It could be both necessary and recommended, depending on what you want to achieve. I've gone through a few awkward moments because of not having RAID in our distribute-replicated volume, but nothing you can't solve shutting down the node and replacing the drive. RAID will give you transparency and tolerance to drive failures and is even better if we talk about a good HW RAID. What about RAID 5, is that possible?
2014-10-27 21:28 GMT-03:00 Lindsay Mathieson <lindsay.mathieson@xxxxxxxxx>:
I have a 2 node proxmox cluster running 16 VM's off a NAS NFS share
over 1GB ethernet.
Looking at moving to local storage shared between the nodes using
Gluster replication, over a dedicated 1GB link. 3TB WD Red drives on
each node.
I was going to setup RAID1 (2*3TB) on each node, but is that overkill?
Read performance would be improved, but the bottleneck for writes is
going to be the 1GB ethernet anyway.
Data is backed up online offsite nightly and DR backups are done
weekly to external drives, because as we all know, RAID is not a
backup :)
--
Lindsay
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users
Pavlik Salles Juan José
_______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://supercolony.gluster.org/mailman/listinfo/gluster-users
