[Gluster-users] Running Gluster client/server on single process

[Tejas N. Bhise]

Roberto,

Since you said you are running distribute each gluster client ( mount ) will get files from multiple servers ( backends ). So you might not save that much. Secondly, any problem in your client code may also kill your server process ( if they are same ) and the other clients/mounts that use backend subvolumes on this server will suffer too.

You may want to try running in the same process and see how much you gain and whether its worth it for your kind of data usage. Let me know how you go forward with this and if you have more questions.

Regards,
Tejas.

----- Original Message -----
From: "Roberto Franchini" <franchini at celi.it>
To: "gluster-users" <gluster-users at gluster.org>
Sent: Sunday, May 16, 2010 7:12:49 PM
Subject: Re: [Gluster-users] Running Gluster client/server on single process

On 5/16/10, Tejas N. Bhise <tejas at gluster.com> wrote:
> Robert,
>
> Is there any specific reason why you want to run the client and server in a
> single process ?


Why? Well, since the boxes are client and server at the same time we
think  running  gluster in single process can save system resources.
We run gluster 3.0.4 on ubuntu 9.10 (4 nodes) and 10.04 (2 nodes)
server. We are going to update all the nodes to 10.04 in few weeks.
4 nodes are application servers (tomcat) and 2 run batches. Each byte
of ram, or cpu cycle, gained  improve our overall performance :)
But maybe running single process will degradate them.
Regards,
R.

-- 
Roberto Franchini
http://www.celi.it
http://www.blogmeter.it
http://www.memesphere.it
Tel +39.011.562.71.15
jabber:ro.franchini at gmail.com skype:ro.franchini
_______________________________________________
Gluster-users mailing list
Gluster-users at gluster.org
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users