blk-mq: count allocated but not started requests in iostats inflight (6131837b) · Commits · 戴 / test

In the legacy block case, we increment the counter right after we allocate the request, not when the driver handles it. In both the legacy and blk-mq cases, part_inc_in_flight() is called from blk_account_io_start() right after we've allocated the request. blk-mq only considers requests started requests as inflight, but this is inconsistent with the legacy definition and the intention in the code. This removes the started condition and instead counts all allocated requests. Fixes: ("blk-mq: provide internal in-flight variant") Signed-off-by:

Omar Sandoval <osandov@fb.com> Signed-off-by:

Jens Axboe <axboe@kernel.dk>

block/blk-mq.c

+9 −12

Original line number	Diff line number	Diff line
		@@ -95,19 +95,16 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
		{
		struct mq_inflight *mi = priv;

		if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
		/*
		* index[0] counts the specific partition that was asked
		* for. index[1] counts the ones that are active on the
		* whole device, so increment that if mi->part is indeed
		* a partition, and not a whole device.
		* index[0] counts the specific partition that was asked for. index[1]
		* counts the ones that are active on the whole device, so increment
		* that if mi->part is indeed a partition, and not a whole device.
		*/
		if (rq->part == mi->part)
		mi->inflight[0]++;
		if (mi->part->partno)
		mi->inflight[1]++;
		}
		}

		void blk_mq_in_flight(struct request_queue q, struct hd_struct part,
		unsigned int inflight[2])

Admin message