Re: [PATCH 4/5] io_uring: add support for batch wait timeout

[Jens Axboe <axboe@kernel.dk>]

On 8/20/24 4:47 PM, Pavel Begunkov wrote:
> On 8/20/24 23:46, Pavel Begunkov wrote:
>> On 8/20/24 00:28, Jens Axboe wrote:
>>> Waiting for events with io_uring has two knobs that can be set:
>>>
>>> 1) The number of events to wake for
>>> 2) The timeout associated with the event
>>>
>>> Waiting will abort when either of those conditions are met, as expected.
>>>
>>> This adds support for a third event, which is associated with the number
>>> of events to wait for. Applications generally like to handle batches of
>>> completions, and right now they'd set a number of events to wait for and
>>> the timeout for that. If no events have been received but the timeout
>>> triggers, control is returned to the application and it can wait again.
>>> However, if the application doesn't have anything to do until events are
>>> reaped, then it's possible to make this waiting more efficient.
>>>
>>> For example, the application may have a latency time of 50 usecs and
>>> wanting to handle a batch of 8 requests at the time. If it uses 50 usecs
>>> as the timeout, then it'll be doing 20K context switches per second even
>>> if nothing is happening.
>>>
>>> This introduces the notion of min batch wait time. If the min batch wait
>>> time expires, then we'll return to userspace if we have any events at all.
>>> If none are available, the general wait time is applied. Any request
>>> arriving after the min batch wait time will cause waiting to stop and
>>> return control to the application.
>>>
>>> Signed-off-by: Jens Axboe <axboe@kernel.dk>
>>> ---
>>>   io_uring/io_uring.c | 75 +++++++++++++++++++++++++++++++++++++++------
>>>   io_uring/io_uring.h |  2 ++
>>>   2 files changed, 67 insertions(+), 10 deletions(-)
>>>
>>> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
>>> index ddfbe04c61ed..d09a7c2e1096 100644
>>> --- a/io_uring/io_uring.c
>>> +++ b/io_uring/io_uring.c
>>> @@ -2363,13 +2363,62 @@ static enum hrtimer_restart io_cqring_timer_wakeup(struct hrtimer *timer)
>>>       return HRTIMER_NORESTART;
>>>   }
>>> +/*
>>> + * Doing min_timeout portion. If we saw any timeouts, events, or have work,
>>> + * wake up. If not, and we have a normal timeout, switch to that and keep
>>> + * sleeping.
>>> + */
>>> +static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer)
>>> +{
>>> +    struct io_wait_queue *iowq = container_of(timer, struct io_wait_queue, t);
>>> +    struct io_ring_ctx *ctx = iowq->ctx;
>>> +
>>> +    /* no general timeout, or shorter, we are done */
>>> +    if (iowq->timeout == KTIME_MAX ||
>>> +        ktime_after(iowq->min_timeout, iowq->timeout))
>>> +        goto out_wake;
>>> +    /* work we may need to run, wake function will see if we need to wake */
>>> +    if (io_has_work(ctx))
>>> +        goto out_wake;
>>> +    /* got events since we started waiting, min timeout is done */
>>> +    if (iowq->cq_min_tail != READ_ONCE(ctx->rings->cq.tail))
>>> +        goto out_wake;
>>> +    /* if we have any events and min timeout expired, we're done */
>>> +    if (io_cqring_events(ctx))
>>> +        goto out_wake;
>>> +
>>> +    /*
>>> +     * If using deferred task_work running and application is waiting on
>>> +     * more than one request, ensure we reset it now where we are switching
>>> +     * to normal sleeps. Any request completion post min_wait should wake
>>> +     * the task and return.
>>> +     */
>>> +    if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
>>> +        atomic_set(&ctx->cq_wait_nr, 1);
>>
>> racy
>>
>> atomic_set(&ctx->cq_wait_nr, 1);
>> smp_mb();
>> if (llist_empty(&ctx->work_llist))
>>      // wake;
> 
> rather if _not_ empty

Yep that one was a given :-)

Updated it, we'll punt to out_wake at that point.

-- 
Jens Axboe