Re: [dm-devel] [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Thu, 2018-02-01 at 19:26 -0500, John Stoffel wrote: > Doesn't this argue that you really want some sort of completions to be > run in this case instead? Instead of busy looping or waiting for a > set amount of time, just fire off a callback to run once you have the > resources available, no?

Re: [dm-devel] [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

> "Bart" == Bart Van Assche writes: Bart> On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: >> But regardless of which wins the race, the queue will have been run. >> Which is all we care about right? Bart> Running the queue is not sufficient. With this patch

Re: [dm-devel] [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 30, 2018 at 6:14 AM, Mike Snitzer wrote: > On Mon, Jan 29 2018 at 4:51pm -0500, > Bart Van Assche wrote: > >> On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: >> > But regardless of which wins the race, the queue will have been run.

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 30, 2018 at 5:51 AM, Bart Van Assche wrote: > On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: >> But regardless of which wins the race, the queue will have been run. >> Which is all we care about right? > > Running the queue is not sufficient. With this

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 30, 2018 at 5:22 AM, Bart Van Assche wrote: > On Mon, 2018-01-29 at 15:33 -0500, Mike Snitzer wrote: >> + * If driver returns BLK_STS_RESOURCE and SCHED_RESTART >> + * bit is set, run queue after 10ms to avoid IO stalls >> +

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Mon, 2018-01-29 at 17:14 -0500, Mike Snitzer wrote: > On Mon, Jan 29 2018 at 4:51pm -0500, > Bart Van Assche wrote: > > > On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: > > > But regardless of which wins the race, the queue will have been run. > > > Which is

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Mon, Jan 29 2018 at 4:51pm -0500, Bart Van Assche wrote: > On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: > > But regardless of which wins the race, the queue will have been run. > > Which is all we care about right? > > Running the queue is not sufficient.

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Mon, 2018-01-29 at 16:44 -0500, Mike Snitzer wrote: > But regardless of which wins the race, the queue will have been run. > Which is all we care about right? Running the queue is not sufficient. With this patch applied it can happen that the block driver returns BLK_STS_DEV_RESOURCE, that the

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Mon, Jan 29 2018 at 4:22pm -0500, Bart Van Assche wrote: > On Mon, 2018-01-29 at 15:33 -0500, Mike Snitzer wrote: > > +* If driver returns BLK_STS_RESOURCE and SCHED_RESTART > > +* bit is set, run queue after 10ms to avoid IO stalls > > +

Re: [PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Mon, 2018-01-29 at 15:33 -0500, Mike Snitzer wrote: > + * If driver returns BLK_STS_RESOURCE and SCHED_RESTART > + * bit is set, run queue after 10ms to avoid IO stalls > + * that could otherwise occur if the queue is idle. >*/ > -

[PATCH V4] blk-mq: introduce BLK_STS_DEV_RESOURCE

From: Ming Lei This status is returned from driver to block layer if device related resource is unavailable, but driver can guarantee that IO dispatch will be triggered in future when the resource is available. Convert some drivers to return BLK_STS_DEV_RESOURCE. Also, if