From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753738Ab3FIJRX (ORCPT ); Sun, 9 Jun 2013 05:17:23 -0400 Received: from szxga02-in.huawei.com ([119.145.14.65]:49335 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751071Ab3FIJRV (ORCPT ); Sun, 9 Jun 2013 05:17:21 -0400 Message-ID: <51B447FE.7060905@huawei.com> Date: Sun, 9 Jun 2013 17:16:46 +0800 From: Li Zefan User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:17.0) Gecko/20130509 Thunderbird/17.0.6 MIME-Version: 1.0 To: Tejun Heo CC: Cgroups , LKML , Containers Subject: [PATCH v3 6/7] cpuset: allow to move tasks to empty cpusets References: <51B4475A.8030509@huawei.com> In-Reply-To: <51B4475A.8030509@huawei.com> Content-Type: text/plain; charset="GB2312" Content-Transfer-Encoding: 7bit X-Originating-IP: [10.135.68.215] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Currently some cpuset behaviors are not friendly when cpuset is co-mounted with other cgroup controllers. Now with this patchset if cpuset is mounted with sane_behavior option, it behaves differently: - Tasks will be kept in empty cpusets when hotplug happens and take masks of ancestors with non-empty cpus/mems, instead of being moved to an ancestor. - A task can be moved into an empty cpuset, and again it takes masks of ancestors, so the user can drop a task into a newly created cgroup without having to do anything for it. As tasks can reside in empy cpusets, here're some rules: - They can be moved to another cpuset, regardless it's empty or not. - Though it takes masks from ancestors, it takes other configs from the empty cpuset. - If the ancestors' masks are changed, those tasks will also be updated to take new masks. v2: add documentation in include/linux/cgroup.h Signed-off-by: Li Zefan --- include/linux/cgroup.h | 3 +++ kernel/cpuset.c | 9 +++++++-- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 53e81a6..74e8b8e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -281,6 +281,9 @@ enum { * and take masks of ancestors with non-empty cpus/mems, instead of * being moved to an ancestor. * + * - cpuset: a task can be moved into an empty cpuset, and again it + * takes masks of ancestors. + * * - memcg: use_hierarchy is on by default and the cgroup file for * the flag is not created. * diff --git a/kernel/cpuset.c b/kernel/cpuset.c index fd7572f..d1d6782 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -479,7 +479,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) */ ret = -ENOSPC; if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress) && - (cpumask_empty(trial->cpus_allowed) || + (cpumask_empty(trial->cpus_allowed) && nodes_empty(trial->mems_allowed))) goto out; @@ -1466,8 +1466,13 @@ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) mutex_lock(&cpuset_mutex); + /* + * We allow to move tasks into an empty cpuset if sane_behavior + * flag is set. + */ ret = -ENOSPC; - if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + if (!cgroup_sane_behavior(cgrp) && + (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, cgrp, tset) { -- 1.8.0.2