Study on fault tolerance method in cloud platform based on workload consolidation model of virtual machine

作     者：Li, Zhixin Liu, Lei Tong, Zeyu 

作者机构：College of Computer Science and Technology Jilin University Changchun130012 China School of Computer Technology and Engineering Changchun Institute Of Technology Changchun130012 China Department of Applied Mathematics and Statistics Johns Hopkins University Baltimore21218 United States 

出 版 物：《Journal of Engineering Science and Technology Review》 (J. Eng. Sci. Technol. Rev.)

年 卷 期：2017年第10卷第5期

页      面：41-49页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0813[工学-建筑学] 0814[工学-土木工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors are grateful for the support provided by the Key Program for Science and Technology Development of Jilin Province of China (Grant No. 20130206052GX) 

主　　题：Virtual machine 

摘      要：The fault tolerance method of virtual machines (VM) guarantees reliability to the service capability of cloud platforms. VM workloads are dynamic and uncertain, and thus, they affect the reliability and task processing capability of entire cloud platforms. In this study, a fault tolerance method based on the VM workload consolidation model was proposed to solve problems concerning the reliability and task processing capability of cloud platforms caused by VM workloads, thus improving the reliability of VMs and overall performance of cloud platforms. First, the method was analyzed on the basis of the distinct relationship of VM workload and VM reliability and task processing capability. Then, the workload state of VM was predicted and analyzed by linear regression using VM workload monitoring data, and the VM workload consolidation algorithm was constructed based on expected workload constraint and optimization of fault tolerance time. Finally, the fault tolerance method based on the VM workload consolidation model was compared with the Radom method and the Max method. Research results demonstrate the potential of the proposed method to improve VM reliability in cloud platforms by 20% and 47% compared with those for the Radom and Max methods, respectively. In the same workload phase, the task completion rate of the proposed method increased significantly (15% and 30%, and 22% and 30%), and the percentages were higher than those for the Radom and Max methods, respectively. Moreover, the proposed method shortened task response time. This study concludes that the workload consolidation of VMs can increase the reliability and task processing capability of VMs. This proposed method can provide technological support to the fault tolerance of VMs in cloud platforms. © 2017 Eastern Macedonia and Thrace Institute of Technology.