[LU-1247] After recovery 7 of 16 OST were deactivated by MDS.

• Type: Bug
• Resolution: Fixed
• Priority: Critical
• Fix Version/s: Lustre 2.3.0, Lustre 2.1.2
• Affects Version/s: Lustre 2.2.0
• Severity: 3
• Assignee: WC Triage
• Reporter: Alexander Boyko

Description

When recovering from failure, 7 of the 16 OSTs on the system were deactivated on the MDS.
The system was down for some hours. Then the fs was restarted (MDS rebooted), and after that, we saw:
snxs2n001 kernel: [ 4557.366336] LustreError: 22332:0:(lov_obd.c:1071:lov_clear_orphans()) error in orphan recovery on OST idx 11/16: rc = -22
snxs2n001 kernel: [ 4557.366343] LustreError: 22332:0:(mds_lov.c:880:__mds_lov_synchronize()) snxs2-OST000b_UUID failed at mds_lov_clear_orphans: -22
snxs2n001 kernel: [ 4557.366348] LustreError: 22332:0:(mds_lov.c:901:__mds_lov_synchronize()) snxs2-OST000b_UUID sync failed -22, deactivating
...
snxs2n004 kernel: [343022.475923] LustreError: 11898:0:(filter.c:3653:filter_handle_precreate()) snxs2-OST000b: ignoring bogus orphan destroy request: obdid 4710212 last_id 4730465
snxs2n004 kernel: [343022.522962] Lustre: Skipped 5 previous similar messages

Issue Links

• Trackbacks: Changelog 2.1 Changes from version 2.1.1 to version 2.1.2 Server support for kernels: 2.6.18308.4.1.el5 (RHEL5) 2.6.32220.17.1.el6 (RHEL6) Client support for unpatched kernels: 2.6.18308.4.1.el5 (RHEL5) 2.6.32220.17.1....