glusterfs.git/xlators/cluster/dht/src/dht-rebalance.c, branch v3.8.11

cluster/dht: Don't update layout in rebalance_task_completion

2017-02-13T08:32:11+00:00

Updating the layout in the dht inode_ctx in
rebalance_task_completion after the file is migrated
is erroneous in case of files with hardlinks.
This step can be skipped as the layout will be set
in the syncop_lookup call post the migration in
dht_migrate_file.

> Change-Id: I24ac798a919585d91a117d6a207e6a31b88486c6
> BUG: 1415761
> Signed-off-by: N Balachandran 
> Reviewed-on: https://review.gluster.org/16457
> Reviewed-by: Raghavendra G 
> Reviewed-by: Susant Palai 
Signed-off-by: N Balachandran 

Change-Id: Ifccffd67b8bc12208efb23101366a1ac7a8c60f5
BUG: 1420184
Reviewed-on: https://review.gluster.org/16561
Smoke: Gluster Build System 
Tested-by: N Balachandran 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Susant Palai 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos

dht/rebalance: remove errno check for failure detection

2017-01-08T11:03:50+00:00

> BUG: 1410355
> Change-Id: I867419ca36a81ef7209e6911a46c1c2c898b8eab
> Signed-off-by: Susant Palai 
> Reviewed-on: http://review.gluster.org/16328
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Smoke: Gluster Build System 
>Reviewed-by: Raghavendra G 
(cherry picked from commit 451ca272d12f2d49522c845d53585520f71525f8)

Change-Id: If05094346fc1fc48f4982db6a195740171ae2fad
BUG: 1410764
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/16348
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos

dht/rebalance: reverify lookup failures

2016-12-28T05:54:41+00:00

race: readdirp has read one entry, and doing a lookup on
that entry, but user might have renamed/removed that entry just
after readdirp but before lookup.

Since remove-brick is a costly opertaion,will ingore any
ENOENT/ESTALE failures and move on.

> Change-Id: I62c7fa93c0b9b7e764065ad1574b97acf51b5996
> BUG: 1408115
> Signed-off-by: Susant Palai 
> Reviewed-on: http://review.gluster.org/15846
> Reviewed-by: Raghavendra G 
> Smoke: Gluster Build System 
> CentOS-regression: Gluster Build System 
> NetBSD-regression: NetBSD Build System 

Change-Id: I62c7fa93c0b9b7e764065ad1574b97acf51b5996
BUG: 1408414
Reviewed-on: http://review.gluster.org/15846
Reviewed-by: Raghavendra G 
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
(cherry picked from commit c20febcb1ffaef3fa29563987e7a3b554aea27b3)
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/16278

cluster/dht: A hard link is lost during rebalance + lookup

2016-12-15T05:32:04+00:00

Problem: A hard link is lost during rebalance + lookup.Rebalance skip
         files if file has hardlink.In dht_migrate_file
         __is_file_migratable () function checks if a file has hardlink,
         if yes file is not migrated but if link is created after call
         this function then link will lost.

Solution: Call __check_file_has_hardlink to check hardlink existence
          after (S+T) bits in migration process ,if file has hardlink
          then skip the file for migrate rebalance process.

> BUG: 1396048
> Change-Id: Ia53c07ef42f1128c2eedf959a757e8df517b9d12
> Signed-off-by: Mohit Agrawal 
> Reviewed-on: http://review.gluster.org/15866
> Reviewed-by: Susant Palai 
> Smoke: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: N Balachandran 
> Reviewed-by: Raghavendra G 
> (cherry picked from commit 71dd2e914d4a537bf74e1ec3a24512fc83bacb1d)

BUG: 1399432
Change-Id: I30e21efd5a054d8a3e640ab3ed8aa7955d083926
Signed-off-by: Mohit Agrawal 
Reviewed-on: http://review.gluster.org/15954
CentOS-regression: Gluster Build System 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: N Balachandran 
Reviewed-by: Raghavendra G

dht: Proper log message if data migration is skipped

2016-11-03T05:33:02+00:00

There was a misleading message from logs about 
available disk space while rebalancing of bricks
while calculating free space.

