Year: 2021
Type: conference-paper
Abstract: Recently, it has become a trend for developers to build applications using the microservice architecture.The functionality of each application is divided into multiple independent microservices, which are interconnected to others.With the emergence of cloud-native technologies, such as Docker and Kubernetes, developers can achieve a consistent and scalable delivery for complex software applications.However, it is challenging to diagnose performance issues in microservices due to the complex runtime environments and the numerous metrics.In this paper, we propose a novel root cause analysis approach named AAMR.AAMR firstly constructs a service dependency graph based on real-time metrics.Next, it updates the anomaly weight of each microservice automatically.Finally, a PageRankbased random walk is applied for further ranking root causes, i.e., ranking potential problematic services.Experiments conducted on Kubernetes clusters show that the proposed approach achieves a good analysis result, which outperforms several state-of-the-art methods.
Author: Zekun Zhang
Institution: Wuhan University
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: G5452219684, G5675372752, G6134627929
OpenAlex ID: W3197415297