xfs: Sort delayed write buffers before dispatch

Currently when the xfsbufd writes delayed write buffers, it pushes
them to disk in the order they come off the delayed write list. If
there are lots of buffers ѕpread widely over the disk, this results
in overwhelming the elevator sort queues in the block layer and we
end up losing the posibility of merging adjacent buffers to minimise
the number of IOs.

Use the new generic list_sort function to sort the delwri dispatch
queue before issue to ensure that the buffers are pushed in the most
friendly order possible to the lower layers.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 60 insertions, 27 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index b306265caa3..4556a4c31e3 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -33,6 +33,7 @@
 #include <linux/migrate.h>
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
+#include <linux/list_sort.h>
 
 #include "xfs_sb.h"
 #include "xfs_inum.h"
@@ -1877,14 +1878,42 @@ xfs_buf_delwri_split(
 
 }
 
+/*
+ * Compare function is more complex than it needs to be because
+ * the return value is only 32 bits and we are doing comparisons
+ * on 64 bit values
+ */
+static int
+xfs_buf_cmp(
+        void            *priv,
+        struct list_head *a,
+        struct list_head *b)
+{
+        struct xfs_buf  *ap = container_of(a, struct xfs_buf, b_list);
+        struct xfs_buf  *bp = container_of(b, struct xfs_buf, b_list);
+        xfs_daddr_t             diff;
+
+        diff = ap->b_bn - bp->b_bn;
+        if (diff < 0)
+                return -1;
+        if (diff > 0)
+                return 1;
+        return 0;
+}
+
+void
+xfs_buf_delwri_sort(
+        xfs_buftarg_t   *target,
+        struct list_head *list)
+{
+        list_sort(NULL, list, xfs_buf_cmp);
+}
+
 STATIC int
 xfsbufd(
         void            *data)
 {
-        struct list_head tmp;
-        xfs_buftarg_t   *target = (xfs_buftarg_t *)data;
-        int             count;
-        xfs_buf_t       *bp;
+        xfs_buftarg_t   *target = (xfs_buftarg_t *)data;
 
         current->flags |= PF_MEMALLOC;
 
@@ -1893,6 +1922,8 @@ xfsbufd(
         do {
                 long    age = xfs_buf_age_centisecs * msecs_to_jiffies(10);
                 long    tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10);
+                int     count = 0;
+                struct list_head tmp;
 
                 if (unlikely(freezing(current))) {
                         set_bit(XBT_FORCE_SLEEP, &target->bt_flags);
@@ -1907,11 +1938,10 @@ xfsbufd(
                 schedule_timeout_interruptible(tout);
 
                 xfs_buf_delwri_split(target, &tmp, age);
-                count = 0;
+                list_sort(NULL, &tmp, xfs_buf_cmp);
                 while (!list_empty(&tmp)) {
-                        bp = list_entry(tmp.next, xfs_buf_t, b_list);
-                        ASSERT(target == bp->b_target);
-
+                        struct xfs_buf *bp;
+                        bp = list_first_entry(&tmp, struct xfs_buf, b_list);
                         list_del_init(&bp->b_list);
                         xfs_buf_iostrategy(bp);
                         count++;
@@ -1937,42 +1967,45 @@ xfs_flush_buftarg(
         xfs_buftarg_t   *target,
         int             wait)
 {
-        struct list_head tmp;
-        xfs_buf_t       *bp, *n;
+        xfs_buf_t       *bp;
         int             pincount = 0;
+        LIST_HEAD(tmp_list);
+        LIST_HEAD(wait_list);
 
         xfs_buf_runall_queues(xfsconvertd_workqueue);
         xfs_buf_runall_queues(xfsdatad_workqueue);
         xfs_buf_runall_queues(xfslogd_workqueue);
 
         set_bit(XBT_FORCE_FLUSH, &target->bt_flags);
-        pincount = xfs_buf_delwri_split(target, &tmp, 0);
+        pincount = xfs_buf_delwri_split(target, &tmp_list, 0);
 
         /*
-         * Dropped the delayed write list lock, now walk the temporary list
+         * Dropped the delayed write list lock, now walk the temporary list.
+         * All I/O is issued async and then if we need to wait for completion
+         * we do that after issuing all the IO.
          */
-        list_for_each_entry_safe(bp, n, &tmp, b_list) {
+        list_sort(NULL, &tmp_list, xfs_buf_cmp);
+        while (!list_empty(&tmp_list)) {
+                bp = list_first_entry(&tmp_list, struct xfs_buf, b_list);
                 ASSERT(target == bp->b_target);
-                if (wait)
+                list_del_init(&bp->b_list);
+                if (wait) {
                         bp->b_flags &= ~XBF_ASYNC;
-                else
-                        list_del_init(&bp->b_list);
-
+                        list_add(&bp->b_list, &wait_list);
+                }
                 xfs_buf_iostrategy(bp);
         }
 
-        if (wait)
+        if (wait) {
+                /* Expedite and wait for IO to complete. */
                 blk_run_address_space(target->bt_mapping);
+                while (!list_empty(&wait_list)) {
+                        bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
 
-        /*
-         * Remaining list items must be flushed before returning
-         */
-        while (!list_empty(&tmp)) {
-                bp = list_entry(tmp.next, xfs_buf_t, b_list);
-
-                list_del_init(&bp->b_list);
-                xfs_iowait(bp);
-                xfs_buf_relse(bp);
+                        list_del_init(&bp->b_list);
+                        xfs_iowait(bp);
+                        xfs_buf_relse(bp);
+                }
         }
 
         return pincount;