I had a 1x replicated fs data test pool, when a osd died I had '1 pg stale+active+clean of cephfs'[1] after a cluster reboot this turned into '1 pg unknown' ceph pg repair did not fix anything (for stale and unknown state) I recreated the pg with: ceph osd force-create-pg pg.id --yes-i-really-mean-it Question now is: Say I had one or two files in this pool/pg, is this still administered in the mds server? Do I need to fix something in the mds? PS. This was just performance testing pool, so at most there could be a few testing images on it, nothing important. [1] https://www.mail-archive.com/ceph-users@ceph.io/msg03147.html