Hi, All! I'm running a small ceph cluster (16.2.3) with cephfs an number of replicas = 3. Recently, after one of the nodes failure, I have performed a number of copy/move (not a delete ones) operations, while on of the pgs was inactive. There was no hangs, no errors reported, but, some directories was disappeared in the directory, where it was moved.
Now, all of pgs are active+clean (some of them are remapped), but missing directories are not returned. I have started journal recovery with the command: cephfs-journal-tool --rank files:all event recover_dentries summary it still working (more then 20 hours till now) without any visible results. I have made snapshots of data and metadata pools, before starting journal recovery, also made a backup of the journal. What is my next steps if the journal recovery will bring no results? Is there a way to manually find a specific directory record directly in the pool and restore it? I can write a program to fetch and parse cephs objects, but, may be, there is a specific tool for that? Thanks in advance, Pavel. _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
