From owner-freebsd-net Wed Aug 14 22:33:42 2002 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 8A37837B400 for ; Wed, 14 Aug 2002 22:33:39 -0700 (PDT) Received: from tp.databus.com (p70-227.acedsl.com [66.114.70.227]) by mx1.FreeBSD.org (Postfix) with ESMTP id D027E43E65 for ; Wed, 14 Aug 2002 22:33:38 -0700 (PDT) (envelope-from barney@databus.com) Received: from databus.com (localhost.databus.com [127.0.0.1]) by tp.databus.com (8.12.5/8.12.5) with ESMTP id g7F5XLXr038183; Thu, 15 Aug 2002 01:33:21 -0400 (EDT) (envelope-from barney@databus.com) Received: (from barney@localhost) by databus.com (8.12.5/8.12.5/Submit) id g7F5XLjx038182; Thu, 15 Aug 2002 01:33:21 -0400 (EDT) Date: Thu, 15 Aug 2002 01:33:21 -0400 From: Barney Wolff To: Mike Silbersack Cc: Barney Wolff , Oleg Polyakov , freebsd-net@FreeBSD.ORG Subject: Re: Initial congestion window increase Message-ID: <20020815053321.GA37994@tp.databus.com> References: <20020814121701.GA27934@tp.databus.com> <20020814233935.F97690-100000@patrocles.silby.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20020814233935.F97690-100000@patrocles.silby.com> User-Agent: Mutt/1.4i Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org RFC2414-5 say no more than 4380, so your first example is wrong. And why do you assume that the jumbo stops at your border? Lots of people connect over non-local areas at gigE, these days. I don't know that they use jumbo, but I don't know that they don't. Internet congestion is measured in bits, not packets. Links don't care about packets and these days neither do routers. Generally, we should just do what the RFCs say, rather than trying to rethink every issue. It's really quite rare that the TCP RFCs are shown to be wrong, and the people who do it get famous. The OS's that deliberately flout the RFCs get famous too, in another way. On Thu, Aug 15, 2002 at 12:05:35AM -0500, Mike Silbersack wrote: > > Hrm, I'm not sure that PMTUD is a strong enough argument against X*MSS > slowstart for gigabit networks. Think about the following cases: > > 1. Server with MTU 1500, client with MTU 1480 (they're going over PPPoE > or something similar.) > > - All four 1500 byte packets sent back to back, all 4 bounced with ICMP > too big messages. Bandwidth wasted: All 4 packets traversing the net, > all 4 icmps coming back across the net. > > 2. Server with MTU 9000, client with MTU 1500. > > - All four 9000 byte packets sent back to back, bounced back at local > border router with MTU of 1500. Bandwidth wasted: Internal network > bandwidth only. Perhaps less than 4 packets, if all data fit into a > single 9000 byte packet. > > Considering this, I don't believe that the gigabit host using jumbo frames > would be any more harmful than a 100mbps host using normal ethernet > frames. -- Barney Wolff I'm available by contract or FT: http://www.databus.com/bwresume.pdf To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message