微软研究峰会2021 | 讲座：基于大规模运维数据的云原生软件多维度分析

Dynamic and static analysis of source code has been widely used in software development practices for purposes such as reverse engineering, design issue detection, and fault localization. Cloud-native software, which is featured by containerized and microservice-based architecture, has been the new trend of cloud-based software. A cloud-native software system can be a large-scale ecosystem consisting of a large number of small services undergoing continuous online evolution. Therefore, the complexity has been shifted from the development of individual services to the service interactions at the architecture level. Cloud-native systems still need software analysis for various purposes, but the basis for software analysis has been turned from source code to operational data. This talk will present our vision and exploration of multidimensional analysis of cloud-native software based on large-scale operational data. Our work combines the analysis of traces, logs, and metrics for different purposes, such as anomaly detection, fault localization, business flow analysis, and architecture evaluation.

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit