Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 24 Jul 2006 16:35:23 -0300
From:      Marcelo Gardini do Amaral <marcelo@registro.br>
To:        Scott Long <scottl@samsco.org>
Cc:        Peter Jeremy <peterjeremy@optushome.com.au>, freebsd-stable@freebsd.org, Ed Maste <emaste@phaedrus.sandvine.ca>
Subject:   Re: How to setup polling on 'bge' interface
Message-ID:  <20060724193523.GB51092@registro.br>
In-Reply-To: <44BFA2EE.7060308@samsco.org>
References:  <20060711190908.GC69272@registro.br> <20060720023856.GA65960@sandvine.com> <20060720112613.GB716@turion.vk2pj.dyndns.org> <44BFA2EE.7060308@samsco.org>

next in thread | previous in thread | raw e-mail | index | archive | help
> >The limited testing I've done on a Sun V20z at work suggests that you
> >can get better routing throughput in interrupt mode than polling mode.
> >YMMV and this is before tweaking the polling parameters.  (My testing
> >also suggests that I don't really need to do any tweaking because
> >the limiting factor is the gigabit interfaces rather than the V20z).

I've noticed a higher (and variable) RTT with polling mode activated,
without tweaking any parameters.

> 
> This might not apply to bge, but the adaptive polling + fast interrupt
> changes that I made to if_em earlier in the year were a huge win over
> the standard polling code in terms of CPU utilization and packets per
> second.  I think it also survived a load that caused normal polling to
> essentially livelock the machine.  And, it had the advantage of
> automatically adapting to bursty loads.

-- 
Att.,

Marcelo Gardini




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060724193523.GB51092>