From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753842AbaFXTNy (ORCPT ); Tue, 24 Jun 2014 15:13:54 -0400 Received: from mail-pb0-f48.google.com ([209.85.160.48]:36840 "EHLO mail-pb0-f48.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752712AbaFXTNx (ORCPT ); Tue, 24 Jun 2014 15:13:53 -0400 From: bsegall@google.com To: tkhai@yandex.ru Cc: Kirill Tkhai , linux-kernel@vger.kernel.org, Peter Zijlstra , Ingo Molnar , Srikar Dronamraju , Mike Galbraith , khorenko@parallels.com, Paul Turner Subject: Re: [PATCH v2 1/3] sched/fair: Disable runtime_enabled on dying rq References: <20140624074148.8738.57690.stgit@tkhai> <1403596432.3462.26.camel@tkhai> <53A9CB23.1080708@yandex.ru> Date: Tue, 24 Jun 2014 12:13:50 -0700 In-Reply-To: <53A9CB23.1080708@yandex.ru> (Kirill Tkhai's message of "Tue, 24 Jun 2014 23:01:55 +0400") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Kirill Tkhai writes: > On 24.06.2014 21:03, bsegall@google.com wrote: >> Kirill Tkhai writes: >> >>> We kill rq->rd on the CPU_DOWN_PREPARE stage: >>> >>> cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains -> >>> -> cpu_attach_domain -> rq_attach_root -> set_rq_offline >>> >>> This unthrottles all throttled cfs_rqs. >>> >>> But the cpu is still able to call schedule() till >>> >>> take_cpu_down->__cpu_disable() >>> >>> is called from stop_machine. >>> >>> This case the tasks from just unthrottled cfs_rqs are pickable >>> in a standard scheduler way, and they are picked by dying cpu. >>> The cfs_rqs becomes throttled again, and migrate_tasks() >>> in migration_call skips their tasks (one more unthrottle >>> in migrate_tasks()->CPU_DYING does not happen, because rq->rd >>> is already NULL). >>> >>> Patch sets runtime_enabled to zero. This guarantees, the runtime >>> is not accounted, and the cfs_rqs won't exceed given >>> cfs_rq->runtime_remaining = 1, and tasks will be pickable >>> in migrate_tasks(). runtime_enabled is recalculated again >>> when rq becomes online again. >>> >>> Ben Segall also noticed, we always enable runtime in >>> tg_set_cfs_bandwidth(). Actually, we should do that for online >>> cpus only. To fix that, we check if a cpu is online when >>> its rq is locked. This guarantees we do not have races with >>> set_rq_offline(), which also requires rq->lock. >>> >>> v2: Fix race with tg_set_cfs_bandwidth(). >>> Move cfs_rq->runtime_enabled=0 above unthrottle_cfs_rq(). >>> >>> Signed-off-by: Kirill Tkhai >>> CC: Konstantin Khorenko >>> CC: Ben Segall >>> CC: Paul Turner >>> CC: Srikar Dronamraju >>> CC: Mike Galbraith >>> CC: Peter Zijlstra >>> CC: Ingo Molnar >>> --- >>> kernel/sched/core.c | 15 +++++++++++---- >>> kernel/sched/fair.c | 22 ++++++++++++++++++++++ >>> 2 files changed, 33 insertions(+), 4 deletions(-) >>> >>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c >>> index 7f3063c..707a3c5 100644 >>> --- a/kernel/sched/core.c >>> +++ b/kernel/sched/core.c >>> @@ -7842,11 +7842,18 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) >>> struct rq *rq = cfs_rq->rq; >>> >>> raw_spin_lock_irq(&rq->lock); >>> - cfs_rq->runtime_enabled = runtime_enabled; >>> - cfs_rq->runtime_remaining = 0; >>> + /* >>> + * Do not enable runtime on offline runqueues. We specially >>> + * make it disabled in unthrottle_offline_cfs_rqs(). >>> + */ >>> + if (cpu_online(i)) { >>> + cfs_rq->runtime_enabled = runtime_enabled; >>> + cfs_rq->runtime_remaining = 0; >>> + >>> + if (cfs_rq->throttled) >>> + unthrottle_cfs_rq(cfs_rq); >>> + } >> >> We can just do for_each_online_cpu, yes? Also we probably need >> get_online_cpus/put_online_cpus, and/or want cpu_active_mask instead >> right? >> > > Yes, we can use for_each_online_cpu/for_each_active_cpu with > get_online_cpus() taken. But it adds one more lock dependence. > This looks worse for me. I mean, you need get_online_cpus anyway - cpu_online is just a test against the same mask that for_each_online_cpu uses, and without taking the lock you can still race with offlining and reset runtime_enabled.