From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934680AbXGYSA1 (ORCPT ); Wed, 25 Jul 2007 14:00:27 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761800AbXGYSAK (ORCPT ); Wed, 25 Jul 2007 14:00:10 -0400 Received: from main.gmane.org ([80.91.229.2]:60357 "EHLO ciao.gmane.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755064AbXGYSAI (ORCPT ); Wed, 25 Jul 2007 14:00:08 -0400 X-Injected-Via-Gmane: http://gmane.org/ To: linux-kernel@vger.kernel.org From: "Frank A. Kingswood" Subject: Re: -mm merge plans for 2.6.23 Date: Wed, 25 Jul 2007 18:55:43 +0100 Message-ID: References: <20070710013152.ef2cd200.akpm@linux-foundation.org> <200707102015.44004.kernel@kolivas.org> <9a8748490707231608h453eefffx68b9c391897aba70@mail.gmail.com> <46A57068.3070701@yahoo.com.au> <2c0942db0707232153j3670ef31kae3907dff1a24cb7@mail.gmail.com> <46A58B49.3050508@yahoo.com.au> <2c0942db0707240915h56e007e3l9110e24a065f2e73@mail.gmail.com> <46A6CC56.6040307@yahoo.com.au> <46A6D7D2.4050708@gmail.com> <1185341449.7105.53.camel@perkele> <46A6E1A1.4010508@yahoo.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: 88-97-16-53.dsl.zen.co.uk User-Agent: Icedove 1.5.0.12 (X11/20070607) In-Reply-To: <46A6E1A1.4010508@yahoo.com.au> Cc: ck@vds.kolivas.org, linux-mm@kvack.org Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Nick Piggin wrote: > OK, this is where I start to worry. Swap prefetch AFAIKS doesn't fix > the updatedb problem very well, because if updatedb has caused swapout > then it has filled memory, and swap prefetch doesn't run unless there > is free memory (not to mention that updatedb would have paged out other > files as well). It is *not* about updatedb. That is just a trivial case which people notice. Therefore fixing updatedb to be nicer, as was discussed at various points in this thread, is *not* the solution. Most users are also *not*at*all* interested in kernel builds as a metric of system performance. When I'm at work, I run a large, commercial, engineering application. While running, it takes most of the system memory (4GB and up), and it reads and writes very large files. Swap prefetch noticeably helps my desktop too. Can I measure it? Not sure. Can people on lkml fix the application? Certainly not. Frank From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Frank A. Kingswood" Subject: Re: -mm merge plans for 2.6.23 Date: Wed, 25 Jul 2007 18:55:43 +0100 Message-ID: References: <20070710013152.ef2cd200.akpm@linux-foundation.org> <200707102015.44004.kernel@kolivas.org> <9a8748490707231608h453eefffx68b9c391897aba70@mail.gmail.com> <46A57068.3070701@yahoo.com.au> <2c0942db0707232153j3670ef31kae3907dff1a24cb7@mail.gmail.com> <46A58B49.3050508@yahoo.com.au> <2c0942db0707240915h56e007e3l9110e24a065f2e73@mail.gmail.com> <46A6CC56.6040307@yahoo.com.au> <46A6D7D2.4050708@gmail.com> <1185341449.7105.53.camel@perkele> <46A6E1A1.4010508@yahoo.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <46A6E1A1.4010508@yahoo.com.au> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: ck-bounces@vds.kolivas.org Errors-To: ck-bounces@vds.kolivas.org To: ck@vds.kolivas.org Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org List-Id: linux-mm.kvack.org Nick Piggin wrote: > OK, this is where I start to worry. Swap prefetch AFAIKS doesn't fix > the updatedb problem very well, because if updatedb has caused swapout > then it has filled memory, and swap prefetch doesn't run unless there > is free memory (not to mention that updatedb would have paged out other > files as well). It is *not* about updatedb. That is just a trivial case which people notice. Therefore fixing updatedb to be nicer, as was discussed at various points in this thread, is *not* the solution. Most users are also *not*at*all* interested in kernel builds as a metric of system performance. When I'm at work, I run a large, commercial, engineering application. While running, it takes most of the system memory (4GB and up), and it reads and writes very large files. Swap prefetch noticeably helps my desktop too. Can I measure it? Not sure. Can people on lkml fix the application? Certainly not. Frank