From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: Re: [PATCH 2/3][NET_BATCH] net core use batching Date: Mon, 01 Oct 2007 09:30:40 -0400 Message-ID: <1191245440.4378.12.camel@localhost> References: <20070914090058.17589.80352.sendpatchset@K50wks273871wss.in.ibm.com> <20070916.161748.48388692.davem@davemloft.net> <1189988958.4230.55.camel@localhost> <1190569987.4256.52.camel@localhost> <1190570205.4256.56.camel@localhost> <1190570317.4256.59.camel@localhost> <1190570409.4256.62.camel@localhost> <1191178346.6165.29.camel@localhost> <20071001001135.75d2b984.billfink@mindspring.com> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: David Miller , krkumar2@in.ibm.com, johnpol@2ka.mipt.ru, herbert@gondor.apana.org.au, kaber@trash.net, shemminger@linux-foundation.org, jagana@us.ibm.com, Robert.Olsson@data.slu.se, rick.jones2@hp.com, xma@us.ibm.com, gaagaan@gmail.com, netdev@vger.kernel.org, rdreier@cisco.com, peter.p.waskiewicz.jr@intel.com, mcarlson@broadcom.com, jeff@garzik.org, mchan@broadcom.com, general@lists.openfabrics.org, kumarkr@linux.ibm.com, tgraf@suug.ch, randy.dunlap@oracle.com, sri@us.ibm.com To: Bill Fink Return-path: Received: from wx-out-0506.google.com ([66.249.82.226]:1589 "EHLO wx-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751628AbXJANar (ORCPT ); Mon, 1 Oct 2007 09:30:47 -0400 Received: by wx-out-0506.google.com with SMTP id h31so3278388wxd for ; Mon, 01 Oct 2007 06:30:46 -0700 (PDT) In-Reply-To: <20071001001135.75d2b984.billfink@mindspring.com> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Mon, 2007-01-10 at 00:11 -0400, Bill Fink wrote: > Have you done performance comparisons for the case of using 9000-byte > jumbo frames? I havent, but will try if any of the gige cards i have support it. As a side note: I have not seen any useful gains or losses as the packet size approaches even 1500B MTU. For example, post about 256B neither the batching nor the non-batching give much difference in either throughput or cpu use. Below 256B, theres a noticeable gain for batching. Note, in the cases of my tests all 4 CPUs are in full-throttle UDP and so the occupancy of both the qdisc queue(s) and ethernet ring is constantly high. For example at 512B, the app is 80% idle on all 4 CPUs and we are hitting in the range of wire speed. We are at 90% idle at 1024B. This is the case with or without batching. So my suspicion is that with that trend a 9000B packet will just follow the same pattern. cheers, jamal