From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751279AbdAQIOW (ORCPT ); Tue, 17 Jan 2017 03:14:22 -0500 Received: from mx2.suse.de ([195.135.220.15]:53034 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750888AbdAQINL (ORCPT ); Tue, 17 Jan 2017 03:13:11 -0500 Subject: Re: getting oom/stalls for ltp test cpuset01 with latest/4.9 kernel To: Ganapatrao Kulkarni References: <075075cc-3149-0df3-dd45-a81df1f1a506@suse.cz> <0ea1cfeb-7c4a-3a3e-9be9-967298ba303c@suse.cz> <20170111164616.GJ16365@dhcp22.suse.cz> <45ed555a-c6a3-fc8e-1e87-c347c8ed086b@suse.cz> <89fec1bd-52b7-7861-2e02-a719c5631610@suse.cz> Cc: Michal Hocko , linux-mm@kvack.org, "linux-kernel@vger.kernel.org" , Mel Gorman From: Vlastimil Babka Message-ID: <7c8ed170-ced9-aa6a-25e0-47cdc6d66eb2@suse.cz> Date: Tue, 17 Jan 2017 09:13:09 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.6.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 01/16/2017 02:22 PM, Vlastimil Babka wrote: >>> >>> no_zone: >>> -- >>> 2.11.0 >>> >> >> this patch did not fix the issue. >> issue still exists! > > Hmm, that's unfortunate. > >> i did bisect and this test passes in 4.4,4.5 and 4.6 >> test failing since 4.7-rc1 > > 4.7 would match the commit I was trying to fix. But I don't see other > problems now. Could you bisect to a single commit then, to be sure? Thanks. Ah, nevermind, I can reproduce the issue easily. After some more poking I now think the bisect would lead to the OOM rework, but it would be a red herring. Seems like this is an interaction between bind mempolicy and cpuset and I see several potential bugs in that area. Which also means there's a non-null nodemask and thus the code in the commit I originally suspected (replacing NULL nodemask with cpuset's mems_allowed) doesn't trigger at all here. Thanks, Vlastimil >> thanks >> Ganapat >>> >>> >>> > > -- > To unsubscribe, send a message with 'unsubscribe linux-mm' in > the body to majordomo@kvack.org. For more info on Linux MM, > see: http://www.linux-mm.org/ . > Don't email: email@kvack.org >