摘要
虚拟化技术抽象了物理计算资源层,将系统资源以资源池的方式进行集中管理,不仅提高了硬件资源利用率,而且可以提供按需服务,因此在企业服务器整合、数据中心、云计算平台中得到了广泛应用.为了满足峰值性能,传统多虚拟机系统常采用过量分配策略,因此造成系统资源的浪费.本文通过分析不同虚拟机的负载特征,提出并实现了一个基于负载特征的虚拟机放置策略.本文利用各种虚拟机负载的互补度,进行多次迭代配对,得到由多台虚拟机组成的配对组,对配对组进行统一分配资源.实验表明,本文提出的方法可将资源利用率较传统方法提高37.5%,较非迭代配对方法提高12.5%.在使用更少的物理机的同时,保持虚拟机性能基本不变.
Currently,virtualization is widely deployed in consolidated server systems,data centers and cloud computing platforms due to its advantages in resource Abstraction and pooling,improved higher resource utilization,and ability to on demand service provisioning.However,traditional Virtual Machines are often over-provisioned to provide peak performance and waste a lot of system resources.In this paper,after the analysis of the workload characteristics of virtual machines,we proposed and implemented a placement strategy of Virtual Machines based on workload characteristics.In our approach,the virtual machines are placed into various groups after several iterations and matchings based on the complementary degree of virtual machines′ workloads.Requested resources are allocated to virtual machines placed in the same group according to the sum of individual resource requests.The experiment results show that the resource utilization of our approach was increased by 37.5% compared to traditional placement approaches,and it was increased by 12.5% compared with non-iterative matching approach.The experiment results also show that our approach uses fewer physical machines and provides acceptable application performance in virtualized environments.
出处
《小型微型计算机系统》
CSCD
北大核心
2013年第3期520-524,共5页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(60873023
61003077)资助
浙江省自然科学基金项目(Y1101092)资助
国家"九七三"重点基础研究发展计划项目(2007CB310906)资助
关键词
放置策略
虚拟机
负载特征
placement strategy
virtual machines
workload characteristics
