From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1758162AbYB0I5O@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1758162AbYB0I5O (ORCPT <rfc822;w@1wt.eu>);
	Wed, 27 Feb 2008 03:57:14 -0500
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754495AbYB0I45
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Wed, 27 Feb 2008 03:56:57 -0500
Received: from smtp-out.google.com ([216.239.33.17]:60003 "EHLO
	smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753435AbYB0I45 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 27 Feb 2008 03:56:57 -0500
DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns;
	h=received:date:from:x-x-sender:to:cc:subject:in-reply-to:
	message-id:references:user-agent:mime-version:content-type;
	b=iifpZR9r6R+iP8guVe+uAEH+P9HC5tOQezZrzaCmGuVM543pMvdr8r4NbicrDOuSx
	NSnGtCCrn4qFCT3o+hvGw==
Date: Wed, 27 Feb 2008 00:47:17 -0800 (PST)
From: David Rientjes <rientjes@google.com>
X-X-Sender: rientjes@chino.kir.corp.google.com
To: Balbir Singh <balbir@linux.vnet.ibm.com>
cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
       KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
       Peter Zijlstra <a.p.zijlstra@chello.nl>, linux-kernel@vger.kernel.org,
       linux-mm@kvack.org, Rik van Riel <riel@redhat.com>,
       Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
       Nick Piggin <npiggin@suse.de>
Subject: Re: [RFC][PATCH] page reclaim throttle take2
In-Reply-To: <47C51856.7060408@linux.vnet.ibm.com>
Message-ID: <alpine.DEB.1.00.0802270045400.31372@chino.kir.corp.google.com>
References: <47C4EF2D.90508@linux.vnet.ibm.com> <alpine.DEB.1.00.0802262115270.1799@chino.kir.corp.google.com> <20080227143301.4252.KOSAKI.MOTOHIRO@jp.fujitsu.com> <alpine.DEB.1.00.0802262145410.31356@chino.kir.corp.google.com> <47C4F9C0.5010607@linux.vnet.ibm.com>
 <alpine.DEB.1.00.0802262201390.1613@chino.kir.corp.google.com> <47C51856.7060408@linux.vnet.ibm.com>
User-Agent: Alpine 1.00 (DEB 882 2007-12-20)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Wed, 27 Feb 2008, Balbir Singh wrote:

> Let's forget node hotplug for the moment, but what if someone
> 
> 1. Changes the machine configuration and adds more nodes, do we expect the
> kernel to be recompiled? Or is it easier to update /etc/sysctl.conf?
> 2. Uses fake NUMA nodes and increases/decreases the number of nodes across
> reboots. Should the kernel be recompiled?
> 

That is why the proposal was made to make this a static configuration 
option, such as CONFIG_NUM_RECLAIM_THREADS_PER_NODE, that will handle both 
situations.

> I am afraid it doesn't. Consider as you scale number of CPU's with the same
> amount of memory, we'll end up making the reclaim problem worse.
> 

The benchmark that have been posted suggest that memory locality is more 
important than lock contention, as I've already mentioned.

		David