From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753895Ab1LLTVW (ORCPT ); Mon, 12 Dec 2011 14:21:22 -0500 Received: from mail-ee0-f46.google.com ([74.125.83.46]:53709 "EHLO mail-ee0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752023Ab1LLTVV (ORCPT ); Mon, 12 Dec 2011 14:21:21 -0500 From: Vincent Guittot To: linux-kernel@vger.kernel.org, linaro-dev@lists.linaro.org, a.p.zijlstra@chello.nl Cc: patches@linaro.org, Vincent Guittot Subject: [RFC] sched: Ensure cpu_power periodic update Date: Mon, 12 Dec 2011 20:21:08 +0100 Message-Id: <1323717668-2143-1-git-send-email-vincent.guittot@linaro.org> X-Mailer: git-send-email 1.7.4.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org With a lot of small tasks, the softirq sched is nearly never called when no_hz is enable. In this case the load_balance is mainly called with the newly_idle mode which doesn't update the cpu_power. Add a next_update field which ensure a maximum update period when there is short activity Signed-off-by: Vincent Guittot --- include/linux/sched.h | 1 + kernel/sched/fair.c | 24 ++++++++++++++++-------- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 64527c4..7178446 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -903,6 +903,7 @@ struct sched_group_power { * single CPU. */ unsigned int power, power_orig; + unsigned long next_update; /* * Number of busy cpus in this group. */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4d2b7a..809f484 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -215,6 +215,8 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, const struct sched_class fair_sched_class; +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + /************************************************************** * CFS operations on generic schedulable entities: */ @@ -3786,6 +3788,11 @@ 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; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgp->next_update = jiffies + interval; if (!child) { update_cpu_power(sd, cpu); @@ -3893,12 +3900,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * domains. In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ - if (idle != CPU_NEWLY_IDLE && local_group) { - if (balance_cpu != this_cpu) { - *balance = 0; - return; - } - update_group_power(sd, this_cpu); + if (local_group) { + if (idle != CPU_NEWLY_IDLE) { + if (balance_cpu != this_cpu) { + *balance = 0; + return; + } + update_group_power(sd, this_cpu); + } else if (time_after_eq(jiffies, group->sgp->next_update)) + update_group_power(sd, this_cpu); } /* Adjust by relative CPU power of the group */ @@ -4917,8 +4927,6 @@ void select_nohz_load_balancer(int stop_tick) static DEFINE_SPINLOCK(balancing); -static unsigned long __read_mostly max_load_balance_interval = HZ/10; - /* * Scale the max load_balance interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. -- 1.7.4.1