block: BARRIER request should imply SYNC

A barrier request should by defintion have priority in get_request
and let the queue be unplugged immediately as it's blocking all forward
progress due to the queue draining.

Most filesystems already get this implicitly by the way how submit_bh
treats the buffer_ordered flag, and gfs2 sets it explicitly.  But btrfs
and XFS are still forgetting to set the flag, as is blkdev_issue_flush
and some places in DM/MD.

For XFS on metadata heavy workloads this gives a consistent speedup
in the 2-3% range.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6a857e24f9477f7fe8fbdb710220d8d05964a95e..efc3539ac5a1f2870779522227d40a23c07a0b20 100644 (file)
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -595,7 +595,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
        if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
                goto skip_barrier;
        get_bh(bh);
-       submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh);
+       submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
        wait_on_buffer(bh);
        if (buffer_eopnotsupp(bh)) {
                clear_buffer_eopnotsupp(bh);

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 68ca1b0491af42051bb6e93f424b3741c1ed7278..5988788314978c426623ed9611516e8fe43901a0 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -136,7 +136,7 @@ struct inodes_stat_t {
  * SWRITE_SYNC
  * SWRITE_SYNC_PLUG    Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
  *                     See SWRITE.
- * WRITE_BARRIER       Like WRITE, but tells the block layer that all
+ * WRITE_BARRIER       Like WRITE_SYNC, but tells the block layer that all
  *                     previously submitted writes must be safely on storage
  *                     before this one is started. Also guarantees that when
  *                     this write is complete, it itself is also safely on
@@ -159,7 +159,7 @@ struct inodes_stat_t {
 #define SWRITE_SYNC_PLUG       \
                        (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
 #define SWRITE_SYNC    (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
-#define WRITE_BARRIER  (WRITE | (1 << BIO_RW_BARRIER))
+#define WRITE_BARRIER  (WRITE_SYNC | (1 << BIO_RW_BARRIER))
 
 /*
  * These aren't really reads or writes, they pass down information about