From owner-freebsd-isp@FreeBSD.ORG  Fri Oct 14 18:12:49 2005
Return-Path: <owner-freebsd-isp@FreeBSD.ORG>
X-Original-To: freebsd-isp@freebsd.org
Delivered-To: freebsd-isp@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 344CC16A422
	for <freebsd-isp@freebsd.org>; Fri, 14 Oct 2005 18:12:49 +0000 (GMT)
	(envelope-from lists@complx.LF.net)
Received: from complx.LF.net (complx.LF.net [212.9.190.63])
	by mx1.FreeBSD.org (Postfix) with ESMTP id D315F43D69
	for <freebsd-isp@freebsd.org>; Fri, 14 Oct 2005 18:12:44 +0000 (GMT)
	(envelope-from lists@complx.LF.net)
Received: from lists by complx.LF.net with local (Exim 4.43)
	id 1EQU2p-000DrR-58; Fri, 14 Oct 2005 20:12:39 +0200
Date: Fri, 14 Oct 2005 20:12:39 +0200
From: Kurt Jaeger <lists@complx.LF.net>
To: Danial Thom <danial_thom@yahoo.com>
Message-ID: <20051014181239.GC62233@complx.LF.net>
References: <20051013204631.51300.qmail@mail.gothambus.com>
	<20051014161100.33377.qmail@web33306.mail.mud.yahoo.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20051014161100.33377.qmail@web33306.mail.mud.yahoo.com>
Cc: freebsd-isp@freebsd.org, Drew Linsalata <drew@gothambus.com>
Subject: Re: Multiport NICs - VLAN and Polling Support?
X-BeenThere: freebsd-isp@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Internet Services Providers <freebsd-isp.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-isp>,
	<mailto:freebsd-isp-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-isp>
List-Post: <mailto:freebsd-isp@freebsd.org>
List-Help: <mailto:freebsd-isp-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-isp>,
	<mailto:freebsd-isp-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 14 Oct 2005 18:12:49 -0000

Hi!

> polling is almost never a performance advantage
> for ethernet, as virtually all modern controllers
> have some sort of interrupt moderation built-in.

We had the case on fbsd 5.4p7 with SMP where bge drivers produced
much slower throughput if we did not use polling. We measured using
ttcp and the difference was from 2-3Mbyte/sec to 11 Mbyte/sec.

Yes, it used more CPU, but for that increase in throughput, it
was worth the expense.

So it looks a bit strange from my part of the world to.

-- 
MfG/Best regards, Kurt Jaeger                                  15 years to go !
LF.net GmbH        fon +49 711 90074-23  pi@LF.net  
Ruppmannstr. 27    fax +49 711 90074-33
D-70565 Stuttgart  mob +49 171 3101372