From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753189AbdHNMEZ (ORCPT ); Mon, 14 Aug 2017 08:04:25 -0400 Received: from mx0b-00082601.pphosted.com ([67.231.153.30]:57791 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753002AbdHNMEW (ORCPT ); Mon, 14 Aug 2017 08:04:22 -0400 Date: Mon, 14 Aug 2017 13:03:49 +0100 From: Roman Gushchin To: David Rientjes CC: Michal Hocko , , Vladimir Davydov , Johannes Weiner , Tetsuo Handa , Tejun Heo , , , , Subject: Re: [v4 2/4] mm, oom: cgroup-aware OOM killer Message-ID: <20170814120349.GA24393@castle.DHCP.thefacebook.com> References: <20170726132718.14806-1-guro@fb.com> <20170726132718.14806-3-guro@fb.com> <20170801145435.GN15774@dhcp22.suse.cz> <20170801152548.GA29502@castle.dhcp.TheFacebook.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.8.3 (2017-05-23) X-Originating-IP: [2620:10d:c092:200::1:aa9f] X-ClientProxiedBy: HE1PR05CA0207.eurprd05.prod.outlook.com (2603:10a6:3:f9::31) To BL2PR15MB1076.namprd15.prod.outlook.com (2603:10b6:201:17::10) X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-Correlation-Id: 010c89c4-79b4-4058-472a-08d4e30c8f25 X-Microsoft-Antispam: UriScan:;BCL:0;PCL:0;RULEID:(300000500095)(300135000095)(300000501095)(300135300095)(22001)(300000502095)(300135100095)(2017030254152)(300000503095)(300135400095)(201703131423075)(201703031133081)(201702281549075)(300000504095)(300135200095)(300000505095)(300135600095)(300000506095)(300135500095);SRVR:BL2PR15MB1076; X-Microsoft-Exchange-Diagnostics: 1;BL2PR15MB1076;3:H19ptWXSTVq2Md1GkkaBCum9Va4m9b/cYJ2QpBMz99vD1/XiPF25WUaQPPFfnD5yoY+Srj1Bv8lyhEMAyZBCnaPXhsi9iD11sE26x9I5tV7Gtg5jvHVm5y2itjy3RzNSRH/rSVB0f4BHI691olNfQrvg9bhnNqkC6C8GksdfbDUg6312gtYhq17dYWLa8f2i2M/jIkQmBvgh3/oiZR/z2CPptyeuOPbbrKNS1zI8KsvMx1Js/kkPu0s1sivUCRLg;25:cw/yjl5VqIYf3tsJzQcdnYiHD1XwjO250IP6AXdeADxzKvt5UJEmjXA0z5nXBn5PPzeUhgq6Z0INbFllOJ/GYpp7cfYqKrwfhPPar1m3rmfMub7dDtMU0ENVnxuDTReyhsF4bG88Lco+b2jshtwk2UDIJxhCGYGXGbO7R4SEo/oH1I0kBrqKP/u7olmxPnyb1PG/Yf+oSbHGdweBHoXEPQyU6RE/SVBMkMlLeU0v6kTIeWgvzWU4fuYEFcMTnE3noTZqu8JS3W84agnBaBTxf5w+0JhrVGz67Ye/kAwMjD/g1mHvYDQgcU+heSAeJUU3UYIProMjtoFGPYNZbx/HCQ==;31:QagJQOwX0dMoCseTg1YcYM2o8Qra9VuvnVlMO/7MkDLPMbW/F8s56Ud6dkBCIeezQUq/6k0HnZksQJEGBQZJ9BGe+dXldK7oz8tps4ZbVrXK1px2QKzJP6t8QYbHf9svLRtHI0GU2EyhK6HNzqM0DvfxlVMuLU+frJzdOyvEo55y9j3y945Z/wbEt9iNBaXaVHTccpGxEKCRpjPWP0sNo79Z6VAl8TJXEUjheWsmcyM= X-MS-TrafficTypeDiagnostic: BL2PR15MB1076: X-Microsoft-Exchange-Diagnostics: 1;BL2PR15MB1076;20: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;4:a9maenc/sTp+KDcfCyesFTPPSUsXMTj/RlQhYmC+NzlVb7ndkcL9hSeAcafN1B4VqvPE46+gjXIct5AoppPUtmjpeuoPhVtX2t9XZX1R0Vz2AWEpQ0qwEthZdUrTqNG8V5veuTo4PZ3uv1o+dl7jpDogYyW4zApd16d5V9OjusnHwLwBNob443oIY2H/ERTw6McsvpIzwStErUXomzNlWYxRV1ARaGqYd2mfXOxzoChbb9DhR3Q4n32Dnem55MB3 X-Exchange-Antispam-Report-Test: UriScan:; X-Microsoft-Antispam-PRVS: X-Exchange-Antispam-Report-CFA-Test: