From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rick Jones Subject: Re: using software TSO on non-TSO capable netdevices Date: Thu, 31 Jul 2008 10:00:32 -0700 Message-ID: <4891EFB0.4040003@hp.com> References: <20080730235004.GC21999@xi.wantstofly.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, Ashish Karkare , Nicolas Pitre To: Lennert Buytenhek Return-path: Received: from g5t0006.atlanta.hp.com ([15.192.0.43]:17336 "EHLO g5t0006.atlanta.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756964AbYGaRAg (ORCPT ); Thu, 31 Jul 2008 13:00:36 -0400 In-Reply-To: <20080730235004.GC21999@xi.wantstofly.org> Sender: netdev-owner@vger.kernel.org List-ID: Lennert Buytenhek wrote: > When using sendfile() to send a GiB worth of zeroes over a single TCP > connection to another host on a 100 Mb/s network, with a vanilla > 2.6.27-rc1 kernel, this runs as expected at wire speed, taking the > following amount of CPU time per test: > > sys 0m5.410s > sys 0m5.380s > sys 0m5.620s > sys 0m5.360s That's output from "time" run against your test program right? Are folks confident that will account for all the CPU time consumed on behalf of that program? FWIW netperf is unwilling to make such an assumption. Perhaps I and it are being too paranoid but there you have it :) rick jones fwiw, there is a TCP_SENDFILE test in netperf