Ceph is a beast and will require at least 2-3 technicians with intricate Ceph knowledge to run multiple (!) Ceph clusters in a business continuity responsible manner.
Because you must be able to deal with Ceph quirks.
If you can shard your data over multiple independent stand-alone ZFS boxes, that would be much simpler and more robust. But it might not scale like Ceph.
Because you must be able to deal with Ceph quirks.
If you can shard your data over multiple independent stand-alone ZFS boxes, that would be much simpler and more robust. But it might not scale like Ceph.