Automatic Root Cause Analysis via Large Language Models for Cloud Incidents

TL;DR

This paper presents RCACopilot, an AI-powered system that automates root cause analysis for cloud incidents, significantly improving efficiency and accuracy over manual methods using large language models.

Contribution

Introduction of RCACopilot, a novel LLM-based system that automates incident handling, diagnosis, and explanation for cloud service reliability.

Findings

RCA accuracy of up to 0.766 achieved

Successfully deployed at Microsoft for over four years

Automates diagnostic information collection and incident categorization

Abstract

Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual investigations of data sources such as logs and traces, are often laborious, error-prone, and challenging for on-call engineers. In this paper, we introduce RCACopilot, an innovative on-call system empowered by the large language model for automating RCA of cloud incidents. RCACopilot matches incoming incidents to corresponding incident handlers based on their alert types, aggregates the critical runtime diagnostic information, predicts the incident's root cause category, and provides an explanatory narrative. We evaluate RCACopilot using a real-world dataset consisting of a year's worth of incidents from Microsoft. Our evaluation demonstrates that RCACopilot achieves RCA accuracy up to 0.766. Furthermore, the diagnostic information collection component of RCACopilot has been successfully in use at Microsoft for over four years.