[Gluster-users] Shared VM disk/image on gluster for redundancy?

[Jeff Darcy]

On 06/29/2010 04:57 PM, Emmanuel Noobadmin wrote:
> Just realized something but most likely it's just me missing it.
>
> If I were to add additional storage servers to the mix, doesn't it
> mean I would have to edit the volume files for every single
> application server and add an entry for datasrv2vol0 then datasrv3vol0
> when I add a fourth? Sounds a little tedious Show me one shred of evidence to the contrary - not just their own words - and I'll consider it,

Indeed it is, but it's pretty much going to be the case for any 
configuration where the entire namespace is shared among all clients.  
Scripted volfile generation helps, but complex data-distribution needs 
will always be reflected in complex volfiles eventually.

>   and also if I didn't
> understand wrongly, replicate will simply use these to replicate the
> same data so I don't get increased capacity, just increased
> redundancy.
>    

You can get either, depending on how you define your lower-level 
replicate volumes.  If you define each to have exactly one app-node 
volume and one data-node volume, then it will replicate each file 
exactly twice no matter how it's used in higher-level nufa volumes.  You 
can add multiple storage/posix volumes per data node to gain even more 
flexibility in how you do that.  That's kind of the genius of the 
translator approach: instead of being limited to the combinations that 
are embedded in monolithic code, you can combine as many volumes on as 
many nodes in as many ways as you want and still end up with a single 
purpose-tuned filesystem for clients to use.