block: switch sync_dirty_buffer() over to WRITE_SYNC
authorJens Axboe <jens.axboe@oracle.com>
Mon, 6 Apr 2009 12:48:08 +0000 (14:48 +0200)
committerLinus Torvalds <torvalds@linux-foundation.org>
Mon, 6 Apr 2009 15:04:54 +0000 (08:04 -0700)
We should now have the logic in place to handle this properly
without regressing on the write performance, so re-enable
the sync writes.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
fs/buffer.c

index 43afaa5d69014da26307910cc8cde01262a5aef6..6e35762b6169be2a30a69462764b71967369a1d8 100644 (file)
@@ -3010,7 +3010,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
        if (test_clear_buffer_dirty(bh)) {
                get_bh(bh);
                bh->b_end_io = end_buffer_write_sync;
-               ret = submit_bh(WRITE, bh);
+               ret = submit_bh(WRITE_SYNC, bh);
                wait_on_buffer(bh);
                if (buffer_eopnotsupp(bh)) {
                        clear_buffer_eopnotsupp(bh);