From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933733AbXGUV3M (ORCPT ); Sat, 21 Jul 2007 17:29:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761672AbXGUV2z (ORCPT ); Sat, 21 Jul 2007 17:28:55 -0400 Received: from toq7.bellnexxia.net ([209.226.175.203]:42959 "EHLO toq7-srv.bellnexxia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760669AbXGUV2y (ORCPT ); Sat, 21 Jul 2007 17:28:54 -0400 Subject: Re: [PATCH 1/3] readahead: drop behind From: Eric St-Laurent To: Peter Zijlstra Cc: linux-kernel , Fengguang Wu , riel , Andrew Morton , Rusty Russell , Tim Pepper , Chris Snook In-Reply-To: <20070721210051.975382000@chello.nl> References: <20070721210005.000228000@chello.nl> <20070721210051.975382000@chello.nl> Content-Type: text/plain Date: Sat, 21 Jul 2007 16:29:07 -0400 Message-Id: <1185049747.27915.8.camel@perkele> Mime-Version: 1.0 X-Mailer: Evolution 2.10.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 2007-21-07 at 23:00 +0200, Peter Zijlstra wrote: > plain text document attachment (readahead-useonce.patch) > Use the read-ahead code to provide hints to page reclaim. > > This patch has the potential to solve the streaming-IO trashes my > desktop problem. > > It tries to aggressively reclaim pages that were loaded in a strong > sequential pattern and have been consumed. Thereby limiting the damage > to the current resident set. > > Signed-off-by: Peter Zijlstra With the fadvise change, it looks like the right solution to me. The patches are for which kernel? They doesn't apply cleanly to 2.6.22.1. It would be useful to have a temporary /proc tunable to enable/disable the heuristic to help test the effects. - Eric