[Gluster-users] High CPU Usage Using Glusterfs

Joseph Hardeman jwhardeman at gmail.com
Sat Mar 10 04:56:15 UTC 2012


Hi Guys,

I have 2 servers with a fresh install of glusterfs and I am seeing a very
high CPU load.  I am trying to just do a very basic config to get this
started and for the life of me, I don't know what could be causing it.  The
CPU goes up to 100% across all 4 CPU's on each gluster node and I am seeing
timeouts coming from the vms that I am testing with.  I simply copied the
glusterfsd.vol.sample, edited the brick option directory and started both
systems.  I then added the peer and the volume and started it.  Now when I
try to create or do anything on a vm, it sends the CPU's to 100% and the
vm's start having issues, slowness, none responsiveness, etc.

Does anyone have a good working configuration that they would be willing to
share?  I am hitting dead ends trying to figure out a good config for
glusterfs (2 nodes) and NFS.

I have installed glusterfs-geo-replication-3.2.5-2.el6.x86_64,
glusterfs-fuse-3.2.5-2.el6.x86_64, glusterfs-core-3.2.5-2.el6.x86_64.  I
probably don't need the geo-replication but the site said to install it. *S*

Thanks

Joe
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20120309/4c4992c3/attachment.html>


More information about the Gluster-users mailing list