From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Wang Subject: Re: TCP_STREAM performance regression on commit b3613118 Date: Tue, 06 Mar 2012 16:26:13 +0800 Message-ID: <4F55CA25.2070503@redhat.com> References: <1329472239.2861.3.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> <20120217.133327.1178765872497293871.davem@davemloft.net> <1330656317.21053.1411.camel@debian> <20120301.220743.2174015405223036036.davem@davemloft.net> <20120306081117.GA17375@feng-i7> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: David Miller , alex.shi@intel.com, eric.dumazet@gmail.com, linux-kernel@vger.kernel.org, tim.c.chen@intel.com, ying.huang@intel.com, netdev@vger.kernel.org To: Feng Tang Return-path: In-Reply-To: <20120306081117.GA17375@feng-i7> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On 03/06/2012 04:11 PM, Feng Tang wrote: > On Thu, Mar 01, 2012 at 10:07:43PM -0500, David Miller wrote: >> > From: Alex Shi >> > Date: Fri, 02 Mar 2012 10:45:17 +0800 >> > >>> > > Add CC to tang feng, He is working on this issue. >> > >> > Is he? I'm pretty sure this is due to the TCP receive window growing >> > issue Eric Dumazet, Neal Cardwell and I are discussing in the thread >> > starting at: >> > >> > http://marc.info/?l=linux-netdev&m=132916352815286&w=2 > Yes, probably, as we did find some clue related with the tcp_r/wmem. > > Here is the regression we found: > On some machines, we found there is about 10% resgression of netperf > TCP-64K loopback test between 3.2 and 3.3-rc1. The exact test is: > ./netperf -t TCP_STREAM -l 60 -H 127.0.0.1 -i 50,3 -I 99,5 -- -s 32768 -S 32768 -m 4096 > > > The test machine is a 2 socket Quad Core Core 2 Duo server(2.66GHz) with > 8 GB RAM. Following are the debug info (ifconfig/netstat -s/tcp_rwmem) > before and after the test: > > The most obvious differences I can see are: > 1) 311 GB vs 241 GB from ifconfig > 2) the difference of the tcp_r/wmem Hi: Could you try the newest kernel? Looks like the difference has been already fixed by commit c43b874d5d714f271b80d4c3f49e05d0cbf51ed2. Thanks