Re: [PATCH ] block: don't call blk_mq_quiesce_queue() during switching mq sched

[Bart Van Assche <Bart.VanAssche@sandisk.com>]

On Fri, 2017-04-28 at 07:42 -0600, Jens Axboe wrote:
> On 04/28/2017 01:32 AM, Ming Lei wrote:
> > We have freezed queue already, not necessary to call
> > blk_mq_quiesce_queue() any more, so remove it.
>=20
> Are you sure? It ensures that we also aren't in the middle of
> blk_mq_make_request(), we need a stable view of the sched
> status throughout that.

Hello Jens,

My understanding is that blk_mq_freeze_queue() provides stronger guarantees
than=A0blk_mq_quiesce_queue(). The former waits until all pending requests =
have
finished while the latter only waits until pending .queue_rq() calls have
finished. blk_mq_freeze_queue() also causes new blk_get_request() calls to
wait until blk_mq_unfreeze_queue() is called while=A0blk_get_request() can
still succeed after blk_mq_quiesce_queue() returned and before
blk_mq_start_stopped_hw_queues() is called.

Regarding blk_mq_make_request(): I think that the blk_queue_enter() call in
generic_make_request() prevents that blk_mq_make_request() gets called afte=
r
a queue has been frozen.

Bart.=