From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754847Ab3LPT0Q (ORCPT ); Mon, 16 Dec 2013 14:26:16 -0500 Received: from mx1.redhat.com ([209.132.183.28]:14363 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754718Ab3LPT0O (ORCPT ); Mon, 16 Dec 2013 14:26:14 -0500 Message-ID: <52AF53BD.7060509@redhat.com> Date: Mon, 16 Dec 2013 14:25:49 -0500 From: Rik van Riel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130625 Thunderbird/17.0.7 MIME-Version: 1.0 To: Mel Gorman CC: Johannes Weiner , Andrew Morton , Dave Hansen , Linux-MM , LKML Subject: Re: [PATCH 5/7] mm: page_alloc: Make zone distribution page aging policy configurable References: <1386943807-29601-1-git-send-email-mgorman@suse.de> <1386943807-29601-6-git-send-email-mgorman@suse.de> In-Reply-To: <1386943807-29601-6-git-send-email-mgorman@suse.de> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 12/13/2013 09:10 AM, Mel Gorman wrote: > Commit 81c0a2bb ("mm: page_alloc: fair zone allocator policy") solved a > bug whereby new pages could be reclaimed before old pages because of > how the page allocator and kswapd interacted on the per-zone LRU lists. > Unfortunately it was missed during review that a consequence is that > we also round-robin between NUMA nodes. This is bad for two reasons > > 1. It alters the semantics of MPOL_LOCAL without telling anyone > 2. It incurs an immediate remote memory performance hit in exchange > for a potential performance gain when memory needs to be reclaimed > later > > No cookies for the reviewers on this one. > > This patch makes the behaviour of the fair zone allocator policy > configurable. By default it will only distribute pages that are going > to exist on the LRU between zones local to the allocating process. This > preserves the historical semantics of MPOL_LOCAL. > > By default, slab pages are not distributed between zones after this patch is > applied. It can be argued that they should get similar treatment but they > have different lifecycles to LRU pages, the shrinkers are not zone-aware > and the interaction between the page allocator and kswapd is different > for slabs. If it turns out to be an almost universal win, we can change > the default. > > Signed-off-by: Mel Gorman Acked-by: Rik van Riel -- All rights reversed