BCL:0;PCL:0;RULEID:(100000700101)(100105000095)(100000701101)(100105300095)(100000702101)(100105100095)(6040450)(601004)(2401047)(5005006)(8121501046)(3002001)(10201501046)(100000703101)(100105400095)(93006095)(93001095)(6041248)(20161123555025)(20161123562025)(20161123560025)(20161123564025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123558100)(6072148)(201708071742011)(100000704101)(100105200095)(100000705101)(100105500095);SRVR:BL2PR15MB1076;BCL:0;PCL:0;RULEID:(100000800101)(100110000095)(100000801101)(100110300095)(100000802101)(100110100095)(100000803101)(100110400095)(100000804101)(100110200095)(100000805101)(100110500095);SRVR:BL2PR15MB1076; X-Forefront-PRVS: 039975700A X-Forefront-Antispam-Report: SFV:NSPM;SFS:(10019020)(7370300001)(4630300001)(6009001)(189002)(199003)(24454002)(1076002)(54906002)(6506006)(2906002)(76176999)(50986999)(33656002)(4326008)(54356999)(4001350100001)(55016002)(42186005)(50466002)(7416002)(6116002)(5660300001)(105586002)(106356001)(229853002)(101416001)(81156014)(8676002)(81166006)(6246003)(68736007)(23726003)(478600001)(6666003)(110136004)(93886004)(7736002)(53936002)(97736004)(83506001)(6916009)(345774005)(2950100002)(189998001)(86362001)(47776003)(9686003)(305945005)(7350300001)(25786009)(18370500001)(42262002);DIR:OUT;SFP:1102;SCL:1;SRVR:BL2PR15MB1076;H:castle.DHCP.thefacebook.com;FPR:;SPF:None;PTR:InfoNoRecords;MX:1;A:1;LANG:en; X-Microsoft-Exchange-Diagnostics: =?us-ascii?Q?1;BL2PR15MB1076;23:MHwWvjuPrDP3RDGtHLfJ6OpszkuoNobuuEbVT5WQF?= =?us-ascii?Q?eaYeCkgOWjhD9H+lLu0PwocSxr/KwK3Ee4CTnBGiYH6jlaQYHLR5UYYSbsNa?= =?us-ascii?Q?oaZVocom7VkKcdW6SOpTmo8D5/Xy4fuU3eURhqnAMSmIHcYF0AOaxIn3KQ1i?= =?us-ascii?Q?Zkjyz0pWYfTkKN/Bk7Sw9Kj9GB12o+A/uVjXw0e1s5+6lDMjpLQpXJdzW+Xe?= =?us-ascii?Q?1jQOLTNzEb0GZM8LN0WpHBfCurRj+BGXZwkWofEUySpXREIrPWTlVo8YXhvJ?= =?us-ascii?Q?eu+KPHiM98FLqHKjOcGmTcFeWf41DxBZi5hM3ceef5pgGqoWck+sv0Hns3Km?= =?us-ascii?Q?zp+cCCAV0aX6YbSR9adJYKIz9HcgODKvhTAmua/aw65kvK4T4uqXihlW047d?= =?us-ascii?Q?NoxDCpSyRsI0TsYtiemIYu6zgIO01/0SRNRpoeG5+eG9L9+t5eDu57y5jIqp?= =?us-ascii?Q?6AnvsUt5rCN25W6nyKIV+Y6RpHg7VjaonQlA6kBVYKHe7m/zVEMsI5EDmJ6u?= =?us-ascii?Q?vLF4vbCB63e6MRCkloKMwhSXefNgabisrm1GVT4B5mqC1RuGFTtQ94c3j8pv?= =?us-ascii?Q?fK2PNI8otLB07l04UZV082qW9RNEaocLhwFW/MocLKT38vPpxpaW/x+J02ro?= =?us-ascii?Q?xB1M7Y3TTLkuJTwpF2XmFVtjR7OfoKgnl8QRiVdQqVfHr0V+O6RKOxTgxB+H?= =?us-ascii?Q?4kKIk0vHvqhqEcssVdF9I4hf5tg3OR5Jo4PNIDk7vBzzb7NomaGcaVM1Ui+4?= =?us-ascii?Q?nbrBLVIMStDsmgvcsuFDeoQOpkE+xpPXfO18k5v/7tyAOPNz2AhoQtBelAfz?= =?us-ascii?Q?PjbHeaq+2NU0twOqap+MwY5mLPmzqtzi+kF0xulok6Qk3O6VAKq6efS2V9jP?= =?us-ascii?Q?lZmTBEkH9EqYEtDAtiNua7ZevjIqUPu2KP4VvjDH8ZDDRzL2TXMXGpo7Acvs?= =?us-ascii?Q?O37WnCSAz6RJnEDpC63rHeEsw97e0DdVP2xXXINfll/hf+bgnp5v2YUAjjRS?= =?us-ascii?Q?MmvLNTheucDVEZB4LPCem4RwSVsyR3N6DBP0XoR/aHPg013FsALJpxSJxymp?= =?us-ascii?Q?ahESliCStFGYS6yQeL+lx0ZK4OfQ04OrFjEME/f33z9vs3vocUCozevsHaOO?= =?us-ascii?Q?rdv7WnQPoTN15OcHtzQfrRyjto8z/GxK4Gx7qGhlyAP3GHWUihv7UjGfM9rw?= =?us-ascii?Q?oAEOGLfyNmqdgpGLqI9n/IAVXT0jN1epQAzdG0Igjo16umBdGhOh7KiyVM9B?= =?us-ascii?Q?QW2er3KsdNmdeoCNkk=3D?