基于OpenStack平台的云计算资源动态调度系统设计  

Design of Cloud Computing Resource Dynamic Scheduling System Based on OpenStack Platform

作　　者：张福铮 黄文琦 李果 张乾坤 ZHANG Fuzheng;HUANG Wenqi;LI Guo;ZHANG Qiankun(China Southern Power Grid Science and Technology Research Institute Co. Ltd., Guangzhou, 510663, China)

机构地区：[1]南方电网科学研究院有限责任公司,广东广州510663

出　　处：《微型电脑应用》2020年第11期63-65,69,共4页Microcomputer Applications

基　　金：南方电网科技项目(SEPRI-K174005)。

摘　　要：由于数据中心的数量以及规模持续增加,如何合理有效利用资源成为当前研究的热点话题。为此设计一种基于OpenStack平台的云计算资源动态调度系统。分析OpenStack平台现有的调度策略以及虚拟机迁移技术,建立数据中心资源模型。根据多重阈值判定虚拟机迁移时机,进行目标虚拟机选取;分别为不同主体的物理资源赋予不同的权值系数,计算总权重并进行排序,根据排序结果选取目的主机,以完成云计算资源动态调度。实验结果表明,对比其他资源调度系统,所设计系统数据中心不均衡度较低,且平均带宽利用率较高,验证了所设计系统的有效性。As the number and scale of data centers continue to increase,how to use resources reasonably and effectively has become a hot topic of current research.Therefore,a dynamic scheduling system of cloud computing resources based on OpenStack platform is designed.This paper analyzes the existing scheduling strategy and virtual machine migration technology of OpenStack platform,and establishes the resource model of data center.According to the multiple thresholds,the migration opportunity of virtual machine is determined,and the target virtual machine is selected;different weight coefficients are given to the physical resources of different entities,the total weight is calculated and sorted,and the target host is selected according to the sorting results to complete the dynamic scheduling of cloud computing resources.The experimental results show that compared with other resource scheduling systems,the designed system has lower data center imbalance and higher average bandwidth utilization,which verifies the effectiveness of the designed system.

关 键 词：OpenStack平台 云计算 资源动态调度 调度系统 

分 类 号：TN99[电子电信—信号与信息处理]