Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752035AbaFXHxv (ORCPT ); Tue, 24 Jun 2014 03:53:51 -0400 Received: from relay.parallels.com ([195.214.232.42]:42482 "EHLO relay.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751257AbaFXHxu (ORCPT ); Tue, 24 Jun 2014 03:53:50 -0400 Message-ID: <1403596424.3462.25.camel@tkhai> Subject: [PATCH v2 0/3] Fix shutdown of cpu which having throttled rq From: Kirill Tkhai To: CC: Peter Zijlstra , Ingo Molnar , , Srikar Dronamraju , "Mike Galbraith" , , Ben Segall , Paul Turner Date: Tue, 24 Jun 2014 11:53:44 +0400 Organization: Parallels Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.8.5-2+b3 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Originating-IP: [10.30.26.172] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is a result of discussion "[PATCH 1/2] sched: Rework migrate_tasks()": https://lkml.org/lkml/2014/6/11/166 The problem is cfs_rq and rt_rq may stay throttled in the moment of task migration from dead cpu. This patch fixes that for fair and RT classes. No fix for deadline class yet, it's coming soon. v2: [1/3]Collision with tg_set_cfs_bandwidth() found by Ben Segall. Code movement. --- Kirill Tkhai (3): sched/fair: Disable runtime_enabled on dying rq sched/rt: __disable_runtime: Enqueue just unthrottled rt_rq back on the stack sched: Rework check_for_tasks() kernel/cpu.c | 33 ++++++++++++++++++++------------- kernel/sched/core.c | 15 +++++++++++---- kernel/sched/fair.c | 22 ++++++++++++++++++++++ kernel/sched/rt.c | 3 +++ 4 files changed, 56 insertions(+), 17 deletions(-) -- Signed-off-by: Kirill Tkhai -- 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/