From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756326AbXFPKZz (ORCPT ); Sat, 16 Jun 2007 06:25:55 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753847AbXFPKYP (ORCPT ); Sat, 16 Jun 2007 06:24:15 -0400 Received: from www.osadl.org ([213.239.205.134]:37171 "EHLO mail.tglx.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753338AbXFPKYK (ORCPT ); Sat, 16 Jun 2007 06:24:10 -0400 Message-Id: <20070616101636.794026871@inhelltoy.tec.linutronix.de> References: <20070616101126.296384219@inhelltoy.tec.linutronix.de> User-Agent: quilt/0.46-1 Date: Sat, 16 Jun 2007 10:36:07 -0000 From: Thomas Gleixner To: LKML Cc: Andrew Morton , Ingo Molnar , Andi Kleen , Chris Wright , Arjan van de Ven , Venkatesh Pallipadi , john stultz Subject: [patch-mm 07/25] Tick management: spread timer interrupt Content-Disposition: inline; filename=tick-spread-timer-interrupts.patch Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org 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 2007-06-16 12:10:21.000000000 +0200 +++ linux-2.6.22-rc4-mm/kernel/time/tick-sched.c 2007-06-16 12:10:23.000000000 +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); + 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); --