From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759555Ab2D0DB7 (ORCPT ); Thu, 26 Apr 2012 23:01:59 -0400 Received: from mx1.redhat.com ([209.132.183.28]:46726 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758159Ab2D0DB5 (ORCPT ); Thu, 26 Apr 2012 23:01:57 -0400 Date: Thu, 26 Apr 2012 22:02:24 -0400 From: Dave Jones To: Steven Rostedt Cc: David Rientjes , linux-mm@kvack.org, Linux Kernel , "Paul E. McKenney" Subject: Re: 3.4-rc4 oom killer out of control. Message-ID: <20120427020224.GA22927@redhat.com> Mail-Followup-To: Dave Jones , Steven Rostedt , David Rientjes , linux-mm@kvack.org, Linux Kernel , "Paul E. McKenney" References: <20120426193551.GA24968@redhat.com> <20120426215257.GA12908@redhat.com> <20120426224419.GA13598@redhat.com> <20120427005448.GD23877@home.goodmis.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120427005448.GD23877@home.goodmis.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Apr 26, 2012 at 08:54:48PM -0400, Steven Rostedt wrote: > > > full_scans is just a counter of how many times it has scanned mergable > > > memory so it should be increasing constantly. Whether pages_to_scan == > > > 1250 and sleep_millisecs == 20 is good for your system is unknown. You > > > may want to try disabling ksm entirely (echo 0 > /sys/kernel/mm/ksm/run) > > > to see if it significantly increases responsiveness for your workload. > > > > You didn't happen to see any RCU CPU stalls, did you? nothing got reported in dmesg.. Dave