MPCDF HPC Performance Monitoring System: Enabling Insight via Job-Specific Analysis

TL;DR

This paper presents a comprehensive HPC performance monitoring system at MPCDF that collects, aggregates, and visualizes job-specific metrics, aiding stakeholders in performance analysis and system management.

Contribution

It introduces a lightweight, open-source middleware and a scalable architecture for detailed, real-time HPC performance monitoring and reporting.

Findings

Enables detailed per-job performance analysis

Improves system management and user support

Demonstrates scalability on large HPC systems

Abstract

This paper reports on the design and implementation of the HPC performance monitoring system deployed to continuously monitor performance metrics of all jobs on the HPC systems at the Max Planck Computing and Data Facility (MPCDF). Thereby it reveals important information to various stakeholders, in particular to users, application support, system administrators, and management. On each compute node, hardware and software performance monitoring data is collected by our newly developed lightweight open-source hpcmd middleware which builds upon standard Linux tools. The data is transported via rsyslog, and aggregated and processed by a Splunk system, enabling detailed per-cluster and per-job interactive analysis in a web browser. Additionally, performance reports are provided to the users as PDF files. Finally, we report on practical experience and benefits from large-scale deployments on MPCDF HPC systems, demonstrating how our solution can be useful to any HPC center.