From owner-freebsd-net@FreeBSD.ORG Mon Jun 30 00:16:37 2008 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 33B9A106564A for ; Mon, 30 Jun 2008 00:16:37 +0000 (UTC) (envelope-from if@xip.at) Received: from chile.gbit.at (ns1.xip.at [193.239.188.99]) by mx1.freebsd.org (Postfix) with ESMTP id 78FCB8FC12 for ; Mon, 30 Jun 2008 00:16:35 +0000 (UTC) (envelope-from if@xip.at) Received: (qmail 29824 invoked from network); 30 Jun 2008 02:16:34 +0200 Received: from unknown (HELO filebunker.xip.at) (86.59.10.180) by chile.gbit.at with (DHE-RSA-AES256-SHA encrypted) SMTP; 30 Jun 2008 02:16:34 +0200 Date: Mon, 30 Jun 2008 02:16:33 +0200 (CEST) From: Ingo Flaschberger To: Paul In-Reply-To: <48681A3D.9040509@gtcomm.net> Message-ID: References: <4867420D.7090406@gtcomm.net> <4867A9A1.9070507@gtcomm.net> <48681A3D.9040509@gtcomm.net> User-Agent: Alpine 1.10 (LFD 962 2008-03-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: FreeBSD Net Subject: Re: Freebsd IP Forwarding performance (question, and some info) [7-stable, current, em, smp] 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, 30 Jun 2008 00:16:37 -0000 Dear Paul, > Yes it does but it seems to use a lot more of one cpu than the others so It's > really not SMP.. Can I stop it from doing this with some setting? > Why can't there be 4 taskq's? it is possible, but it need to be coded. hz 4000 is also too high, use 1000-2000 http://www.tancsa.com/blast.html > Also with full internet table I can't even do 100kpps without errors.. I > don't get it :/ I could do 300kpps on a p3 and now I have a 3ghz xeon and > 2.2ghz opteron brand new hardware and can barely get more than that.. > Doesn't make sense to me. have you tested with freebsd 6? or try dragonfly? Kind regards, Ingo Flaschberger