[Gluster-users] Way to improve GlusterFS performance for serving rails applications?
hsanson at gmail.com
Fri Oct 29 16:23:03 UTC 2010
I am testing GlusterFS for hosting Rails web applications but the performance
is incredibly poor.
I installed GLusterFS 3.1 in two servers (Ubuntu 10.10 LTS 64 bit) with 1TB
disk each formated with ext4. Then created a replicated volume:
sudo gluster volume create opt replica 2 transport tcp host1:/opt host2:/opt
then mounted the volume using the GlusterFS client on my web app server that
contains my rails applications:
host1:/opt /opt glusterfs defaults,_netdev 0 0 # in /etc/fstab
The problem is that if I run any rails application when stored in the gluster
volume it take minutes to start and then each page load take 5~10 secs. If
instead I run the rails app from the local hard disk in the same machine it
goes fast as thunder.
To give an idea here is some output from rails log file:
# Using gluster to store the rails application takes 5.6 secs to render a page
Completed in 5645ms (View: 2948, DB: 46) | 200 OK
# Using local storage it take 400ms to render the same page
Completed in 401ms (View: 296, DB: 34) | 200 OK
All machines (both storage and rails app) are connected to the same switch via
1GB ethernet and there is no other traffic in that switch (is isolated).
Am I doing something wrong or missing something or is this expected?
Are there any options I can set when mounting the partition to improve
Are there any options I can use when creating the volume to improve
More information about the Gluster-users