summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorSage Weil <sage@newdream.net>2010-10-29 21:41:32 +0200
committerChris Mason <chris.mason@oracle.com>2010-10-30 03:42:10 +0200
commit531cb13f1e417c060b54f979e1659ecd69bea650 (patch)
tree6b421ac1ddf7cad271cd0c767f0c19e6c4f826df /fs
parentBtrfs: add SNAP_CREATE_ASYNC ioctl (diff)
downloadlinux-531cb13f1e417c060b54f979e1659ecd69bea650.tar.xz
linux-531cb13f1e417c060b54f979e1659ecd69bea650.zip
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>
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/ioctl.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e8a26a3aac3e..fdd88f2f1ece 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -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: