From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754894AbXFZALz (ORCPT ); Mon, 25 Jun 2007 20:11:55 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751941AbXFZALs (ORCPT ); Mon, 25 Jun 2007 20:11:48 -0400 Received: from smtp2.linux-foundation.org ([207.189.120.14]:43307 "EHLO smtp2.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751272AbXFZALr (ORCPT ); Mon, 25 Jun 2007 20:11:47 -0400 Date: Mon, 25 Jun 2007 17:11:15 -0700 From: Andrew Morton To: Thomas Gleixner Cc: Andi Kleen , Ingo Molnar , Arjan van de Ven , Venkatesh Pallipadi , John Stultz , Chris Wright , LKML Subject: Re: [patch -mm 09/28] Tick management: spread timer interrupt Message-Id: <20070625171115.73a42e93.akpm@linux-foundation.org> In-Reply-To: <20070623124030.531042944@inhelltoy.tec.linutronix.de> References: <20070623124005.931747831@inhelltoy.tec.linutronix.de> <20070623124030.531042944@inhelltoy.tec.linutronix.de> X-Mailer: Sylpheed version 2.2.7 (GTK+ 2.8.6; i686-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 23 Jun 2007 13:32:34 -0000 Thomas Gleixner wrote: > From: john stultz > > After discussing w/ Thomas over IRC, it seems the issue is the sched > tick fires on every cpu at the same time, causing extra lock contention. > > This smaller change, adds an extra offset per cpu so the ticks don't > line up. This patch also drops the idle latency from 40us down to under > 20us. > > Signed-off-by: john stultz > Signed-off-by: Thomas Gleixner > > --- > kernel/time/tick-sched.c | 7 ++++++- > 1 file changed, 6 insertions(+), 1 deletion(-) > > Index: linux-2.6.22-rc4-mm/kernel/time/tick-sched.c > =================================================================== > --- linux-2.6.22-rc4-mm.orig/kernel/time/tick-sched.c 2007-06-23 14:38:56.000000000 +0200 > +++ linux-2.6.22-rc4-mm/kernel/time/tick-sched.c 2007-06-23 14:38:58.000000000 +0200 > @@ -573,6 +573,7 @@ void tick_setup_sched_timer(void) > { > struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); > ktime_t now = ktime_get(); > + u64 offset; > > /* > * Emulate tick processing via per-CPU hrtimers: > @@ -581,8 +582,12 @@ void tick_setup_sched_timer(void) > ts->sched_timer.function = tick_sched_timer; > ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; > > - /* Get the next period */ > + /* Get the next period (per cpu) */ > ts->sched_timer.expires = tick_init_jiffy_update(); > + offset = ktime_to_ns(tick_period) >> 1; > + do_div(offset, NR_CPUS); With CONFIG_NR_CPUS=128 on a 2-way this'll be a pretty lumpy spreading? Perhaps it woud be better to use num_possible_cpus() here? > + offset *= smp_processor_id(); > + ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset); > > for (;;) { > hrtimer_forward(&ts->sched_timer, now, tick_period); > > --