glusterfs.git/xlators/cluster/afr/src, branch v3.5.3beta2

cluster/afr: Fix excessive logging in glfsheal log file

2014-10-27T15:47:49+00:00

Wrong afr_local_t instance was being used in the missing entry sh
check in afr_self_heal(), which was leading to entrylk failure messages
of the following kind in glfsheal logfile:

[2014-10-21 12:39:04.109875] I
[afr-self-heal-common.c:2146:afr_sh_post_nb_entrylk_missing_entry_sh_cbk]
0-vol-replicate-1: Non blocking entrylks failed

The fix involves sending the right "local" to
afr_can_start_missing_entry_gfid_self_heal().

After fixing this, there were two more codepaths giving out too many log messages
of the following kinds:

[2014-10-21 22:19:29.568533] E [afr-self-heal-data.c:1611:afr_sh_data_open_cbk]
0-dis-rep-replicate-1: open of 8a858b02-0fc7-4713-9f61-8ca28dea82c0
failed on child dis-rep-client-2 (Stale file handle)

[2014-10-21 22:19:29.577948] E [afr-self-heal-entry.c:2353:afr_sh_post_nonblocking_entry_cbk]
0-dis-rep-replicate-1: Non Blocking entrylks failed for ff9c82c4-5c0c-4ed9-b745-604a28dc352d.

which are also fixed appropriately as part of this patch.

Change-Id: Idd8d8e5735ee7a4ac36f369525f96e53276e0859
BUG: 1153629
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/8965
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos

logs: Do selective logging for errnos

2014-10-22T07:32:40+00:00

        Backport of http://review.gluster.org/8918
                    http://review.gluster.org/8955

Problem:
Just after replace-brick the mount logs are filled with ENOENT/ESTALE
warning logs because the file is yet to be self-healed now that the
brick is new.

Fix:
Do conditional logging for the logs. ENOENT/ESTALE will be logged at
lower log level. Only when debug logs are enabled, these logs will
be written to the logfile.

BUG: 1155073
Change-Id: Icf06f2fc4f2f91e199de24a88bcb0ce9b8955ebd
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8960
Reviewed-by: Krutika Dhananjay 
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos

cluster/afr: Fix sizeof typo

2014-10-18T08:40:11+00:00

Change-Id: Ib82a1c4967f0880c91c114e4baae08bdbe77bb60
BUG: 1153626
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8935
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos

Only cleanup priv->shd.statistics if created

2014-10-07T07:42:29+00:00

It is possible that the statistics array was never created and
dereferencing it may case a segfault.

BUG: 1147156
Change-Id: If905457ba985add62c3ed543bced1313640af762
Signed-off-by: Tiziano Müller 
Reviewed-on: http://review.gluster.org/8873
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Reviewed-by: Niels de Vos

cluster/afr: Launch self-heal only when all the brick status is known

2014-10-01T07:14:21+00:00

Problem:
File goes into split-brain because of wrong erasing of xattrs.

RCA:
The issue happens because index self-heal is triggered even before all the
bricks are up. So what ends up happening while erasing the xattrs is, xattrs
are erased only on the sink brick for the brick that it thinks is up leading to
split-brain

Example:
lets say the xattrs before heal started are:
brick 2:
trusted.afr.vol1-client-2=0x000000020000000000000000
trusted.afr.vol1-client-3=0x000000020000000000000000

brick 3:
trusted.afr.vol1-client-2=0x000010040000000000000000
trusted.afr.vol1-client-3=0x000000000000000000000000

if only brick-2 came up at the time of triggering the self-heal only
'trusted.afr.vol1-client-2' is erased leading to the following xattrs:

brick 2:
trusted.afr.vol1-client-2=0x000000000000000000000000
trusted.afr.vol1-client-3=0x000000020000000000000000

brick 3:
trusted.afr.vol1-client-2=0x000010040000000000000000
trusted.afr.vol1-client-3=0x000000000000000000000000

So the file goes into split-brain.

Change-Id: I79f9a289d2118a715d262398221037b684a53d2a
BUG: 1142614
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8757
Tested-by: Gluster Build System 
Reviewed-by: Krutika Dhananjay 
Reviewed-by: Niels de Vos

cluster/afr: Handle EAGAIN properly in inodelk

2014-09-29T07:00:31+00:00

Problem:
When one of the brick is taken down and brough back up in a replica pair, locks
on that brick will be allowed. Afr returns inodelk success even when one of the
bricks already has the lock taken.

Fix:
If any brick returns EAGAIN return failure to parent xlator.

Note: This change only works for non-blocking inodelks. This patch addresses
dht-synchronization which uses non-blocking locks for rename. Blocking lock is
issued by only one of the rebalance processes. So for now there is no
possibility of deadlock.

Change-Id: I07673f8873263da334e03f35c6cdb5db9410a616
BUG: 1141733
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8739
Tested-by: Gluster Build System 
Reviewed-by: Raghavendra G 
Reviewed-by: Niels de Vos

cluster/afr: Fix a minor typo.

2014-08-26T16:12:21+00:00

Change-Id: I2e1bb21febb6754ed8772df6342c5c06aac95046
BUG: 1133949
Signed-off-by: Vijay Bellur 
Reviewed-on: http://review.gluster.org/8545
Reviewed-by: Humble Devassy Chirammal 
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos

cluster/afr: Fix leaks in self-heal code path

2014-07-18T10:28:22+00:00

Change-Id: I5301ec9ebac27afe52e85cad75e6395d7f891355
BUG: 1120151
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8316
Tested-by: Gluster Build System 
Reviewed-by: Krishnan Parthasarathi 
Reviewed-by: Ravishankar N 
Reviewed-by: Niels de Vos

cluster/afr: Fix resolution issues with afr

2014-06-24T16:26:13+00:00

Problem with afr:
Lets say there is a directory hierarchy a/b/c/d on the mount and the
user is cd'ed into the directory. Bring down one of the bricks of replica and
remove all directories/files to simulate disk replacement on that brick. Now
this brick is brought back up. Creates on the cd'ed directory fail with ESTALE.
Basically before sending a create of 'f' inside 'd', fuse sends a lookup to
make sure the file is not present.  On one of the bricks  'd' is present and
'f' is not so it sends ENOENT as response. On the new brick 'd' itself is not
present. So it sends ESTALE. In afr ESTALE is considered to be special errno on
witnessing which lookup has to fail. And ESTALE is given more priority than
ENOENT. Due to these reasons lookup fails with ESTALE rather than ENOENT. Since
lookup didn't fail with ENOENT, 'create' can't be issued so the command is
failed with ESTALE.

Solution:
Afr needs to consider ESTALE errno normally and ENOENT needs to
be given more priority so that operations like create can proceed even when
only one of the brick is up and running. Whenever client xlator identifies
that gfid-changed, it sets that information in lookup xdata. Afr uses this
information to fail the lookup with ESTALE so that top xlator can send
fresh lookup.

Change-Id: Ie8e0e327542fd644409eb5dadf451679afa1c0e5
BUG: 1112348
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/8154
Tested-by: Justin Clift 
Tested-by: Gluster Build System 
Reviewed-by: Ravishankar N 
Reviewed-by: Niels de Vos

cluster/afr: remove unused variable

2014-05-15T13:31:03+00:00

Fix a compiler warning about unused variable. Missed to catch this in
http://review.gluster.org/7723

Change-Id: Iac97051edb97bdd7dbc5f0fd0f2528d4d404d16d
BUG: 1096040
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/7765
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos