First, do not panic :)
Secondly, verify that the number of pg pools is adapted to the need and the cluster.
Third, if I understood correctly, there was a too small number of pg in the pool and the data is essentially on a PG => wait for the data to be distributed correctly.
If possible, there is pg-upmap for a finer distribution of PGs.
ceph-users mailing list -- firstname.lastname@example.org
To unsubscribe send an email to email@example.com