基于阈值滑动窗口机制的虚拟机迁移判决算法

Dynamic Threshold Window Algorithm for Virtual Machines Migration Decision

数据中心是云计算中数据运算、交换、存储的中心。近年来以虚拟机为粒度的虚拟机放置管理成为云数据中心能耗管理、实现动态可伸缩资源提供的重要支撑技术。在虚拟机放置的动态管理阶段,虚拟机迁移触发机制主要是根据物理主机中资源利用率的变化情况,决定是否需要将虚拟机迁移到其它主机。迁移时机判决准确能够有效地平衡过热点并关掉过冷点。当前的迁移时机缺乏对整个数据中心负载变化行为趋势的反映,也因为静态的阈值设定容易发生频繁的迁移,造成不必要的迁移代价和传输开销。提出了基于阈值滑动窗口机制的虚拟机迁移判决算法(iWnd),其能够根据整个数据中心任务量的多少动态调整高低阈值间窗口的大小,减少了任务量满负荷时期需要迁移虚拟机的数量,从而避免不必要的迁移开销和传输代价,有效地实现节能。在云计算平台Cloudsim上进行了仿真实验。结果表明,提出的iWnd算法在减少虚拟机迁移数量、降低迁移失败率上有良好的效果,同时并未产生过多额外的功耗。

Cloud data center（DC） is the center of data operation, exchange and storage. Based on virtualization technolo- gy, virtual maehine（VM） placement has become an important technology for power management and elastic resource provision. In the stage of dynamic VMs management, with the changes of resources utilization, migration trigger mecha- nism will determine when to migrate the VMs from one host to the other. The accurate judgment of trigger time can balance the hot spots effectively and turn off cold spots in DC. However, current migration trigger mechanism lacks the response to the changes of DC workloads, and static threshold setting is easy to cause frequent migration with unnecessary migration and transmission cost. To solve these problems, a dynamic threshold setting algorithm, iWnd was proposed,which adjusts the size of threshold windows according to the workloads on the whole DC. In addition, iWnd reduces the number of VMs which need to be migrated, avoiding unnecessary migration and transmission cost and saving power. We made the experiments on a simulated cloud environment using Cloudsim toolkit. Our efforts show that iWnd can effectively reduce the number of VMs migration and migration failure rate without producing additional power consumption.