Btrfs: make SNAP_DESTROY async

There is no reason to force an immediate commit when deleting a snapshot.
Users have some expectation that space from a deleted snapshot be freed
immediately, but even if we do commit the reclaim is a background process.

If users _do_ want the deletion to be durable, they can call 'sync'.

Signed-off-by: Sage Weil <sage@newdream.net>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit is contained in:
Sage Weil 2010-10-29 15:41:32 -04:00 committed by Chris Mason
parent 72fd032e94
commit 531cb13f1e

View File

@ -1351,7 +1351,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
BUG_ON(ret);
}
ret = btrfs_commit_transaction(trans, root);
ret = btrfs_end_transaction(trans, root);
BUG_ON(ret);
inode->i_flags |= S_DEAD;
out_up_write: