From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751410AbZCIM4t (ORCPT ); Mon, 9 Mar 2009 08:56:49 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751256AbZCIM41 (ORCPT ); Mon, 9 Mar 2009 08:56:27 -0400 Received: from casper.infradead.org ([85.118.1.10]:36099 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751185AbZCIM4Z (ORCPT ); Mon, 9 Mar 2009 08:56:25 -0400 Subject: [PATCH] sched: optimize ttwu vs group scheduling From: Peter Zijlstra To: Ingo Molnar Cc: lkml Content-Type: text/plain Date: Mon, 09 Mar 2009 13:56:21 +0100 Message-Id: <1236603381.8389.455.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.25.92 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org We can avoid the sched domain walk on try_to_wake_up() when we know there are no groups. Signed-off-by: Peter Zijlstra --- kernel/sched.c | 16 +++++++++++++++- 1 files changed, 15 insertions(+), 1 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 4414926..188ce3d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -331,6 +331,13 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; */ static DEFINE_SPINLOCK(task_group_lock); +#ifdef CONFIG_SMP +static int root_task_group_empty(void) +{ + return list_empty(&root_task_group->children); +} +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_USER_SCHED # define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) @@ -391,6 +398,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #else +#ifdef CONFIG_SMP +static int root_task_group_empty(void) +{ + return 1; +} +#endif + static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } static inline struct task_group *task_group(struct task_struct *p) { @@ -2363,7 +2377,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) sync = 0; #ifdef CONFIG_SMP - if (sched_feat(LB_WAKEUP_UPDATE)) { + if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) { struct sched_domain *sd; this_cpu = raw_smp_processor_id();