From owner-freebsd-net@FreeBSD.ORG Wed Jul 2 10:05:26 2003 Return-Path: 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 2267B37B437 for ; Wed, 2 Jul 2003 10:05:26 -0700 (PDT) Received: from laptop.tenebras.com (laptop.tenebras.com [66.92.188.18]) by mx1.FreeBSD.org (Postfix) with SMTP id E7CF543FD7 for ; Wed, 2 Jul 2003 10:05:23 -0700 (PDT) (envelope-from kudzu@tenebras.com) Received: (qmail 20886 invoked from network); 2 Jul 2003 17:05:22 -0000 Received: from sapphire.tenebras.com (HELO tenebras.com) (192.168.188.241) by 0 with SMTP; 2 Jul 2003 17:05:22 -0000 Message-ID: <3F0310CE.5070302@tenebras.com> Date: Wed, 02 Jul 2003 10:05:18 -0700 From: Michael Sierchio User-Agent: Mozilla/5.0 (X11; U; Linux i386; en-US; rv:1.3.1) Gecko/20030425 X-Accept-Language: en-us, zh-tw, zh-cn, fr, en, de-de MIME-Version: 1.0 To: Eugene Grosbein References: <20030703002247.A2097@grosbein.pp.ru> In-Reply-To: <20030703002247.A2097@grosbein.pp.ru> Content-Type: text/plain; charset=us-ascii; format=flowed 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 List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 02 Jul 2003 17:05:26 -0000 Eugene Grosbein wrote: > Then, if prioritized packed arrives when FIFO is not empty, > it will not be allowed to go out before packets without ipprecedence > that are already in FIFO. That's bad. That's not quite right. The prioritized packet will presumably be handled by a different (dummynet) queue, and that queue will have a higher weight than the other queue (for lower priority traffic). Luigi will correct me if I'm wrong, but it's probably important to keep the high-priority VoIP queue small -- either in bytes or packets, representing the actual bandwidth. This will cause he WFQ to kick in. Because of fairness, it won't *prevent* low-priority packets from being transmitted -- and that's important, since queueing systems can suffer horrible locks from a small amount of traffic otherwise -- but it should accomplish your goal. Tuning is your job, though, Zhenya. ;-)