From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758586AbYDTRTr (ORCPT ); Sun, 20 Apr 2008 13:19:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754115AbYDTRTj (ORCPT ); Sun, 20 Apr 2008 13:19:39 -0400 Received: from one.firstfloor.org ([213.235.205.2]:37275 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752994AbYDTRTj (ORCPT ); Sun, 20 Apr 2008 13:19:39 -0400 Message-ID: <480B7B1E.7010707@firstfloor.org> Date: Sun, 20 Apr 2008 19:19:26 +0200 From: Andi Kleen User-Agent: Thunderbird 1.5.0.12 (X11/20060911) MIME-Version: 1.0 To: =?UTF-8?B?SsO2cm4gRW5nZWw=?= CC: Willy Tarreau , Mark Lord , Adrian Bunk , Alan Cox , Shawn Bohrer , Ingo Molnar , Andrew Morton , Linux Kernel Mailing List , Arjan van de Ven , Thomas Gleixner Subject: Re: x86: 4kstacks default References: <20080420080901.GF1595@cs181133002.pp.htv.fi> <20080420090623.7b173ef1@the-village.bc.nu> <20080420085104.GG1595@cs181133002.pp.htv.fi> <20080420103611.2c0d3519@the-village.bc.nu> <20080420104444.GI1595@cs181133002.pp.htv.fi> <87y778aezh.fsf@basil.nowhere.org> <20080420124717.GH8474@1wt.eu> <480B44C4.4060104@rtr.ca> <20080420133857.GB26536@1wt.eu> <480B50F1.8040309@firstfloor.org> <20080420164133.GB20694@logfs.org> In-Reply-To: <20080420164133.GB20694@logfs.org> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Jörn Engel wrote: > On Sun, 20 April 2008 16:19:29 +0200, Andi Kleen wrote: >> Only if you believe that 4K stack pages are a worthy goal. >> As far as I can figure out they are not. They might have been >> a worthy goal on crappy 2.4 VMs, but these times are long gone. >> >> The "saving memory on embedded" argument also does not >> quite convince me, it is unclear if that is really >> a significant amount of memory on these systems and if that >> couldn't be addressed better (e.g. in running generally >> less kernel threads). I don't have numbers on this, >> but then the people who made this argument didn't have any >> either :) > > It is not uncommon for embedded systems to be designed around 16MiB. But these are SoC systems. Do they really run x86? (note we're talking about an x86 default option here) Also I suspect in a true 16MB system you have to strip down everything kernel side so much that you're pretty much outside the "validated by testers" realm that Adrian cares about. > When dealing in those dimensions, savings of 100k are substantial. In > some causes they may be the difference between 16MiB or 32MiB, which > translates to manufacturing costs. In others it simply means that the > system can cache If you need the stack you don't have any less cache foot print. If you don't need it you don't have any either. -Andi