From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rick Jones Subject: Re: [PATCH] myr10ge: again fix lro_gen_skb() alignment Date: Fri, 24 Apr 2009 10:13:52 -0700 Message-ID: <49F1F350.2080402@hp.com> References: <20090415.030213.249634462.davem@davemloft.net> <49E5DABB.9070806@myri.com> <49E64BE4.1050908@myri.com> <20090415.164248.188350673.davem@davemloft.net> <20090416085022.GA19731@gondor.apana.org.au> <49EE1C32.1060202@myri.com> <20090422104811.GA30981@gondor.apana.org.au> <49EF39B4.1040607@myri.com> <20090424054557.GA24575@gondor.apana.org.au> <49F1B468.7020605@myri.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: Herbert Xu , David Miller , brice@myri.com, sgruszka@redhat.com, netdev@vger.kernel.org To: Andrew Gallatin Return-path: Received: from g4t0016.houston.hp.com ([15.201.24.19]:21865 "EHLO g4t0016.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753023AbZDXRNz (ORCPT ); Fri, 24 Apr 2009 13:13:55 -0400 In-Reply-To: <49F1B468.7020605@myri.com> Sender: netdev-owner@vger.kernel.org List-ID: > This is strange. I wonder if it might be a cache footprint issue? > My intentionally weak receiver is an athlon64 x2 "Toledo", and > has only 512KB L2 cache. I can re-test with a core-2 based Xeon. A point about netperf :) By default, it will use one more buffer than the initial size of the socket buffer divided by the send/recv buffer size - this goes back to days of copy-avoidance, a flavor of which can be found in reading: ftp://ftp.cup.hp.com/dist/networking/briefs/copyavoid.pdf particularly section 3.2. It can be overridden with the global -W option: -W send,recv Set the number of send,recv buffers Of course, this will interact with other things such as: The default send/recv size will be the send/recv socket buffer size. That can be overridden with the test-specific -m/-M options. The default socket buffer size will be whatever the system gives it. That can be overridden with the test-specific -s/-S options. So, the various options can have a non-trivial effect on the cache footprint of the data netperf is shoving around. rick jones