Analyzing HPC Support Tickets: Experience and Recommendations

TL;DR

This paper analyzes HPC support tickets to improve support tools, automate issue categorization, and recommend system enhancements, aiming to enhance problem resolution efficiency and system health monitoring.

Contribution

It introduces proof of concept tools for automating ticket categorization and similarity detection, and proposes new reporting categories for HPC support systems.

Findings

Automated ticket categorization prototype developed

Similarity recommendation system demonstrated

New reporting categories proposed

Abstract

High performance computing (HPC) user support teams are the first line of defense against large-scale problems, as they are often the first to learn of problems reported by users. Developing tools to better assist support teams in solving user problems and tracking issue trends is critical for maintaining system health. Our work examines the Los Alamos National Laboratory HPC Consult Team's user support ticketing system and develops proof of concept tools to automate tasks such as category assignment and similar ticket recommendation. We also generate new categories for reporting and discuss ideas to improve future ticketing systems.