From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vladimir Davydov Subject: Re: [PATCH 03/14] net: tcp_memcontrol: properly detect ancestor socket pressure Date: Sat, 14 Nov 2015 15:45:52 +0300 Message-ID: <20151114124552.GI31308@esperanza> References: <1447371693-25143-1-git-send-email-hannes@cmpxchg.org> <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Return-path: Content-Disposition: inline In-Reply-To: <1447371693-25143-4-git-send-email-hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Transfer-Encoding: 7bit To: Johannes Weiner Cc: David Miller , Andrew Morton , Tejun Heo , Michal Hocko , netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, kernel-team-b10kYP2dOMg@public.gmane.org On Thu, Nov 12, 2015 at 06:41:22PM -0500, Johannes Weiner wrote: > When charging socket memory, the code currently checks only the local > page counter for excess to determine whether the memcg is under socket > pressure. But even if the local counter is fine, one of the ancestors > could have breached its limit, which should also force this child to > enter socket pressure. This currently doesn't happen. > > Fix this by using page_counter_try_charge() first. If that fails, it > means that either the local counter or one of the ancestors are in > excess of their limit, and the child should enter socket pressure. > > Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov For the record: it was broken by commit 3e32cb2e0a12 ("mm: memcontrol: lockless page counters"). From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lf0-f53.google.com (mail-lf0-f53.google.com [209.85.215.53]) by kanga.kvack.org (Postfix) with ESMTP id 87B8D6B025B for ; Sat, 14 Nov 2015 07:46:09 -0500 (EST) Received: by lfdo63 with SMTP id o63so65736415lfd.2 for ; Sat, 14 Nov 2015 04:46:09 -0800 (PST) Received: from relay.parallels.com (relay.parallels.com. [195.214.232.42]) by mx.google.com with ESMTPS id kk6si18414949lbb.138.2015.11.14.04.46.08 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Sat, 14 Nov 2015 04:46:08 -0800 (PST) Date: Sat, 14 Nov 2015 15:45:52 +0300 From: Vladimir Davydov Subject: Re: [PATCH 03/14] net: tcp_memcontrol: properly detect ancestor socket pressure Message-ID: <20151114124552.GI31308@esperanza> References: <1447371693-25143-1-git-send-email-hannes@cmpxchg.org> <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> Sender: owner-linux-mm@kvack.org List-ID: To: Johannes Weiner Cc: David Miller , Andrew Morton , Tejun Heo , Michal Hocko , netdev@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@fb.com On Thu, Nov 12, 2015 at 06:41:22PM -0500, Johannes Weiner wrote: > When charging socket memory, the code currently checks only the local > page counter for excess to determine whether the memcg is under socket > pressure. But even if the local counter is fine, one of the ancestors > could have breached its limit, which should also force this child to > enter socket pressure. This currently doesn't happen. > > Fix this by using page_counter_try_charge() first. If that fails, it > means that either the local counter or one of the ancestors are in > excess of their limit, and the child should enter socket pressure. > > Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov For the record: it was broken by commit 3e32cb2e0a12 ("mm: memcontrol: lockless page counters"). -- 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 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751336AbbKNMqL (ORCPT ); Sat, 14 Nov 2015 07:46:11 -0500 Received: from relay.parallels.com ([195.214.232.42]:45574 "EHLO relay.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750998AbbKNMqJ (ORCPT ); Sat, 14 Nov 2015 07:46:09 -0500 Date: Sat, 14 Nov 2015 15:45:52 +0300 From: Vladimir Davydov To: Johannes Weiner CC: David Miller , Andrew Morton , Tejun Heo , Michal Hocko , , , , , Subject: Re: [PATCH 03/14] net: tcp_memcontrol: properly detect ancestor socket pressure Message-ID: <20151114124552.GI31308@esperanza> References: <1447371693-25143-1-git-send-email-hannes@cmpxchg.org> <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> X-ClientProxiedBy: US-EXCH2.sw.swsoft.com (10.255.249.46) To MSK-EXCH1.sw.swsoft.com (10.67.48.55) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Nov 12, 2015 at 06:41:22PM -0500, Johannes Weiner wrote: > When charging socket memory, the code currently checks only the local > page counter for excess to determine whether the memcg is under socket > pressure. But even if the local counter is fine, one of the ancestors > could have breached its limit, which should also force this child to > enter socket pressure. This currently doesn't happen. > > Fix this by using page_counter_try_charge() first. If that fails, it > means that either the local counter or one of the ancestors are in > excess of their limit, and the child should enter socket pressure. > > Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov For the record: it was broken by commit 3e32cb2e0a12 ("mm: memcontrol: lockless page counters"). From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vladimir Davydov Subject: Re: [PATCH 03/14] net: tcp_memcontrol: properly detect ancestor socket pressure Date: Sat, 14 Nov 2015 15:45:52 +0300 Message-ID: <20151114124552.GI31308@esperanza> References: <1447371693-25143-1-git-send-email-hannes@cmpxchg.org> <1447371693-25143-4-git-send-email-hannes@cmpxchg.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: David Miller , Andrew Morton , Tejun Heo , Michal Hocko , , , , , To: Johannes Weiner Return-path: Content-Disposition: inline In-Reply-To: <1447371693-25143-4-git-send-email-hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: netdev.vger.kernel.org On Thu, Nov 12, 2015 at 06:41:22PM -0500, Johannes Weiner wrote: > When charging socket memory, the code currently checks only the local > page counter for excess to determine whether the memcg is under socket > pressure. But even if the local counter is fine, one of the ancestors > could have breached its limit, which should also force this child to > enter socket pressure. This currently doesn't happen. > > Fix this by using page_counter_try_charge() first. If that fails, it > means that either the local counter or one of the ancestors are in > excess of their limit, and the child should enter socket pressure. > > Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov For the record: it was broken by commit 3e32cb2e0a12 ("mm: memcontrol: lockless page counters").