= X-Microsoft-Exchange-Diagnostics: 1;BL2PR15MB1076;6:oW96O/7ZeZEHETYxLbqb3KOzxRkUOrN68JQDC32WThuInh+JhTfoC1S+dHZCqlIBxA02WvWr3ckFnz7pVuekUk/ok0bmHIXFZUGgaspyONiQXx8mgpXhGRCvEUjMr/yTlXmfoQceblfyP4kNf/eF89i98RtL0m2Ltuh44Hhqjrwa0PebupHpVZUwWbLXgd0SsrEkCOlA6egHxGzesnxxy7r6BmMAU4m6k49d3yDYq7y6WOJefP0eaobEDE5vYMn0kXvv+n+S7vAoXz5NQtnT/K1z7zw+D6AxpYLrOwjV2JMB061ZvKXfRvrLcUsNR7RhQCpV1GrlLiMkkjGpllRiiA==;5:cb/BkQ34KOSmeNLwoTlu55Few2rh0oC9QOSx8mF4AwJh43oVJr26qSohSZ9dF1wwndVEDglzHSbenMFFCHnfjU9bUCOZmaeVIRtb8uz1e0HrlixTkcxmV717lz5fOWU3GIudmhZR1QR/cdX7GZ17Ng==;24:5GttfPJtDNazqsl8mvoC/8HzVSppmI0T2q2xadYNxOxu/1tHeC4yyyvWyoxJav57gd8P4nRS/j6SS5CeAP8YVTW7DsFLeuWivBqQ5MqufGc=;7:B5ibMLgKABidpE2+ZLCpHidLsxxvqgxF27rUElypxpV7eifJhBMJwwz1pEtwBvjxkj0d/S+P6Z2VkOt5GlnGNiak3YdfAbxZ3AmlB44lcJpIZDRVqdrBvM2m9DO89IVQLg7x/Ub/PArYBB4kawIuJJScCeGp76GSOeC3EGJBlt8M6Oe18QvdNhAL8GMP9CAqNaQJS920k3LArl1tncS9KkxqDeAAiPXc9OTMncx1I48= SpamDiagnosticOutput: 1:99 SpamDiagnosticMetadata: NSPM X-Microsoft-Exchange-Diagnostics: 1;BL2PR15MB1076;20:sY61VYIYg//Z9ax7srFxZgwlJUCqW5N2n+MQfaMIULu+LaYAwIRuXDWzuGR2va0rPC9IL+FF1I8aoQB3jqXF9ZwAQ1JfaWKUolIPOpPBGpcmmhItYolWpY3XW8znWLSLrDoyFpKUN5UBuVcG1sD8JusbBkhcBJavDprolsvMwOg= X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Aug 2017 12:04:02.5998 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL2PR15MB1076 X-OriginatorOrg: fb.com X-Proofpoint-Spam-Reason: safe X-FB-Internal: Safe X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-08-14_10:,, signatures=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 08, 2017 at 04:06:38PM -0700, David Rientjes wrote: > On Tue, 1 Aug 2017, Roman Gushchin wrote: > > > > To the rest of the patch. I have to say I do not quite like how it is > > > implemented. I was hoping for something much simpler which would hook > > > into oom_evaluate_task. If a task belongs to a memcg with kill-all flag > > > then we would update the cumulative memcg badness (more specifically the > > > badness of the topmost parent with kill-all flag). Memcg will then > > > compete with existing self contained tasks (oom_badness will have to > > > tell whether points belong to a task or a memcg to allow the caller to > > > deal with it). But it shouldn't be much more complex than that. > > > > I'm not sure, it will be any simpler. Basically I'm doing the same: > > the difference is that you want to iterate over tasks and for each > > task traverse the memcg tree, update per-cgroup oom score and find > > the corresponding memcg(s) with the kill-all flag. I'm doing the opposite: > > traverse the cgroup tree, and for each leaf cgroup iterate over processes. > > > > Also, please note, that even without the kill-all flag the decision is made > > on per-cgroup level (except tasks in the root cgroup). > > > > I think your implementation is preferred and is actually quite simple to > follow, and I would encourage you to follow through with it. It has a > similar implementation to what we have done for years to kill a process > from a leaf memcg. Hi David! Thank you for the support. > > I did notice that oom_kill_memcg_victim() calls directly into > __oom_kill_process(), however, so we lack the traditional oom killer > output that shows memcg usage and potential tasklist. I think we should > still be dumping this information to the kernel log so that we can see a > breakdown of charged memory. I think the existing output is too verbose for the case, when we kill a cgroup with many processes inside. But I absolutely agree, that we need some debug output, I'll add it in v5. Thanks!