[Linux-cluster] Is there any software available for HPC monitoring

[Subhendu Ghosh]

Jamshed Zaidi wrote:
> Hello to everyone, this is my 2nd post on this group i want to know that 
> any Open source tool which is available for monitoring and managing HPC 
> (high performance clustering) ???. i got Ganglia. Its amazing effort by 
> *University** of California , Berkeley. your response will be appreciated.*
> 
> http://www.technorabit.com/2008/09/04/monitoring-hpc/


Both Ganglia and Collectd will allow you to capture system performance 
history. Collectd has a Nagios plugin that can be used to escalate based on 
performance thresholds. Others have integrated Ganglia with Nagios as well.

The real answer depends on what you mean by monitoring- fault, performance, other?

-regards
Subhendu

-- 
Subhendu Ghosh
Solutions Architect
Red Hat