From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail191.messagelabs.com (mail191.messagelabs.com [216.82.242.19]) by kanga.kvack.org (Postfix) with ESMTP id B13618D0039 for ; Tue, 8 Mar 2011 00:31:20 -0500 (EST) Received: from wpaz17.hot.corp.google.com (wpaz17.hot.corp.google.com [172.24.198.81]) by smtp-out.google.com with ESMTP id p285UPsL023144 for ; Mon, 7 Mar 2011 21:30:26 -0800 Received: from gye5 (gye5.prod.google.com [10.243.50.5]) by wpaz17.hot.corp.google.com with ESMTP id p285U2jN032428 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NOT) for ; Mon, 7 Mar 2011 21:30:24 -0800 Received: by gye5 with SMTP id 5so2266013gye.38 for ; Mon, 07 Mar 2011 21:30:24 -0800 (PST) Date: Mon, 7 Mar 2011 21:30:19 -0800 (PST) From: David Rientjes Subject: Re: [patch] memcg: add oom killer delay In-Reply-To: <20110308131723.e434cb89.kamezawa.hiroyu@jp.fujitsu.com> Message-ID: References: <20110223150850.8b52f244.akpm@linux-foundation.org> <20110303135223.0a415e69.akpm@linux-foundation.org> <20110307162912.2d8c70c1.akpm@linux-foundation.org> <20110307165119.436f5d21.akpm@linux-foundation.org> <20110307171853.c31ec416.akpm@linux-foundation.org> <20110308115108.36b184c5.kamezawa.hiroyu@jp.fujitsu.com> <20110308121332.de003f81.kamezawa.hiroyu@jp.fujitsu.com> <20110308131723.e434cb89.kamezawa.hiroyu@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-linux-mm@kvack.org List-ID: To: KAMEZAWA Hiroyuki Cc: Andrew Morton , Balbir Singh , Daisuke Nishimura , linux-mm@kvack.org On Tue, 8 Mar 2011, KAMEZAWA Hiroyuki wrote: > Hmm? That's an unexpected answer. Why system's capacity is problem here ? > (root memcg has no 'limit' always.) > > Is it a problem that 'there is no 'guarantee' or 'private page pool' > for daemons ? > It's not an inherent problem of memcg, it's a configuration issue: if your userspace application cannot respond to address an oom condition in a memcg for whatever reason (such as it being in an oom memcg itself), then there's a chance that the memcg will livelock since the kernel cannot do anything to fix the issue itself. That's aside from the general purpose of the new memory.oom_delay_millisecs: users may want a grace period for userspace to increase the hard limit or kill a task before deferring to the kernel. That seems exponentially more useful than simply disabling the oom killer entirely with memory.oom_control. I think it's unfortunate memory.oom_control was merged frst and seems to have tainted this entire discussion. -- 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/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: email@kvack.org