Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934083AbXLPNs2 (ORCPT ); Sun, 16 Dec 2007 08:48:28 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1765905AbXLPNsU (ORCPT ); Sun, 16 Dec 2007 08:48:20 -0500 Received: from bizon.gios.gov.pl ([212.244.124.8]:51133 "EHLO bizon.gios.gov.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932100AbXLPNsT (ORCPT ); Sun, 16 Dec 2007 08:48:19 -0500 Date: Sun, 16 Dec 2007 14:46:36 +0100 (CET) From: Krzysztof Oledzki X-X-Sender: olel@bizon.gios.gov.pl To: Andrew Morton cc: Linus Torvalds , Linux Kernel Mailing List , Nick Piggin , Peter Zijlstra , Thomas Osterried , protasnb@gmail.com, bugme-daemon@bugzilla.kernel.org, Thomas Osterried Subject: Re: [Bug 9182] Critical memory leak (dirty pages) In-Reply-To: <20071216015112.d0ab08a1.akpm@linux-foundation.org> Message-ID: References: <20071215221935.306A5108068@picon.linux-foundation.org> <20071215203539.d6f71e96.akpm@linux-foundation.org> <20071216015112.d0ab08a1.akpm@linux-foundation.org> MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="-187430788-1450121612-1197812796=:25065" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3600 Lines: 104 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. ---187430788-1450121612-1197812796=:25065 Content-Type: TEXT/PLAIN; charset=ISO-8859-2; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE On Sun, 16 Dec 2007, Andrew Morton wrote: > On Sun, 16 Dec 2007 10:33:20 +0100 (CET) Krzysztof Oledzki = wrote: > >> >> >> On Sat, 15 Dec 2007, Andrew Morton wrote: >> >>> On Sun, 16 Dec 2007 00:08:52 +0100 (CET) Krzysztof Oledzki wrote: >>> >>>> >>>> >>>> On Sat, 15 Dec 2007, bugme-daemon@bugzilla.kernel.org wrote: >>>> >>>>> http://bugzilla.kernel.org/show_bug.cgi?id=3D9182 >>>>> >>>>> >>>>> ------- Comment #33 from protasnb@gmail.com 2007-12-15 14:19 ------- >>>>> Krzysztof, I'd hate point you to a hard path (at least time consuming= ), but >>>>> you've done a lot of digging by now anyway. How about git bisecting b= etween >>>>> 2.6.20-rc2 and rc1? Here is great info on bisecting: >>>>> http://www.kernel.org/doc/local/git-quick.html >>>> >>>> As I'm smarter than git-bistect I can tell that 2.6.20-rc1-git8 is as = bad >>>> as 2.6.20-rc2 but 2.6.20-rc1-git8 with one patch reverted seems to be = OK. >>>> So it took me only 2 reboots. ;) >>>> >>>> The guilty patch is the one I proposed just an hour ago: >>>> http://git.kernel.org/?p=3Dlinux%2Fkernel%2Fgit%2Fstable%2Flinux-2.6= =2E20.y.git;a=3Dcommitdiff_plain;h=3Dfba2591bf4e418b6c3f9f8794c9dd8fe40ae7b= d9 >>>> >>>> So: >>>> - 2.6.20-rc1: OK >>>> - 2.6.20-rc1-git8 with fba2591bf4e418b6c3f9f8794c9dd8fe40ae7bd9 reve= rted: OK >>>> - 2.6.20-rc1-git8: very BAD >>>> - 2.6.20-rc2: very BAD >>>> - 2.6.20-rc4: very BAD >>>> - >=3D 2.6.20: BAD (but not *very* BAD!) >>>> >>> >>> well.. We have code which has been used by *everyone* for a year and i= t's >>> misbehaving for you alone. >> >> No, not for me alone. Probably only I and Thomas Osterried have systems >> where it is so easy to reproduce. Please note that the problem exists on >> my all systems, but only on one it is critical. It is enough to run >> "sync; sleep 1; sunc; sleep 1; sync; grep Drirty /proc/meminfo" to be su= re. >> With =3D>2.6.20-rc1-git8 it *never* falls to 0 an *all* my hosts but onl= y >> on one it goes to ~200MB in about 2 weeks and then everything dies: >> http://bugzilla.kernel.org/attachment.cgi?id=3D13824 >> http://bugzilla.kernel.org/attachment.cgi?id=3D13825 >> http://bugzilla.kernel.org/attachment.cgi?id=3D13826 >> http://bugzilla.kernel.org/attachment.cgi?id=3D13827 >> >>> I wonder what you're doing that is different/special. >> Me to. :| >> >>> Which filesystem, which mount options >> >> - ext3 on RAID1 (MD): / - rootflags=3Ddata=3Djournal > > It wouldn't surprise me if this is specific to data=3Djournal: that > journalling mode is pretty complex wrt dairty-data handling and isn't wel= l > tested. > > Does switching that to data=3Dwriteback change things? I'll confirm this tomorrow but it seems that even switching to=20 data=3Dordered (AFAIK default o ext3) is indeed enough to cure this problem= =2E Two questions remain then: why system dies when dirty reaches ~200MB=20 and what is wrong with ext3+data=3Djournal with >=3D2.6.20-rc2? Best regards, =09=09=09=09Krzysztof Ol=EAdzki ---187430788-1450121612-1197812796=:25065-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/