From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1422879AbXCOPG6 (ORCPT ); Thu, 15 Mar 2007 11:06:58 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1422881AbXCOPG5 (ORCPT ); Thu, 15 Mar 2007 11:06:57 -0400 Received: from mx1.redhat.com ([66.187.233.31]:52689 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1422879AbXCOPG5 (ORCPT ); Thu, 15 Mar 2007 11:06:57 -0400 Message-ID: <45F960D9.1020609@redhat.com> Date: Thu, 15 Mar 2007 11:06:01 -0400 From: Rik van Riel Organization: Red Hat, Inc User-Agent: Thunderbird 1.5.0.7 (X11/20061008) MIME-Version: 1.0 To: Nick Piggin CC: Peter Zijlstra , Ashif Harji , linux-mm@kvack.org, Jan Kara , linux-kernel@vger.kernel.org, akpm@linux-foundation.org Subject: Re: [PATCH] mm/filemap.c: unconditionally call mark_page_accessed References: <20070312142012.GH30777@atrey.karlin.mff.cuni.cz> <20070312143900.GB6016@wotan.suse.de> <20070312151355.GB23532@duck.suse.cz> <20070312173500.GF23532@duck.suse.cz> <20070313185554.GA5105@duck.suse.cz> <1173955154.25356.28.camel@twins> <20070315123859.GC8321@wotan.suse.de> In-Reply-To: <20070315123859.GC8321@wotan.suse.de> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Nick Piggin wrote: > On Thu, Mar 15, 2007 at 11:39:14AM +0100, Peter Zijlstra wrote: >> On Wed, 2007-03-14 at 15:58 -0400, Ashif Harji wrote: >>> This patch unconditionally calls mark_page_accessed to prevent pages, >>> especially for small files, from being evicted from the page cache despite >>> frequent access. >> Since we're hackling over the use-once stuff again... >> >> /me brings up: http://marc.info/?l=linux-mm&m=115316894804385&w=2 and >> ducks. > > Join the club ;) > > http://groups.google.com.au/group/linux.kernel/msg/7b3237b8e715475b?hl=en& > > I can't find the patch where I actually did combine it with a PG_usedonce > bit, but the end result is pretty similar to your patch. Except for the bit where vmscan throws away page cache pages with PageReferenced set, unless they are mapped :) Also, pages that only got accessed once will have the referenced bit set too, so your patch gives no way to distinguish between pages that were accessed once and pages that were accessed multiple times. > And I think one > or two others have also independently invented the same thing. > > So it *has* to be good, doesn't it? ;) No argument there :) -- Politics is the struggle between those who want to make their country the best in the world, and those who believe it already is. Each group calls the other unpatriotic.