From: Andreas Dilger Subject: Re: large file system & high object count testing Date: Mon, 31 Aug 2009 17:13:31 -0600 Message-ID: <20090831231331.GJ4197@webber.adilger.int> References: <4A9BFB88.5030409@redhat.com> <4A9C0220.1040503@redhat.com> <20090831205608.GE4197@webber.adilger.int> <4A9C3A7B.3050302@redhat.com> <150c16850908311425vbc1c0a1if2a7d8ed56f650f5@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Ric Wheeler , linux-ext4@vger.kernel.org, "Ted Ts'o" To: Justin Maggard Return-path: Received: from sca-es-mail-1.Sun.COM ([192.18.43.132]:39049 "EHLO sca-es-mail-1.sun.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751452AbZHaXNe (ORCPT ); Mon, 31 Aug 2009 19:13:34 -0400 Received: from fe-sfbay-10.sun.com ([192.18.43.129]) by sca-es-mail-1.sun.com (8.13.7+Sun/8.12.9) with ESMTP id n7VNDUhe012898 for ; Mon, 31 Aug 2009 16:13:32 -0700 (PDT) Content-disposition: inline Received: from conversion-daemon.fe-sfbay-10.sun.com by fe-sfbay-10.sun.com (Sun Java(tm) System Messaging Server 7u2-7.04 64bit (built Jul 2 2009)) id <0KP900000KABHY00@fe-sfbay-10.sun.com> for linux-ext4@vger.kernel.org; Mon, 31 Aug 2009 16:13:30 -0700 (PDT) In-reply-to: <150c16850908311425vbc1c0a1if2a7d8ed56f650f5@mail.gmail.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Aug 31, 2009 14:25 -0700, Justin Maggard wrote: > On Aug 31, 2009 =A013:02 -0400, Ric Wheeler wrote: > > Mount after fsck: > > Aug 31 12:27:12 megadeth kernel: EXT4-fs (dm-75): > > ext4_check_descriptors: Checksum for group 487 failed (59799!=3D468= 27) > > Aug 31 12:27:12 megadeth kernel: EXT4-fs (dm-75): group descriptors > > corrupted! >=20 > Ah, so it's not just me. It looks like you're seeing the exact same > thing I reported a few days ago in the ">16TB issues" thread. You > don't even have to do anything fancy to make this happen. My test > case involves simply creating 5 directories on the newly-created > 64-bit filesystem, and running e2fsck on it immediately after > unmounting to get the same results. Justin, could you please replicate this corruption, collecting some additional information before & after. My recollection is that the corruption appears in the first few groups, so 64kB should be plenty to capture the group descriptor tables (where the checksum is kept). - mke2fs - dd if=3D/dev/XXX bs=3D4k count=3D16 | gzip -9 > /tmp/gdt-new.gz - mkdir ... - sync - dd if=3D/dev/XXX bs=3D4k count=3D16 | gzip -9 > /tmp/gdt-mkdir.gz - umount - dd if=3D/dev/XXX bs=3D4k count=3D16 | gzip -9 > /tmp/gdt-umount.gz - e2fsck - dd if=3D/dev/XXX bs=3D4k count=3D16 | gzip -9 > /tmp/gdt-e2fsck.gz Cheers, Andreas -- Andreas Dilger Sr. Staff Engineer, Lustre Group Sun Microsystems of Canada, Inc. -- To unsubscribe from this list: send the line "unsubscribe linux-ext4" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html