Bug: 1390870

Backprt of http://review.gluster.org/#/c/15345/

Change-Id: Ie9df0b2cbf00faaf13a0a3f0dbd657377a082755
Signed-off-by: ankitraj 
Reviewed-on: http://review.gluster.org/15765
Tested-by: ankitraj
CentOS-regression: Gluster Build System 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Raghavendra G

dht/rebalance: allocate migrator thread pool dynamically

2016-08-10T10:21:54+00:00

Problems: The maximum number of migratior threads created was static set
to "40". And the number of these threads get created in rebalance depends
on the number of cores user has. If the number of cores exceeds 40, a
crash or memory corruption can be seen.

Fix: Make the migratior thread pool dynamic.

> Change-Id: Ifbdac8a1a396363dd75e2f6bcb454070cfdbf839
> BUG: 1362069
> Reviewed-on: http://review.gluster.org/15000
> Smoke: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: Raghavendra G 
(cherry picked from commit b8e8bfc7e4d3eaf76bb637221bc6392ec10ca54b)

Change-Id: Ifbdac8a1a396363dd75e2f6bcb454070cfdbf839
BUG: 1362069
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/15061
Smoke: Gluster Build System 
Tested-by: N Balachandran 
Reviewed-by: N Balachandran 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System

dht : add metalock/unlock

2016-06-06T06:33:57+00:00

Change-Id: I842a7ea1b286f1b893b200fe647597e7fd0f2105
BUG: 1338501
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/14631
Tested-by: Kotresh HR 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Raghavendra G 
CentOS-regression: Gluster Build System

tier/detach: Clear tier-fix-layout-complete xattr after migration threads join

2016-05-18T20:04:33+00:00

Previously we had wrongly placed the clearing tier-fix-layout-complete
xattr before the joining of migration threads. This would lead to
situations where failure of clearing the xattr would cause the
premature death of migration threads.

Now we clear the xattr only after the data movement threads join,
ensuring that all migration is done.

This is a backport of 14285

> Change-Id: I829b671efa165ae13dbff7b00707434970b37a09
> BUG: 1334839
> Signed-off-by: Joseph Fernandes 
Signed-off-by: Dan Lambright 

Change-Id: I08cc92db1fb8d48026ca51743be6cafe385d1b79
BUG: 1336152
Reviewed-on: http://review.gluster.org/14342
Smoke: Gluster Build System 
Reviewed-by: Joseph Fernandes
Tested-by: Dan Lambright 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

tier/detach : During detach check if background fixlayout is done

2016-05-06T20:11:38+00:00

During detach check if background fixlayout is done, if not done ignore
the case and continue detach.

Backport of http://review.gluster.org/14147

> Change-Id: I5d5cfc0e73d0eb217fdeab54c432dc4af8bc598d
> BUG: 1332136
> Signed-off-by: Joseph Fernandes 
> Reviewed-on: http://review.gluster.org/14147
> Smoke: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: N Balachandran 
> Reviewed-by: Dan Lambright 
> Signed-off-by: Joseph Fernandes 

Change-Id: I16f0320a2c07ac1d137bd4f27697722049df803c
BUG: 1333803
Signed-off-by: Joseph Fernandes 
Reviewed-on: http://review.gluster.org/14241
Smoke: Gluster Build System 
Tested-by: Joseph Fernandes
NetBSD-regression: NetBSD Build System 
Reviewed-by: Niels de Vos 
CentOS-regression: Gluster Build System

dht/rebalance: add lock migration fop to dht_migrate_file

2016-05-02T01:05:14+00:00

Change-Id: Id0e7400c8ae950c90d42a3ddf8b558a14959a1f8
BUG: 1326085
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/14074
Smoke: Gluster Build System 
Reviewed-by: Niels de Vos 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System