From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758449AbYEIV7g (ORCPT ); Fri, 9 May 2008 17:59:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753203AbYEIV7W (ORCPT ); Fri, 9 May 2008 17:59:22 -0400 Received: from 2605ds1-ynoe.1.fullrate.dk ([90.184.12.24]:48177 "EHLO shrek.krogh.cc" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753104AbYEIV7V (ORCPT ); Fri, 9 May 2008 17:59:21 -0400 Message-ID: <4824C936.9000103@krogh.cc> Date: Fri, 09 May 2008 23:59:18 +0200 From: Jesper Krogh User-Agent: Thunderbird 2.0.0.14 (X11/20080502) MIME-Version: 1.0 To: David Miller CC: yhlu.kernel@gmail.com, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Subject: Re: NIU - Sun Neptune 10g - Transmit timed out reset (2.6.24) References: <86802c440805071130m62c1f4edydb3316dac4a2aba2@mail.gmail.com> <20080507.141521.193714938.davem@davemloft.net> <482498D5.9060008@krogh.cc> <20080509.143229.174354251.davem@davemloft.net> In-Reply-To: <20080509.143229.174354251.davem@davemloft.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org David Miller wrote: > From: Jesper Krogh > Date: Fri, 09 May 2008 20:32:53 +0200 > >> When it works I doesnt seem to be able to get it pass 500MB/s. > > With this card you really need multiple cpus and multiple threads > sending data through the card in order to fill the 10Gb pipe. > > Single connections will not fill the pipe. The server is a Sun X4600 with 8 x dual-core CPU's, setup with 64 NFS-threads. The other end of the fiber goes into a switch with gigabit ports connected to 48 dual-core cpus. The test was done doing a dd on a 4.5GB file from the server to /dev/null on the clients. The number of contextswitches seems enourmous.. over 120.000 sometimes. When transmitting around the same amount of data (4xgigabit bonded with 802.3ad) 4x110MB/s the amount of contextswitches only reaches 3-4.000. I have no idea if this has any relevance. Should this setup not be able to fill the pipe? -- Jesper