>
> Please drop the patch in my last email, and apply the following patch
and see
> if we can make a difference:
Ming,
I dropped early patch and applied the below patched. Now, I am getting
expected performance (3.0M IOPS).
Below patch fix the performance issue. See perf report after applying the
same -
8.52% [kernel] [k] sbitmap_any_bit_set
4.19% [kernel] [k] blk_mq_run_hw_queue
3.76% [megaraid_sas] [k] complete_cmd_fusion
3.24% [kernel] [k] scsi_queue_rq
2.53% [megaraid_sas] [k] megasas_build_ldio_fusion
2.34% [megaraid_sas] [k] megasas_build_and_issue_cmd_fusion
2.18% [kernel] [k] entry_SYSCALL_64
1.85% [kernel] [k] syscall_return_via_sysret
1.78% [kernel] [k] blk_mq_run_hw_queues
1.59% [kernel] [k] gup_pmd_range
1.49% [kernel] [k] _raw_spin_lock_irqsave
1.24% [kernel] [k] scsi_dec_host_busy
1.23% [kernel] [k] blk_mq_free_request
1.23% [kernel] [k] blk_mq_get_request
0.96% [kernel] [k] __slab_free
0.91% [kernel] [k] aio_complete
0.90% [kernel] [k] __sched_text_start
0.89% [megaraid_sas] [k] megasas_queue_command
0.85% [kernel] [k] __fget
0.84% [kernel] [k] scsi_mq_get_budget
I will do some more testing and update the results.
Kashyap
>
> diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index
> 3d6780504dcb..69d6bffcc8ff 100644
> --- a/block/blk-mq-debugfs.c
> +++ b/block/blk-mq-debugfs.c
> @@ -627,6 +627,9 @@ static int hctx_active_show(void *data, struct
seq_file
> *m) {
> struct blk_mq_hw_ctx *hctx = data;
>
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> +
> seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
> return 0;
> }
> diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index
> 309ec5079f3f..58ef83a34fda 100644
> --- a/block/blk-mq-tag.c
> +++ b/block/blk-mq-tag.c
> @@ -30,6 +30,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
> */
> bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) {
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> +
> if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
> !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
> atomic_inc(&hctx->tags->active_queues);
> @@ -55,6 +58,9 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) {
> struct blk_mq_tags *tags = hctx->tags;
>
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> +
> if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
> return;
>
> @@ -74,6 +80,10 @@ static inline bool hctx_may_queue(struct
> blk_mq_hw_ctx *hctx,
>
> if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED))
> return true;
> +
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> +
> if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
> return true;
>
> diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index
> 61deab0b5a5a..84e9b46ffc78 100644
> --- a/block/blk-mq-tag.h
> +++ b/block/blk-mq-tag.h
> @@ -36,11 +36,22 @@ extern void blk_mq_tag_wakeup_all(struct
> blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct
> request_queue *q, busy_iter_fn *fn,
> void *priv);
>
> +static inline struct blk_mq_hw_ctx *blk_mq_master_hctx(
> + struct blk_mq_hw_ctx *hctx)
> +{
> + return hctx->queue->queue_hw_ctx[0];
> +}
> +
> +
> static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue
*bt,
> struct blk_mq_hw_ctx
*hctx)
> {
> if (!hctx)
> return &bt->ws[0];
> +
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> +
> return sbq_wait_ptr(bt, &hctx->wait_index); }
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c index
> 49d73d979cb3..4196ed3b0085 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -303,7 +303,7 @@ static struct request *blk_mq_rq_ctx_init(struct
> blk_mq_alloc_data *data,
> } else {
> if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
> rq_flags = RQF_MQ_INFLIGHT;
> - atomic_inc(&data->hctx->nr_active);
> + blk_mq_inc_nr_active(data->hctx);
> }
> rq->tag = tag;
> rq->internal_tag = -1;
> @@ -517,7 +517,7 @@ void blk_mq_free_request(struct request *rq)
>
> ctx->rq_completed[rq_is_sync(rq)]++;
> if (rq->rq_flags & RQF_MQ_INFLIGHT)
> - atomic_dec(&hctx->nr_active);
> + blk_mq_dec_nr_active(hctx);
>
> if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
> laptop_io_completion(q->backing_dev_info);
> @@ -1064,7 +1064,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
> if (rq->tag >= 0) {
> if (shared) {
> rq->rq_flags |= RQF_MQ_INFLIGHT;
> - atomic_inc(&data.hctx->nr_active);
> + blk_mq_inc_nr_active(data.hctx);
> }
> data.hctx->tags->rqs[rq->tag] = rq;
> }
> diff --git a/block/blk-mq.h b/block/blk-mq.h index
> 633a5a77ee8b..f1279b8c2289 100644
> --- a/block/blk-mq.h
> +++ b/block/blk-mq.h
> @@ -193,6 +193,20 @@ unsigned int blk_mq_in_flight(struct request_queue
> *q, struct hd_struct *part); void blk_mq_in_flight_rw(struct
request_queue
> *q, struct hd_struct *part,
> unsigned int inflight[2]);
>
> +static inline void blk_mq_inc_nr_active(struct blk_mq_hw_ctx *hctx) {
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> + atomic_inc(&hctx->nr_active);
> +}
> +
> +static inline void blk_mq_dec_nr_active(struct blk_mq_hw_ctx *hctx) {
> + if (hctx->flags & BLK_MQ_F_HOST_TAGS)
> + hctx = blk_mq_master_hctx(hctx);
> + atomic_dec(&hctx->nr_active);
> +}
> +
> static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx
*hctx)
> {
> struct request_queue *q = hctx->queue; @@ -218,7 +232,7 @@ static
> inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
>
> if (rq->rq_flags & RQF_MQ_INFLIGHT) {
> rq->rq_flags &= ~RQF_MQ_INFLIGHT;
> - atomic_dec(&hctx->nr_active);
> + blk_mq_dec_nr_active(hctx);
> }
> }
>
> Thanks,
> Ming
