一种能耗感知的虚拟集群CPU资源自动再配置方法  

Automatic Power-Aware Reconfiguration of Processor Resource in Virtualized Clusters

作　　者：金海[1,2] 邓莉[1,2] 吴松[1,2] 石宣化[1,2] 周理科[1,2] 

机构地区：[1]服务计算技术与系统教育部重点实验室华中科技大学武汉430074 [2]集群与网格计算湖北省重点实验室华中科技大学武汉430074

出　　处：《计算机研究与发展》2011年第7期1123-1133,共11页Journal of Computer Research and Development

基　　金：国家“九七三”重点基础研究计划基金项目(2007CB310900);国家自然科学基金项目(61073024,60973037);教育部新世纪优秀人才支持计划基金项目(NCET07-0334);武汉市晨光科技计划基金项目(201050231075)

摘　　要：系统虚拟化技术可以动态再配置应用环境的计算资源.当前动态资源配置方法主要关注于保证具有动态负载应用的服务质量.这些方法受应用性能驱动并常常增加资源控制系统的响应延迟.针对上述问题提出了以资源使用状态为驱动的资源再配置方法(resource-use-status-drivenresource reconfigurationscheme,RUSiC),自动适应动态负载变化来满足应用性能的资源需求.RUSiC被设计成2层架构的资源再配置模型,基于实时的资源使用状态,及时用较小的开销为应用调整合适的资源配置.同时,RUSiC也考虑到电能的有效使用,在资源的新配置中通过尽可能减少激活物理节点的数量避免大量不必要的电能消耗及相关的冷却费用.实验数据表明,在应用负载变化时,RUSiC能快速监测并响应变化的资源需求,并在保证应用性能的前提下,使用较小数量的激活物理节点.Virtualization provides significant benefits of system maintenance, load balancing, fault tolerance, and power-saving in clusters or data centers. It also enables dynamic reconfiguration of computing resource for application environment. However, current dynamic resource control approaches mainly focus on how to satisfy the application-level quality of service （QoS） when application workloads vary with time. They are driven by application performance, which is often specific to certain class of applications and also weakens the response capability of control systems. In this paper, a resource-use-status-driven resource reconfiguration scheme （RUSiC） is presented to automatically adapt to dynamic workload changes to meet the demands of application performance. According to the new characteristics introduced by system virtualization, the scheme is designed to be a two-layer resource reconfiguration model to exactly grasp the demands of applications. Based on real resource use status, the scheme adjusts proper resource configuration for applications in time. Furthermore, the scheme introduces power-saving into resource reconfiguration process and avoids considerable unnecessary power and cooling consumption by reducing the number of active physical nodes in a new resource configuration. Experiments demonstrate that the scheme can quickly detect and respond to shifting resource demands as application workloads change over time.

关 键 词：系统虚拟化 虚拟机 实时迁移 多核处理器 资源再配置 

分 类 号：TP315[自动化与计算机技术—计算机软件与理论]