From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754461AbZELKWu (ORCPT ); Tue, 12 May 2009 06:22:50 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752250AbZELKWj (ORCPT ); Tue, 12 May 2009 06:22:39 -0400 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:50555 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751013AbZELKWi (ORCPT ); Tue, 12 May 2009 06:22:38 -0400 From: KOSAKI Motohiro To: KOSAKI Motohiro Subject: Re: [tip:sched/core] sched: cpuacct: Use bigger percpu counter batch values for stats counters Cc: kosaki.motohiro@jp.fujitsu.com, Peter Zijlstra , Ingo Molnar , mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, schwidefsky@de.ibm.com, balajirrao@gmail.com, dhaval@linux.vnet.ibm.com, balbir@linux.vnet.ibm.com, bharata@linux.vnet.ibm.com, tglx@linutronix.de, kamezawa.hiroyu@jp.fujitsu.com, linux-tip-commits@vger.kernel.org In-Reply-To: <20090512190346.D638.A69D9226@jp.fujitsu.com> References: <1242122579.11251.325.camel@twins> <20090512190346.D638.A69D9226@jp.fujitsu.com> Message-Id: <20090512191650.D63E.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.50.07 [ja] Date: Tue, 12 May 2009 19:22:36 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > > On Tue, 2009-05-12 at 19:01 +0900, KOSAKI Motohiro wrote: > > > +#ifdef CONFIGCONFIG_SMP > > > > typo ? > > yes, this week is my memorial stupid one ;) ok, assemble list indicate current patch have no typo ;) ffffffff814ae920: 48 c7 40 30 10 eb 2a movq $0xffffffff812aeb10,0x30(%rax) ffffffff814ae927: 81 ffffffff814ae928: c7 05 3e 37 fe ff 01 movl $0x1,-0x1c8c2(%rip) # ffffffff81492070 ffffffff814ae92f: 00 00 00 ffffffff814ae932: 8b 05 28 52 fe ff mov -0x1add8(%rip),%eax # ffffffff81493b60 ffffffff814ae938: 89 05 36 37 fe ff mov %eax,-0x1c8ca(%rip) # ffffffff81492074 ffffffff814ae93e: 41 5c pop %r12 --------------------------------------------------------- Subject: [PATCH] cpuacct: Use bigger percpu counter batch values for stats counters on archs that have VIRT_CPU_ACCOUNTING=y percpu counters used to accumulate statistics in cpuacct controller use the default batch value [max(2*nr_cpus, 32)] which can be too small for archs that define VIRT_CPU_ACCOUNTING. In such archs, a tick could result in cputime updates in the range of thousands. As a result, cpuacct_update_stats() would end up acquiring the percpu counter spinlock on every tick which is not good for performance. Let those architectures to have a bigger batch threshold so that percpu counter spinlock isn't taken on every tick. This change doesn't affect the archs which don't define VIRT_CPU_ACCOUNTING and they continue to have the default percpu counter batch value. Cc: Balaji Rao Cc: Dhaval Giani Cc: KAMEZAWA Hiroyuki Cc: Peter Zijlstra Cc: Balbir Singh Cc: Ingo Molnar Cc: Martin Schwidefsky Signed-off-by: Bharata B Rao Signed-off-by: KOSAKI Motohiro --- kernel/sched.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) Index: b/kernel/sched.c =================================================================== --- a/kernel/sched.c 2009-05-12 13:12:59.000000000 +0900 +++ b/kernel/sched.c 2009-05-12 19:04:49.000000000 +0900 @@ -870,6 +870,8 @@ static __read_mostly int scheduler_runni */ int sysctl_sched_rt_runtime = 950000; +static __read_mostly s32 cpuacct_batch; + static inline u64 global_rt_period(void) { return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; @@ -9284,6 +9286,10 @@ void __init sched_init(void) perf_counter_init(); +#ifdef CONFIG_SMP + cpuacct_batch = jiffies_to_cputime(percpu_counter_batch); +#endif + scheduler_running = 1; } @@ -10457,7 +10463,8 @@ static void cpuacct_update_stats(struct ca = task_ca(tsk); do { - percpu_counter_add(&ca->cpustat[idx], val); + __percpu_counter_add(&ca->cpustat[idx], val, cpuacct_batch); + ca = ca->parent; } while (ca); rcu_read_unlock();