diff mbox series

[RFC,1/3] block: add flag 'nowait_requests' into queue limits

Message ID 159101502963.180989.6228080995222059011.stgit@buzz (mailing list archive)
State New, archived
Headers show
Series block: allow REQ_NOWAIT to some bio-based/stacked devices | expand

Commit Message

Konstantin Khlebnikov June 1, 2020, 12:37 p.m. UTC
Add flag for marking bio-based queues which support REQ_NOWAIT.
Set for all request based (mq) devices.

Stacking device should set it after blk_set_stacking_limits() if method
make_request() itself doesn't delay requests or handles REQ_NOWAIT.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
---
 block/blk-core.c       |    4 ++--
 block/blk-mq.c         |    3 +++
 block/blk-settings.c   |    3 +++
 include/linux/blkdev.h |    1 +
 4 files changed, 9 insertions(+), 2 deletions(-)

Comments

Christoph Hellwig June 3, 2020, 4:58 a.m. UTC | #1
On Mon, Jun 01, 2020 at 03:37:09PM +0300, Konstantin Khlebnikov wrote:
> Add flag for marking bio-based queues which support REQ_NOWAIT.
> Set for all request based (mq) devices.
> 
> Stacking device should set it after blk_set_stacking_limits() if method
> make_request() itself doesn't delay requests or handles REQ_NOWAIT.

I don't think this belongs into the queue limits.  For example a
stacking driver that always defers requests to a workqueue can support
REQ_NOWAIT entirely independent of the underlying devices.  I think
this just needs to be a simple queue flag.
Konstantin Khlebnikov June 3, 2020, 8:24 a.m. UTC | #2
On 03/06/2020 07.58, Christoph Hellwig wrote:
> On Mon, Jun 01, 2020 at 03:37:09PM +0300, Konstantin Khlebnikov wrote:
>> Add flag for marking bio-based queues which support REQ_NOWAIT.
>> Set for all request based (mq) devices.
>>
>> Stacking device should set it after blk_set_stacking_limits() if method
>> make_request() itself doesn't delay requests or handles REQ_NOWAIT.
> 
> I don't think this belongs into the queue limits.  For example a
> stacking driver that always defers requests to a workqueue can support
> REQ_NOWAIT entirely independent of the underlying devices.  I think
> this just needs to be a simple queue flag.
> 

For O_DIRECT I/O REQ_NOWAIT not just about non-blocking submition.
It also provides instant feedback about contention. Like ECN from network.
This feedback is useful for rate-control and balancing load between replicas.

If upper layer simply remaps and forwards requests below then to forward
contention all layers of stacked device should support this feature.
That's why I've put it as flag into limits - to reuse limits stacking.

If any layer defers request, then it should somehow limit size of backlog
at the same time to provide sane behaviour for REQ_NOWAIT regardless of
behaviour lower devices. So, then it could simply set that flag in limits.

Also I want to add handing into blk-qos/throttler - never delay REQ_NOWAIT.
diff mbox series

Patch

diff --git a/block/blk-core.c b/block/blk-core.c
index c4b015004796..9139a316e6d4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -892,9 +892,9 @@  generic_make_request_checks(struct bio *bio)
 
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * if queue does not support this flag.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+	if ((bio->bi_opf & REQ_NOWAIT) && !q->limits.nowait_requests)
 		goto not_supported;
 
 	if (should_fail_bio(bio))
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a7785df2c944..0c3daa0cda87 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2952,6 +2952,9 @@  struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	 */
 	q->poll_nsec = BLK_MQ_POLL_CLASSIC;
 
+	/* Request based queue always supports REQ_NOWAIT */
+	q->limits.nowait_requests = 1;
+
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 	blk_mq_add_queue_tag_set(set, q);
 	blk_mq_map_swqueue(q);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 14397b4c4b53..8f96c7324497 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -59,6 +59,7 @@  void blk_set_default_limits(struct queue_limits *lim)
 	lim->io_opt = 0;
 	lim->misaligned = 0;
 	lim->zoned = BLK_ZONED_NONE;
+	lim->nowait_requests = 0;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -486,6 +487,8 @@  int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
+	t->nowait_requests &= b->nowait_requests;
+
 	t->misaligned |= b->misaligned;
 
 	alignment = queue_limit_alignment_offset(b, start);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 32868fbedc9e..5f612dda34c2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -346,6 +346,7 @@  struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
+	unsigned char		nowait_requests;
 	enum blk_zoned_model	zoned;
 };