[Ganglia-general] Multiple data sources within single grid?

2014-10-22 Thread Loris Bennett
Hi, I have a system comprising 100 compute nodes, 2 administration nodes (in a high-availability set-up) and a dedicated log-in node. I would like to monitor these three groups separately and save the RRD files in file system provided by either NFS or DRBD. My questions are: 1. Is each of

[Ganglia-general] Configuration problem after failover

2015-03-20 Thread Loris Bennett
Hi, I have the following in my gmetad.conf data_source Admin_Nodes 10 admin:8648 data_source Compute_Nodes 10 admin:8649 and when I look at the ports in use, I have $ netstat -plane | egrep 'gmon|gme' tcp0 0 0.0.0.0:86510.0.0.0:* LISTEN 493

Re: [Ganglia-general] Configuration problem after failover

2015-03-24 Thread Loris Bennett
On 03/20/2015 10:23 AM, Loris Bennett wrote: Hi, I have the following in my gmetad.conf data_source Admin_Nodes 10 admin:8648 data_source Compute_Nodes 10 admin:8649 and when I look at the ports in use, I have $ netstat -plane | egrep 'gmon|gme' tcp0 0 0.0.0.0:8651

Re: [Ganglia-general] Configuration problem after failover

2015-03-26 Thread Loris Bennett
Rick Cobb rick_c...@ieee.org writes: Generally what you do is have all the compute nodes send to a gmond server on the administrative nodes, and then have gmetad poll that gmond. You use a unicast setup on the compute node gmonds to do this (IIRC, you can have them send to more than one for