From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [RFC v2: Patch 1/3] net: hand off skb list to other cpu to submit to upper layer Date: Sat, 14 Mar 2009 02:53:40 +0100 Message-ID: <20090314015340.GM11935@one.firstfloor.org> References: <65634d660903131358h765bef64y6a0f1b0db7400f6f@mail.gmail.com> <20090313.140217.143696945.davem@davemloft.net> <65634d660903131459m645eb468y3ad850a1fd56d447@mail.gmail.com> <20090313.151913.21135937.davem@davemloft.net> <65634d660903131724s49009177pdc11005aa76a4b56@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Miller , yanmin_zhang@linux.intel.com, bhutchings@solarflare.com, andi@firstfloor.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, herbert@gondor.apana.org.au, jesse.brandeburg@intel.com, shemminger@vyatta.com To: Tom Herbert Return-path: Received: from one.firstfloor.org ([213.235.205.2]:34385 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1765156AbZCNBxf (ORCPT ); Fri, 13 Mar 2009 21:53:35 -0400 Content-Disposition: inline In-Reply-To: <65634d660903131724s49009177pdc11005aa76a4b56@mail.gmail.com> Sender: netdev-owner@vger.kernel.org List-ID: > Yes, we are using a 10G NIC that supports multi-queue. The number of > RX queues supported is half the number of cores on our platform, so > that is going to limit the parallelism. With multi-queue turned on we The standard wisdom is that you don't necessarily need to transmit to each core, but rather to each shared mid or least level cache. Once the data is cache hot (or cache near) distributing it further in software is comparable cheap. So this means you don't necessarily need as many queues as cores, but more as many as big caches. -Andi -- ak@linux.intel.com -- Speaking for myself only.