基于用户云服务集群的资源动态调度研究  

Research on Dynamic Resource Scheduling Based on User Cloud Service Cluster

作　　者：马龙 陈庆奎[1] MA Long;CHEN Qingkui(School of Optical-Electrical Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093)

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200093

出　　处：《计算机与数字工程》2023年第7期1513-1518,共6页Computer & Digital Engineering

基　　金：国家自然科学基金项目(编号:61572325);上海重点科技攻关项目(编号:19DZ1208903);上海智能家居大规模物联共性技术工程中心项目(编号:GCZX14014)资助。

摘　　要：用户购买云服务器设施来搭建用户服务器集群,并将业务迁移到云服务器上后,很大程度上没有充分利用购买的计算资源。而随着业务量访问增加,传统的用户集群往往会通过增加服务节点来应对此情况,此时又需购买额外的云服务设施。论文基于传统用户的集群系统,使用改进的TOPSIS(逼近理想解排序法)算法结合集群监控信息来动态调度集群中节点上的应用。实验表明,该方案可以充分发挥用户购买的云服务器设施的计算资源,利用用户私有闲置资源来应对业务的突发访问,合理的调度用户服务器集群之间的业务应用分配,提高用户集群资源利用率的同时也保证了应用服务质量,节约了用户成本。After users purchase cloud server facilities to build user server clusters and migrate their business to cloud servers,they have largely underutilized the purchased computing resources.As business access increases,traditional user clusters often re-spond to this situation by adding service nodes,and at this time additional cloud service facilities need to be purchased.This article is based on the cluster system of traditional users,and uses the improved TOPSIS(Technique for Order Preferenceby Similarity to Ideal Solution)algorithm combined with cluster monitoring information to dynamically schedule applications on the nodes in the cluster.Experiments show that this solution can make full use of the computing resources of the cloud server facilities purchased by users,use users'private idle resources to cope with sudden business accesses,rationally schedule business application distribution among user server clusters,and improve user cluster resource utilization.At the same time,the application service quality is guaran-teed and user costs are saved.

关 键 词：用户集群 TOPSIS 集群监控 动态调度 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]