Gluster users - Jul 2009 - DHT and AFR question

Hi,

I'm setting up gluster to share /usr/local among 24 compute nodes.  The 
basic goal is to be able to change files in /usr/local in one place, and 
have it replicate out to all the other nodes.

What I'd like to avoid is having a single point of failure where one (or 
several) nodes go down and the gluster volume becomes unavailable 
everywhere.  I've begun to set it up using this example 
<http://www.gluster.org/docs/index.php/Mixing_DHT_and_AFR>.

If all the nodes are both client and servers, how many replicate volumes 
should I have?  I don't want a ton of replication traffic, but 
redundancy is important.  Maximizing the size of the volume is less 
important to me since I'm just reclaiming otherwise unused local disk 
space on the nodes.

Thanks,
Matt

----- "Matt M" <misterdot at gmail.com> wrote:
 
> If all the nodes are both client and servers, how many replicate
> volumes should I have?  I don't want a ton of replication traffic, but 
> redundancy is important.  Maximizing the size of the volume is less 
> important to me since I'm just reclaiming otherwise unused local disk
> space on the nodes.
You can export /usr/local on each node, and then group two nodes each
into a replicate volume to get 12 replicate volumes. You can then
group these 12 into a single distribute volume, and mount this
volume on all the 24 nodes.

Vikas
-- 
Engineer - http://gluster.com/