From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752594Ab1GSIjk (ORCPT ); Tue, 19 Jul 2011 04:39:40 -0400 Received: from cantor2.suse.de ([195.135.220.15]:45725 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752386Ab1GSIjj (ORCPT ); Tue, 19 Jul 2011 04:39:39 -0400 Date: Tue, 19 Jul 2011 09:39:32 +0100 From: Mel Gorman To: Shaohua Li Cc: Andrew Morton , linux-mm , lkml Subject: Re: [PATCH]vmscan: fix a livelock in kswapd Message-ID: <20110719083932.GD5349@suse.de> References: <1311059367.15392.299.camel@sli10-conroe> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <1311059367.15392.299.camel@sli10-conroe> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jul 19, 2011 at 03:09:27PM +0800, Shaohua Li wrote: > I'm running a workload which triggers a lot of swap in a machine with 4 nodes. > After I kill the workload, I found a kswapd livelock. Sometimes kswapd3 or > kswapd2 are keeping running and I can't access filesystem, but most memory is > free. This looks like a regression since commit 08951e545918c159. > Node 2 and 3 have only ZONE_NORMAL, but balance_pgdat() will return 0 for > classzone_idx. The reason is end_zone in balance_pgdat() is 0 by default, if > all zones have watermark ok, end_zone will keep 0. > Later sleeping_prematurely() always returns true. Because this is an order 3 > wakeup, and if classzone_idx is 0, both balanced_pages and present_pages > in pgdat_balanced() are 0. > We add a special case here. If a zone has no page, we think it's balanced. This > fixes the livelock. > > Signed-off-by: Shaohua Li > Acked-by: Mel Gorman It's also needed for 3.0 and 2.6.39-stable I believe. -- Mel Gorman SUSE Labs