+static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_shared_sbitmap_attrs[] = { + {"state", 0400, hctx_state_show}, + {"flags", 0400, hctx_flags_show}, + {"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops}, + {"busy", 0400, hctx_busy_show}, + {"ctx_map", 0400, hctx_ctx_map_show}, + {"sched_tags", 0400, hctx_sched_tags_show}, + {"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show}, + {"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write}, + {"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write}, + {"queued", 0600, hctx_queued_show, hctx_queued_write}, + {"run", 0600, hctx_run_show, hctx_run_write}, + {"active", 0400, hctx_active_show}, + {"dispatch_busy", 0400, hctx_dispatch_busy_show}, + {} +};You may use macro or whatever to avoid so the duplication.
Let me check alternatives.
+ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { {"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops}, {"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops}, @@ -878,13 +895,17 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { struct blk_mq_ctx *ctx; + struct blk_mq_tag_set *set = q->tag_set; char name[20]; int i;snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);- debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs);+ if (blk_mq_is_sbitmap_shared(set)) + debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_shared_sbitmap_attrs); + else + debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs);hctx_for_each_ctx(hctx, ctx, i)blk_mq_debugfs_register_ctx(hctx, ctx); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 92843e3e1a2a..7db16e49f6f6 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -60,9 +60,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. */ -static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, +static inline bool hctx_may_queue(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { + struct blk_mq_hw_ctx *hctx = data->hctx; + struct request_queue *q = data->q; unsigned int depth, users;if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))@@ -84,15 +86,15 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); - return atomic_read(&hctx->nr_active) < depth; + return __blk_mq_active_requests(hctx, q) < depth;There is big change on 'users' too: users = atomic_read(&hctx->tags->active_queues); Originally there is single hctx->tags for these HBAs, now there are many hctx->tags, so 'users' may become much smaller than before.
Can you please check how I handled that in the next patch? There we record the number of active request queues per set.
(I will note that I could have combined some of these patches, but I liked the piecemeal appraoch, and none of these paths are enabled until later).
Maybe '->active_queues' can be moved to tag_set for blk_mq_is_sbitmap_shared().}static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,struct sbitmap_queue *bt) { if (!(data->flags & BLK_MQ_REQ_INTERNAL) && - !hctx_may_queue(data->hctx, bt)) - return BLK_MQ_NO_TAG; + !hctx_may_queue(data, bt)) + return -1;BLK_MQ_NO_TAG should have been returned.
OK, I missed that in the rebase.
if (data->shallow_depth) return __sbitmap_queue_get_shallow(bt, data->shallow_depth); else diff --git a/block/blk-mq.c b/block/blk-mq.c index 77120dd4e4d5..0f7e062a1665 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -283,7 +283,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, } else { if (data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) { rq_flags = RQF_MQ_INFLIGHT; - atomic_inc(&data->hctx->nr_active); + __blk_mq_inc_active_requests(data->hctx, data->q); } rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; @@ -527,7 +527,7 @@ 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_active_requests(hctx, q);if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))laptop_io_completion(q->backing_dev_info); @@ -1073,7 +1073,7 @@ 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_active_requests(rq->mq_hctx, rq->q); } data.hctx->tags->rqs[rq->tag] = rq; } diff --git a/block/blk-mq.h b/block/blk-mq.h index 1a283c707215..9c1e612c2298 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -202,6 +202,32 @@ static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx) return true; }+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx,+ struct request_queue *q) +{ + if (blk_mq_is_sbitmap_shared(q->tag_set)) + atomic_inc(&q->nr_active_requests_shared_sbitmap); + else + atomic_inc(&hctx->nr_active); +} + +static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx, + struct request_queue *q) +{ + if (blk_mq_is_sbitmap_shared(q->tag_set)) + atomic_dec(&q->nr_active_requests_shared_sbitmap); + else + atomic_dec(&hctx->nr_active); +} + +static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx, + struct request_queue *q) +{ + if (blk_mq_is_sbitmap_shared(q->tag_set))I'd suggest to add one hctx version of blk_mq_is_sbitmap_shared() since q->tag_set is seldom used in fast path, and hctx->flags is more efficient than tag_set->flags.
OK Thanks, John
