LLM-Powered Fully Automated Chaos Engineering: Towards Enabling Anyone to Build Resilient Software Systems at Low Cost
This work addresses the problem of enabling non-experts to build resilient software systems at low cost, representing an incremental advancement by automating manual processes in Chaos Engineering.
The paper tackles the labor-intensive and expertise-dependent nature of Chaos Engineering by proposing ChaosEater, a system that automates the entire CE cycle using Large Language Models for Kubernetes-based software systems, demonstrating consistent completion of reasonable CE cycles with significantly low time and monetary costs in case studies.
Chaos Engineering (CE) is an engineering technique aimed at improving the resilience of distributed systems. It involves intentionally injecting faults into a system to test its resilience, uncover weaknesses, and address them before they cause failures in production. Recent CE tools automate the execution of predefined CE experiments. However, planning such experiments and improving the system based on the experimental results still remain manual. These processes are labor-intensive and require multi-domain expertise. To address these challenges and enable anyone to build resilient systems at low cost, this paper proposes ChaosEater, a system that automates the entire CE cycle with Large Language Models (LLMs). It predefines an agentic workflow according to a systematic CE cycle and assigns subdivided processes within the workflow to LLMs. ChaosEater targets CE for software systems built on Kubernetes. Therefore, the LLMs in ChaosEater complete CE cycles through software engineering tasks, including requirement definition, code generation, testing, and debugging. We evaluate ChaosEater through case studies on small- and large-scale Kubernetes systems. The results demonstrate that it consistently completes reasonable CE cycles with significantly low time and monetary costs. Its cycles are also qualitatively validated by human engineers and LLMs.