glusterfs.git/xlators/features, branch v3.3.0beta3

Fix compiler warnings and typos from Debian build.

2012-04-10T21:37:29+00:00

Mostly to do with "-Werror=format-security" being buggy, but while we're
here we might as well fix some typos and such.  Credit goes to Patrick
Matthäi  for pointing these out.

Change-Id: Ia32d1111d7c10b1f213df85d86b17a1326248ffd
BUG: 811387
Signed-off-by: Jeff Darcy 
Reviewed-on: http://review.gluster.com/3117
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

geo-rep / gsyncd: shuffle directory entries in crawl

2012-04-05T12:12:59+00:00

In order to randomize the walk of the file tree.

Change-Id: I9fc3b83d5804914a50faae8df7dbcfed2ba6f4b4
BUG: 809675
Signed-off-by: Csaba Henk 
Reviewed-on: http://review.gluster.com/3079
Tested-by: Gluster Build System 
Reviewed-by: Venky Shankar

locks, stripe: check if dict is NULL before refing it

2012-04-03T11:20:48+00:00

Change-Id: Ifab58504280ed92e4435f7805052745e56bef5ef
BUG: 808003
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/3073
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

quota: log msgs indicating NULL parent inode in DEBUG level.

2012-04-03T07:57:56+00:00

with name-less lookups its common to hit situations where parent
inode is NULL.

Signed-off-by: Raghavendra G 
Change-Id: I980b14c3d4691e850ae15768f73cf1b7d867e930
BUG: 809032
Reviewed-on: http://review.gluster.com/3071
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

features/locks: INIT the list before insert_merge

2012-03-31T12:17:09+00:00

Change-Id: I1612565e2bbf1811a85341016b86571bdf6e5062
BUG: 805994
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.com/3047
Tested-by: Gluster Build System 
Reviewed-by: Jeff Darcy 
Reviewed-by: Vijay Bellur

features/locks: check whether dict is NULL before refing it

2012-03-29T14:47:11+00:00

Change-Id: I8906b80e584466aceb5a7402e3cee6ac2a552fab
BUG: 808003
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/3036
Tested-by: Gluster Build System 
Reviewed-by: Jeff Darcy

core: adding extra data for fops

2012-03-22T23:40:27+00:00

with this change, the xlator APIs will have a dictionary as extra
argument, which is passed between all the layers. This can be
utilized for overloading in some of the operations.

Change-Id: I58a8186b3ef647650280e63f3e5e9b9de7827b40
Signed-off-by: Amar Tumballi 
BUG: 782265
Reviewed-on: http://review.gluster.com/2960
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

features/locks: Avoid race in pl_inode_get

2012-03-21T18:16:17+00:00

Change-Id: I6c7b878fb43863137aac6552ee66f091534a6296
BUG: 770080
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.com/2998
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

features/locks: Avoid race in creating domains

2012-03-21T18:15:15+00:00

Thread:1                 |       Thread:2
-----------------------------------------
1) Does inodelk on inode1| 1) Does inodelk on inode1
2) It tries to get the   | 2) It tries to get the
dom object for the volume| dom object for the volume
volname-replicate-0. But | volname-replicate-0. But
the domain list is empty.| the domain list is empty.
3) Create the new domain |
dom1 and add it to head  |
of the list of domains.  |
4) inodelk happens on    | 3) Create the new domain
dom1 on range r1.        | dom2 and add it to head
                         | of the list of domains.
                         | 4) inodelk happens on dom2 on range r2
5) unlock for r1 comes   | 5) Unlock on r2 succeeds.
on inode1.               |
6) It tries to get the   |
domain, of the inodelk   |
for volume               |
volname-replicate-0, gets|
dom2 but the lock on     |
range r1 is not present  |
so it fails.             |

subsequent inode lock, unlocks will keep happening on the domain dom2.
The stale lock present in the dom1 on range r1 will live on.
It wont cause any hangs, but the statedump will always be scary.

Change-Id: I9adc120d33febf685b30859cc307768c2fc63ae5
BUG: 770080
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.com/2993
Tested-by: Gluster Build System 
Reviewed-by: Jeff Darcy 
Reviewed-by: Anand Avati

features/marker: Replacing -1 with GF_CLIENT_PID_GSYNCD as part of code cleanup.

2012-03-20T14:47:21+00:00

Change-Id: Ia665060bff636b372904a726aba5249de9ade124
BUG: 769494
Signed-off-by: Mohammed Junaid 
Reviewed-on: http://review.gluster.com/2971
Tested-by: Gluster Build System 
Reviewed-by: Csaba Henk