Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932423AbcLBJhw (ORCPT ); Fri, 2 Dec 2016 04:37:52 -0500 Received: from mail-wj0-f195.google.com ([209.85.210.195]:35069 "EHLO mail-wj0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757935AbcLBJhs (ORCPT ); Fri, 2 Dec 2016 04:37:48 -0500 Date: Fri, 2 Dec 2016 10:37:35 +0100 From: Michal Hocko To: Boris Zhmurov Cc: paulmck@linux.vnet.ibm.com, Paul Menzel , Donald Buczek , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: INFO: rcu_sched detected stalls on CPUs/tasks with `kswapd` and `mem_cgroup_shrink_node` Message-ID: <20161202093734.GE6830@dhcp22.suse.cz> References: <20161128105425.GY31360@linux.vnet.ibm.com> <3a4242cb-0198-0a3b-97ae-536fb5ff83ec@kernelpanic.ru> <20161128143435.GC3924@linux.vnet.ibm.com> <20161128150509.GG3924@linux.vnet.ibm.com> <66fd50e1-a922-846a-f427-7654795bd4b5@kernelpanic.ru> <20161130174802.GM18432@dhcp22.suse.cz> <20161130182552.GN18432@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.6.0 (2016-04-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1081 Lines: 26 On Thu 01-12-16 21:10:01, Boris Zhmurov wrote: > Michal Hocko 30/11/16 21:25: > > >>> Do I get it right that s@cond_resched_rcu_qs@cond_resched@ didn't help? > >> > >> I didn't try that. I've tried 4 patches from Paul's linux-rcu tree. > >> I can try another portion of patches, no problem :) > > > > Replacing cond_resched_rcu_qs in shrink_node_memcg by cond_resched would > > be really helpful to tell whether we are missing a real scheduling point > > or whether something more serious is going on here. > > Well, I can confirm, that replacing cond_resched_rcu_qs in > shrink_node_memcg by cond_resched also makes dmesg clean from RCU CPU > stall warnings. > > I've attached patch (just modification of Paul's patch), that fixes RCU > stall messages in situations, when all memory is used by > couchbase/memcached + fs cache and linux starts to use swap. OK, thanks for the confirmation! I will send a patch because it is true that we do not have any scheduling point if no pages can be isolated fromm the LRU. This might be what you are seeing. -- Michal Hocko SUSE Labs