Re: [boost] [asio] inefficiency in the polling

Subject: Re: [boost] [asio] inefficiency in the polling
From: Mathias Gaunard (mathias.gaunard_at_[hidden])
Date: 2016-09-27 13:24:56

Data on the network may be more high-priority than work in the queue.
This is the case for example for financial applications which need to react
to market data coming from the network as quickly as possible.

On 27 September 2016 at 16:10, Tatsuyuki Ishi <ishitatsuyuki_at_[hidden]>
wrote:

> The current run/poll_one does polling regardless if there's task in the
> queue.
>
> If there's task in the queue, polling is just a waste of system call, since
> there's already a job to do.
>
> Also, my common use case is "wait and consume all work", which is not
> covered efficiently by current design. (run_one+poll takes two system
> calls)
>
> Side note: on Windows asio performs even worse, it only retrieve one event
> per syscall... Not sure if it's intended.
>
> Friendly note: please use "Reply to All" when replying to me.
>
> _______________________________________________
> Unsubscribe & other changes: http://lists.boost.org/
> mailman/listinfo.cgi/boost
>