glusterfs.git/tests/basic, branch v3.8.3

tests: do not let gfapi-trunc fail

2016-08-21T11:41:41+00:00

gfapi-trunc test was mistakenly backported as .t in through
http://review.gluster.org/15149. gfapi tests are currently not
compiled/linked correctly in release-3.8 and earlier. Until then, tests
need to be run manually, and not in our automated regression framework.

Change-Id: I45d69564b4340475d4ea60f825fa7288dad65849
BUG: 1368738
Signed-off-by: Oleksandr Natalenko 
Reviewed-on: http://review.gluster.org/15223
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos 
Smoke: Gluster Build System

gfapi: add missing glfs_truncate

2016-08-12T11:19:56+00:00

> Reviewed-on: http://review.gluster.org/13927
> Smoke: Gluster Build System 
> CentOS-regression: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> Reviewed-by: Kaleb KEITHLEY 

BUG: 1366281
Change-Id: I80b016090a4d9d86278a0a5144dd58c0cbfe9bb2
Signed-off-by: Jeff Darcy 
Signed-off-by: Oleksandr Natalenko 
Reviewed-on: http://review.gluster.org/15149
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Kaleb KEITHLEY 
Reviewed-by: Prashanth Pai

nfs: allow hostnames with dashes in exports/netgroups files

2016-08-05T13:19:28+00:00

Hostnames with dashes (like "vagrant-testVM") are not correctly parsed
when reading the exports/netgroups files. This bacomes obvious when
running ./run-tests-in-vagrant.sh because it causes
tests/basic/mount-nfs-auth.t and tests/basic/netgroup_parsing.t to fail.

The regex for hostname (in exports) and the entry and hostname
(netgroups) parsing does not include the "-" sign, and hence the
hostnames are splitted at it.

Cherry picked from commit e5221d288e41d29d89d52f8deab657d2285a852c:
> BUG: 1350237
> Change-Id: I38146a283561e1fa386cc841c43fd3b1e30a87ad
> Signed-off-by: Niels de Vos 
> Reviewed-on: http://review.gluster.org/14809
> Smoke: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: Jeff Darcy 

Change-Id: I38146a283561e1fa386cc841c43fd3b1e30a87ad
BUG: 1357834
Signed-off-by: Niels de Vos 
Reviewed-on: http://review.gluster.org/14955
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: jiffin tony Thottan

tests: Fix get_pending_heal_count check in ec

2016-07-30T11:40:12+00:00

Backport of http://review.gluster.org/#/c/15006/

Change-Id: I3d274bdc2036392af942a17a0e0bf28f431c947b
BUG: 1360574
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/15047
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Xavier Hernandez

tests: Fix spurious failures with split-brain-favorite-child-policy.t

2016-07-28T14:03:08+00:00

Problem:
It is not guranteed that the self-heal daemon would apply the new option
as soon as volume set is executed because all the command gurantees is that
the process is notified of the change in volfile. Shd still needs to fetch
volfile and reconfigure. If the next volume heal command comes even before
the reconfigure happens, then the heal won't happen.

Fix:
Restart shd to make sure it has the option loaded with new value.

 >BUG: 1358976
 >Change-Id: I3ed30ebbec17bd06caa632e79e9412564f431b19
 >Signed-off-by: Pranith Kumar K 
 >Reviewed-on: http://review.gluster.org/14978
 >Smoke: Gluster Build System 
 >Reviewed-by: Krutika Dhananjay 
 >Tested-by: Jeff Darcy 
 >NetBSD-regression: NetBSD Build System 
 >CentOS-regression: Gluster Build System 
 >Reviewed-by: Jeff Darcy 

BUG: 1360573
Change-Id: I09e097dbdc2cae659ad1617d336945eb804b09a5
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/15022
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Ravishankar N

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

tests: Fix timing issue in ec.t

2016-07-27T14:29:05+00:00

Problem:
Because of timing issue sometimes the mount is unmounted
even before the version is updated, this is leading to
not triggering heals.

Fix:
One way to fix this would be to increate 'sleep 2' to 'sleep 10'
but that would slow things down. I changed the way ec learns
it needs xattr healing so that it triggers heals even when the
xattrs are not marked correctly.

 >Change-Id: I1c82041166443ae7079dd99b89ea2ed170233ba3
 >BUG: 1359001
 >Signed-off-by: Pranith Kumar K 
 >Reviewed-on: http://review.gluster.org/14980
 >Smoke: Gluster Build System 
 >NetBSD-regression: NetBSD Build System 
 >CentOS-regression: Gluster Build System 
 >Reviewed-by: Jeff Darcy 

BUG: 1360575
Change-Id: I3e7812e3b54caee651e20d4f5dd7dded2f2aa8d6
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/15024
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Niels de Vos

afr, index: Clean up stale directory and file indices in granular entry sh

2016-07-15T13:43:13+00:00

	Backport of: http://review.gluster.org/14832

Specifically when a directory tree is removed (rm -rf)
while a brick is down, both the directory index and the
name indices of the files and subdirs under it will remain.
Self-heal will need to pick up these and remove them.

Towards this, afr sh will now also crawl indices/entry-changes
and call an rmdir on the dir if the directory index is stale.

On the brick side, rmdir fop has been implemented for index xl,
which would delete the directory index and its contents if present
in a synctask.

Change-Id: I08f45201adca56737ec2be1aab5433aebaefefd0
BUG: 1355609
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/14920
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Ravishankar N 
Reviewed-by: Jeff Darcy

features/index: Delete parent dir indices when heal on it is complete

2016-07-15T07:03:13+00:00

        Backport of: http://review.gluster.org/#/c/14781

In this patch, the state information about whether a directory
gfid index is present or not is stored in the inode ctx with
values IN and NOTIN. This saves index xl the need to perform
stat() everytime an index_entry_create() is called.

When a brick is restarted these in-memory inode ctx records will
be gone. So when granular entry heal happens after a brick is restarted,
and a post-op is done on the parent, if the state gotten from inode ctx
is UNKNOWN, then index xl does a stat to initialize the state as IN or
NOTIN. Note that this is a one-time operation for the lifetime of the
brick. Such a change also helps avoid calling index_del() in
xattrop_index_action() periodically even when granular self-heal is
disabled or when the volume type is disperse.

Change-Id: I037d0a8936381fbe3105e2e78489bfa571e5bdb0
BUG: 1355609
Signed-off-by: Krutika Dhananjay 
Reviewed-on: http://review.gluster.org/14896
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Smoke: Gluster Build System

cli: fix crash in arbiter keyword parsing

2016-06-20T11:41:29+00:00

Backport of http://review.gluster.org/#/c/14738/

A negative case like `gluster volume create volname arbiter 3 /bricks{1..3}`
must not crash. 'arbiter' keyword is valid only for (3 way) replica volumes.

The .t that is added will crash and create a core *without* the fix when
run but will still pass all TESTs. Since the regression framework fails
the .t if it creates a core,  we can consider it a valid test 'that
fails without the fix'.

Change-Id: Ie2d7ced66025ea3617d30f6f823b22401e6d2fde
BUG: 1348055
Signed-off-by: Ravishankar N 
(cherry picked from commit b5c492dfea2d2e2075aa88d7153fba57b06e739d)
Reviewed-on: http://review.gluster.org/14764
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Atin Mukherjee