Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 28 Apr 2009 09:52:41 -0700
From:      Julian Elischer <julian@elischer.org>
To:        fabient@freebsd.org
Cc:        barney_cordoba@yahoo.com, Ed Maste <emaste@freebsd.org>, freebsd-net@freebsd.org
Subject:   Re: Interrupts + Polling mode (similar to Linux's NAPI)
Message-ID:  <49F73459.9080803@elischer.org>
In-Reply-To: <F14F044E-B39E-476B-A9DE-0EDB4D5265BE@netasq.com>
References:  <160513.83122.qm@web63904.mail.re1.yahoo.com> <F14F044E-B39E-476B-A9DE-0EDB4D5265BE@netasq.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Fabien Thomas wrote:
> 
> To share my results:
> 
> I have done at work modification to the polling code to do SMP polling 
> (previously posted to this ml).
> 
> SMP polling (dynamic group of interface binded to CPU) does not 
> significantly improve the throughput (lock contention seems to be the 
> cause here).
> The main advantage of polling with modern interface is not the PPS 
> (which is nearly the same) but the global efficiency of the system when 
> using multiple interfaces (which is the case for Firewall).
> The best configuration we have found with FreeBSD 6.3 is to do polling 
> on one CPU and keep the other CPU free for other processing. In this 
> configuration the whole system
> is more efficient than with interrupt where all the CPU are busy 
> processing interrupt thread.
> 

so it would (might) be worth while working out a framework
by which this could be achieved.

> Regards,
> Fabien
> 




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?49F73459.9080803>