03-19T13:33:12+00:00

Part 2/2 patch to enable users analyze and resolve
split-brain.

This patch enables :
1) Users to inspect the files in data and metadata split-brain.
2) Resolve the split-brain.
Both using a series of setfattr commands.

Consider a volume "test" with 2 bricks.

1) To inspect a file f1:
setfattr -n replica.split-brain-choice -v test-client-0 f1
        After the execution of this command, if no read_subvol
is found, reads will be served from test-client-0 (corresponding
to brick-0).

2) To resolve split-brain :
setfattr -n replica.split-brain-heal-finalize -v test-client-0 f1
        Execution of this command will lead to the resolution
of data and metadata split-brain with subvol mentioned in the
command (test-client-0 here) as the source and the rest as sink.

Change-Id: Ia20f3ee5abd3119e3d54fcc599f1e55ac65fd179
BUG: 1191396
Signed-off-by: Anuradha 
Reviewed-on: http://review.gluster.org/9743
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Gluster Build System

Tests: ls portability regarding dot-files

2015-03-18T10:46:46+00:00

When run as root, BSD ls(1) lists dot-files, which includes
.glusterfs in split-brain-healing.t's usage. This leads to failure.
gfid-self-heal.t suffers the same problem.

Fix by filtering out dot-files in ls(1) output

NB: split-brain-healing.t also requires http://review.gluster.org/9831
to pass on NetBSD.

BUG: 1129939
Change-Id: Ic572d3abf685e9b43f32ddee8a13b5f5c4ae641f
Signed-off-by: Emmanuel Dreyfus 
Reviewed-on: http://review.gluster.org/9885
Tested-by: Gluster Build System 
Reviewed-by: Ravishankar N 
Reviewed-by: Kaleb KEITHLEY

cluster/afr: Implementation of quorum-reads

2015-03-06T05:56:20+00:00

Provide a way of disabling reads when quorum is not met.

Change-Id: Ic4f57c2b87a0b8514600759de3a7a47e217fe3b5
BUG: 1187885
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/9543
Reviewed-by: Ravishankar N 
Tested-by: Gluster Build System