From owner-freebsd-net@FreeBSD.ORG Mon Feb 26 13:55:21 2007 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 8ED7D16A403 for ; Mon, 26 Feb 2007 13:55:21 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.freebsd.org (Postfix) with ESMTP id F3EB013C478 for ; Mon, 26 Feb 2007 13:55:20 +0000 (UTC) (envelope-from andre@freebsd.org) Received: (qmail 90832 invoked from network); 26 Feb 2007 13:28:39 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 26 Feb 2007 13:28:39 -0000 Message-ID: <45E2E6CB.8030707@freebsd.org> Date: Mon, 26 Feb 2007 14:55:23 +0100 From: Andre Oppermann User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) MIME-Version: 1.0 To: Kip Macy References: <45E19B54.9060007@freebsd.org> <45E1A3B4.7090002@freebsd.org> <2a41acea0702252053v2357b5f5tefbcf58375be1a2f@mail.gmail.com> <2a41acea0702252325k4ec64d59m95a63bebaf6ea30c@mail.gmail.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-net , Jack Vogel Subject: Re: improved TSO interface needed X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 Feb 2007 13:55:21 -0000 Kip Macy wrote: >> 64K is the max, and I believe that is taking into account the headers. >> What size are you seeing that is larger? Even if an mbuf chain comes >> down that large, it does NOT form a single packet, it is packetized by >> the hardware into MTU size, as I said, on the wire, ie as the receiver >> sees it, its just a lot of packets. The only question is whether the >> transmit hardware can handle it. Do you have eivdence of some >> hardware that supports TSO in the driver that cant?? > > I see this when torture testing a couple of different 10GigE cards > running at line rate. Your reported overshooting of 10 bytes is due to a buglet that didn't appear until now. Please try this fix: http://people.freebsd.org/~andre/tso_fix-20070226.diff -- Andre