blk-mq: implement hybrid poll mode for sync O_DIRECT

This patch enables a hybrid polling mode. Instead of polling after IO
submission, we can induce an artificial delay, and then poll after that.
For example, if the IO is presumed to complete in 8 usecs from now, we
can sleep for 4 usecs, wake up, and then do our polling. This still puts
a sleep/wakeup cycle in the IO path, but instead of the wakeup happening
after the IO has completed, it'll happen before. With this hybrid
scheme, we can achieve big latency reductions while still using the same
(or less) amount of CPU.

Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-By: Stephen Bates <sbates@raithlin.com>
Reviewed-By: Stephen Bates <sbates@raithlin.com>

1 files changed, 50 insertions, 0 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f39e69c732cc..8cb248fb6a68 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -332,6 +332,7 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 	rq->rq_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
 	blk_mq_put_tag(hctx, ctx, tag);
 	blk_queue_exit(q);
 }
@@ -2468,11 +2469,60 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
+static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
+				     struct request *rq)
+{
+	struct hrtimer_sleeper hs;
+	enum hrtimer_mode mode;
+	ktime_t kt;
+
+	if (!q->poll_nsec || test_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags))
+		return false;
+
+	set_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
+
+	/*
+	 * 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);
+
+	mode = HRTIMER_MODE_REL;
+	hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+	hrtimer_set_expires(&hs.timer, kt);
+
+	hrtimer_init_sleeper(&hs, current);
+	do {
+		if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
+			break;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		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));
+
+	__set_current_state(TASK_RUNNING);
+	destroy_hrtimer_on_stack(&hs.timer);
+	return true;
+}
+
 static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	struct request_queue *q = hctx->queue;
 	long state;
 
+	/*
+	 * If we sleep, have the caller restart the poll loop to reset
+	 * the state. Like for the other success return cases, the
+	 * caller is responsible for checking if the IO completed. If
+	 * 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))
+		return true;
+
 	hctx->poll_considered++;
 
 	state = current->state;