[PATCH 04/14] blk-mq-sched: improve dispatching from sw queue

[Ming Lei <ming.lei@xxxxxxxxxx>]

SCSI devices use host-wide tagset, and the shared
driver tag space is often quite big. Meantime
there is also queue depth for each lun(.cmd_per_lun),
which is often small.

So lots of requests may stay in sw queue, and we
always flush all belonging to same hw queue and
dispatch them all to driver, unfortunately it is
easy to cause queue busy becasue of the small
per-lun queue depth. Once these requests are flushed
out, they have to stay in hctx->dispatch, and no bio
merge can participate into these requests, and
sequential IO performance is hurted.

This patch improves dispatching from sw queue when
there is per-request-queue queue depth by taking
request one by one from sw queue, just like the way
of IO scheduler.

Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
 block/blk-mq-sched.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 47a25333a136..3510c01cb17b 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -96,6 +96,9 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
 	bool can_go = true;
 	LIST_HEAD(rq_list);
+	struct request *(*dispatch_fn)(struct blk_mq_hw_ctx *) =
+		has_sched_dispatch ? e->type->ops.mq.dispatch_request :
+			blk_mq_dispatch_rq_from_ctxs;
 
 	/* RCU or SRCU read lock is needed before checking quiesced flag */
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
@@ -126,26 +129,28 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 		can_go = blk_mq_dispatch_rq_list(q, &rq_list);
-	} else if (!has_sched_dispatch) {
+	} else if (!has_sched_dispatch && !q->queue_depth) {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
 		blk_mq_dispatch_rq_list(q, &rq_list);
+		can_go = false;
 	}
 
+	if (!can_go)
+		return;
+
 	/*
 	 * We want to dispatch from the scheduler if we had no work left
 	 * on the dispatch list, OR if we did have work but weren't able
 	 * to make progress.
 	 */
-	if (can_go && has_sched_dispatch) {
-		do {
-			struct request *rq;
+	do {
+		struct request *rq;
 
-			rq = e->type->ops.mq.dispatch_request(hctx);
-			if (!rq)
-				break;
-			list_add(&rq->queuelist, &rq_list);
-		} while (blk_mq_dispatch_rq_list(q, &rq_list));
-	}
+		rq = dispatch_fn(hctx);
+		if (!rq)
+			break;
+		list_add(&rq->queuelist, &rq_list);
+	} while (blk_mq_dispatch_rq_list(q, &rq_list));
 }
 
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
-- 
2.9.4