block: hold queue if flush is running for non-queueable flush drive

commit 3ac0cc4508709d42ec9aa351086c7d38bfc0660c upstream.

In some drives, flush requests are non-queueable. When flush request is
running, normal read/write requests can't run. If block layer dispatches
such request, driver can't handle it and requeue it.  Tejun suggested we
can hold the queue when flush is running. This can avoid unnecessary
requeue.  Also this can improve performance. For example, we have
request flush1, write1, flush 2. flush1 is dispatched, then queue is
hold, write1 isn't inserted to queue. After flush1 is finished, flush2
will be dispatched. Since disk cache is already clean, flush2 will be
finished very soon, so looks like flush2 is folded to flush1.

In my test, the queue holding completely solves a regression introduced by
commit 53d63e6b0dfb95882ec0219ba6bbd50cde423794:

    block: make the flush insertion use the tail of the dispatch list

    It's not a preempt type request, in fact we have to insert it
    behind requests that do specify INSERT_FRONT.

which causes about 20% regression running a sysbench fileio
workload.

Stable: 2.6.39 only

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/block/blk-flush.c b/block/blk-flush.c
index 6c9b5e189e624888860e5185d1d9b3479b3e49a4..bb21e4c36f70ca437162356edd87d2ce3a265a46 100644 (file)
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -212,13 +212,19 @@ static void flush_end_io(struct request *flush_rq, int error)
        }
 
        /*
-        * Moving a request silently to empty queue_head may stall the
-        * queue.  Kick the queue in those cases.  This function is called
-        * from request completion path and calling directly into
-        * request_fn may confuse the driver.  Always use kblockd.
+        * Kick the queue to avoid stall for two cases:
+        * 1. Moving a request silently to empty queue_head may stall the
+        * queue.
+        * 2. When flush request is running in non-queueable queue, the
+        * queue is hold. Restart the queue after flush request is finished
+        * to avoid stall.
+        * This function is called from request completion path and calling
+        * directly into request_fn may confuse the driver.  Always use
+        * kblockd.
         */
-       if (queued)
+       if (queued || q->flush_queue_delayed)
                blk_run_queue_async(q);
+       q->flush_queue_delayed = 0;
 }
 
 /**

diff --git a/block/blk.h b/block/blk.h
index 61263463e38e17be7c7f742f0bbe9233eec2ecd2..1f798b5a6f194b6429e33899b441fec4c83da31e 100644 (file)
--- a/block/blk.h
+++ b/block/blk.h
@@ -61,7 +61,26 @@ static inline struct request *__elv_next_request(struct request_queue *q)
                        rq = list_entry_rq(q->queue_head.next);
                        return rq;
                }
-
+               /*
+                * Flush request is running and flush request isn't queueable
+                * in the drive, we can hold the queue till flush request is
+                * finished. Even we don't do this, driver can't dispatch next
+                * requests and will requeue them. And this can improve
+                * throughput too. For example, we have request flush1, write1,
+                * flush 2. flush1 is dispatched, then queue is hold, write1
+                * isn't inserted to queue. After flush1 is finished, flush2
+                * will be dispatched. Since disk cache is already clean,
+                * flush2 will be finished very soon, so looks like flush2 is
+                * folded to flush1.
+                * Since the queue is hold, a flag is set to indicate the queue
+                * should be restarted later. Please see flush_end_io() for
+                * details.
+                */
+               if (q->flush_pending_idx != q->flush_running_idx &&
+                               !queue_flush_queueable(q)) {
+                       q->flush_queue_delayed = 1;
+                       return NULL;
+               }
                if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
                        return NULL;
        }

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 96f605cf8ef45599450747c498cf0ecdf6413d01..75851eb18ff7fc11affcf3431b9655e20ceef09d 100644 (file)
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -365,6 +365,7 @@ struct request_queue
         */
        unsigned int            flush_flags;
        unsigned int            flush_not_queueable:1;
+       unsigned int            flush_queue_delayed:1;
        unsigned int            flush_pending_idx:1;
        unsigned int            flush_running_idx:1;
        unsigned long           flush_pending_since;