glusterfs.git/xlators/cluster/afr/src/afr-self-heal-data.c, branch v3.8.8

afr: allow I/O when favorite-child-policy is enabled

2017-01-08T10:48:49+00:00

Problem:
Currently, I/O on a split-brained file fails even when the
favorite-child-policy is set until the self-heal is complete.

Fix:
If a valid 'source' is found using the set favorite-child-policy, inspect
and reset the afr pending xattrs on the 'sinks' (inside appropriate locks),
refresh the inode and then proceed with the read or write transaction.

The resetting itself happens in the self-heal code and hence can also
happen in the client side background-heal or by the shd's index-heal in
addition to the txn code path explained above. When it happens in via
heal, we also add checks in undo-pending to not reset the sink xattrs
again.

> Reviewed-on: http://review.gluster.org/15673
> Tested-by: Pranith Kumar Karampuri 
> Smoke: Gluster Build System 
> Reviewed-by: Pranith Kumar Karampuri 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 

Change-Id: Ic8c1317720cb26bd114b6fe6af4e58c73b864626
BUG: 1378547
Signed-off-by: Ravishankar N 
Reported-by: Simon Turcotte-Langevin 
Reviewed-on: http://review.gluster.org/16091
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Smoke: Gluster Build System 
Reviewed-by: Niels de Vos

afr: some coverity fixes

2016-07-28T13:54:49+00:00

Note: This is a backport of http://review.gluster.org/14895.
It contains:
i) fixes that prevent deadlocks (afr-common.c).
ii) fixes over-writing op-errno=ENOMEM with possible other values
(afr-inode-read.c).
iii) prevents doing further operations with a NULL dictionary if
allocation fails (afr-self-heal-data.c).
iv) prevents falsely marking a sink as healed if metadata heal fails
midway(afr-self-heal-metadata.c).
v) other minor fixes.

Considering the above are not trivial fixes, the patch is a good
candidate for merging in 3.8 branch.

Thanks to Krutika for a cleaner way to track inode refs in
afr_set_split_brain_choice().

Change-Id: I2d968d05b815ad764b7e3f8aa9ad95a792b3c1df
BUG: 1360556
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/15018
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Krutika Dhananjay 
Reviewed-by: Pranith Kumar Karampuri

afr: Automagic unsplit-brain by [ctime|mtime|size|majority]

2016-05-27T14:56:37+00:00

Backport of http://review.gluster.org/#/c/14026/

Introduce cluster.favorite-child-policy which when enabled with
[ctime|mtime|size|majority], automatically heals files that are in
split-brian.

The majority policy will not pick a source if there is no majority.
The other three policies pick the first brick with a valid reply and
non-zero ctime/mtime/size as source.

Change-Id: I93623a914dce2839957fce87b514050e9d274d4c
BUG: 1339639
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/14535
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri

cluster/afr: Do not fsync when durability is off

2016-04-27T15:06:35+00:00

BUG: 1329501
Change-Id: Id402c20f2fa19b22bc402295e03e7a0ea96b0c40
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/14048
Reviewed-by: Ravishankar N 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Jeff Darcy

cluster/afr: Fix inode-leak in data self-heal

2016-04-25T06:17:43+00:00

Thanks to Olia-Kremmyda for finding the bug on github review,
https://github.com/gluster/glusterfs/commit/b8106d1127f034ffa88b5dd322c23a10e023b9b6

Change-Id: Ib8640ed0c331a635971d5d12052f0959c24f76a2
BUG: 1329773
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/14052
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Ravishankar N 
Reviewed-by: Krutika Dhananjay

cluster/afr: Fix partial heals in 3-way replication

2016-04-15T09:51:06+00:00

Problem:
When there are 2 sources and one sink and if two self-heal daemons
try to acquire locks at the same time, there is a chance that it
gets a lock on one source and sink leading partial to heal. This will
need one more heal from the remaining source to sink for the complete
self-heal. This is not optimal.

Fix:
Upgrade non-blocking locks to blocking lock on all the subvolumes, if
the number of locks acquired is majority and there were eagains.

BUG: 1318751
Change-Id: Iae10b8d3402756c4164b98cc49876056ff7a61e5
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/13766
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Ravishankar N

cluster/afr: Choose local child as source if possible

2016-03-11T19:14:56+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

cluster/afr: Fix heal-info slow response while IO is in progress

2016-02-04T06:58:37+00:00

Now heal-info does an open() on the file being examined so that
the client at some point sees open-fd count being > 1 and releases
the eager-lock so that heal-info doesn't remain blocked forever
until IO completes.

Change-Id: Icc478098e2bc7234408728b54d8185102b3540dc
BUG: 1297695
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/13326
Reviewed-by: Ravishankar N 
Smoke: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Pranith Kumar Karampuri 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

afr: skip healing data blocks for arbiter

2016-01-18T13:44:50+00:00

1 ....but still do other parts of data-self-heal like restoring the time
and undo pending xattrs.

2. Perform undo_pending inside inodelks.

3. If arbiter is the only sink, do these other parts of data-self-heal
inside a single lock-unlock sequence.

Change-Id: I64c9d5b594375f852bfb73dee02c66a9a67a7176
BUG: 1286017
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/12777
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri

heal : Changed heal info to process all indices directories

2015-12-03T00:00:16+00:00

Change-Id: Ida863844e14309b6526c1b8434273fbf05c410d2
BUG: 1250803
Signed-off-by: Anuradha Talur 
Reviewed-on: http://review.gluster.org/12658
Tested-by: NetBSD Build System 
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur