On Mon, Jun 22, 2020 at 08:24:39AM +0200, Hannes Reinecke wrote:

quoted

On 6/17/20 1:26 PM, Kashyap Desai wrote:

quoted

quoted

->queued is increased only and not decreased just for debug
->purpose so far, so
it can't be relied for this purpose.

Thanks. I overlooked that that it is only incremental counter.

quoted

One approach is to add one similar counter, and maintain it by

scheduler's

quoted

insert/dispatch callback.

I tried below  and I see performance is on expected range.

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index

fdcc2c1..ea201d0 100644

--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c

@@ -485,6 +485,7 @@ void blk_mq_sched_insert_request(struct request

*rq, bool at_head,

                 list_add(&rq->queuelist, &list);
                 e->type->ops.insert_requests(hctx, &list, at_head);
+               atomic_inc(&hctx->elevator_queued);
         } else {
                 spin_lock(&ctx->lock);
                 __blk_mq_insert_request(hctx, rq, at_head); @@
-511,8 +512,10 @@ void blk_mq_sched_insert_requests(struct
blk_mq_hw_ctx *hctx,
         percpu_ref_get(&q->q_usage_counter);

         e = hctx->queue->elevator;
-       if (e && e->type->ops.insert_requests)
+       if (e && e->type->ops.insert_requests) {
                 e->type->ops.insert_requests(hctx, list, false);
+               atomic_inc(&hctx->elevator_queued);
+       }
         else {
                 /*
                  * try to issue requests directly if the hw queue
isn't diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index
126021f..946b47a 100644

--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h

@@ -74,6 +74,13 @@ static inline bool blk_mq_sched_has_work(struct

blk_mq_hw_ctx *hctx)
  {
         struct elevator_queue *e = hctx->queue->elevator;

+       /* If current hctx has not queued any request, there is no
+ need to
run.
+        * blk_mq_run_hw_queue() on hctx which has queued IO will

handle

quoted

quoted

+        * running specific hctx.
+        */
+       if (!atomic_read(&hctx->elevator_queued))
+               return false;
+
         if (e && e->type->ops.has_work)
                 return e->type->ops.has_work(hctx);

diff --git a/block/blk-mq.c b/block/blk-mq.c index f73a2f9..48f1824

100644

--- a/block/blk-mq.c
+++ b/block/blk-mq.c

@@ -517,8 +517,10 @@ void blk_mq_free_request(struct request *rq)
         struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

         if (rq->rq_flags & RQF_ELVPRIV) {
-               if (e && e->type->ops.finish_request)
+               if (e && e->type->ops.finish_request) {
                         e->type->ops.finish_request(rq);
+                       atomic_dec(&hctx->elevator_queued);
+               }
                 if (rq->elv.icq) {
                         put_io_context(rq->elv.icq->ioc);
                         rq->elv.icq = NULL; @@ -2571,6 +2573,7 @@

blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set
*set,
                 goto free_hctx;

         atomic_set(&hctx->nr_active, 0);
+       atomic_set(&hctx->elevator_queued, 0);
         if (node == NUMA_NO_NODE)
                 node = set->numa_node;
         hctx->numa_node = node;

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index

66711c7..ea1ddb1 100644

--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h

@@ -139,6 +139,10 @@ struct blk_mq_hw_ctx {
          * shared across request queues.
          */
         atomic_t                nr_active;
+       /**
+        * @elevator_queued: Number of queued requests on hctx.
+        */
+       atomic_t                elevator_queued;

         /** @cpuhp_online: List to store request if CPU is going to

die */

quoted

quoted

         struct hlist_node       cpuhp_online;

Would it make sense to move it into the elevator itself?

I am not sure where exactly I should add this counter since I need counter
per hctx. Elevator data is per request object.
Please suggest.

That is my initial suggestion, and the counter is just done for bfq &

mq-

deadline, then we needn't to pay the cost for others.

I have updated patch -

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a1123d4..3e0005c 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c

@@ -4640,6 +4640,12 @@ static bool bfq_has_work(struct blk_mq_hw_ctx

*hctx)
 {
        struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;

+       /* If current hctx has not queued any request, there is no need to
run.
+        * blk_mq_run_hw_queue() on hctx which has queued IO will handle
+        * running specific hctx.
+        */
+       if (!atomic_read(&hctx->elevator_queued))
+               return false;
        /*
         * Avoiding lock: a race on bfqd->busy_queues should cause at
         * most a call to dispatch for nothing

@@ -5554,6 +5561,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx

*hctx,
                rq = list_first_entry(list, struct request, queuelist);
                list_del_init(&rq->queuelist);
                bfq_insert_request(hctx, rq, at_head);
+              atomic_inc(&hctx->elevator_queued);
        }
 }

@@ -5925,6 +5933,7 @@ static void bfq_finish_requeue_request(struct

request *rq)

        if (likely(rq->rq_flags & RQF_STARTED)) {
                unsigned long flags;
+              struct blk_mq_hw_ctx *mq_hctx = rq->mq_hctx;

                spin_lock_irqsave(&bfqd->lock, flags);

@@ -5934,6 +5943,7 @@ static void bfq_finish_requeue_request(struct

request *rq)
                bfq_completed_request(bfqq, bfqd);
                bfq_finish_requeue_request_body(bfqq);

+              atomic_dec(&hctx->elevator_queued);
                spin_unlock_irqrestore(&bfqd->lock, flags);
        } else {
                /*

diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 126021f..946b47a 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h

@@ -74,6 +74,13 @@ static inline bool blk_mq_sched_has_work(struct

blk_mq_hw_ctx *hctx)
 {
        struct elevator_queue *e = hctx->queue->elevator;

+       /* If current hctx has not queued any request, there is no need to
run.
+        * blk_mq_run_hw_queue() on hctx which has queued IO will handle
+        * running specific hctx.
+        */
+       if (!atomic_read(&hctx->elevator_queued))
+               return false;
+
        if (e && e->type->ops.has_work)
                return e->type->ops.has_work(hctx);

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f73a2f9..82dd152 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c

@@ -2571,6 +2571,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct

blk_mq_tag_set *set,
                goto free_hctx;

        atomic_set(&hctx->nr_active, 0);
+      atomic_set(&hctx->elevator_queued, 0);
        if (node == NUMA_NO_NODE)
                node = set->numa_node;
        hctx->numa_node = node;

diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index b57470e..703ac55 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c

@@ -533,6 +533,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx

*hctx,
                rq = list_first_entry(list, struct request, queuelist);
                list_del_init(&rq->queuelist);
                dd_insert_request(hctx, rq, at_head);
+              atomic_inc(&hctx->elevator_queued);
        }
        spin_unlock(&dd->lock);
 }

@@ -562,6 +563,7 @@ static void dd_prepare_request(struct request *rq)
 static void dd_finish_request(struct request *rq)
 {
        struct request_queue *q = rq->q;
+      struct blk_mq_hw_ctx *hctx = rq->mq_hctx;

        if (blk_queue_is_zoned(q)) {
                struct deadline_data *dd = q->elevator->elevator_data;

@@ -570,15 +572,23 @@ static void dd_finish_request(struct request *rq)
                spin_lock_irqsave(&dd->zone_lock, flags);
                blk_req_zone_write_unlock(rq);
                if (!list_empty(&dd->fifo_list[WRITE]))
-                       blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
+                       blk_mq_sched_mark_restart_hctx(hctx);
                spin_unlock_irqrestore(&dd->zone_lock, flags);
        }
+       atomic_dec(&hctx->elevator_queued);
 }

 static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
        struct deadline_data *dd = hctx->queue->elevator->elevator_data;

+       /* If current hctx has not queued any request, there is no need to

run.
+        * blk_mq_run_hw_queue() on hctx which has queued IO will handle
+        * running specific hctx.
+        */
+       if (!atomic_read(&hctx->elevator_queued))
+               return false;
+
        return !list_empty_careful(&dd->dispatch) ||
                !list_empty_careful(&dd->fifo_list[0]) ||
                !list_empty_careful(&dd->fifo_list[1]);

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 66711c7..ea1ddb1 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h

@@ -139,6 +139,10 @@ struct blk_mq_hw_ctx {
         * shared across request queues.
         */
        atomic_t                nr_active;
+       /**
+        * @elevator_queued: Number of queued requests on hctx.
+        */
+       atomic_t                elevator_queued;

        /** @cpuhp_online: List to store request if CPU is going to die */
        struct hlist_node       cpuhp_online;

Thanks,
Ming