On 11/6/06, Nathaniel Rutman <[EMAIL PROTECTED]> wrote:
What version of Lustre are you all using?
Sumit Narayan wrote:
> Hi,
>
> I am stuck at the same point too! Here is my log.
>
> Nov 6 10:17:43 cluster3 kernel: Lustre:
> 3942:0:(module.c:382:init_libcfs_module()) maximum lustre stack 8192
> Nov 6 10:17:47 cluster3 kernel: Lustre: Added LNI [EMAIL PROTECTED]
> <mailto: [EMAIL PROTECTED]> [8/256]
> Nov 6 10:17:47 cluster3 kernel: Lustre: Accept secure, port 988
> Nov 6 10:18:01 cluster3 kernel: Lustre: OBD class driver Build
> Version: 1.4.7-19691231190000-PRISTINE-.usr.src.linux-2.6.12.6,
> [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]>
> Nov 6 10:18:01 cluster3 kernel: Lustre: Filtering OBD driver;
> [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]>
> Nov 6 10:18:02 cluster3 kernel: Lustre: Lustre Lite Client File
> System; [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]>
> Nov 6 10:18:02 cluster3 kernel: kjournald starting. Commit interval
> 5 seconds
> Nov 6 10:18:02 cluster3 kernel: LDISKFS FS on loop0, internal journal
> Nov 6 10:18:02 cluster3 kernel: LDISKFS-fs: mounted filesystem with
> ordered data mode.
> Nov 6 10:18:02 cluster3 kernel: Lustre:
> 4186:0:(filter.c:574:filter_init_server_data()) ost1-test:
> initializing new last_rcvd
> Nov 6 10:18:02 cluster3 kernel: Lustre: OST ost1-test now serving
> /dev/loop0 (ee8dee13-12db-4e06-8009-a5c7192d5956) with recovery enabled
> Nov 6 10:18:03 cluster3 kernel: kjournald starting. Commit interval
> 5 seconds
> Nov 6 10:18:03 cluster3 kernel: LDISKFS FS on loop1, internal journal
> Nov 6 10:18:03 cluster3 kernel: LDISKFS-fs: mounted filesystem with
> ordered data mode.
> Nov 6 10:18:03 cluster3 kernel: Lustre:
> 4383:0:(filter.c:574:filter_init_server_data()) ost2-test:
> initializing new last_rcvd
> Nov 6 10:18:03 cluster3 kernel: Lustre: OST ost2-test now serving
> /dev/loop1 (c1ae26ee-23ca-4a56-8475-10e9373d9875) with recovery enabled
> Nov 6 10:18:04 cluster3 kernel: kjournald starting. Commit interval
> 5 seconds
> Nov 6 10:18:04 cluster3 kernel: LDISKFS FS on loop2, internal journal
> Nov 6 10:18:04 cluster3 kernel: LDISKFS-fs: mounted filesystem with
> ordered data mode.
> Nov 6 10:18:04 cluster3 kernel: Lustre:
> 4417:0:(mds_fs.c:239:mds_init_server_data()) mds-test: initializing
> new last_rcvd
> Nov 6 10:18:04 cluster3 kernel: Lustre: MDT mds-test now serving
> /dev/loop2 (a110e01c-14b9-4cd6-b61a-3c39f231785f) with recovery enabled
> Nov 6 10:18:04 cluster3 kernel: Lustre: MDT mds-test has stopped.
> Nov 6 10:18:05 cluster3 kernel: kjournald starting. Commit interval
> 5 seconds
> Nov 6 10:18:05 cluster3 kernel: LDISKFS FS on loop2, internal journal
> Nov 6 10:18:05 cluster3 kernel: LDISKFS-fs: mounted filesystem with
> ordered data mode.
> Nov 6 10:18:05 cluster3 kernel: LustreError:
> 4586:0:(lvfs.h:130:ll_lookup_one_len()) bad inode returned
> 14032/1995494705
> Nov 6 10:18:05 cluster3 kernel: LustreError:
> 4586:0:(mds_fs.c:472:mds_fs_setup()) cannot create LOGS directory: rc
> = -2
> Nov 6 10:18:05 cluster3 kernel: LustreError:
> 4586:0:(handler.c:1878:mds_setup()) mds-test: MDS filesystem method
> init failed: rc = -2
> Nov 6 10:18:05 cluster3 kernel: LustreError:
> 4588:0:(obd_config.c:288:class_cleanup()) Device 4 not setup
>
> I had tried putting some extra logs and it appears that lustre fails
> when trying to enter the ROOT directory of probably the loop-mounted
> MDS. That's when it says bad inode. But I am unable to figure out the
> reason why that is happening. Any idea what could be wrong?
>
> A similar issue was noticed before...
> http://www.archivesat.com/ClusterFS/thread445676.htm
>
> Thanks in advance...
>
> regards,
> Sumit
>
>
> On 11/3/06, *Ronald Rivest* <[EMAIL PROTECTED]
> <mailto:[EMAIL PROTECTED] >> wrote:
>
> Hi,
>
> I am trying to install Lustre on a single node, behaving as all 3.
> I am trying to get this done from the source code of Lustre.
> However, when I try to start the lustre
>
> $ lconf --reformat local.xml
>
> I get the following error:
>
> .........
> .........
> MDSDEV:mds-test mds-test_UUID /tmp/mds-test ldiskfs 50000 yes
> MDS mount options: errors=remount-ro
> LustreError: 15565:0:(lvfs.h:130:ll_lookup_one_len()) bad inode
> returned 14/529619894
> LustreError: 15565:0:(mds_fs.c:472:mds_fs_setup()) cannot create
> LOGS directory: rc = -2
> LustreError: 15565:0:(handler.c:1878:mds_setup()) mds-test: MDS
> filesystem method init failed: rc=-2
> LustreError: 15567:0:(obd_config.c:288:class_cleanup()) Device 4
> not setup
> MDS failed to start. Check the syslog for details. (May need to
> run lconf --write-conf)
>
> I am using the default configuration and setup as given in the
> Lustre manual.
>
> Could someone highlight what the problem is?
>
> Thanks.
> RR
>
> _______________________________________________
> Lustre-discuss mailing list
> [email protected] <mailto:[email protected]>
> https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
>
>
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> Lustre-discuss mailing list
> [email protected]
> https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
>
_______________________________________________ Lustre-discuss mailing list [email protected] https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
