From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753691Ab2INFsV (ORCPT ); Fri, 14 Sep 2012 01:48:21 -0400 Received: from mga02.intel.com ([134.134.136.20]:23161 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751430Ab2INFsT (ORCPT ); Fri, 14 Sep 2012 01:48:19 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.80,421,1344236400"; d="scan'208";a="203627608" From: Alex Shi To: mingo@redhat.com, peterz@infradead.org, tglx@linutronix.de, suresh.b.siddha@intel.com, venki@google.com Cc: linux-kernel@vger.kernel.org Subject: [PATCH v2 3/3] sched/balance: remove on_null_domain() in trigger_load_balance Date: Fri, 14 Sep 2012 13:47:25 +0800 Message-Id: <1347601645-20139-4-git-send-email-alex.shi@intel.com> X-Mailer: git-send-email 1.7.12 In-Reply-To: <1347601645-20139-1-git-send-email-alex.shi@intel.com> References: <1347601645-20139-1-git-send-email-alex.shi@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org According to Suresh's inverstigation, the first on_null_domain in trigger_load_balance is for avoiding unnecessary loadbalances(from softirq) when a SMP kernel running on UP machine. The second on_null_domain is not needed, since nohz_kick_needed() will return 0 in this scenario. So, remove the 2nd on_null_domain calling. Signed-off-by: Alex Shi --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 60d5505..1ae2c66 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4938,7 +4938,7 @@ void trigger_load_balance(struct rq *rq, int cpu) likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); #ifdef CONFIG_NO_HZ - if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) + if (nohz_kick_needed(rq, cpu)) nohz_balancer_kick(cpu); #endif } -- 1.7.12