From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754559AbcGEKtd (ORCPT ); Tue, 5 Jul 2016 06:49:33 -0400 Received: from outbound-smtp04.blacknight.com ([81.17.249.35]:50695 "EHLO outbound-smtp04.blacknight.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751268AbcGEKtc (ORCPT ); Tue, 5 Jul 2016 06:49:32 -0400 Date: Tue, 5 Jul 2016 11:49:28 +0100 From: Mel Gorman To: Hillf Danton Cc: linux-kernel , linux-mm@kvack.org, Andrew Morton Subject: Re: [PATCH 21/31] mm, page_alloc: Wake kswapd based on the highest eligible zone Message-ID: <20160705104928.GJ11498@techsingularity.net> References: <00e101d1d689$b9a1d730$2ce58590$@alibaba-inc.com> <00e201d1d68a$84b72100$8e256300$@alibaba-inc.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <00e201d1d68a$84b72100$8e256300$@alibaba-inc.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jul 05, 2016 at 02:57:38PM +0800, Hillf Danton wrote: > > > > The ac_classzone_idx is used as the basis for waking kswapd and that is based > > on the preferred zoneref. If the preferred zoneref's highest zone is lower > > than what is available on other nodes, it's possible that kswapd is woken > > on a zone with only higher, but still eligible, zones. As classzone_idx > > is strictly adhered to now, it causes a problem because eligible pages > > are skipped. > > > > For example, node 0 has only DMA32 and node 1 has only NORMAL. An allocating > > context running on node 0 may wake kswapd on node 1 telling it to skip > > all NORMAL pages. > > > > Signed-off-by: Mel Gorman > > --- > Acked-by: Hillf Danton > Thanks. I also noticed when applying the ack that "zoneref's highest zone" should have been "zoneref's first zone" so fixed that too. -- Mel Gorman SUSE Labs