From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Zhang, Yanmin" Subject: Re: [RFC v1] hand off skb list to other cpu to submit to upper layer Date: Thu, 05 Mar 2009 09:04:36 +0800 Message-ID: <1236215076.2567.105.camel@ymzhang> References: <1235546423.2604.556.camel@ymzhang> <20090224.233115.240823417.davem@davemloft.net> <1236158868.2567.93.camel@ymzhang> <20090304.013937.129768263.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: herbert@gondor.apana.org.au, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, jesse.brandeburg@intel.com, shemminger@vyatta.com To: David Miller Return-path: Received: from mga10.intel.com ([192.55.52.92]:55810 "EHLO fmsmga102.fm.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750775AbZCEBFC (ORCPT ); Wed, 4 Mar 2009 20:05:02 -0500 In-Reply-To: <20090304.013937.129768263.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Wed, 2009-03-04 at 01:39 -0800, David Miller wrote: > From: "Zhang, Yanmin" > Date: Wed, 04 Mar 2009 17:27:48 +0800 >=20 > > Both the new skb_record_rx_queue and current kernel have an > > assumption on multi-queue. The assumption is it's best to send out > > packets from the TX of the same number of queue like the one of RX > > if the receved packets are related to the out packets. Or more > > direct speaking is we need send packets on the same cpu on which we > > receive them. The start point is that could reduce skb and data > > cache miss. >=20 > We have to use the same TX queue for all packets for the same > connection flow (same src/dst IP address and ports) otherwise > we introduce reordering. > Herbert brought this up, now I have explicitly brought this up, > and you cannot ignore this issue. Thanks. =EF=BB=BFStephen Hemminger brought it up and explained what reo= rder is. I answered in a reply (sorry for not clear) that mostly we need spr= ead packets among RX/TX in a 1:1 mapping or N:1 mapping. For example, all p= ackets received from RX 8 will be spreaded to TX 0 always. >=20 > You must not knowingly reorder packets, and using different TX > queues for packets within the same flow does that. Thanks for you rexplanation which is really consistent with =EF=BB=BFSt= ephen's speaking.