From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030185AbXCOMvF (ORCPT ); Thu, 15 Mar 2007 08:51:05 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1030194AbXCOMvF (ORCPT ); Thu, 15 Mar 2007 08:51:05 -0400 Received: from ns2.suse.de ([195.135.220.15]:57376 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030185AbXCOMvC (ORCPT ); Thu, 15 Mar 2007 08:51:02 -0400 Date: Thu, 15 Mar 2007 13:50:56 +0100 From: Nick Piggin To: Dave Kleikamp Cc: Ashif Harji , Xiaoning Ding , Andreas Mohr , 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 Message-ID: <20070315125056.GE8321@wotan.suse.de> References: <1173962816.14380.8.camel@kleikamp.austin.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1173962816.14380.8.camel@kleikamp.austin.ibm.com> User-Agent: Mutt/1.5.9i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Mar 15, 2007 at 07:46:56AM -0500, Dave Kleikamp wrote: > On Thu, 2007-03-15 at 01:22 -0400, Ashif Harji wrote: > > > I would tend to agree with David that: "Any application doing many > > tiny-sized reads isn't exactly asking for great performance." As well, > > applications concerned with performance and caching problems can read in a > > file in PAGE_SIZE chunks. I still think the simple fix of removing the > > condition is the best approach, but I'm certainly open to alternatives. > > A possible alternative might be to store the offset within the page in > the readahead state, and call mark_page_accessed() when the read offset > is less than or equal to the previous offset. That could be a good idea. We definitely want to look at ways to solve with within the existing approach before any large scale change in behaviour.