glusterfs.git/xlators, branch v3.7.10

Revert "cluster/ec: Rebalance hangs during rename"

2016-04-01T07:15:51+00:00

This reverts commit 3d34c495d547866a533bc0614b14163381830095, which
broke building rpms and possibly other packages as well.

Change-Id: I2c10a613599e63bc0cbdb1b405cd87be9efa4a99

features/changelog: Don't modify 'pargfid' in 'resolve_pargfid_to_path'

2016-03-31T15:56:13+00:00

Backport of http://review.gluster.org/#/c/13845/

If 'changelog' is enabled and 'changelog.capture-del-path' option is on
it calls 'resolve_pargfid_to_path' which modifies 'pargfid' sent by
caller.  'changelog_unlink' calls this routine directly with
'loc->pargfid' resulting it being modified and point to root instead of
actual pargfid. This is a nasty bug and could cause the deletion of
entry on root directory instead on actual parent when 'loc->path' is
not present.  Hence this fix to make 'pargfid' a const pointer and
'resolve_pargfid' to work on copy of pargfid.

Glusterfind session creation enables these options by default to
capture deleted entry path in changelog.

Thanks Pranith for root causing this.

BUG: 1322552
Change-Id: I9f2bc44b5604b224462594c12b7d79e68198d693
Signed-off-by: Kotresh HR 
Reviewed-on: http://review.gluster.org/13861
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Venky Shankar

cluster/ec: Rebalance hangs during rename

2016-03-31T12:45:50+00:00

Problem:
During the rename of a particular file (ec
is holding blocking inodelk on the parent
directory), if the rename of another file
under the same directory comes. EC does not
release the lock and goes ahead and renames
the "new" file with the "already held lock".

That causes rebalance process to be blocked
on a lock which has been acquired by rename.

Solution:
While rename fop comes, ec takes blocking inodelk
on old and new parent of the file. Before releasing,
every lock held by ec, it waits for some "time" to
see if that lock can be reused by the next fop.
If within this "time" some other request comes,
it releases this lock based on condition
"lock count > 1"

To get this "lock count" for rename fop, we have
implemented "pl_rename" in feature/lock. Also,
on ec side, changed the condition to release the lock
based on the type of fop and old and new parent
directories.

master-
http://review.gluster.org/#/c/13460/

Change-Id: I979dbab1185df962e8f305a6074ae1186ffe7db0
Bug: 1322299
Signed-off-by: Ashish Pandey 
Reviewed-on: http://review.gluster.org/13849
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Pranith Kumar Karampuri

server: send lookup on root inode when itable is created

2016-03-31T12:15:32+00:00

This is a backport of http://review.gluster.org/#/c/13837

 * xlators like quota, marker, posix_acl can cause problems
   if inode-ctx are not created.
   sometime these xlarors may not get lookup on root inode
   with below cases
   1) client may not send lookup on root inode (like NSR leader)
   2) if the xlators on one of the bricks are not up,
      and client sending lookup during this time: brick
      can miss the lookup
   It is always better to make sure that there is one lookup
   on root. So send a first lookup when the inode table is created

 * When sending lookup on root, new inode is created, we need to
   use itable->root instead

> Change-Id: Iff2eeaa1a89795328833a7761789ef588f11218f
> BUG: 1320818
> Signed-off-by: vmallika 
> Reviewed-on: http://review.gluster.org/13837
> Smoke: Gluster Build System 
> CentOS-regression: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> Reviewed-by: Jeff Darcy 

Change-Id: I0abf45444c21b3bc77b5a75ab9a2049a411048d3
BUG: 1320892
Signed-off-by: vmallika 
Reviewed-on: http://review.gluster.org/13862
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Jeff Darcy

md-cache: Cache gluster-swift metadata

2016-03-31T07:48:53+00:00

> BUG: 1317785
> Change-Id: Ie02b8fc294802f8fdf49dee8bf97f1e6177d92bd
> Signed-off-by: Prashanth Pai 
> Reviewed-on: http://review.gluster.org/13735
> Smoke: Gluster Build System 
> Reviewed-by: Poornima G 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: Niels de Vos 
> Reviewed-by: Gaurav Kumar Garg 

BUG: 1317788
Change-Id: I86efca6a829cdda70ec7ed7fe0a16b73c25888c3
Signed-off-by: Prashanth Pai 
Reviewed-on: http://review.gluster.org/13753
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos 
Smoke: Gluster Build System

features/index: Get gfid type in readdir

2016-03-31T07:03:26+00:00

 >Change-Id: I2a6174e1af70a94a52b0b735fd8504800a7ea173
 >BUG: 1313135
 >Signed-off-by: Pranith Kumar K 
 >Reviewed-on: http://review.gluster.org/13553
 >Reviewed-by: Krutika Dhananjay 
 >Smoke: Gluster Build System 
 >NetBSD-regression: NetBSD Build System 
 >Reviewed-by: Anuradha Talur 
 >CentOS-regression: Gluster Build System 
 >(cherry picked from commit 459d0a5e173f9d9f597aec89f81e5377425eb8fb)

Change-Id: I3384906201129d3e03a56bc4b071302028f6953b
BUG: 1322516
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/13858
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Anuradha Talur

cluster/afr: Choose local child as source if possible

2016-03-31T06:30:54+00:00

It is better to choose local brick as source if possible to prevent
over the wire read thus saving on bandwidth. Also changed code to not
attempt data-heal if 'source' is selected as arbiter.

 >Change-Id: I9a328d0198422280b13a30ab99545370a301dfea
 >BUG: 1314150
 >Signed-off-by: Pranith Kumar K 
 >Reviewed-on: http://review.gluster.org/13585
 >Smoke: Gluster Build System 
 >NetBSD-regression: NetBSD Build System 
 >Reviewed-by: Krutika Dhananjay 
 >Tested-by: Krutika Dhananjay 
 >CentOS-regression: Gluster Build System 
 >Reviewed-by: Jeff Darcy 
 >(cherry picked from commit 2807e3fc005630213ab7ad251fef13d61c07ac6b)

Change-Id: I24ea66683f81e238a6c1850664a49fe554011a0a
BUG: 1322521
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/13860
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Ravishankar N

glusterd: Add a new event to handle multi-net probes

2016-03-31T03:39:11+00:00

  Backport of d0cb21b from master

This allows GlusterD to send updates to all other nodes when attaching
new addresses using multi-net peer probe.

Change-Id: I62846be750ab3721912e7b49656594347ea61723
BUG: 1314366
Signed-off-by: Kaushal M 
Reviewed-originally-on: http://review.gluster.org/13817
Reviewed-on: http://review.gluster.org/13840
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System

debug/trace: Print {acm}times as integers

2016-03-30T08:40:12+00:00

        Backport of: http://review.gluster.org/#/c/13826/

This helps in debugging issues with mtime, ctime etc.

Change-Id: Ib98a0845d17351dd86ba90c3837b6f4bc78a94a1
BUG: 1312721
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/13844
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Niels de Vos 
CentOS-regression: Gluster Build System

posix: Filter gsyncd stime xattr

2016-03-29T08:36:09+00:00

Filter gsyncd stime xattr in lookup as well.
The value of stime would be different among
replica bricks and EC bricks. AFR and EC
should not take any action on these as it
could be different.

Change-Id: If577f6115b36e036af2292ea0eaae93110f006ba
Reviewed on: http://review.gluster.org/13678
BUG: 1313623
Signed-off-by: Kotresh HR 
Reviewed-on: http://review.gluster.org/13679
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Pranith Kumar Karampuri