blk-mq: issue directly if hw queue isn't busy in case of 'none'

In case of 'none' io scheduler, when hw queue isn't busy, it isn't
necessary to enqueue request to sw queue and dequeue it from
sw queue because request may be submitted to hw queue asap without
extra cost, meantime there shouldn't be much request in sw queue,
and we don't need to worry about effect on IO merge.

There are still some single hw queue SCSI HBAs(HPSA, megaraid_sas, ...)
which may connect high performance devices, so 'none' is often required
for obtaining good performance.

This patch improves IOPS and decreases CPU unilization on megaraid_sas,
per Kashyap's test.

Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index fdc129e64cc4e8a133216eea3ee303e34bb4a939..cf9c66c6d35a866c63a8a1785eeab769ec3298d4 100644 (file)
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -405,8 +405,19 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 
        if (e && e->type->ops.mq.insert_requests)
                e->type->ops.mq.insert_requests(hctx, list, false);
-       else
+       else {
+               /*
+                * try to issue requests directly if the hw queue isn't
+                * busy in case of 'none' scheduler, and this way may save
+                * us one extra enqueue & dequeue to sw queue.
+                */
+               if (!hctx->dispatch_busy && !e && !run_queue_async) {
+                       blk_mq_try_issue_list_directly(hctx, list);
+                       if (list_empty(list))
+                               return;
+               }
                blk_mq_insert_requests(hctx, ctx, list);
+       }
 
        blk_mq_run_hw_queue(hctx, run_queue_async);
 }

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 73a43b81b17dcc3e4511b3f9465470e5931b5dfc..21f3eda98431372fb1728e37c2917831e224b180 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1691,13 +1691,16 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
        ret = q->mq_ops->queue_rq(hctx, &bd);
        switch (ret) {
        case BLK_STS_OK:
+               blk_mq_update_dispatch_busy(hctx, false);
                *cookie = new_cookie;
                break;
        case BLK_STS_RESOURCE:
        case BLK_STS_DEV_RESOURCE:
+               blk_mq_update_dispatch_busy(hctx, true);
                __blk_mq_requeue_request(rq);
                break;
        default:
+               blk_mq_update_dispatch_busy(hctx, false);
                *cookie = BLK_QC_T_NONE;
                break;
        }
@@ -1780,6 +1783,23 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq)
        return ret;
 }
 
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+               struct list_head *list)
+{
+       while (!list_empty(list)) {
+               blk_status_t ret;
+               struct request *rq = list_first_entry(list, struct request,
+                               queuelist);
+
+               list_del_init(&rq->queuelist);
+               ret = blk_mq_request_issue_directly(rq);
+               if (ret != BLK_STS_OK) {
+                       list_add(&rq->queuelist, list);
+                       break;
+               }
+       }
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
        const int is_sync = op_is_sync(bio->bi_opf);
@@ -1880,7 +1900,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
                        blk_mq_try_issue_directly(data.hctx, same_queue_rq,
                                        &cookie);
                }
-       } else if (q->nr_hw_queues > 1 && is_sync) {
+       } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
+                       !data.hctx->dispatch_busy)) {
                blk_mq_put_ctx(data.ctx);
                blk_mq_bio_to_request(rq, bio);
                blk_mq_try_issue_directly(data.hctx, rq, &cookie);

diff --git a/block/blk-mq.h b/block/blk-mq.h
index bc2b24735ed413454693aa39a72f0cfc92704b6e..9497b47e2526c62006f00101cc7acffd35e7e299 100644 (file)
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -64,6 +64,8 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 
 /* Used by blk_insert_cloned_request() to issue request directly */
 blk_status_t blk_mq_request_issue_directly(struct request *rq);
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+                                   struct list_head *list);
 
 /*
  * CPU -> queue mappings