From owner-freebsd-net@FreeBSD.ORG Fri Oct 17 14:04:18 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 428D816A4B3 for ; Fri, 17 Oct 2003 14:04:18 -0700 (PDT) Received: from mtiwmhc12.worldnet.att.net (mtiwmhc12.worldnet.att.net [204.127.131.116]) by mx1.FreeBSD.org (Postfix) with ESMTP id 493A243FAF for ; Fri, 17 Oct 2003 14:04:17 -0700 (PDT) (envelope-from cmascott@att.net) Received: from callisto.local (197.cambridge-02rh16rt.ma.dial-access.att.net[12.91.19.197]) by worldnet.att.net (mtiwmhc12) with ESMTP id <2003101721041511200ike42e>; Fri, 17 Oct 2003 21:04:15 +0000 Received: from callisto.local (localhost.local [127.0.0.1]) by callisto.local (8.12.8p1/8.12.8) with ESMTP id h9HL4Fxf000734; Fri, 17 Oct 2003 17:04:15 -0400 (EDT) (envelope-from cmascott@callisto.local) Received: (from cmascott@localhost) by callisto.local (8.12.8p1/8.12.8/Submit) id h9HL4EK3000733; Fri, 17 Oct 2003 17:04:14 -0400 (EDT) Date: Fri, 17 Oct 2003 17:04:14 -0400 (EDT) From: Carl Mascott Message-Id: <200310172104.h9HL4EK3000733@callisto.local> To: oppermann@pipeline.ch In-Reply-To: <3F9040AC.7F117AFA@pipeline.ch> cc: freebsd-net@freebsd.org Subject: Re: TCP window size issues 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: Fri, 17 Oct 2003 21:04:18 -0000 Actually I have just fixed it in my copy of 4.8-R. I have a document that describes the problem and my solution. I could send you that and/or a set of patches. You might want to sketch out your own solution before you look at mine, though. Also, I'm not done testing mine yet. > Carl Mascott wrote: > > > > 2. The 4.4BSD TCP implementation has never had the correct precedence > > rules for setting window sizes. App-set values should take > > precedence over all others. Routing table values should take > > precedence over kernel default values. The fix for PR 11966 > > alters the behavior but still doesn't implement these precedence > > rules. > > I'll fix this in my tcp_hostcache patch currently under review by > Sam Leffler and Ruslan Ermilov (however that is for -CURRENT).