On Wed, Mar 25, 2015 at 6:37 PM, Robert LeBlanc <robert@xxxxxxxxxxxxx> wrote: > As far as the foreign journal, I would run dd over the journal > partition and try it again. It sounds like something didn't get > cleaned up from a previous run. I wrote zeros on the journal device re-created the journal with "ceph-osd --makejournal", and it seems that the latter command didn't write anything on the partition: starting osd.196 at :/0 osd_data /var/lib/ceph/osd/ceph-196 /var/lib/ceph/osd/ceph-196/journal SG_IO: bad/missing sense data, sb[]: 70 00 05 00 00 00 00 28 00 00 00 00 20 00 00 00 00 00 00 85 55 ac 01 00 00 00 00 00 00 00 20 00 SG_IO: bad/missing sense data, sb[]: 70 00 05 00 00 00 00 28 00 00 00 00 20 00 00 00 00 00 00 85 55 ac 01 00 00 00 00 00 00 00 20 00 HDIO_DRIVE_CMD(identify) failed: Input/output error 2015-04-07 14:07:53.703247 7f0e32433900 -1 journal FileJournal::open: ondisk fsid 00000000-0000-0000-0000-000000000000 doesn't match expected 35cd523e-4a74-41ae-908a-f25267a94dac, invalid (someone else's?) journal 2015-04-07 14:07:53.703569 7f0e32433900 -1 filestore(/var/lib/ceph/osd/ceph-196) mount failed to open journal /var/lib/ceph/osd/ceph-196/journal: (22) Invalid argument 2015-04-07 14:07:53.703956 7f0e32433900 -1 ** ERROR: error converting store /var/lib/ceph/osd/ceph-196: (22) Invalid argument Note the "fsid 00000..." line. I've also tried to zap and re-create with ceph-deploy, same results. Maybe it's not writing to the journal file because of the "bad missing data" error? It's strange thought, that error seems to come from "hdparm -W" not working on those disks, but I have the same error on *all* of my disks... Any other idea? .a. -- antonio.s.messina@xxxxxxxxx antonio.messina@xxxxxx +41 (0)44 635 42 22 S3IT: Service and Support for Science IT http://www.s3it.uzh.ch/ University of Zurich Winterthurerstrasse 190 CH-8057 Zurich Switzerland _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |