[Gluster-users] Serious performance problem

[Lindsay Mathieson]

On 27 October 2015 at 08:06, Stefan Michael Guenther <s.guenther at in-put.de>
wrote:

> But I learned from the mailing list, that this is a common message and
> that I shouldn't me concerned about it.
>
> But the problem is, when I copy a 1.2 GB file from /root to /mnt (gluster
> volume mounted via nfs) this takes more than 24 seconds. Copying the same
> file to /tmp takes less than one second, according to the time command.
>

Hi Stefan, a bit more information on your setup would be useful
- Brick topology - replica 3? distributed?
- Node hardware (Mem/CPU)
- Network Setup (Number of cards per node, speed)

But assuming a replica 3 setup a 1GB ethernet then the numbers are close to
what you would expect. When you copy a file to the mount it is
simultaneously copied to the other two bricks over the network connection.
Copying 1.2 GB over 1G ethernet takes approx 10 seconds, and you are
copying it to two other bricks, so 20 seconds total. And that assumes the
network isn't loaded with other demands.

With std 1Gb Ethernet, your limiting factor will be your network speed.


Also, Gluster 3.2 is pretty old and no longer getting updates, you might
want to consider upgrading to 3.5, 3.6 or 3.7 :) I believe its a tricky
upgrade, so don't rush into it.




-- 
Lindsay
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20151027/1497eb4d/attachment.html>