Ganglia

From Consultancy.EdVoncken.NET

Ganglia was designed for monitoring of HPC clusters.

Ganglia / Nagios Integration

Ganglia excels at large-scale monitoring. Nagios excels at alerting. These two qualities can be combined to build a highly scalable monitoring and alerting system.

• Ganglia and Nagios, Part 1: Monitor enterprise clusters with Ganglia

Ganglia issues

In some configurations, Ganglia keeps spewing messages to syslog:

 RRD_update illegal attempt to update using time 1234567890 \
   when last update time is 1234567890 (minimum one second step)

This error has been cropping up for years now; a quick Google search reveals:

• Illegal attempt to update RRDs with multiple gmetad
• RRD_update illegal attempt to update using time 1252671437 when last update time is 1252671437 (minimum one second step)