From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751963Ab2GZJho (ORCPT ); Thu, 26 Jul 2012 05:37:44 -0400 Received: from mailout-de.gmx.net ([213.165.64.22]:42609 "HELO mailout-de.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751206Ab2GZJhn (ORCPT ); Thu, 26 Jul 2012 05:37:43 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX18TyTIHE9QTjUYKlPRAc3gYU0Dp9B4zbgJEKNZKDF uysFxXUY2M1Fgt Message-ID: <1343295457.6863.43.camel@marge.simpson.net> Subject: Re: [PATCH 1/2] sched: recover SD_WAKE_AFFINE in select_task_rq_fair and code clean up From: Mike Galbraith To: Alex Shi Cc: mingo@redhat.com, peterz@infradead.org, linux-kernel@vger.kernel.org, suresh.b.siddha@intel.com Date: Thu, 26 Jul 2012 11:37:37 +0200 In-Reply-To: <1343280446-24019-1-git-send-email-alex.shi@intel.com> References: <1343280446-24019-1-git-send-email-alex.shi@intel.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 X-Y-GMX-Trusted: 0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2012-07-26 at 13:27 +0800, Alex Shi wrote: > if (affine_sd) { > - if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) > + if (wake_affine(affine_sd, p, sync)) > prev_cpu = cpu; > > new_cpu = select_idle_sibling(p, prev_cpu); Hm, if cpu == prev_cpu, asking wake_affine() if it's ok to put wakee back where it came from is wasted cycles.. that's where the task is headed regardless of reply. -Mike