一个面向边缘服务系统资源监测的预警方法  

An Early Warning Method for Resource Monitoring of Edge Service System

作　　者：胡焱兵 陈庆奎[1] 

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海

出　　处：《软件工程与应用》2023年第2期318-329,共12页Software Engineering and Applications

摘　　要：边缘服务系统当中存在着众多计算节点,计算节点的资源是变化的,这些资源分为静态资源和动态资源。为了更好地发挥边缘服务集群系统的性能,充分利用各节点的资源,提升系统的可靠性与稳定性,构建一个针对集群系统资源的监控预警系统是很有必要的。目前有很多集群监控系统都很有特色,但是新有的监测底层工具提供了极大的方便性,本文利用现有的Prometheus和Grafana以及睿象云的优势特性,提取三者各自的优势功能,同时以本文设计的集成中间部件作为调节器,构建了一个集成中间件监控预警系统,通过此监控预警系统来支持边缘服务系统的资源监测的实现。实验结果表明,该监控预警系统能准确检测和及时报警系统出现的异常,保障了服务系统的安全性,使得其稳定运行。There are many computing nodes in the edge service system, and the resources of the computing nodes are changing, and these resources are divided into static resources and dynamic resources. In order to better utilize the performance of the edge service cluster system, make full use of the resources of each node, and improve the reliability and stability of the system, it is necessary to build a monitoring and early warning system for cluster system resources. At present, many cluster monitoring systems are very distinctive, but the new monitoring underlying tools provide great convenience. This paper uses the existing advantages of Prometheus, Grafana and Cloud Alert to extract the respective advantages of the three functions. At the same time, using the integrated middleware designed in this paper as a regulator, an integrated middleware monitoring and early warning system is constructed, through which the monitoring and early warning system supports the realization of resource monitoring of the edge service system. The experimental results show that the monitoring and early warning system can accurately detect and timely alarm the abnormality of the system, which ensures the security of the service system and makes it run stably.

关 键 词：监控预警 PROMETHEUS Grafana 睿象云 集成中间件 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]