cfq-iosched: fix sequential write regression

We have a 10-15% performance regression for sequential writes on TCQ/NCQ
enabled drives in 2.6.21-rcX after the CFQ update went in.  It has been
reported by Valerie Clement <valerie.clement@bull.net> and the Intel
testing folks.  The regression is because of CFQ's now more aggressive
queue control, limiting the depth available to the device.

This patches fixes that regression by allowing a greater depth when only
one queue is busy.  It has been tested to not impact sync-vs-async
workloads too much - we still do a lot better than 2.6.20.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

block/cfq-iosched.c

@@ -986,9 +986,9 @@ __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	 * expire an async queue immediately if it has used up its slice. idle
 	 * queue always expire after 1 dispatch round.
 	 */
-	if ((!cfq_cfqq_sync(cfqq) &&
+	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
 	    cfqd->dispatch_slice >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
-	    cfq_class_idle(cfqq)) {
+	    cfq_class_idle(cfqq))) {
 		cfqq->slice_end = jiffies + 1;
 		cfq_slice_expired(cfqd, 0, 0);
 	}
@@ -1051,6 +1051,7 @@ cfq_dispatch_requests(request_queue_t *q, int force)
 	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
 		int max_dispatch;
 
+		if (cfqd->busy_queues > 1) {
 			/*
 			 * Don't repeat dispatch from the previous queue.
 			 */
@@ -1064,6 +1065,7 @@ cfq_dispatch_requests(request_queue_t *q, int force)
 			 */
 			if (cfqd->rq_in_driver && cfq_cfqq_idle_window(cfqq))
 				break;
+		}
 
 		cfq_clear_cfqq_must_dispatch(cfqq);
 		cfq_clear_cfqq_wait_request(cfqq);
@@ -1370,7 +1372,9 @@ cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk,
 		atomic_set(&cfqq->ref, 0);
 		cfqq->cfqd = cfqd;
 
+		if (key != CFQ_KEY_ASYNC)
 			cfq_mark_cfqq_idle_window(cfqq);
+
 		cfq_mark_cfqq_prio_changed(cfqq);
 		cfq_mark_cfqq_queue_new(cfqq);
 		cfq_init_prio_data(cfqq);