ccolumbu at hotmail.com
Fri Mar 5 19:58:28 UTC 2010
You only need to run glusterfs-volgen once.
It will create the .vol files you need then you copy them around.
Answer to #1:
You will run it on the primary server.
--export-directory must be a 2.x thing cause I don't use it in 3.x.
I am assuming that the --export-directory should equal the <path to mount point of the partition to share> from my how to.
Answer to #2:
The reason you have multiple servers listed in the glusterfs-volgen command is that you are creating a client side replication or distribution, so each client
needs to know about each server. This is also why you only have to run the command once. In effect you are creating a config file for all nodes and all servers
at the same time.
I hope that clears things up.
m.roth at 5-cent.us wrote:
> Well, my manager wants me to try to get glusterfs working from the rpms
> that the CentOS team has, so it's try to get 2.0.8 working. I started to
> follow Chad's process... and ran into the same thing that started me on
> this: his glusterfs-volgen has *no* --export-directory in the command.
> Googling, I found <http://www.cs.cmu.edu/~ewalter/gluster/> which is, in
> fact, 2.0.8. However, there's things I still don't get. Now, I've
> installed the server and common on all my nodes. I've only installed
> common and client on my head node (this is an HPC cluster that I'm
> building this on).
> 1) where do I run the glusterfs-volgen command, on the head (client) box,
> or on each of the servers?
> 2) if the latter, why does the command offer the option of listing
> multiple hosts?
> I have, as the link I posted recommends, symlinked /etc/glusterfs with
> /usr/local/etc/glusterfs. I've created the directories I want as part of
> this on each of my nodes, all with the same name.
> Once I get this part, then I'll get to the client side...
> Gluster-users mailing list
> Gluster-users at gluster.org
More information about the Gluster-users