Btrfs: don't auto defrag a file when doing directIO

If we runt the direct IO, we should not run auto defrag, because it may
introduce buffered IO vs direcIO problem, and make direct IO slow down.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

1 files changed, 0 insertions, 3 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 657f16d9c78b..bf609581c5d0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5692,9 +5692,6 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
         if (IS_ERR(trans))
                 return ERR_CAST(trans);
 
-        if (start <= BTRFS_I(inode)->disk_i_size && len < 64 * 1024)
-                btrfs_add_inode_defrag(trans, inode);
-
         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         alloc_hint = get_extent_allocation_hint(inode, start, len);