虚拟机迁移是数据中心提供的重要功能之一,可以有效地均衡各个基础设施中的工作负载。为有效地减少虚拟机迁移的总时间和对服务性能的影响,该文提出基于代价评估的启发式算法(Heuristic Algorithm based on Cost Evaluation, HACE)。算法在虚拟机迁移的每一步中综合考虑网络中的剩余带宽和迁移时间,通过有机结合并行算法和启发式算法,解决软件定义网络中数据中心大量虚拟机同时迁移时的迁移序列问题。算法在保证安全、依赖关系和性能要求的同时,减少虚拟机的总迁移时间。实验结果表明,与贪心算法相比,该算法能够减少虚拟机总迁移时间达到52.1%,提高迁移性能,确保服务质量。
Virtual machine migration is one of the important features of the data center, which can effectively balance the workload of each infrastructure. In order to reduce the total time of virtual machine migration and impact on service performance, a Heuristic Algorithm based on Cost Evaluation (HACE) is proposed in this paper. The proposed algorithm considers both the residual bandwidth of the network and migration time in every step of the virtual machine migration. And through organic combination of parallel algorithm and heuristic algorithm, it solves migration sequence problem of numerous virtual machines in Software Defined Network (SDN). The algorithm reduces the total migration time of the virtual machine while ensuring the security, dependence and performance requirements. Comparing with the greedy algorithm, experiments show that the algorithm can reduce the total migration time of the virtual machine by up to 52.1%, improve the migration performance and ensure the quality of service.
史久根,许辉亮, 陆立鹏. 软件定义网络中数据中心虚拟机迁移序列问题的研究[J]. 电子与信息学报, 2017, 39(5): 1193-1199.
SHI Jiugen, XU Huiliang, LU Lipeng. Research on the Migration Queue of Data Center’s Virtual Machine in Software Defined Networks. JEIT, 2017, 39(5): 1193-1199.
KREUTZ D, RAMOS F M V, and ESTEVES V P. Software defined networking: A comprehensive survey[J]. Proceedings of the IEEE, 2015, 103(1): 14-76. doi: 10.1109/JPROC.2014. 2371999.
[2]
HERMENIER F, LORCA X, and MENAUD J M. Entropy: A consolidation manager for clusters[C]. Proceedings of the ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, Washington, DC, USA, 2009: 41-50. doi: 10.1145/1508293.1508300.
[3]
BARI M F, ZHANI M F, ZHANG Q, et al. CQNCR: Optimal VM migration planning in cloud data centers[C]. Proceedings of IFIP Networking Conference, Trondheim, Norway, 2014: 1-9. doi: 10.1109/IFIPNetworking. 2014. 6857120.
[4]
DUOLIKUN D, WATANABE R, KATAOKA H, et al. An energy-aware migration of virtual machines[C]. 2016 IEEE 30th International Conference on Advanced Information Networking and Application, Crans-Montana, 2016: 557-564. doi: 10.1109/AINA.2016.156.
[5]
MAIO V D, KECSKEMETI G, and PRODAN R. A workload-aware energy model for virtual machine migration[C]. 2015 IEEE International Conference on Cluster Computing, Chicago, IL, 2015: 274-283. doi: 10.1109/ CLUSTER.2015.47.
[6]
GHORBANI S and CAESAR M. Walk the Line: Consistent network updates with bandwidth guarantees[C]. Proceedings of the First Workshop on Hot Topics in Software Defined Networks, HotSDN’12, New York, NY, USA, 2012: 67-72. doi: 10.1145/2342441.2342455.
[7]
YE Kejiang, JIANG Xiaohong, MA Ran, et al. VC-migration: live migration of virtual clusters in the cloud[C]. Proceedings of the 13th ACM/IEEE International Conference on Grid Computing, Beijing, China, 2012: 209-218. doi: 10.1109/Grid. 2012.27.
GAO Xianming, ZHANG Xiaozhe, WANG Baosheng, et al. Historical forwarding overhead based the resource scheduling algorithm for the virtual router[J]. Journal of Electronics & Information Technology, 2015, 37(3): 686-692. doi: 10.11999/ JEIT140491.
LIU Zhongjin, ZHUO Zihan, HE Yueying, et al. Dynamical Weighted Scheduling Algorithm supporting fair bandwidth allocation of virtual networks[J]. Journal of Electronics & Information Technology, 2016, 38(10): 2654-2659. doi: 10.11999/JEIT151485.
[10]
WOOD T, SHENOY P, VENKATARAMANI A, et al. Sandpiper: Black-box and gray-box resource management for virtual machines[J]. Computer Networks, 2009, 53(17): 2923-2938. doi: 10.1016/j.comnet.2009.04.014.
[11]
ZHANI M F, ZHANG Q, SIMONA G, et al. VDC Planner: dynamic migration-aware virtual data center embedding for clouds[C]. Proceedings of the 13th IFIP/IEEE International Symposiun on Integrated Network Management, Ghent, Belgium, 2013: 18-25.
[12]
GUO Chuanxiong, LU Guohan, WANG H J, et al. SecondNet: A data center network virtualization architecture with bandwidth guarantees[C]. Proceedings of the 6th International Conference, Philadelphia PA, USA, 2010. doi: 10.1145/ 1921168.1921188.
[13]
AMANI A and ZAMANIFAR K. Improving the time of live migration virtual machine by optimized algorithm scheduler credit[C]. Proceedings of the 4th International conference on Computer and Knowledge Engineering (ICCKE), 2014: 346-351. doi: 10.1109/ICCKE.2014.6993374.
[14]
CERRONI W and ESPOSITO F. Optimizing live migration of multiple virtual machines[J]. IEEE Transactions on Cloud Computing, 2016. doi: 10.1109/TCC.2016.2567381.
[15]
MANN V, GUPTA A, DUTTA P, et al. Remedy: Network-aware steady state VM management for data centers[C]. Proceedings of the 11th International IFIP TC 6 Networking Conference, Prague, Czech Republic, 2012: 190-204. doi: 10.1007/978-3-642-30045-5_15.
[16]
GANDHI R and MESTRE J. Combinatorial algorithms for data migration to minimize average completion time[C]. Proceedings of the 9th International Conference on Approximation Algorithms for Combinatorial Optimization Problems, Barcelona, Spain, 2006: 128-139. doi: 10.1007/ 11830924_14.
[17]
BARI M F, BOUTABA R, ESTEVES R, et al. Data center network virtualization: A survey[J]. IEEE Communications Surveys & Tutorials, 2013, 15(2): 909-928. doi: 10.1109/ SURV.2012.090512.00043.