block: optimize generic_unplug_device()

Original patch from Mikulas Patocka <mpatocka@redhat.com>

Mike Anderson was doing an OLTP benchmark on a computer with 48 physical
disks mapped to one logical device via device mapper.

He found that there was a slowdown on request_queue->lock in function
generic_unplug_device. The slowdown is caused by the fact that when some
code calls unplug on the device mapper, device mapper calls unplug on all
physical disks. These unplug calls take the lock, find that the queue is
already unplugged, release the lock and exit.

With the below patch, performance of the benchmark was increased by 18%
(the whole OLTP application, not just block layer microbenchmarks).

So I'm submitting this patch for upstream. I think the patch is correct,
because when more threads call simultaneously plug and unplug, it is
unspecified, if the queue is or isn't plugged (so the patch can't make
this worse). And the caller that plugged the queue should unplug it
anyway. (if it doesn't, there's 3ms timeout).

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

1 files changed, 5 insertions, 3 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index b754a4a..1b7dddf 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -253,9 +253,11 @@ EXPORT_SYMBOL(__generic_unplug_device);
  **/
 void generic_unplug_device(struct request_queue *q)
 {
-	spin_lock_irq(q->queue_lock);
-	__generic_unplug_device(q);
-	spin_unlock_irq(q->queue_lock);
+	if (blk_queue_plugged(q)) {
+		spin_lock_irq(q->queue_lock);
+		__generic_unplug_device(q);
+		spin_unlock_irq(q->queue_lock);
+	}
 }
 EXPORT_SYMBOL(generic_unplug_device);