linux-kernel - [PATCH V5 6/7] blk-mq-sched: improve dispatching from sw queue

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170930102720.30219-7-ming.lei@redhat.com>
Date:   Sat, 30 Sep 2017 18:27:19 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     Jens Axboe <axboe@...com>, linux-block@...r.kernel.org,
        Christoph Hellwig <hch@...radead.org>,
        Mike Snitzer <snitzer@...hat.com>, dm-devel@...hat.com
Cc:     Bart Van Assche <bart.vanassche@...disk.com>,
        Laurence Oberman <loberman@...hat.com>,
        Paolo Valente <paolo.valente@...aro.org>,
        Oleksandr Natalenko <oleksandr@...alenko.name>,
        Tom Nguyen <tom81094@...il.com>, linux-kernel@...r.kernel.org,
        linux-scsi@...r.kernel.org, Omar Sandoval <osandov@...com>,
        Ming Lei <ming.lei@...hat.com>
Subject: [PATCH V5 6/7] blk-mq-sched: improve dispatching from sw queue

SCSI devices use host-wide tagset, and the shared
driver tag space is often quite big. Meantime
there is also queue depth for each lun(.cmd_per_lun),
which is often small.

So lots of requests may stay in sw queue, and we
always flush all belonging to same hw queue and
dispatch them all to driver, unfortunately it is
easy to cause queue busy because of the small
per-lun queue depth. Once these requests are flushed
out, they have to stay in hctx->dispatch, and no bio
merge can participate into these requests, and
sequential IO performance is hurted.

This patch improves dispatching from sw queue when
there is per-request-queue queue depth by taking
request one by one from sw queue, just like the way
of IO scheduler.

Reviewed-by: Omar Sandoval <osandov@...com>
Reviewed-by: Bart Van Assche <bart.vanassche@....com>
Tested-by: Oleksandr Natalenko <oleksandr@...alenko.name>
Tested-by: Tom Nguyen <tom81094@...il.com>
Tested-by: Paolo Valente <paolo.valente@...aro.org>
Signed-off-by: Ming Lei <ming.lei@...hat.com>
---
 block/blk-mq-sched.c   | 53 ++++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/blk-mq.h |  2 ++
 2 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 538f363f39ca..3ba112d9dc15 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -105,6 +105,42 @@ static void blk_mq_do_dispatch_sched(struct request_queue *q,
 	} while (blk_mq_dispatch_rq_list(q, &rq_list));
 }
 
+static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
+					  struct blk_mq_ctx *ctx)
+{
+	unsigned idx = ctx->index_hw;
+
+	if (++idx == hctx->nr_ctx)
+		idx = 0;
+
+	return hctx->ctxs[idx];
+}
+
+static void blk_mq_do_dispatch_ctx(struct request_queue *q,
+				   struct blk_mq_hw_ctx *hctx)
+{
+	LIST_HEAD(rq_list);
+	struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);
+	bool dispatched;
+
+	do {
+		struct request *rq;
+
+		rq = blk_mq_dequeue_from_ctx(hctx, ctx);
+		if (!rq)
+			break;
+		list_add(&rq->queuelist, &rq_list);
+
+		/* round robin for fair dispatch */
+		ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);
+
+		dispatched = blk_mq_dispatch_rq_list(q, &rq_list);
+	} while (dispatched);
+
+	if (!dispatched)
+		WRITE_ONCE(hctx->dispatch_from, ctx);
+}
+
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
@@ -142,18 +178,31 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 		do_sched_dispatch = blk_mq_dispatch_rq_list(q, &rq_list);
-	} else if (!has_sched_dispatch) {
+	} else if (!has_sched_dispatch && !q->queue_depth) {
+		/*
+		 * If there is no per-request_queue depth, we
+		 * flush all requests in this hw queue, otherwise
+		 * pick up request one by one from sw queue for
+		 * avoiding to mess up I/O merge when dispatch
+		 * run out of resource, which can be triggered
+		 * easily by per-request_queue queue depth
+		 */
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
 		blk_mq_dispatch_rq_list(q, &rq_list);
 	}
 
+	if (!do_sched_dispatch)
+		return;
+
 	/*
 	 * We want to dispatch from the scheduler if there was nothing
 	 * on the dispatch list or we were able to dispatch from the
 	 * dispatch list.
 	 */
-	if (do_sched_dispatch && has_sched_dispatch)
+	if (has_sched_dispatch)
 		blk_mq_do_dispatch_sched(q, e, hctx);
+	else
+		blk_mq_do_dispatch_ctx(q, hctx);
 }
 
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2747469cedaf..fccabe00fb55 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -30,6 +30,8 @@ struct blk_mq_hw_ctx {
 
 	struct sbitmap		ctx_map;
 
+	struct blk_mq_ctx	*dispatch_from;
+
 	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
 
-- 
2.9.5