AI 中文总结
提出KRCA系统，通过多阶段流水线（API级钻取、骨架因果图、记忆增强多智能体框架）实现超大规模微服务的高效根因定位与故障分类，AC@1达0.88和0.79，诊断时间减少77.3%。
AI 中文摘要
超大规模微服务系统已成为大型互联网公司的标准基础设施。这些系统由众多松散耦合的微服务组成，通过持续开发和部署独立演进。这种复杂性使得故障不可避免，需要高效的根因分析（RCA）来帮助站点可靠性工程师（SRE）快速定位根因服务并分类故障类型。然而，现有的RCA方法往往难以适应这些系统的极端动态性和大规模性。在本文中，我们提出了KRCA，一个为超大规模微服务系统设计的端到端RCA系统。为了管理巨大的搜索空间，KRCA采用多阶段流水线，首先进行API级钻取以隔离可疑服务。然后，它从异常指标实例化基于骨架的因果图，作为高召回率的结构先验，之后利用记忆增强的多智能体框架验证因果关系并生成最终故障报告。通过结合结构化因果约束与多智能体推理，KRCA在诊断准确性与实时生产环境的效率需求之间取得了平衡。实验结果表明，KRCA在根因服务定位和故障类型分类上的AC@1得分分别为0.88和0.79，比最强基线至少高出31%的绝对增益。KRCA已在快手生产环境部署超过六个月，平均诊断时间减少77.3%。
英文摘要
Hyper-scale microservice systems have become the standard infrastructure for large-scale Internet companies. These systems consist of numerous loosely coupled microservices that evolve independently through continuous development and deployment. Such complexity makes failures unavoidable, necessitating efficient Root Cause Analysis (RCA) to help Site Reliability Engineers (SREs) quickly localize root cause services and classify failure types. However, existing RCA methods often struggle to adapt to the extreme dynamism and massive scale of these systems. In this paper, we present KRCA, an end-to-end RCA system designed for hyper-scale microservice systems. To manage the vast search space, KRCA employs a multi-stage pipeline that begins with an API-level drilldown to isolate suspicious services. It then instantiates a skeleton-based causal graph from anomalous metrics to serve as a high-recall structural prior, before utilizing a memory-augmented multi-agent framework to verify causality and generate the final failure report. By combining structured causal constraints with multi-agent reasoning, KRCA employs balances diagnostic accuracy with the efficiency requirements of real-time production use. Experimental results show that KRCA achieves AC@1 scores of 0.88 and 0.79 for root cause service localization and failure type classification, outperforming the strongest baseline by at lease 31% in absolute gains. KRCA has been deployed in Kuaishou's production environment for over six months, reducing the average diagnosis time by 77.3%.
