计算机科学 ›› 2016, Vol. 43 ›› Issue (11): 210-214.doi: 10.11896/j.issn.1002-137X.2016.11.041
余勇,车建华,徐焕良,蒋诚智
YU Yong, CHE Jian-hua, XU Huan-liang and JIANG Cheng-zhi
摘要: 针对Xen虚拟机系统执行网络I/O密集型负载时容易耗尽Domain0的CPU资源而过载和执行计算密集型负载时在客户域平均性能与数目之间存在线性规划的问题,提出了两个负载类型相关的性能模型。首先,通过分析Xen虚拟机系统处理网络I/O操作的CPU资源消耗规律,建立了CPU核共享和CPU核隔离两种情况下的客户域网络I/O操作请求次数计算模型;然后,通过分析多个相同客户域并行执行计算密集型负载的平均性能与一个相同客户域执行相同负载的性能表现之间的关系,建立了并行执行计算密集型负载的客户域平均性能分析模型。实验结果表明,两个性能模型能够有效地限制客户域提交的网络I/O操作请求次数以防止Xen虚拟机系统过载,并求解给定资源配置情况下执行计算密集型负载的Xen虚拟机系统客户域伸缩性数目。
[1] Barham P,Dragovic B,Fraser K,et al.Xen and the art of virtua-lization[C]∥Proceedings of the 19th ACM Symposium on Ope-rating Systems Principles(SOSP 2003).Bolton Landing,NY,USA,2003:164-177 [2] Shi L,Zou D Q,Jin H.Xen Virtualization Technology [M].Wuhan:Huazhong University of Science and Technology Press.2009:83-89(in Chinese) 石磊,邹德清,金海.Xen虚拟化技术[M].武汉:华中科技大学出版社,2009:83-89 [3] Bard Y.An analytic model of the VM/370 system[J].Proc.of IBM Journal of Research and Development,1978,22(5):498-508 [4] Wang S,Zhang W B,Wu H,et al.Approach of quantifying virtual machine Performance Interference Based on Hardware Performance Counter[J].Journal of Software,2015,6(8):2074-2090(in Chinese) 王卅,张文博,吴恒,等.一种基于硬件计数器的虚拟机性能干扰估算方法[J].软件学报,2015,6(8):2074-2090 [5] Yang L,Dai Y,Zhang B,et al.Queueing network based performance model for multi-tiered Web application with consideration of performance interference among virtual machine[J].Computer Science,2015,42(1):47-49(in Chinese) 杨雷,代钰,张斌,等.考虑虚拟机间性能互扰基于排队网的多层 Web应用性能分析模型[J].计算机科学,2015,42(1):47-49 [6] Zhou D Q,Si Q Q.Energy-efficient virtual machine placement for heterogeneous cloud platform[J].Computer Science,2015,42(3):81-84(in Chinese) 周东清,佀庆乾.异构云平台中能源有效的虚拟机部署研究[J].计算机科学,2015,2(3):81-84 [7] Akoush S,Sohan R,Rice A,et al.Predicting the performance of virtual machine migration[C]∥2010 IEEE International Symposium on Modeling,Analysis & Simulation of Computer and Telecommunication Systems(MASCOTS).IEEE,2010:37-46 [8] Ye K,Jiang X,Chen S,et al.Analyzing and modeling the performance in xen-based virtual cluster environment[C]∥2010 12th IEEE International Conference on High Performance Computing and Communications(HPCC).IEEE,2010:273-280 [9] Benevenuto F,Fernandes C,Santos M,et al.Performance mo-dels for virtualized applications[M]∥Frontiers of High Perfor-mance Computing and Networking-ISPA 2006 Workshops.Springer Berlin Heidelberg,2006:427-439 [10] Meng F,Du G,He H,et al.Performance Modeling on the Basis of Application Type in Virtualized Environments[J].Journal of Software,2013,8(11):2847-2854 [11] Wood T,Cherkasova L,Ozonat K,et al.Profiling and modeling resource usage of virtualized applications[C]∥Proceedings of the 9th ACM/IFIP/USENIX International Conference on Middleware.Springer-Verlag New York,Inc.,2008:366-387 [12] Menon A,Santos J R,Turner Y,et al.Diagnosing Performance Overheads in the Xen Virtual Machine Environment[C]∥Proc.of First ACM/USENIX Conference on Virtual Execution Environments(VEE05).Chicago,IL,2005:13-23 [13] Gupta D,Gardner R,Cherkasova L.XenMon:QoS Monitoringand Performance Profiling Tool[R].Technical Report HPL-2005-187,HP Labs,2005 [14] HP Labs.Welcome to the httperf homepage[EB/OL].http://www.hpl.hp.com/research/linux/httperf |
No related articles found! |
|