[Gluster-users] RAID options for Gluster

[Brian Candler]

On Fri, Jun 15, 2012 at 10:14:02AM +0000, Fernando Frediani (Qube) wrote:
> Going to the idea of using RAID controllers would you think that for say
> 16 disks(or 12) Raid 5 would be fine given the data is already replicated
> somewhere in another node in a very unlikely event you loose a node.

I'd personally choose no more than 12 in a RAID set, but it's down to a
personal level of comfort.  You might also want to think about having a hot
spare.

> Now
> in a node with more number of disk slots could create multiple Raid 5
> logical volumes, but will Gluster be smart enough to not put replicated
> data on two logical volumes residing on the same node ?

As I said before, this is not "smart" but is done via explicit
configuration. See:
http://download.gluster.com/pub/gluster/glusterfs/3.2/Documentation/AG/html/sect-Administration_Guide--Setting_Volumes-Distributed_Replicated.html

Read the "Note" section highlighted in green.

> I don't even consider using RAID 10 as that would be a big waste

Performance, capacity, cheapness: choose any two.

> Also in a medium sized cluster it
> would give a good throughput when running backups for example.

It depends. Backing up to a tarfile: it will likely perform well. Creating
tons of individual small files: it will likely suck, especially if the
backup process is single-threaded.

Regards,

Brian.