Hi! Thank you for your help! The cluster is running healthily for a day now. Regarding the problem, I just checked in the release notes [1] and on docs.ceph.com and did not find the right invocation after an upgrade. Maybe that ought to be fixed. >> [upgrade from luminous to mimic with prior cephfs snapshots] > The correct commands should be: > > ceph daemon <mds of rank 0> scrub_path / force recursive repair > ceph daemon <mds of rank 0> scrub_path '~mdsdir' force recursive [1] https://ceph.com/releases/v13-2-0-mimic-released/ [2] https://www.google.com/search?q=site%3Adocs.ceph.com+scrub_path+inurl%3Amimic&oq=site%3Adocs.ceph.com+scrub_path+inurl%3Amimic Cheers, Tobias Florek _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |