Cloud incidents pose major operational challenges in production, with unresolved production cloud incidents cost on average over $2M per hour. Prior research identifies code- and configuration-related issues as the predominant category of root causes in cloud incidents. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosing code- and configuration-caused cloud incidents. PRAXIS employs an LLM-driven structured traversal over two types of graph: (1) a service dependency graph (SDG) that captures microservice-level dependencies; and (2) a hammock-block program dependence graph (PDG) that captures code-level dependencies for each microservice. Together, these graphs encode microservice- and code-level dependencies and the LLM acts as a traversal policy over these graphs, moving between services and code dependencies to localize and explain failures. Compared to state-of-the-art ReAct baselines, PRAXIS improves RCA accuracy by up to 3.1x while reducing token consumption by 3.8x. PRAXIS is demonstrated on a set of 30 comprehensive real-world incidents that is being compiled into an RCA benchmark.
翻译:云事件在生产环境中构成重大运维挑战,未解决的云生产事件平均每小时造成超过200万美元损失。先前研究指出,代码与配置相关问题在云事件根因中占据主导地位。本文提出PRAXIS——一个用于诊断代码与配置引发的云事件的智能体工作流编排器。PRAXIS采用大语言模型驱动的结构化遍历机制,作用于两类图结构:(1) 捕获微服务级依赖关系的服务依赖图;(2) 为每个微服务构建的捕获代码级依赖关系的鞍块程序依赖图。这些图共同编码了微服务级与代码级依赖关系,大语言模型作为图遍历策略,通过在服务与代码依赖间迁移来实现故障定位与解释。相较于最先进的ReAct基线方法,PRAXIS将根因分析准确率最高提升3.1倍,同时降低3.8倍的令牌消耗。该研究基于30个真实场景的完整事件集验证了PRAXIS的有效性,该事件集正在被整合为根因分析基准测试集。