Hello
As my organization transitions to Ceph, we are going to end
up with about 10PB older, out-of-warranty storage hardware
that we would like to continue using, until it becomes too
hard to maintain or fails, for non-critical purposes
(scratch space, replicas of backups in cold storage, etc.).
I am looking for advice about whether it would be better to
set up a separate Ceph cluster for such older hardware or to
create a special device class for it in our production Ceph
cluster.
Part of the challenge is that this older hardware is not
Ceph-friendly: a lot of it consists of big fibre channel
shelves of disks connected to a small number of servers.
Also, when one of these old servers or disks fails, they
will not be replaced.
What do people think? Would I be better off creating a new
cluster or a new device class within our production cluster?
Or is using basically dying hardware like this just a bad idea?
Thanks very much
Vlad
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx