From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753288Ab0HWNii (ORCPT ); Mon, 23 Aug 2010 09:38:38 -0400 Received: from smtp106.prem.mail.ac4.yahoo.com ([76.13.13.45]:37409 "HELO smtp106.prem.mail.ac4.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1752730Ab0HWNig (ORCPT ); Mon, 23 Aug 2010 09:38:36 -0400 X-Yahoo-SMTP: _Dag8S.swBC1p4FJKLCXbs8NQzyse1SYSgnAbY0- X-YMail-OSG: mxjz8mwVM1mVl.cUcRZNdRHxYmmZSidSezii1MlmStShDXm smhZv5IR.3rftEetdW9gp3vpqwhAPxzagEtkZTMdM9cZtlLQ8jdADnl_wKDj SucHNC9a4W.8tS5okun6gbHSe5If65j3tkN94O.mGGMA21zhdajrgE6HK_S7 WLHVBE3CRoMRPnMbx2.Z22IZMi9yJHkdN5gNoFc7o73F0.z2wAVeW5QMdp53 h X-Yahoo-Newman-Property: ymail-3 Date: Mon, 23 Aug 2010 08:38:25 -0500 (CDT) From: Christoph Lameter X-X-Sender: cl@router.home To: Mel Gorman cc: Andrew Morton , Linux Kernel List , linux-mm@kvack.org, Rik van Riel , Johannes Weiner , Minchan Kim , KAMEZAWA Hiroyuki , KOSAKI Motohiro Subject: Re: [PATCH 0/3] Reduce watermark-related problems with the per-cpu allocator V2 In-Reply-To: <20100823130127.GP19797@csn.ul.ie> Message-ID: References: <1282550442-15193-1-git-send-email-mel@csn.ul.ie> <20100823130127.GP19797@csn.ul.ie> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 23 Aug 2010, Mel Gorman wrote: > > The maximum time for which the livelock can exists is the vm stat > > interval. By default the counters are brought up to date at least once per > > second or if a certain delta was violated. Drifts are controlled by the > > delta configuration. > > > > While there is a maximum time (2 seconds I think) the drift can exist > in, a machine under enough pressure can make a mess of the watermarks > during that time. If it wasn't the case, these livelocks with 0 pages > free wouldn't be happening. So because we go way beyond the watermarks we reach a state in which a livelock exists that does not go away when the counters are finally updated? From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail172.messagelabs.com (mail172.messagelabs.com [216.82.254.3]) by kanga.kvack.org (Postfix) with SMTP id 827996B03BC for ; Mon, 23 Aug 2010 09:38:34 -0400 (EDT) Date: Mon, 23 Aug 2010 08:38:25 -0500 (CDT) From: Christoph Lameter Subject: Re: [PATCH 0/3] Reduce watermark-related problems with the per-cpu allocator V2 In-Reply-To: <20100823130127.GP19797@csn.ul.ie> Message-ID: References: <1282550442-15193-1-git-send-email-mel@csn.ul.ie> <20100823130127.GP19797@csn.ul.ie> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-linux-mm@kvack.org To: Mel Gorman Cc: Andrew Morton , Linux Kernel List , linux-mm@kvack.org, Rik van Riel , Johannes Weiner , Minchan Kim , KAMEZAWA Hiroyuki , KOSAKI Motohiro List-ID: On Mon, 23 Aug 2010, Mel Gorman wrote: > > The maximum time for which the livelock can exists is the vm stat > > interval. By default the counters are brought up to date at least once per > > second or if a certain delta was violated. Drifts are controlled by the > > delta configuration. > > > > While there is a maximum time (2 seconds I think) the drift can exist > in, a machine under enough pressure can make a mess of the watermarks > during that time. If it wasn't the case, these livelocks with 0 pages > free wouldn't be happening. So because we go way beyond the watermarks we reach a state in which a livelock exists that does not go away when the counters are finally updated? -- 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