一句话：提出 ErrorPrism，结合静态分析与 LLM 智能体，自动重建微服务中从日志到根源的完整错误传播路径。
云服务系统中故障会级联传播。现代微服务开发中广泛使用的错误包装会在函数调用栈的每一层为错误添加上下文，形成从技术根源到业务影响的错误链，但从最终日志消息回溯完整错误传播路径十分困难，现有方法效果不佳。本文提出 ErrorPrism，用于自动重建生产微服务中的错误传播路径。它先对服务代码仓库进行静态分析，构建函数调用图并将日志字符串映射到候选函数，从而大幅缩小路径搜索空间；然后使用 LLM 智能体进行迭代反向搜索，精确重建完整的多跳错误路径。在 ByteDance 的 67 个生产微服务上对 102 个真实错误进行评估，ErrorPrism 达到 97.0% 的重建准确率，优于现有静态分析和基于 LLM 的方法。它为工业微服务系统中的根因分析提供了有效且实用的工具。
Reliability management in cloud service systems is challenging due to the cascading effect of failures. Error wrapping, a practice prevalent in modern microservice development, enriches errors with context at each layer of the function call stack, constructing an error chain that describes a failure from its technical origin to its business impact. However, this also presents a significant traceability problem when recovering the complete error propagation path from the final log message back to its source. Existing approaches are ineffective at addressing this problem. To fill this gap, we present ErrorPrism in this work for automated reconstruction of error propagation paths in production microservice systems. ErrorPrism first performs static analysis on service code repositories to build a function call graph and map log strings to relevant candidate functions. This significantly reduces the path search space for subsequent analysis. Then, ErrorPrism employs an LLM agent to perform an iterative backward search to accurately reconstruct the complete, multi-hop error path. Evaluated on 67 production microservices at ByteDance, ErrorPrism achieves 97.0% accuracy in reconstructing paths for 102 real-world errors, outperforming existing static analysis and LLM-based approaches. ErrorPrism provides an effective and practical tool for root cause analysis in industrial microservice systems.
DOI 原文 ·
@inproceedings{paperbot9393,
title = {ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systems},
author = {Junsong Pu and Yichen Li and Zhuangbin Chen and Jinyang Liu and Zhihan Jiang and Jianjun Chen and Rui Shi and Zibin Zheng and Tieying Zhang},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00292}
}