Case Study: National Energy Research Scientific Computing Center achieves better HPC facility monitoring with Grafana and Psychart

Monitoring HPC system health with Grafana and Psychart

The National Energy Research Scientific Computing Center (NERSC) operates powerful high-performance computing systems and needed to closely monitor its data center's environmental conditions to prevent equipment damage and inefficiency. Their challenge was that existing visualizations for critical psychrometric data were overwhelming, making it difficult to quickly discern the state of the air being supplied to their systems.

Using Grafana, NERSC engineer Nicolas Ventura built an integrated solution called Psychart, an open-source panel that visualizes real-time psychrometric data. This Grafana-based tool allows operators to instantly see if air conditions are within optimal ranges, leading to better system maintenance and preventing potential damage. The solution has been extremely successful, with over 8,000 downloads, and has been adopted by other national labs for monitoring their facilities.

National Energy Research Scientific Computing Center (NERSC)

Nicolas Ventura

Critical Facilities Engineer