From owner-freebsd-net@FreeBSD.ORG  Sat Jul  5 19:52:30 2003
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 7982337B401
	for <net@freebsd.org>; Sat,  5 Jul 2003 19:52:30 -0700 (PDT)
Received: from www.svzserv.kemerovo.su (www.svzserv.kemerovo.su
	[213.184.65.80])
	by mx1.FreeBSD.org (Postfix) with ESMTP id 4746643FBF
	for <net@freebsd.org>; Sat,  5 Jul 2003 19:52:28 -0700 (PDT)
	(envelope-from eugen@kuzbass.ru)
Received: from kuzbass.ru (kost [213.184.65.82])h662qMCo024333;
	Sun, 6 Jul 2003 10:52:23 +0800 (KRAST)
	(envelope-from eugen@kuzbass.ru)
Message-ID: <3F078E39.ABC0822F@kuzbass.ru>
Date: Sun, 06 Jul 2003 10:49:29 +0800
From: Eugene Grosbein <eugen@kuzbass.ru>
Organization: SVZServ
X-Mailer: Mozilla 4.8 [en] (Win98; U)
X-Accept-Language: ru,en
MIME-Version: 1.0
To: Luigi Rizzo <rizzo@icir.org>
References: <20030703002247.A2097@grosbein.pp.ru>
	<3F0310CE.5070302@tenebras.com> <3F03867A.79F82968@kuzbass.ru>
	<20030705123332.A60972@xorpc.icir.org>
Content-Type: text/plain; charset=koi8-r
Content-Transfer-Encoding: 7bit
cc: net@freebsd.org
Subject: Re: ipprecedence
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.1
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: Sun, 06 Jul 2003 02:52:30 -0000

Luigi Rizzo wrote:

> Bottom line -- the whole architecture has been designed with
> FIFO in mind, and implementing any different queueing policy
> will involve some significant rewriting of the device drivers,
> plus, potentially, some significant performance loss.

Thank you for detailed explanation.  I hope that dummynet's WFQ
would be sufficient but not sure: will it correctly process
weights whith zero-bandwidth pipe?

I mean one dummynet pipe (bw 0) and two dummynet queues for that pipe
assigning weight 1 and weight 100. That's for each direction of traffic,
of course.

Eugene