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

[Pavel Begunkov <asml.silence@gmail.com>]

On 8/20/24 23:58, Jens Axboe wrote:
> 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.

Another concern is racing with the task [re]setting ->cq_wait_nr
in io_cqring_wait(), e.g. because of a spurious wake up.

-- 
Pavel Begunkov