Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study
This addresses the challenge of inefficient manual log analysis for IT support teams, though it appears incremental as it applies existing LLM methods to a specific domain.
The paper tackles the problem of analyzing large volumes of logs in IT software support by proposing a tool that uses Large Language Models (LLMs) for automated log processing and issue diagnosis, resulting in time savings of over 300 man-hours and estimated cost savings of $15,444 per month from deployment across 70 products.
IT environments typically have logging mechanisms to monitor system health and detect issues. However, the huge volume of generated logs makes manual inspection impractical, highlighting the importance of automated log analysis in IT Software Support. In this paper, we propose a log analytics tool that leverages Large Language Models (LLMs) for log data processing and issue diagnosis, enabling the generation of automated insights and summaries. We further present a novel approach for efficiently running LLMs on CPUs to process massive log volumes in minimal time without compromising output quality. We share the insights and lessons learned from deployment of the tool - in production since March 2024 - scaled across 70 software products, processing over 2000 tickets for issue diagnosis, achieving a time savings of 300+ man hours and an estimated $15,444 per month in manpower costs compared to the traditional log analysis practices.