From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1753410AbXDISqR@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753410AbXDISqR (ORCPT <rfc822;w@1wt.eu>);
	Mon, 9 Apr 2007 14:46:17 -0400
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753412AbXDISqQ
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Mon, 9 Apr 2007 14:46:16 -0400
Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:33432 "EHLO
	relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org
	with ESMTP id S1753410AbXDISqP (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 9 Apr 2007 14:46:15 -0400
Date: Mon, 9 Apr 2007 11:46:14 -0700 (PDT)
From: Christoph Lameter <clameter@sgi.com>
X-X-Sender: clameter@schroedinger.engr.sgi.com
To: Andi Kleen <ak@suse.de>
cc: akpm@linux-foundation.org, linux-mm@kvack.org,
       linux-kernel@vger.kernel.org
Subject: Re: [QUICKLIST 3/4] Quicklist support for x86_64
In-Reply-To: <200704092043.14335.ak@suse.de>
Message-ID: <Pine.LNX.4.64.0704091144270.8783@schroedinger.engr.sgi.com>
References: <20070409182509.8559.33823.sendpatchset@schroedinger.engr.sgi.com>
 <20070409182520.8559.33529.sendpatchset@schroedinger.engr.sgi.com>
 <200704092043.14335.ak@suse.de>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, 9 Apr 2007, Andi Kleen wrote:

> On Monday 09 April 2007 20:25:20 Christoph Lameter wrote:
> 
> >  #endif /* _X86_64_PGALLOC_H */
> > Index: linux-2.6.21-rc5-mm4/arch/x86_64/kernel/process.c
> > ===================================================================
> > --- linux-2.6.21-rc5-mm4.orig/arch/x86_64/kernel/process.c	2007-04-07 18:07:47.000000000 -0700
> > +++ linux-2.6.21-rc5-mm4/arch/x86_64/kernel/process.c	2007-04-07 18:09:30.000000000 -0700
> > @@ -207,6 +207,7 @@
> >  			if (__get_cpu_var(cpu_idle_state))
> >  				__get_cpu_var(cpu_idle_state) = 0;
> >  
> > +			check_pgt_cache();
> 
> Wouldn't it be better to do that on memory pressure only (register
> it as a shrinker)?

It has to be done in sync with tlb flushing. Doing that on memory pressure 
would complicate things significantly. Also idling means that the cache 
grows cold.