From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756557Ab0JSChc (ORCPT ); Mon, 18 Oct 2010 22:37:32 -0400 Received: from mail-iw0-f174.google.com ([209.85.214.174]:38780 "EHLO mail-iw0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755928Ab0JSCh3 convert rfc822-to-8bit (ORCPT ); Mon, 18 Oct 2010 22:37:29 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=L+5ufpKQLuB2j9sRBJjqTPjsFbjXf75SgUI6sJqZM8nFoDwOf9Ckm0/7j0/pQ4cDGG i9TAjJB3QuuHYti3bTrnVg6g9Qz87obbafl/Y59WHpriW5OdCJ3E76cdW4dA5NJLW9mp WnAG3faH/APSX2sDVceQynQa6CEWbyKHb/FyQ= MIME-Version: 1.0 In-Reply-To: <20101019022451.GA8310@localhost> References: <20100915091118.3dbdc961@notabene> <4C90139A.1080809@redhat.com> <20100915122334.3fa7b35f@notabene> <20100915082843.GA17252@localhost> <20100915184434.18e2d933@notabene> <20101018151459.2b443221@notabene> <20101018161504.GB29500@localhost> <20101018145859.eee1ae33.akpm@linux-foundation.org> <20101019093142.509d6947@notabene> <20101018154137.90f5325f.akpm@linux-foundation.org> <20101019022451.GA8310@localhost> Date: Tue, 19 Oct 2010 11:37:29 +0900 Message-ID: Subject: Re: Deadlock possibly caused by too_many_isolated. From: Minchan Kim To: Wu Fengguang Cc: Andrew Morton , Neil Brown , Rik van Riel , KOSAKI Motohiro , KAMEZAWA Hiroyuki , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "Li, Shaohua" Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Oct 19, 2010 at 11:24 AM, Wu Fengguang wrote: > On Tue, Oct 19, 2010 at 06:41:37AM +0800, Andrew Morton wrote: >> On Tue, 19 Oct 2010 09:31:42 +1100 >> Neil Brown wrote: >> >> > On Mon, 18 Oct 2010 14:58:59 -0700 >> > Andrew Morton wrote: >> > >> > > On Tue, 19 Oct 2010 00:15:04 +0800 >> > > Wu Fengguang wrote: >> > > >> > > > Neil find that if too_many_isolated() returns true while performing >> > > > direct reclaim we can end up waiting for other threads to complete their >> > > > direct reclaim.  If those threads are allowed to enter the FS or IO to >> > > > free memory, but this thread is not, then it is possible that those >> > > > threads will be waiting on this thread and so we get a circular >> > > > deadlock. >> > > > >> > > > some task enters direct reclaim with GFP_KERNEL >> > > >   => too_many_isolated() false >> > > >     => vmscan and run into dirty pages >> > > >       => pageout() >> > > >         => take some FS lock >> > > >           => fs/block code does GFP_NOIO allocation >> > > >             => enter direct reclaim again >> > > >               => too_many_isolated() true >> > > >                 => waiting for others to progress, however the other >> > > >                    tasks may be circular waiting for the FS lock.. >> >> I'm assuming that the last four "=>"'s here should have been indented >> another stop. > > Yup. I'll fix it in next post. > >> > > > The fix is to let !__GFP_IO and !__GFP_FS direct reclaims enjoy higher >> > > > priority than normal ones, by honouring them higher throttle threshold. >> > > > >> > > > Now !GFP_IOFS reclaims won't be waiting for GFP_IOFS reclaims to >> > > > progress. They will be blocked only when there are too many concurrent >> > > > !GFP_IOFS reclaims, however that's very unlikely because the IO-less >> > > > direct reclaims is able to progress much more faster, and they won't >> > > > deadlock each other. The threshold is raised high enough for them, so >> > > > that there can be sufficient parallel progress of !GFP_IOFS reclaims. >> > > >> > > I'm not sure that this is really a full fix.  Torsten's analysis does >> > > appear to point at the real bug: raid1 has code paths which allocate >> > > more than a single element from a mempool without starting IO against >> > > previous elements. >> > >> > ... point at "a" real bug. >> > >> > I think there are two bugs here. >> > The raid1 bug that Torsten mentions is certainly real (and has been around >> > for an embarrassingly long time). >> > The bug that I identified in too_many_isolated is also a real bug and can be >> > triggered without md/raid1 in the mix. >> > So this is not a 'full fix' for every bug in the kernel :-), > >> > but it could well be a full fix for this particular bug. > > Yeah it aims to be a full fix for one bug. > >> Can we just delete the too_many_isolated() logic?  (Crappy comment > > If the two cond_resched() calls can be removed from > shrink_page_list(), the major cause of too many pages being > isolated will be gone. However the writeback-waiting logic after > should_reclaim_stall() will also block the direct reclaimer for long > time with pages isolated, which may bite under pathological conditions. > >> describes what the code does but not why it does it). > > Good point. The comment could be improved as follows. > > Thanks, > Fengguang > > --- > Subject: vmscan: comment too_many_isolated() > From: Wu Fengguang > Date: Tue Oct 19 09:53:23 CST 2010 > > Comment "Why it's doing so" rather than "What it does" > as proposed by Andrew Morton. > > Signed-off-by: Wu Fengguang Reviewed-by: Minchan Kim -- Kind regards, Minchan Kim