]> git-server-git.apps.pok.os.sepia.ceph.com Git - ceph.git/commit
librbd: enforce write ordering with snapshot
authorJason Dillaman <dillaman@redhat.com>
Sat, 14 Feb 2015 06:24:44 +0000 (01:24 -0500)
committerJosh Durgin <jdurgin@redhat.com>
Mon, 16 Feb 2015 22:27:25 +0000 (14:27 -0800)
commitb220b2a5a6eb79f560a24801e44910394223a5b5
tree09d90c1c12500808f43cfeed8a3105384cff6525
parent0de6b6179abe5ec57e5336bba4638585f26dd22e
librbd: enforce write ordering with snapshot

The md_lock is now held for reading when scheduling write/discards.
Since snap_create now holds the lock for writing and flushes all
pending IO, write/discard operations will now be consistent for a
given request across objects.

Signed-off-by: Jason Dillaman <dillaman@redhat.com>
src/librbd/AioRequest.cc
src/librbd/AioRequest.h
src/librbd/internal.cc