bfq: update internal depth state when queue depth changes

* bfq: update internal depth state when queue depth changes
@ 2019-01-18 17:34 Jens Axboe
  2019-01-19 11:13 ` Kai Krakow
  0 siblings, 1 reply; 5+ messages in thread
From: Jens Axboe @ 2019-01-18 17:34 UTC (permalink / raw)
  To: linux-block; +Cc: Paolo Valente, Oleksandr Natalenko, hurikhan77+bko

A previous commit moved the shallow depth and BFQ depth map calculations
to be done at init time, moving it outside of the hotter IO path. This
potentially causes hangs if the users changes the depth of the scheduler
map, by writing to the 'nr_requests' sysfs file for that device.

Add a blk-mq-sched hook that allows blk-mq to inform the scheduler if
the depth changes, so that the scheduler can update its internal state.

Reported-by: Paolo Valente <paolo.valente@linaro.org>
Fixes: f0635b8a416e ("bfq: calculate shallow depths at init time")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index cd307767a134..b09589915667 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5342,7 +5342,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	return min_shallow;
 }
 
-static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
@@ -5350,6 +5350,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
 
 	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
 	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+	bfq_depth_updated(hctx);
 	return 0;
 }
 
@@ -5772,6 +5777,7 @@ static struct elevator_type iosched_bfq_mq = {
 		.requests_merged	= bfq_requests_merged,
 		.request_merged		= bfq_request_merged,
 		.has_work		= bfq_has_work,
+		.depth_updated		= bfq_depth_updated,
 		.init_hctx		= bfq_init_hctx,
 		.init_sched		= bfq_init_queue,
 		.exit_sched		= bfq_exit_queue,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ba37b9e15e9..a047b297ade5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3101,6 +3101,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		}
 		if (ret)
 			break;
+		if (q->elevator && q->elevator->type->ops.depth_updated)
+			q->elevator->type->ops.depth_updated(hctx);
 	}
 
 	if (!ret)
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2e9e2763bf47..6e8bc53740f0 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -31,6 +31,7 @@ struct elevator_mq_ops {
 	void (*exit_sched)(struct elevator_queue *);
 	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+	void (*depth_updated)(struct blk_mq_hw_ctx *);
 
 	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
 	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);

-- 
Jens Axboe


^ permalink raw reply related	[flat|nested] 5+ messages in thread