Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753313Ab0AUPai (ORCPT ); Thu, 21 Jan 2010 10:30:38 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752592Ab0AUPai (ORCPT ); Thu, 21 Jan 2010 10:30:38 -0500 Received: from e23smtp06.au.ibm.com ([202.81.31.148]:57011 "EHLO e23smtp06.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751539Ab0AUPah (ORCPT ); Thu, 21 Jan 2010 10:30:37 -0500 Message-ID: <4B587317.6060404@linux.vnet.ibm.com> Date: Thu, 21 Jan 2010 21:00:31 +0530 From: Balbir Singh Reply-To: balbir@linux.vnet.ibm.com User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.1.5) Gecko/20091209 Fedora/3.0-4.fc12 Lightning/1.0b1 Thunderbird/3.0 MIME-Version: 1.0 To: KAMEZAWA Hiroyuki CC: "linux-mm@kvack.org" , "linux-kernel@vger.kernel.org" , "nishimura@mxp.nes.nec.co.jp" , kirill@shutemov.name Subject: Re: [PATCH mmotm] memcg use generic percpu allocator instead of private one References: <20100120161825.15c372ac.kamezawa.hiroyu@jp.fujitsu.com> <4B56CEF0.2040406@linux.vnet.ibm.com> <20100121110759.250ed739.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <20100121110759.250ed739.kamezawa.hiroyu@jp.fujitsu.com> X-Enigmail-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2073 Lines: 52 On Thursday 21 January 2010 07:37 AM, KAMEZAWA Hiroyuki wrote: > On Wed, 20 Jan 2010 15:07:52 +0530 > Balbir Singh wrote: > >>> This includes no functional changes. >>> >>> Signed-off-by: KAMEZAWA Hiroyuki >> >> >> Before review, could you please post parallel pagefault data on a large >> system, since root now uses these per cpu counters and its overhead is >> now dependent on these counters. Also the data read from root cgroup is >> also dependent on these, could you make sure that is not broken. >> > Hmm, I rewrote test program for avoidng mmap_sem. This version does fork() > instead of pthread_create() and meausre parallel-process page fault speed. > > [Before patch] > [root@bluextal memory]# /root/bin/perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault-fork 8 > > Performance counter stats for './multi-fault-fork 8' (5 runs): > > 45256919 page-faults ( +- 0.851% ) > 602230144 cache-misses ( +- 0.187% ) > > 61.020533723 seconds time elapsed ( +- 0.002% > > [After patch] > [root@bluextal memory]# /root/bin/perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault-fork 8 > > Performance counter stats for './multi-fault-fork 8' (5 runs): > > 46007166 page-faults ( +- 0.339% ) > 599553505 cache-misses ( +- 0.298% ) > > 61.020937843 seconds time elapsed ( +- 0.004% ) > > slightly improved ? But this test program does some extreme behavior and > you can't see difference in real-world applications, I think. > So, I guess this is in error-range in famous (not small) benchmarks. Looks good, please give me a couple of days to test, I'll revert back with numbers and review. -- Three Cheers, Balbir Singh -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/