From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753665Ab0E1G1R (ORCPT ); Fri, 28 May 2010 02:27:17 -0400 Received: from e23smtp01.au.ibm.com ([202.81.31.143]:59860 "EHLO e23smtp01.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753076Ab0E1G1O (ORCPT ); Fri, 28 May 2010 02:27:14 -0400 Date: Fri, 28 May 2010 11:57:01 +0530 From: Balbir Singh To: KOSAKI Motohiro Cc: "Luis Claudio R. Goncalves" , Oleg Nesterov , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Thomas Gleixner , Peter Zijlstra , David Rientjes , Mel Gorman , williams@redhat.com Subject: Re: [RFC] oom-kill: give the dying task a higher priority Message-ID: <20100528062701.GA3519@balbir.in.ibm.com> Reply-To: balbir@linux.vnet.ibm.com References: <20100528035147.GD11364@uudg.org> <20100528043339.GZ3519@balbir.in.ibm.com> <20100528134133.7E24.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20100528134133.7E24.A69D9226@jp.fujitsu.com> User-Agent: Mutt/1.5.20 (2009-08-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * KOSAKI Motohiro [2010-05-28 13:46:53]: > > * Luis Claudio R. Goncalves [2010-05-28 00:51:47]: > > > > > @@ -382,6 +382,8 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, > > > */ > > > static void __oom_kill_task(struct task_struct *p, int verbose) > > > { > > > + struct sched_param param; > > > + > > > if (is_global_init(p)) { > > > WARN_ON(1); > > > printk(KERN_WARNING "tried to kill init!\n"); > > > @@ -413,8 +415,9 @@ static void __oom_kill_task(struct task_struct *p, int verbose) > > > */ > > > p->rt.time_slice = HZ; > > > set_tsk_thread_flag(p, TIF_MEMDIE); > > > - > > > force_sig(SIGKILL, p); > > > + param.sched_priority = MAX_RT_PRIO-1; > > > + sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); > > > } > > > > > > > I would like to understand the visible benefits of this patch. Have > > you seen an OOM kill tasked really get bogged down. Should this task > > really be competing with other important tasks for run time? > > What you mean important? Until OOM victim task exit completely, the system have no memory. > all of important task can't do anything. > > In almost kernel subsystems, automatically priority boost is really bad idea because > it may break RT task's deterministic behavior. but OOM is one of exception. The deterministic > was alread broken by memory starvation. > I am still not convinced, specially if we are running under mem cgroup. Even setting SCHED_FIFO does not help, you could have other things like cpusets that might restrict the CPUs you can run on, or any other policy and we could end up contending anyway with other SCHED_FIFO tasks. > That's the reason I acked it. If we could show faster recovery from OOM or anything else, I would be more convinced. -- Three Cheers, Balbir