On Fri, Nov 11, 2016 at 10:11:27PM -0700, Jens Axboe wrote:
> The previous commit introduced the hybrid sleep/poll mode. Take
> that one step further, and use the completion latencies to
> automatically sleep for half the mean completion time. This is
> a good approximation.
>
> This changes the 'io_poll_delay' sysfs file a bit to expose the
> various options. Depending on the value, the polling code will
> behave differently:
>
> -1 Never enter hybrid sleep mode
> 0 Use half of the completion mean for the sleep delay
> >0 Use this specific value as the sleep delay
>
> Signed-off-by: Jens Axboe <axboe@xxxxxx>
> ---
> block/blk-mq.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++----
> block/blk-sysfs.c | 26 ++++++++++++------
> include/linux/blkdev.h | 2 +-
> 3 files changed, 88 insertions(+), 14 deletions(-)
>
[snip]
> static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
> + struct blk_mq_hw_ctx *hctx,
> struct request *rq)
> {
> struct hrtimer_sleeper hs;
> + enum hrtimer_mode mode;
> + unsigned int nsecs;
> ktime_t kt;
>
> - if (!q->poll_nsec || test_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags))
> + if (test_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags))
> + return false;
> +
> + /*
> + * poll_nsec can be:
> + *
> + * -1: don't ever hybrid sleep
> + * 0: use half of prev avg
> + * >0: use this specific value
> + */
> + if (q->poll_nsec == -1)
> + return false;
> + else if (q->poll_nsec > 0)
> + nsecs = q->poll_nsec;
> + else
> + nsecs = blk_mq_poll_nsecs(q, hctx, rq);
> +
> + if (!nsecs)
> return false;
>
> set_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
> @@ -2477,9 +2539,10 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
> * This will be replaced with the stats tracking code, using
> * 'avg_completion_time / 2' as the pre-sleep target.
> */
> - kt = ktime_set(0, q->poll_nsec);
> + kt = ktime_set(0, nsecs);
>
> - hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> + mode = HRTIMER_MODE_REL;
> + hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
> hrtimer_set_expires(&hs.timer, kt);
>
> hrtimer_init_sleeper(&hs, current);
> @@ -2487,10 +2550,11 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
> if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
> break;
> set_current_state(TASK_UNINTERRUPTIBLE);
> - hrtimer_start_expires(&hs.timer, HRTIMER_MODE_REL);
> + hrtimer_start_expires(&hs.timer, mode);
> if (hs.task)
> io_schedule();
> hrtimer_cancel(&hs.timer);
> + mode = HRTIMER_MODE_ABS;
> } while (hs.task && !signal_pending(current));
This fix should be folded into patch 2.
> __set_current_state(TASK_RUNNING);
> @@ -2510,7 +2574,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
> * the IO isn't complete, we'll get called again and will go
> * straight to the busy poll loop.
> */
> - if (blk_mq_poll_hybrid_sleep(q, rq))
> + if (blk_mq_poll_hybrid_sleep(q, hctx, rq))
> return true;
>
> hctx->poll_considered++;
[snip]
--
Omar
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
