diff options
author | Krutika Dhananjay <kdhananj@redhat.com> | 2016-03-29 18:36:08 +0530 |
---|---|---|
committer | Pranith Kumar Karampuri <pkarampu@redhat.com> | 2016-04-16 22:43:47 -0700 |
commit | bd8ab0567017fd4dddfea738eae0bccc40b85527 (patch) | |
tree | 87fdd50fdb0b8aa1e34e08f9690fe11a79819f4c /xlators/cluster/afr/src/afr-inode-read.c | |
parent | 02a235b5a5fcfffd17debfbf3fceeddffe171682 (diff) |
features/shard: Make o-direct writes work with sharding
Backport of: http://review.gluster.org/#/c/13846/
With files opened with o-direct, the expectation is that
the IO performed on the fds is byte aligned wrt the sector size
of the underlying device. With files getting sharded, a single
write from the application could be broken into more than one write
falling on different shards which _might_ cause the original byte alignment
property to be lost. To get around this, shard translator will send fsync
on odirect writes to emulate o-direct-like behavior in the backend.
Change-Id: I992e10162afcca17a19d9cba3bcb187a31c618ae
BUG: 1325843
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/13966
Smoke: Gluster Build System <jenkins@build.gluster.com>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Diffstat (limited to 'xlators/cluster/afr/src/afr-inode-read.c')
0 files changed, 0 insertions, 0 deletions