From 349302da83529539040d2516de1deec1e09f491c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 9 Oct 2021 13:10:39 -0600 Subject: [PATCH] block: improve batched tag allocation Add a blk_mq_get_tags() helper, which uses the new sbitmap API for allocating a batch of tags all at once. This both simplifies the block code for batched allocation, and it is also more efficient than just doing repeated calls into __sbitmap_queue_get(). This reduces the sbitmap overhead in peak runs from ~3% to ~1% and yields a performanc increase from 6.6M IOPS to 6.8M IOPS for a single CPU core. Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 15 ++++++++++ block/blk-mq-tag.h | 2 ++ block/blk-mq.c | 87 +++++++++++++++++++++++++++++++++++------------------- 3 files changed, 73 insertions(+), 31 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 72a2724..c43b972 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -86,6 +86,21 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, return __sbitmap_queue_get(bt); } +unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, + unsigned int *offset) +{ + struct blk_mq_tags *tags = blk_mq_tags_from_data(data); + struct sbitmap_queue *bt = &tags->bitmap_tags; + unsigned long ret; + + if (data->shallow_depth ||data->flags & BLK_MQ_REQ_RESERVED || + data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + return 0; + ret = __sbitmap_queue_get_batch(bt, nr_tags, offset); + *offset += tags->nr_reserved_tags; + return ret; +} + unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index d8ce89f..71c2f7d 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -38,6 +38,8 @@ extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, int node, int alloc_policy); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); +unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, + unsigned int *offset); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, diff --git a/block/blk-mq.c b/block/blk-mq.c index 568773d..97b9118 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -354,6 +354,38 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, return rq; } +static inline struct request * +__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data, + u64 alloc_time_ns) +{ + unsigned int tag, tag_offset; + struct request *rq; + unsigned long tags; + int i, nr = 0; + + tags = blk_mq_get_tags(data, data->nr_tags, &tag_offset); + if (unlikely(!tags)) + return NULL; + + for (i = 0; tags; i++) { + if (!(tags & (1UL << i))) + continue; + tag = tag_offset + i; + tags &= ~(1UL << i); + rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns); + rq->rq_next = *data->cached_rq; + *data->cached_rq = rq; + } + data->nr_tags -= nr; + + if (!data->cached_rq) + return NULL; + + rq = *data->cached_rq; + *data->cached_rq = rq->rq_next; + return rq; +} + static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) { struct request_queue *q = data->q; @@ -389,42 +421,35 @@ retry: blk_mq_tag_busy(data->hctx); /* + * Try batched alloc if we want more than 1 tag. + */ + if (data->nr_tags > 1) { + rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns); + if (rq) + return rq; + data->nr_tags = 1; + } + + /* * Waiting allocations only fail because of an inactive hctx. In that * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ - do { - tag = blk_mq_get_tag(data); - if (tag == BLK_MQ_NO_TAG) { - if (data->flags & BLK_MQ_REQ_NOWAIT) - break; - /* - * Give up the CPU and sleep for a random short time to - * ensure that thread using a realtime scheduling class - * are migrated off the CPU, and thus off the hctx that - * is going away. - */ - msleep(3); - goto retry; - } - - rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns); - if (!--data->nr_tags || e || - (data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) - return rq; - - /* link into the cached list */ - rq->rq_next = *data->cached_rq; - *data->cached_rq = rq; - data->flags |= BLK_MQ_REQ_NOWAIT; - } while (1); - - if (!data->cached_rq) - return NULL; + tag = blk_mq_get_tag(data); + if (tag == BLK_MQ_NO_TAG) { + if (data->flags & BLK_MQ_REQ_NOWAIT) + return NULL; + /* + * Give up the CPU and sleep for a random short time to + * ensure that thread using a realtime scheduling class + * are migrated off the CPU, and thus off the hctx that + * is going away. + */ + msleep(3); + goto retry; + } - rq = *data->cached_rq; - *data->cached_rq = rq->rq_next; - return rq; + return blk_mq_rq_ctx_init(data, tag, alloc_time_ns); } struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, -- 2.7.4