On F_WRLCKed, Dec 03, 2014 at 01:39:56AM -0500, Krutika Dhananjay wrote:
> Come to think of it, it does not really matter whether the two bricks are on the same node or not.
> In either case, there may not be a lock contention between healers associated with different bricks, irrespective of whether they are part of the same SHD or SHDs on different nodes.
The traces I have been collecting suggest the two healers locks the same
inodes Here is what happens when gluster volume heal full is invoked:
two inodes, each of them locking on each subvolume.
[afr-self-heald.c:699:afr_shd_full_healer]
0-patchy-replicate-0: starting full sweep on subvol patchy-client-0
[afr-self-heald.c:699:afr_shd_full_healer]
0-patchy-replicate-0: starting full sweep on subvol patchy-client-1
[afr-self-heal-metadata.c:328:afr_selfheal_metadata]
0-XXXmanu: afr_selfheal_tryinodelk 3fb88af1-fe9b-421a-a197-3bf2fc88768b
[client.c:1672:client_inodelk]
0-XXXmanu: INODELK patchy-replicate-0:self-heal patchy-client-0 F_WRLCK
[client.c:1672:client_inodelk]
0-XXXmanu: INODELK patchy-replicate-0:self-heal patchy-client-1 F_WRLCK
[afr-self-heal-metadata.c:328:afr_selfheal_metadata]
0-XXXmanu: afr_selfheal_tryinodelk 3fb88af1-fe9b-421a-a197-3bf2fc88768b
[client.c:1672:client_inodelk]
0-XXXmanu: INODELK patchy-replicate-0:self-heal patchy-client-0 F_WRLCK
[client.c:1672:client_inodelk]
0-XXXmanu: INODELK patchy-replicate-0:self-heal patchy-client-1 F_WRLCK
--
Emmanuel Dreyfus
manu@xxxxxxxxxx
_______________________________________________
Gluster-devel mailing list
Gluster-devel@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-devel
