[dm-devel] [PATCH V5 2/8] blk-mq-sched: use q->queue_depth as hint for q->nr_requests

[Ming Lei]

SCSI sets q->queue_depth from shost->cmd_per_lun, and
q->queue_depth is per request_queue and more related to
scheduler queue compared with hw queue depth, which can be
shared by queues, such as TAG_SHARED.

This patch tries to use q->queue_depth as hint for computing
q->nr_requests, which should be more effective than
current way.

Reviewed-by: Bart Van Assche <bart.vanassche at wdc.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Tested-by: Oleksandr Natalenko <oleksandr at natalenko.name>
Tested-by: Tom Nguyen <tom81094 at gmail.com>
Tested-by: Paolo Valente <paolo.valente at linaro.org>
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 block/blk-mq-sched.h | 18 +++++++++++++++---
 block/blk-mq.c       | 27 +++++++++++++++++++++++++--
 block/blk-mq.h       |  1 +
 block/blk-settings.c |  2 ++
 4 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 1d47f3fda1d0..906b10c54f78 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -99,12 +99,24 @@ static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
 static inline unsigned blk_mq_sched_queue_depth(struct request_queue *q)
 {
 	/*
-	 * Default to double of smaller one between hw queue_depth and 128,
+	 * q->queue_depth is more close to scheduler queue, so use it
+	 * as hint for computing scheduler queue depth if it is valid
+	 */
+	unsigned q_depth = q->queue_depth ?: q->tag_set->queue_depth;
+
+	/*
+	 * Default to double of smaller one between queue depth and 128,
 	 * since we don't split into sync/async like the old code did.
 	 * Additionally, this is a per-hw queue depth.
 	 */
-	return 2 * min_t(unsigned int, q->tag_set->queue_depth,
-				   BLKDEV_MAX_RQ);
+	q_depth = 2 * min_t(unsigned int, q_depth, BLKDEV_MAX_RQ);
+
+	/*
+	 * when queue depth of driver is too small, we set queue depth
+	 * of scheduler queue as 128 which is the default setting of
+	 * block legacy code.
+	 */
+	return max_t(unsigned, q_depth, BLKDEV_MAX_RQ);
 }
 
 #endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7cb3f87334c0..561a663cdd0e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2694,7 +2694,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 }
 EXPORT_SYMBOL(blk_mq_free_tag_set);
 
-int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
+static int __blk_mq_update_nr_requests(struct request_queue *q,
+				       bool sched_only,
+				       unsigned int nr)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
@@ -2713,7 +2715,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		 * If we're using an MQ scheduler, just update the scheduler
 		 * queue depth. This is similar to what the old code would do.
 		 */
-		if (!hctx->sched_tags) {
+		if (!sched_only && !hctx->sched_tags) {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->tags,
 							min(nr, set->queue_depth),
 							false);
@@ -2733,6 +2735,27 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return ret;
 }
 
+int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
+{
+	return __blk_mq_update_nr_requests(q, false, nr);
+}
+
+/*
+ * When drivers update q->queue_depth, this API is called so that
+ * we can use this queue depth as hint for adjusting scheduler
+ * queue depth.
+ */
+int blk_mq_update_sched_queue_depth(struct request_queue *q)
+{
+	unsigned nr;
+
+	if (!q->mq_ops || !q->elevator)
+		return 0;
+
+	nr = blk_mq_sched_queue_depth(q);
+	return __blk_mq_update_nr_requests(q, true, nr);
+}
+
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 							int nr_hw_queues)
 {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 915de58572e7..5bca6ce1f01d 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -37,6 +37,7 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 				bool wait);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
+int blk_mq_update_sched_queue_depth(struct request_queue *q);
 
 /*
  * Internal helpers for allocating/freeing the request map
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 8559e9563c52..c2db38d2ec2b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -878,6 +878,8 @@ void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
 	wbt_set_queue_depth(q->rq_wb, depth);
+
+	WARN_ON(blk_mq_update_sched_queue_depth(q));
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
-- 
2.9.5