Received: with ECARTIS (v1.0.0; list linux-xfs); Mon, 27 Oct 2003 10:31:59 -0800 (PST) Received: from twin.jikos.cz (IDENT:root@twin.jikos.cz [213.151.79.26]) by oss.sgi.com (8.12.10/8.12.10) with SMTP id h9RIVE25018325 for ; Mon, 27 Oct 2003 10:31:15 -0800 Received: from localhost (jikos@localhost) by twin.jikos.cz (8.11.6/8.11.6) with ESMTP id h9NLnxu13114; Thu, 23 Oct 2003 23:49:59 +0200 Date: Thu, 23 Oct 2003 23:49:59 +0200 (CEST) From: Jirka Kosina To: linux-kernel@vger.kernel.org cc: linux-xfs@oss.sgi.com Subject: 2.6.0-test8 XFS bug Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-archive-position: 822 X-ecartis-version: Ecartis v1.0.0 Sender: linux-xfs-bounce@oss.sgi.com Errors-to: linux-xfs-bounce@oss.sgi.com X-original-sender: jikos@jikos.cz Precedence: bulk X-list: linux-xfs Content-Length: 4147 Lines: 70 Hi, I've installed 2.6.0-test8 on machine attached to HW raid, made 5.5TB partition (using LVM) and made XFS filesystem on this partition. This partittion was exported to cca 25 nodes. I started some stress tests (writing and reading files through NFS) from these nodes to this partition and went home. The other day I found out that syslog filled up /var/log/messages with backtraces (see below), and the XFS filesystem went just totally crappy (for example when I had some file on this partition, and did simple cp to another name, the content of the new file was corrupted (NFS was not involved in this)). When I make this partition ext3, things seem to work well. The backtrace: Oct 22 13:12:56 storage2 kernel: 0x0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Oct 22 13:12:56 storage2 kernel: Filesystem "dm-0": XFS internal error xfs_alloc_read_agf at line 2208 of file fs/xfs/xfs_alloc.c. Caller 0xc01e8f5c Oct 22 13:12:56 storage2 kernel: Call Trace: Oct 22 13:12:56 storage2 kernel: [] xfs_alloc_read_agf+0x19e/0x214 Oct 22 13:12:56 storage2 kernel: [] xfs_alloc_fix_freelist+0x458/0x46e Oct 22 13:12:56 storage2 last message repeated 2 times Oct 22 13:12:56 storage2 kernel: [] xfs_trans_log_buf+0x6e/0xa8 Oct 22 13:12:56 storage2 kernel: [] xfs_bmbt_get_state+0x2f/0x3c Oct 22 13:12:56 storage2 kernel: [] xfs_alloc_vextent+0x2f4/0x520 Oct 22 13:12:56 storage2 kernel: [] xfs_bmap_alloc+0x8eb/0x1856 Oct 22 13:12:56 storage2 kernel: [] xfs_iomap_write_delay+0x35e/0x40a Oct 22 13:12:56 storage2 kernel: [] xfs_bmbt_get_state+0x2f/0x3c Oct 22 13:12:56 storage2 kernel: [] xfs_bmapi+0xfaf/0x165c Oct 22 13:12:56 storage2 kernel: [] _xfs_imap_to_bmap+0x35/0x28e Oct 22 13:12:56 storage2 kernel: [] xfs_bmbt_get_state+0x2f/0x3c Oct 22 13:12:56 storage2 kernel: [] xfs_bmap_do_search_extents+0xb8/0x3f0 Oct 22 13:12:56 storage2 kernel: [] xfs_trans_unlocked_item+0x39/0x58 Oct 22 13:12:56 storage2 kernel: [] xfs_log_reserve+0xc1/0xc6 Oct 22 13:12:56 storage2 kernel: [] xfs_iomap_write_allocate+0x2b5/0x4c4 Oct 22 13:12:56 storage2 kernel: [] generic_file_aio_write_nolock+0x244/0xa9e Oct 22 13:12:56 storage2 kernel: [] xfs_iomap+0x411/0x54a Oct 22 13:12:56 storage2 kernel: [] map_blocks+0x72/0x128 Oct 22 13:12:56 storage2 kernel: [] page_state_convert+0x4fa/0x626 Oct 22 13:12:56 storage2 kernel: [] ip_local_deliver+0x1b7/0x1c8 Oct 22 13:12:56 storage2 kernel: [] ip_rcv+0x341/0x4a2 Oct 22 13:12:56 storage2 kernel: [] linvfs_writepage+0x60/0x10c Oct 22 13:12:56 storage2 kernel: [] mpage_writepages+0x21f/0x2f6 Oct 22 13:12:56 storage2 kernel: [] process_backlog+0x6e/0xfe Oct 22 13:12:56 storage2 kernel: [] linvfs_writepage+0x0/0x10c Oct 22 13:12:56 storage2 kernel: [] do_writepages+0x36/0x38 Oct 22 13:12:56 storage2 kernel: [] __filemap_fdatawrite+0xe3/0xec Oct 22 13:12:57 storage2 kernel: [] filemap_fdatawrite+0x17/0x1c Oct 22 13:12:57 storage2 kernel: [] nfsd_sync+0x63/0xc0 Oct 22 13:12:57 storage2 kernel: [] vfs_writev+0x60/0x64 Oct 22 13:12:57 storage2 kernel: [] nfsd_write+0x1c7/0x356 Oct 22 13:12:57 storage2 kernel: [] udp_sendpage+0x16d/0x2d0 Oct 22 13:12:57 storage2 kernel: [] skb_copy_and_csum_bits+0x1e3/0x2b0 Oct 22 13:12:57 storage2 kernel: [] nfsd_proc_write+0xa8/0x122 Oct 22 13:12:57 storage2 kernel: [] nfsd_dispatch+0xe8/0x1e8 Oct 22 13:12:57 storage2 kernel: [] nfsd_dispatch+0x0/0x1e8 Oct 22 13:12:57 storage2 kernel: [] svc_process+0x4f9/0x684 Oct 22 13:12:57 storage2 kernel: [] nfsd+0x1ff/0x3c6 Oct 22 13:12:57 storage2 kernel: [] nfsd+0x0/0x3c6 Oct 22 13:12:57 storage2 kernel: [] kernel_thread_helper+0x5/0xc P.S.: I am subscribed only to LKML, so please if replying to linux-xfs mailing list, be so kind and CC: me. Thanks. -- JiKos.