Separate ceph cluster vs special device class for older storage

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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



[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux