ChaosEater: Fully Automating Chaos Engineering with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kikuta, Daisuke, Ikeuchi, Hiroki, Tajiri, Kengo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910912369131520
author Kikuta, Daisuke
Ikeuchi, Hiroki
Tajiri, Kengo
author_facet Kikuta, Daisuke
Ikeuchi, Hiroki
Tajiri, Kengo
contents Chaos Engineering (CE) is an engineering technique aimed at improving the resiliency of distributed systems. It involves artificially injecting specific failures into a distributed system and observing its behavior in response. Based on the observation, the system can be proactively improved to handle those failures. Recent CE tools implement the automated execution of predefined CE experiments. However, defining these experiments and improving the system based on the experimental results still remain manual. To reduce the costs of the manual operations, we propose ChaosEater, a system for automating the entire CE operations with Large Language Models (LLMs). It predefines the agentic workflow according to a systematic CE cycle and assigns subdivided operations within the workflow to LLMs. ChaosEater targets CE for Kubernetes systems, which are managed through code (i.e., Infrastructure as Code). Therefore, the LLMs in ChaosEater perform software engineering tasks to complete CE cycles, including requirement definition, code generation, debugging, and testing. We evaluate ChaosEater through case studies on both small and large Kubernetes systems. The results demonstrate that it stably completes reasonable single CE cycles with significantly low time and monetary costs. The CE cycles are also qualitatively validated by human engineers and LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11107
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChaosEater: Fully Automating Chaos Engineering with Large Language Models
Kikuta, Daisuke
Ikeuchi, Hiroki
Tajiri, Kengo
Software Engineering
Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
Chaos Engineering (CE) is an engineering technique aimed at improving the resiliency of distributed systems. It involves artificially injecting specific failures into a distributed system and observing its behavior in response. Based on the observation, the system can be proactively improved to handle those failures. Recent CE tools implement the automated execution of predefined CE experiments. However, defining these experiments and improving the system based on the experimental results still remain manual. To reduce the costs of the manual operations, we propose ChaosEater, a system for automating the entire CE operations with Large Language Models (LLMs). It predefines the agentic workflow according to a systematic CE cycle and assigns subdivided operations within the workflow to LLMs. ChaosEater targets CE for Kubernetes systems, which are managed through code (i.e., Infrastructure as Code). Therefore, the LLMs in ChaosEater perform software engineering tasks to complete CE cycles, including requirement definition, code generation, debugging, and testing. We evaluate ChaosEater through case studies on both small and large Kubernetes systems. The results demonstrate that it stably completes reasonable single CE cycles with significantly low time and monetary costs. The CE cycles are also qualitatively validated by human engineers and LLMs.
title ChaosEater: Fully Automating Chaos Engineering with Large Language Models
topic Software Engineering
Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
url https://arxiv.org/abs/2501.11107