On Tue, 16 Feb 2010 12:00:01 +0100, [email protected] wrote:
> Send libev mailing list submissions to
>       [email protected]
> 
> To subscribe or unsubscribe via the World Wide Web, visit
>       http://lists.schmorp.de/cgi-bin/mailman/listinfo/libev
> or, via email, send a message with subject or body 'help' to
>       [email protected]
> 
> You can reach the person managing the list at
>       [email protected]
> 
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of libev digest..."
> 
> 
> Today's Topics:
> 
>    1. Re: sub milisec socket server write (Neeraj Rai)
>    2. Re: sub milisec socket server write (Marc Lehmann)
> 
> 
> ----------------------------------------------------------------------
> 
> Message: 1
> Date: Mon, 15 Feb 2010 18:18:26 -0800 (PST)
> From: Neeraj Rai <[email protected]>
> Subject: Re: sub milisec socket server write
> To: Marc Lehmann <[email protected]>
> Cc: [email protected]
> Message-ID: <[email protected]>
> Content-Type: text/plain; charset=iso-8859-1
> 
> 
> --- On Mon, 2/15/10, Marc Lehmann <[email protected]> wrote:
> 
>> From: Marc Lehmann <[email protected]>
>> Subject: Re: sub milisec socket server write
>> To: "Neeraj Rai" <[email protected]>
>> Cc: [email protected]
>> Date: Monday, February 15, 2010, 12:14 AM
>> On Sun, Feb 14, 2010 at 05:25:10PM
>> -0800, Neeraj Rai <[email protected]>
>> wrote:
>> > There is a trade off between latency and cpu usage. If
>> we sleep 1ms after each queue drain, cpu usage is almost nil
>> on no activity, but latency is ~1ms.
>> > If sleep is omitted, the cpu usage is 100% crowding
>> out other procs on same box.
>> > Q1. is this the best way to do this ?

I think that it is possible to use sleep(0) system call.
In Linux kernel it helps to shedule the processes queue.


Volodymyr Skrypka.

_______________________________________________
libev mailing list
[email protected]
http://lists.schmorp.de/cgi-bin/mailman/listinfo/libev

Reply via email to