Hi! A followup to my previous message http://lists.ceph.com/pipermail/ceph-users-ceph.com/2016-February/007392.html . Due to some maintenance we had in out network I restarted all the nodes and the gateway one by one. Now when I run
radosgw-admin bucket check --fix --check-objects --bucket %bucket name% it runs for hours (23 hours already) on a ~10 GB bucket with ~1500 objects. I see some activity going on with "ceph -w", ~200 op/s and ~30mb/s of reads and nothing more. BTW, the same applies to radosgw-admin bucket list --bucket %bucket name% I can still use tools like s3 explorer and s3 api works on this bucket, except listing of one specific prefix though. Is there a way to trace what is going on? Is there any description on the bucket to pool mapping internals, so I can track the inconsistency myself? -- Best regards, Alexey Kuntsevich
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com