Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753134AbaGJN6m (ORCPT ); Thu, 10 Jul 2014 09:58:42 -0400 Received: from mail-ob0-f174.google.com ([209.85.214.174]:36268 "EHLO mail-ob0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751051AbaGJN6k (ORCPT ); Thu, 10 Jul 2014 09:58:40 -0400 MIME-Version: 1.0 In-Reply-To: <20140710110644.GX3935@laptop> References: <1404144343-18720-1-git-send-email-vincent.guittot@linaro.org> <1404144343-18720-8-git-send-email-vincent.guittot@linaro.org> <20140710110644.GX3935@laptop> From: Vincent Guittot Date: Thu, 10 Jul 2014 15:58:20 +0200 Message-ID: Subject: Re: [PATCH v3 07/12] sched: test the cpu's capacity in wake affine To: Peter Zijlstra Cc: Ingo Molnar , linux-kernel , Russell King - ARM Linux , LAK , Preeti U Murthy , Morten Rasmussen , Mike Galbraith , Nicolas Pitre , "linaro-kernel@lists.linaro.org" , Daniel Lezcano , Dietmar Eggemann Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 10 July 2014 13:06, Peter Zijlstra wrote: > On Mon, Jun 30, 2014 at 06:05:38PM +0200, Vincent Guittot wrote: >> Currently the task always wakes affine on this_cpu if the latter is idle. >> Before waking up the task on this_cpu, we check that this_cpu capacity is not >> significantly reduced because of RT tasks or irq activity. >> >> Use case where the number of irq and/or the time spent under irq is important >> will take benefit of this because the task that is woken up by irq or softirq >> will not use the same CPU than irq (and softirq) but a idle one which share >> its cache. > > The above, doesn't seem to explain: > >> + } else if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) { >> + this_eff_load = 0; >> + } >> + >> + balanced = this_eff_load <= prev_eff_load; > > this. Why would you unconditionally allow wake_affine across cache > domains? The current policy is to use this_cpu if this_load <= 0. I want to keep the current wake affine policy for all sched_domain that doesn't share cache so if the involved CPUs don't share cache, I clear this_eff_load to force balanced to be true. But when CPUs share their cache, we not only look at idleness but also at available capacity of prev and local CPUs. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/