基于国产ARM虚拟化平台的动态内存调度设计  

Dynamic memory scheduling design based on domestic ARM virtualization platform

作　　者：张勋臣 袁刚[1] 樊荣[1] Zhang Xunchen;Yuan Gang;Fan Rong(No.722 Research Institute,China Shipbuilding Industry Corporation,Wuhan,430205)

机构地区：[1]中国船舶重工集团公司第七二二研究所,湖北武汉430205

出　　处：《信息通信》2020年第12期63-67,共5页Information & Communications

摘　　要：为丰富虚拟化技术在未来的国产自主服务器上的应用,文章基于KVM虚拟化方案设计,针对传统静态分配内存资源在虚拟机上机械僵化、效率不高的问题,通过Ballooning内存技术,并结合智能优化算法,提出了一种由动态感知模块、预留保护模块、内存自适应模块组成的动态内存调度方案。实验结果表明,在使用动态内存调度方案下,实现了虚拟机内存的自动化部署,有效提高了虚拟机内存系统的性能。In order to enrich the application of virtualization technology on domestic autonomous servers in the future, this paper is based on the design of KVM virtualization scheme. Aiming at the mechanical rigidity and inefficiency of traditional statically allocated memory resources on virtual machines, Ballooning memory technology is adopted and combined with the intelligent optimization algorithm, a dynamic memory scheduling scheme consisting of a dynamic sensing module, a reservation protection module, and a memory adaptive module is proposed. The experimental results show that under the dynamic memory scheduling scheme, the automatic deployment of virtual machine memory is realized, which effectively improves the performance of the virtual machine memory system.

关 键 词：国产化 KVM 内存调度 智能优化算法 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]