Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756206AbZFJGoR (ORCPT ); Wed, 10 Jun 2009 02:44:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753290AbZFJGoF (ORCPT ); Wed, 10 Jun 2009 02:44:05 -0400 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:47079 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752777AbZFJGoD (ORCPT ); Wed, 10 Jun 2009 02:44:03 -0400 From: KOSAKI Motohiro To: Andrew Morton Subject: Re: [PATCH 1/3] Reintroduce zone_reclaim_interval for when zone_reclaim() scans and fails to avoid CPU spinning at 100% on NUMA Cc: kosaki.motohiro@jp.fujitsu.com, Mel Gorman , Christoph Lameter , Rik van Riel , yanmin.zhang@intel.com, Wu Fengguang , linuxram@us.ibm.com, linux-mm , LKML In-Reply-To: <20090609222301.8da002ae.akpm@linux-foundation.org> References: <20090608151151.GI15070@csn.ul.ie> <20090609222301.8da002ae.akpm@linux-foundation.org> Message-Id: <20090610154016.DDC3.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.50.07 [ja] Date: Wed, 10 Jun 2009 15:44:03 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1442 Lines: 39 Hi > On Mon, 8 Jun 2009 16:11:51 +0100 Mel Gorman wrote: > > > On Mon, Jun 08, 2009 at 10:55:55AM -0400, Christoph Lameter wrote: > > > On Mon, 8 Jun 2009, Mel Gorman wrote: > > > > > > > > The tmpfs pages are unreclaimable and therefore should not be on the anon > > > > > lru. > > > > > > > > > > > > > tmpfs pages can be swap-backed so can be reclaimable. Regardless of what > > > > list they are on, we still need to know how many of them there are if > > > > this patch is to be avoided. > > > > > > If they are reclaimable then why does it matter? They can be pushed out if > > > you configure zone reclaim to be that aggressive. > > > > > > > Because they are reclaimable by kswapd or normal direct reclaim but *not* > > reclaimable by zone_reclaim() if the zone_reclaim_mode is not configured > > appropriately. > > Ah. (zone_reclaim_mode & RECLAIM_SWAP) == 0. That was important info. > > Couldn't the lack of RECLAIM_WRITE cause a similar problem? Old kernel can makes easily. but currenly we have proper dirty page limit. Thus all pages can't become dirty and zone-reclaim can found cleaner page. In the other hand, plenty tmpfs pages can be mede easily. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/