From owner-freebsd-net@FreeBSD.ORG  Tue Oct 28 12:04:28 2008
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 648F4106567A
	for <freebsd-net@freebsd.org>; Tue, 28 Oct 2008 12:04:28 +0000 (UTC)
	(envelope-from gizmen@blurp.pl)
Received: from albion.azs.pwr.wroc.pl (albion.azs.pwr.wroc.pl [156.17.17.145])
	by mx1.freebsd.org (Postfix) with ESMTP id 20ECF8FC0A
	for <freebsd-net@freebsd.org>; Tue, 28 Oct 2008 12:04:27 +0000 (UTC)
	(envelope-from gizmen@blurp.pl)
Received: from [10.8.1.27] (unknown [212.127.90.234])
	(using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits))
	(No client certificate requested)
	by albion.azs.pwr.wroc.pl (Postfix) with ESMTPSA id 53F64116FB;
	Tue, 28 Oct 2008 13:04:25 +0100 (CET)
From: Bartosz Giza <gizmen@blurp.pl>
Organization: BLURP.pl
To: freebsd-net@freebsd.org
Date: Tue, 28 Oct 2008 14:04:23 +0100
User-Agent: KMail/1.9.7
References: <200810281235.53508.gizmen@blurp.pl>
	<200810281309.58262.bartosz.giza@korbank.pl>
	<ge6t20$7n1$1@ger.gmane.org>
In-Reply-To: <ge6t20$7n1$1@ger.gmane.org>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Message-Id: <200810281404.24067.gizmen@blurp.pl>
Cc: Ivan Voras <ivoras@freebsd.org>
Subject: Re: two NIC on 2 core system (scheduling problem)
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-net>
List-Post: <mailto:freebsd-net@freebsd.org>
List-Help: <mailto:freebsd-net-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Tue, 28 Oct 2008 12:04:28 -0000

Tuesday 28 of October 2008 12:29:54 Ivan Voras napisa=C5=82(a):
> Bartosz Giza wrote:
> > Tuesday 28 of October 2008 11:49:21 Oleksandr Samoylyk napisa=C5=82(a):
> >> Ivan Voras wrote:
> >>> Bartosz Giza wrote:
> >>>> Another question is why em0 taskq is eating so much cpu ? BGE
> >>>> interface is actually one that pushes 2 times more packets than em0
> >>>> and it uses about half cpu comparing to em0. Is that not strange ?
> >>>> Could someone tell my why is this happening ? BGE is faster ? or
> >>>> maybe i can tune some
> >>>
> >>> I have the same problem - em0 taskq eating incredible amounts of CPU.
> >>> If you find a solution, contact me!
> >>
> >> It could be not just a problem with em driver.
> >> Firstly, it's good to make profiling and find out what exactly eats
> >> CPU time.
> >
> > Yes, we should make some profiling, but it is quite hard on busy
> > production router. When i turn on pooling on em0 card swi1: net is
> > using about 3% of cpu. So it is quite big difference between  20% with
> > tasq and 3% with polling.
>
> Is the difference reflected in your system / idle CPU time? (i.e. does
> your idle time increase for ~~ 17%?)

Yes exactly my idle time is increasing ~17%
=46or now i am not using polling But i am preparing the same machine for mu=
ch=20
more bussier router and i am not sure that this router with em cards will=20
suffice.