[tarantool-patches] Re: [PATCH v2 05/11] vinyl: implement quota wait queue without fiber_cond

[Konstantin Osipov]

* Vladimir Davydov <vdavydov.dev at gmail.com> [18/09/28 21:00]:
> Using fiber_cond as a wait queue isn't very convenient, because:
>  - It doesn't allow us to put a spuriously woken up fiber back to the
>    same position in the queue where it was, thus violating fairness.
>  - It doesn't allow us to check whether we actually need to wake up a
>    fiber or it will have to go back to sleep anyway as it needs more
>    memory than currently available.
>  - It doesn't allow us to implement a multi-queue approach where fibers
>    that have different priorities are put to different queues.
> 
> So let's rewrite the wait queue with plain rlist and fiber_yield.

Maybe you could factor out this change into an abstraction in fiber.[hc]?
Or fix fiber_cond to be fair?

>  
> @@ -92,7 +91,17 @@ vy_quota_check_limit(struct vy_quota *q)
>  static void
>  vy_quota_signal(struct vy_quota *q)
>  {
> -	fiber_cond_signal(&q->cond);
> +	if (!rlist_empty(&q->wait_queue)) {
> +		struct vy_quota_wait_node *n;
> +		n = rlist_first_entry(&q->wait_queue,
> +				      struct vy_quota_wait_node, in_wait_queue);
> +		/*
> +		 * No need in waking up a consumer if it will have
> +		 * to go back to sleep immediately.
> +		 */
> +		if (vy_quota_may_use(q, n->size))
> +			fiber_wakeup(n->fiber);
> +	}
>  }

-- 
Konstantin Osipov, Moscow, Russia, +7 903 626 22 32
http://tarantool.io - www.twitter.com/kostja_osipov