From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761848AbYG3NgA (ORCPT ); Wed, 30 Jul 2008 09:36:00 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755957AbYG3Nft (ORCPT ); Wed, 30 Jul 2008 09:35:49 -0400 Received: from smarthost02.mail.zen.net.uk ([212.23.3.141]:36260 "EHLO smarthost02.mail.zen.net.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751120AbYG3Nfs (ORCPT ); Wed, 30 Jul 2008 09:35:48 -0400 Date: Wed, 30 Jul 2008 14:35:29 +0100 From: Ben Hutchings To: David Miller Cc: tony.luck@intel.com, jgarzik@redhat.com, linux-kernel@vger.kernel.org, linux-ia64@vger.kernel.org, netdev@vger.kernel.org, matthew@wil.cx, holt@sgi.com, linux-net-drivers@solarflare.com Subject: Re: [Patch] fix ia64 build failure when CONFIG_SFC=m Message-ID: <20080730133527.GI10471@solarflare.com> References: <20080729013650.GH9663@sgi.com> <57C9024A16AD2D4C97DC78E552063EA3080BA318@orsmsx505.amr.corp.intel.com> <20080729174839.GG10471@solarflare.com> <20080729.140040.72089155.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080729.140040.72089155.davem@davemloft.net> User-Agent: Mutt/1.4.1i X-Originating-Smarthost02-IP: [82.69.137.158] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org David Miller wrote: > From: Ben Hutchings > Date: Tue, 29 Jul 2008 18:48:41 +0100 > > > I think a single core in each package can generally saturate the > > memory bus and this is why spreading the load wider is not useful. > > I disagree, especially for routing and firewall setups. > > You want as many cpu threads as possible, even on the same core, > doing the routing and firewall lookups through the various > datastructures, in parallel. So far as I can see, hardly anyone is doing routing at 10G speeds on Linux. If they were, the horrible interaction with LRO would presumably have been found and fixed earlier. Besides which, internal benchmarking showed that we could route 1500-byte packets bidirectionally at very near line rate using one core on each of two multi-core packages. (I can give more details if you want.) The default can in any case be overridden using the rss_cpus module parameter. If you want to add a core network setting for that, I think we'd be happy to use it. Ben. -- Ben Hutchings, Senior Software Engineer, Solarflare Communications Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.