From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Greear Subject: Re: tcp bw in 2.6 Date: Tue, 02 Oct 2007 09:48:46 -0700 Message-ID: <4702766E.80202@candelatech.com> References: <20071002005917.GB5480@bitmover.com> <20071002150935.GC17418@bitmover.com> <20071002154137.GD17418@bitmover.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: lm@bitmover.com, Herbert Xu , torvalds@linux-foundation.org, davem@davemloft.net, wscott@bitmover.com, netdev@vger.kernel.org Return-path: Received: from ns2.lanforge.com ([66.165.47.211]:40826 "EHLO ns2.lanforge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752794AbXJBQuD (ORCPT ); Tue, 2 Oct 2007 12:50:03 -0400 In-Reply-To: <20071002154137.GD17418@bitmover.com> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Larry McVoy wrote: > Interesting data point. My test case is like this: > > server > bind > listen > while (newsock = accept...) > transfer() > > client > connect > transfer > > If the server side is the source of the data, i.e, it's transfer is a > write loop, then I get the bad behaviour. If I switch them so the data > flows in the other direction, then it works, I go from about 14K pkt/sec > to 43K pkt/sec. > > Can anyone else reproduce this? I can extract the test case from lmbench > so it is standalone but I suspect that any test case will do it. I'll > try with the one that John sent. Yup, s/read/write/ and s/write/read/ > in his two files at the appropriate places and I get exactly the same > behaviour. > > So is this a bug or intentional? > I have a more complex configuration & application, but I don't see this problem in my testing. Using e1000 nics and modern hardware I can set up a connection between two machines and run 800+Mbps in both directions, or near line speed in one direction if the other direction is mostly silent. I am purposefully setting the socket send/rx buffers, as well has twiddling with the tcp and netdev related tunables. If you want, I can email these tweaks to you. NICs and busses have a huge impact on performance, so make sure those are good. Thanks, Ben -- Ben Greear Candela Technologies Inc http://www.candelatech.com