From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752241AbZH0PJi (ORCPT ); Thu, 27 Aug 2009 11:09:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751947AbZH0PJh (ORCPT ); Thu, 27 Aug 2009 11:09:37 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:39827 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751726AbZH0PJW (ORCPT ); Thu, 27 Aug 2009 11:09:22 -0400 Message-Id: <20090827150524.077452157@chello.nl> References: <20090827150051.846026837@chello.nl> User-Agent: quilt/0.46-1 Date: Thu, 27 Aug 2009 17:00:55 +0200 From: Peter Zijlstra To: Ingo Molnar Cc: linux-kernel@vger.kernel.org, Gautham R Shenoy , Andreas Herrmann , Balbir Singh , Peter Zijlstra Subject: [RFC][PATCH 4/6] sched: dynamic cpu_power Content-Disposition: inline; filename=sched-lb-4.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Recompute the cpu_power for each cpu during load-balance Signed-off-by: Peter Zijlstra LKML-Reference: --- kernel/sched.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) Index: linux-2.6/kernel/sched.c =================================================================== --- linux-2.6.orig/kernel/sched.c +++ linux-2.6/kernel/sched.c @@ -3691,14 +3691,46 @@ static inline int check_power_save_busie } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static void update_sched_power(struct sched_domain *sd) +unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long smt_gain = sd->smt_gain; + + smt_gain /= weight; + + return smt_gain; +} + +static void update_cpu_power(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long power = SCHED_LOAD_SCALE; + struct sched_group *sdg = sd->groups; + unsigned long old = sdg->__cpu_power; + + /* here we could scale based on cpufreq */ + + if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { + power *= arch_smt_gain(sd, cpu); + power >>= SCHED_LOAD_SHIFT; + } + + /* here we could scale based on RT time */ + + if (power != old) { + sdg->__cpu_power = power; + sdg->reciprocal_cpu_power = reciprocal_value(power); + } +} + +static void update_group_power(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; unsigned long power = sdg->__cpu_power; if (!child) { - /* compute cpu power for this cpu */ + update_cpu_power(sd, cpu); return; } @@ -3743,7 +3775,7 @@ static inline void update_sg_lb_stats(st if (local_group) { balance_cpu = group_first_cpu(group); if (balance_cpu == this_cpu) - update_sched_power(sd); + update_group_power(sd, this_cpu); } /* Tally up the load of all CPUs in the group */ --