From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753099Ab0AUPZs (ORCPT ); Thu, 21 Jan 2010 10:25:48 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752894Ab0AUPZr (ORCPT ); Thu, 21 Jan 2010 10:25:47 -0500 Received: from e28smtp02.in.ibm.com ([122.248.162.2]:55761 "EHLO e28smtp02.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751611Ab0AUPZr (ORCPT ); Thu, 21 Jan 2010 10:25:47 -0500 Message-ID: <4B5871F3.5020800@linux.vnet.ibm.com> Date: Thu, 21 Jan 2010 20:55:39 +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: Anton Blanchard CC: Martin Schwidefsky , Bharata B Rao , KOSAKI Motohiro , Ingo Molnar , mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl, balajirrao@gmail.com, dhaval@linux.vnet.ibm.com, tglx@linutronix.de, kamezawa.hiroyu@jp.fujitsu.com, akpm@linux-foundation.org, Tony Luck , Fenghua Yu , Heiko Carstens , linux390@de.ibm.com Subject: Re: [PATCH] sched: cpuacct: Use bigger percpu counter batch values for stats counters References: <20090512102412.GG6351@balbir.in.ibm.com> <20090512102939.GB11714@elte.hu> <20090512193656.D647.A69D9226@jp.fujitsu.com> <20090716081010.GB3134@in.ibm.com> <20090716083948.GA2950@kryten> <20090820051038.GF21100@kryten> <20100118044142.GS12666@kryten> <20100118104213.64231c1e@mschwide.boeblingen.de.ibm.com> <20100118095527.GV12666@kryten> In-Reply-To: <20100118095527.GV12666@kryten> 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 On Monday 18 January 2010 03:25 PM, Anton Blanchard wrote: > > Hi Martin, > >> For s390 the jiffies_to_cputime is a compile time constant. No need to >> initialize it at runtime, no? > > Indeed it is, I didn't look closely enough. Same with ia64 so no work to > do on either arch :) > >> The patch itself trades some accuracy (larger cpu accounting value that >> are stored per-cpu) against runtime overhead (spinlock to transfer the >> value to the global variable in __percpu_counter_add). Did you >> calculate how big the loss in accuracy is? > > The idea is we are already batching percpu_counter_batch jiffies, so > with CONFIG_VIRT_CPU_ACCOUNTING we batch the equivalent amount in > cputime. > Hi, Peter, Ingo Could we please pick up the patch for -tip? -- Three Cheers, Balbir Singh