From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756318AbYGAR6g (ORCPT ); Tue, 1 Jul 2008 13:58:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752190AbYGAR61 (ORCPT ); Tue, 1 Jul 2008 13:58:27 -0400 Received: from hellhawk.shadowen.org ([80.68.90.175]:1567 "EHLO hellhawk.shadowen.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751917AbYGAR60 (ORCPT ); Tue, 1 Jul 2008 13:58:26 -0400 From: Andy Whitcroft To: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org, Mel Gorman , Andy Whitcroft Subject: [RFC PATCH 0/4] Reclaim page capture v1 Date: Tue, 1 Jul 2008 18:58:38 +0100 Message-Id: <1214935122-20828-1-git-send-email-apw@shadowen.org> X-Mailer: git-send-email 1.5.6.1.201.g3e7d3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org For sometime we have been looking at mechanisms for improving the availability of larger allocations under load. One of the options we have explored is the capturing of pages freed under direct reclaim in order to increase the chances of free pages coelescing before they are subject to reallocation by racing allocators. Following this email is a patch stack implementing page capture during direct reclaim. It consits of four patches. The first two simply pull out existing code into helpers for reuse. The third makes buddy's use of struct page explicit. The fourth contains the meat of the changes, and its leader contains a much fuller description of the feature. I have done a fair amount of comparitive testing with and without this patch set and in broad brush I am seeing improvements in hugepage allocations (worst case size) success of the order of 5% which under load for systems with larger hugepages represents a doubling of the number of pages available. Testing is still ongoing to confirm these results. Against: 2.6.26-rc6 (with the explicit page flags patches) Comments? -apw