From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752101AbdBJJWl (ORCPT ); Fri, 10 Feb 2017 04:22:41 -0500 Received: from szxga03-in.huawei.com ([119.145.14.66]:23214 "EHLO szxga03-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751045AbdBJJWY (ORCPT ); Fri, 10 Feb 2017 04:22:24 -0500 Subject: Re: [RFC] 3.10 kernel- oom with about 24G free memory To: Michal Hocko References: <9a22aefd-dfb8-2e4c-d280-fc172893bcb4@huawei.com> <20170209132628.GI10257@dhcp22.suse.cz> <20170209134131.GJ10257@dhcp22.suse.cz> <20170210070930.GA9346@dhcp22.suse.cz> <7d01fea5-66d6-b6ac-918d-19ec8a15dbaf@huawei.com> <20170210085232.GD10893@dhcp22.suse.cz> CC: Vlastimil Babka , , , Tetsuo Handa , Hanjun Guo From: Yisheng Xie Message-ID: <42e61739-ddfb-e13e-69e0-d1c1ac948a6d@huawei.com> Date: Fri, 10 Feb 2017 17:15:59 +0800 User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.1.0 MIME-Version: 1.0 In-Reply-To: <20170210085232.GD10893@dhcp22.suse.cz> Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit X-Originating-IP: [10.177.29.40] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Michal, Thanks for comment! On 2017/2/10 16:52, Michal Hocko wrote: > On Fri 10-02-17 16:48:58, Yisheng Xie wrote: >> Hi Michal, >> >> Thanks for comment! >> On 2017/2/10 15:09, Michal Hocko wrote: >>> On Fri 10-02-17 09:13:58, Yisheng Xie wrote: >>>> hi Michal, >>>> Thanks for your comment. >>>> >>>> On 2017/2/9 21:41, Michal Hocko wrote: > [...] >>>>>> OK, so this is a memcg OOM killer which panics because the configuration >>>>>> says so. The OOM report doesn't say so and that is the bug. dump_header >>>>>> is memcg aware and mem_cgroup_out_of_memory initializes oom_control >>>>>> properly. Is this Vanilla kernel? >>>> >>>> That means we should raise the limit of that memcg to avoid memcg OOM killer, right? >>> >>> Why do you configure the system to panic on memcg OOM in the first >>> place. This is a wrong thing to do in 99% of cases. >> >> For our production think it should use reboot to recovery the system when OOM, >> instead of killing user's key process. Maybe not the right thing. > > I can understand that for the global oom killer but not for memcg. You > can recover the oom even without killing any process. You can simply > increase the limit from the userspace when the oom event is triggered. So you mean set oom_kill_disable and increase the limit from userspace when memcg under_oom, right? Thanks Yisheng Xie. > > Trigerring the panic on memcg oom killer is both dangerous and most > probably something you do not want. >