From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail190.messagelabs.com (mail190.messagelabs.com [216.82.249.51]) by kanga.kvack.org (Postfix) with SMTP id EE6576B01C1 for ; Mon, 31 May 2010 01:46:06 -0400 (EDT) Received: by ywh17 with SMTP id 17so651430ywh.1 for ; Sun, 30 May 2010 22:46:05 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <20100531140443.b36a4f02.kamezawa.hiroyu@jp.fujitsu.com> References: <20100528143605.7E2A.A69D9226@jp.fujitsu.com> <20100528145329.7E2D.A69D9226@jp.fujitsu.com> <20100528125305.GE11364@uudg.org> <20100528140623.GA11041@barrios-desktop> <20100528143617.GF11364@uudg.org> <20100528151249.GB12035@barrios-desktop> <20100528152842.GH11364@uudg.org> <20100528154549.GC12035@barrios-desktop> <20100528164826.GJ11364@uudg.org> <20100531092133.73705339.kamezawa.hiroyu@jp.fujitsu.com> <20100531140443.b36a4f02.kamezawa.hiroyu@jp.fujitsu.com> Date: Mon, 31 May 2010 14:46:05 +0900 Message-ID: Subject: Re: [RFC] oom-kill: give the dying task a higher priority From: Minchan Kim Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: KAMEZAWA Hiroyuki Cc: "Luis Claudio R. Goncalves" , KOSAKI Motohiro , balbir@linux.vnet.ibm.com, Oleg Nesterov , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Thomas Gleixner , Peter Zijlstra , David Rientjes , Mel Gorman , williams@redhat.com List-ID: On Mon, May 31, 2010 at 2:04 PM, KAMEZAWA Hiroyuki wrote: > On Mon, 31 May 2010 14:01:03 +0900 > Minchan Kim wrote: > >> Hi, Kame. >> >> On Mon, May 31, 2010 at 9:21 AM, KAMEZAWA Hiroyuki >> wrote: >> > On Fri, 28 May 2010 13:48:26 -0300 >> > "Luis Claudio R. Goncalves" wrote: >> >> >> >> oom-killer: give the dying task rt priority (v3) >> >> >> >> Give the dying task RT priority so that it can be scheduled quickly a= nd die, >> >> freeing needed memory. >> >> >> >> Signed-off-by: Luis Claudio R. Gon=C3=A7alves >> >> >> >> diff --git a/mm/oom_kill.c b/mm/oom_kill.c >> >> index 84bbba2..2b0204f 100644 >> >> --- a/mm/oom_kill.c >> >> +++ b/mm/oom_kill.c >> >> @@ -266,6 +266,8 @@ static struct task_struct *select_bad_process(uns= igned long *ppoints) >> >> =C2=A0 */ >> >> =C2=A0static void __oom_kill_task(struct task_struct *p, int verbose) >> >> =C2=A0{ >> >> + =C2=A0 =C2=A0 struct sched_param param; >> >> + >> >> =C2=A0 =C2=A0 =C2=A0 if (is_global_init(p)) { >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 WARN_ON(1); >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 printk(KERN_WARNING = "tried to kill init!\n"); >> >> @@ -288,6 +290,8 @@ static void __oom_kill_task(struct task_struct *p= , int verbose) >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0* exit() and clear out its resources quick= ly... >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0*/ >> >> =C2=A0 =C2=A0 =C2=A0 p->time_slice =3D HZ; >> >> + =C2=A0 =C2=A0 param.sched_priority =3D MAX_RT_PRIO-10; >> >> + =C2=A0 =C2=A0 sched_setscheduler(p, SCHED_FIFO, ¶m); >> >> =C2=A0 =C2=A0 =C2=A0 set_tsk_thread_flag(p, TIF_MEMDIE); >> >> >> > >> > BTW, how about the other threads which share mm_struct ? >> >> Could you elaborate your intention? :) >> > > IIUC, the purpose of rising priority is to accerate dying thread to exit(= ) > for freeing memory AFAP. But to free memory, exit, all threads which shar= e > mm_struct should exit, too. I'm sorry if I miss something. How do we kill only some thread and what's the benefit of it? I think when if some thread receives KILL signal, the process include the thread will be killed. I think > Thanks, > -Kame > > > > --=20 Kind regards, Minchan Kim -- 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