From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753286Ab2IZHmP (ORCPT ); Wed, 26 Sep 2012 03:42:15 -0400 Received: from tee.schottelius.org ([77.109.138.222]:41443 "EHLO mx3.schottelius.org" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752778Ab2IZHmM (ORCPT ); Wed, 26 Sep 2012 03:42:12 -0400 Date: Wed, 26 Sep 2012 08:03:12 +0200 From: Nico Schottelius To: Dave Kleikamp Cc: David Rientjes , Nico Schottelius , Arend van Spriel , "linux-kernel@vger.kernel.org" , "linux-wireless@vger.kernel.org" , Dave Kleikamp , jfs-discussion@lists.sourceforge.net Subject: Re: Out of memory on 3.5 kernels Message-ID: <20120926060312.GC16575@schottelius.org> Mail-Followup-To: Nico Schottelius , Dave Kleikamp , David Rientjes , Arend van Spriel , "linux-kernel@vger.kernel.org" , "linux-wireless@vger.kernel.org" , Dave Kleikamp , jfs-discussion@lists.sourceforge.net References: <505B1FA0.6030100@broadcom.com> <20120921194931.GA732@schottelius.org> <5061C8A2.1020605@oracle.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <5061C8A2.1020605@oracle.com> User-Agent: echo $message | gpg -e $sender -s | netcat mailhost 25 X-Netzseite: http://www.nico.schottelius.org/ X-System-Info: brief (Linux 3.5.4-1-ARCH x86_64) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Good morning, Dave Kleikamp [Tue, Sep 25, 2012 at 10:07:14AM -0500]: > >> Active / Total Objects (% used) : 1165130 / 1198087 (97.2%) > >> Active / Total Slabs (% used) : 81027 / 81027 (100.0%) > >> Active / Total Caches (% used) : 69 / 101 (68.3%) > >> Active / Total Size (% used) : 1237249.81K / 1246521.94K (99.3%) > >> Minimum / Average / Maximum Object : 0.01K / 1.04K / 15.23K > >> > >> OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME > >> 993607 993607 100% 1.21K 75358 26 2411456K jfs_ip > > > > Well that doesn't look good. 100% of the inode cache for jfs are being > > used which either means > > > > - there's a memory leak, or > > maybe a missing iput() somewhere? > > Nico, does unmounting the usb drive after killing the backup clean up > the jfs inode cache? Iirc, it does not. I'll check this evening, because doing the backup currently forces me to reboot my productive system. > > - there's some sort of throttling issue in jfs. > > > > And those objects are consuming ~2.3GB of slab on your 4GB machine and > > seems to only have occurred between v3.4.2 to v3.5.3. > > Almost nothing in jfs has changed between these releases. Only this: > > vfs: Rename end_writeback() to clear_inode() The other obscurity is that the root filesystem is also jfs - it's not only the usb disk. Cheers, Nico -- PGP key: 7ED9 F7D3 6B10 81D7 0EC5 5C09 D7DC C8E4 3187 7DF0