From de1482974080ec9ef414bf048b2646b246b63f6e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 14 Oct 2017 17:22:29 +0800 Subject: blk-mq: introduce .get_budget and .put_budget in blk_mq_ops For SCSI devices, there is often a per-request-queue depth, which needs to be respected before queuing one request. Currently blk-mq always dequeues the request first, then calls .queue_rq() to dispatch the request to lld. One obvious issue with this approach is that I/O merging may not be successful, because when the per-request-queue depth can't be respected, .queue_rq() has to return BLK_STS_RESOURCE, and then this request has to stay in hctx->dispatch list. This means it never gets a chance to be merged with other IO. This patch introduces .get_budget and .put_budget callback in blk_mq_ops, then we can try to get reserved budget first before dequeuing request. If the budget for queueing I/O can't be satisfied, we don't need to dequeue request at all. Hence the request can be left in the IO scheduler queue, for more merging opportunities. Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux/blk-mq.h') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 50c6485cb04f..901457df3d64 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -90,6 +90,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef blk_status_t (get_budget_fn)(struct blk_mq_hw_ctx *); +typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -111,6 +113,15 @@ struct blk_mq_ops { */ queue_rq_fn *queue_rq; + /* + * Reserve budget before queue request, once .queue_rq is + * run, it is driver's responsibility to release the + * reserved budget. Also we have to handle failure case + * of .get_budget for avoiding I/O deadlock. + */ + get_budget_fn *get_budget; + put_budget_fn *put_budget; + /* * Called on request timeout */ -- cgit