COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
Yichen Li, Yulun Wu, Jinyang Liu, Zhihan Jiang, Zhuangbin Chen, Guangba Yu, Michael R. Lyu
Abstract
Runtime failures are commonplace in modern distributed systems. When such issues arise, users often turn to platforms such as Github or JIRA to report them and request assistance. Automatically identifying the root cause of these failures is critical for ensuring high reliability and availability. However, prevailing automatic root cause analysis (RCA) approaches rely significantly on comprehensive runtime monitoring data, which is often not fully available in issue platforms. Recent methods leverage large language models (LLMs) to analyze issue reports, but their effectiveness is limited by incomplete or ambiguous user-provided information. To obtain more accurate and comprehensive RCA results, the core idea of this work is to extract additional diagnostic clues from code to supplement data-limited issue reports. Specifically, we propose COCA, a code knowledge enhanced root cause analysis approach for issue reports. Based on the data within issue reports, COCA intelligently extracts relevant code snippets and reconstructs execution paths, providing a comprehensive execution context for further RCA. Subsequently, COCA constructs a prompt combining historical issue reports along with profiled code knowledge, enabling the LLMs to generate detailed root cause summaries and localize responsible components. Our evaluation on datasets from five real-world distributed systems demonstrates that COCA significantly outperforms existing methods, achieving a 28.3% improvement in root cause localization and a 22.0% improvement in root cause summarization. Furthermore, COCA's performance consistency across various LLMs underscores its robust generalizability. Bug ID Closed Major JobClient fails, removes files and in turn crashes MR AM Version: 0.23.0 Resolution: Fixed Assignee: Maintainer Reporter: Reporter Name Description We ran into this multiple times. MR JobClient crashes immediately. the application was created and added to the list of apps. So if the client contacts the RM, it returns the application which perhaps is still in NEW state.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 074d9ee7-7456-41df-b91f-f7e7f3ed7a2aCited by top-tier papers1
Ask how each one uses itBuilds on22
- CodeT5+: Open Code Large Language Models for Code Understanding and GenerationYue Wang, Hung Le, Akhilesh Gotmare, Nghi D. Q. Bui et al.EMNLP 2023 · 339 citations
- Using an LLM to Help With Code UnderstandingDaye Nam, Andrew Macvean, Vincent J. Hellendoorn, Bogdan Vasilescu et al.ICSE 2024 · 264 citations
- Automatic Root Cause Analysis via Large Language Models for Cloud IncidentsYinfang Chen, Huaibing Xie, Minghua Ma, Yu Kang et al.EuroSys 2024 · 175 citations
- Nezha: Interpretable Fine-Grained Root Causes Analysis for Microservices on Multi-modal Observability DataGuangba Yu, Pengfei Chen, Yufeng Li, Hongyang Chen et al.FSE 2023 · 131 citations
- Eadro: An End-to-End Troubleshooting Framework for Microservices on Multi-source DataCheryl Lee, Tianyi Yang, Zhuangbin Chen, Yuxin Su et al.ICSE 2023 · 99 citations
Related papers
- OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?Junjielong Xu, Qinan Zhang, Zhiqing Zhong, Shilin He et al.ICLR 2025
- MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal KnowledgeShuai Liang, Pengfei Chen, Bozhe Tian, Gou Tan et al.FSE 2026 · 4 citations
- RCAFlow: A Workflow-Informed Hierarchical Planning Multi-Agent System for Root Cause AnalysisYufei Gao, Zhengong Cai, Bowei YangAAAI 2026
- FoundRoot: Towards Foundation Model for Root Cause Analysis via Structured Deep ThinkingZhe Xie, Zeyan Li, Xiao He, Shenglin Zhang et al.ICSE 2026
- Planning a Large Language Model for Static Detection of Runtime Errors in Code SnippetsSmit Patel, Aashish Yadavally, Hridya Dhulipala, Tien N. NguyenICSE 2025 · 1 citation
