From owner-freebsd-stable@FreeBSD.ORG Tue Apr 19 20:56:20 2005 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6001316A4CE for ; Tue, 19 Apr 2005 20:56:20 +0000 (GMT) Received: from xciv.org (82-44-19-101.cable.ubr03.newm.blueyonder.co.uk [82.44.19.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9C0EF43D49 for ; Tue, 19 Apr 2005 20:56:19 +0000 (GMT) (envelope-from paul@xciv.org) Received: from tuscan.xciv.org (localhost.xciv.org [127.0.0.1]) by tuscan.xciv.org (8.12.9p2/8.12.9) with ESMTP id j3JHnE9N000895; Tue, 19 Apr 2005 18:49:14 +0100 (BST) (envelope-from paul@tuscan.xciv.org) Received: (from paul@localhost) by tuscan.xciv.org (8.12.9p2/8.12.9/Submit) id j3JHnEfE000894; Tue, 19 Apr 2005 18:49:14 +0100 (BST) (envelope-from paul) Date: Tue, 19 Apr 2005 18:49:14 +0100 (BST) Message-Id: <200504191749.j3JHnEfE000894@tuscan.xciv.org> Mime-Version: 1.0 X-Newsreader: knews 1.0b.1 Organization: iso.org.dod.internet References: <200504180317.j3I3Hmdo068332@aurora.sol.net> In-Reply-To: <200504180317.j3I3Hmdo068332@aurora.sol.net> From: paul@xciv.org (Paul Civati) X-Original-Newsgroups: xciv.lists.freebsd.stable To: freebsd-stable@freebsd.org Content-Type: text/plain; charset=us-ascii cc: paul@xciv.org Subject: Re: Tuning for router performance X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: freebsd-stable@freebsd.org List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 19 Apr 2005 20:56:20 -0000 In article <200504180317.j3I3Hmdo068332@aurora.sol.net>, jgreco@ns.sol.net (Joe Greco) writes: > No problems with high traffic rates. (For the purposes of this discussion, > all traffic except ssh to the router is traffic /thru/ the router). Yes sorry I should have also mentioned I was specifically using 64byte packets for PPS testing - not entirely real world traffic. > I find this interesting, because the aggregate traffic through the router > is clearly not anywhere near a gigabit. So it does appear that there is > some sort of inadvertent cap on PPS here. I think there always will be at some point, if only because the hardware isn't not optimised for the task. > 2) We need to remember that the design of the P4SC{8,i} is a bit crappy, > in that the onboard ports consist of one CSA port (no problem here) > and one PCI port - which Supermicro wisely placed on the 32-bit, 33 MHz > legacy PCI bus. This could potentially limit the throughput on that > port. Not a problem for me as I'm only using the ethernet on that bus. -Paul-