RCAEval
收藏资源简介:
RCAEval数据集由皇家墨尔本理工大学和新南威尔士大学等机构创建,旨在支持微服务系统中的根因分析(RCA)。该数据集包含735个故障案例,来自三个微服务系统,涵盖11种故障类型,包括资源、网络和代码级故障。数据集通过多源遥测数据(如指标、日志和跟踪)进行收集,支持多种RCA方法的开发与评估。数据集的创建过程包括在Kubernetes集群中部署微服务系统,并通过Prometheus、Datadog Vector等工具收集数据。RCAEval数据集主要应用于微服务系统的故障诊断和根因分析,旨在提高系统的可靠性和可用性。
The RCAEval dataset was developed by institutions including RMIT University, the University of New South Wales, and other relevant institutions to support root cause analysis (RCA) in microservice systems. It contains 735 fault cases from three microservice systems, covering 11 fault types such as resource, network, and code-level faults. The dataset is collected via multi-source telemetry data including metrics, logs, and traces, which facilitates the development and evaluation of various RCA approaches. The dataset construction workflow involves deploying microservice systems on Kubernetes clusters and collecting data using tools like Prometheus, Datadog Vector, and other similar tools. The RCAEval dataset is primarily utilized for fault diagnosis and root cause analysis of microservice systems, with the objective of enhancing system reliability and availability.




