[Gluster-users] Gluster performance

Lone Wolf lonewolf4 at gmail.com
Tue Sep 27 11:15:50 UTC 2011

So I have this setup:
2 servers connected via a VPN (slow connection) since they are physically
Using the CLI I created a replicated volume with one brick on each server.
The problem starts when the access to the mounted volume is slow, "# time ls
/mount_point" is giving me around 0.5seconds
But if I cut the VPN connection the time goes down to around 0.005sec.
So I am assuming gluster is distributing the reads, being created with the
CLI I tried to edit the configurations manually and added "option
read-subvolume volume_name" to the cluster/replicate volume, being the
read-subvolume the local one.
But gluster still refuses to use only the local server.
Is there a way to force it? What I need is just gluster to keep the
directory mirrored, but the reads for performance reasons should be done
only locally and not using the remote server.

Thanks in advance
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20110927/bd6569b0/attachment.html>

More information about the Gluster-users mailing list