Abstract:As an elastic control approach,switch migration plays an important role in multi-controller load balancing in software defined networking (SDN).In order to solve the problems of low migration efficiency and high migration cost in the existing schemes,this paper proposes Switch Dynamic Migration (SDM) Strategy based on efficiency optimization.We firstly analyze the composition of controller loads in detail,set up the load difference matrix to know the distribution of loads,and introduce a trigger factor,which is used to judge load balancing on controllers through comparing the overload threshold.Then,we formulate the migration objects,and introduce the migration efficiency model,which considers load balance rate and migration cost simultaneously to select the migrating switches and immigrating controllers.Finally,we set migration triplet to complete the migration mapping and achieve the efficient switch migration.Simulation results show this mechanism could lower controller response time effectively,reduce migration cost and improve controller throughputs.Besides,it keeps high load balancing rate and has good topology adaptability.
姚蓝, 胡涛, 伊鹏, 胡宇翔, 兰巨龙, 李子勇. SDN中基于效能优化的交换机动态迁移策略[J]. 电子学报, 2019, 47(7): 1482-1489.
YAO Lan, HU Tao, YI Peng, HU Yu-xiang, LAN Ju-long, LI Zi-yong. Switch Dynamic Migration Strategy Based on Efficiency Optimization in SDN. Acta Electronica Sinica, 2019, 47(7): 1482-1489.
[1] Dave T.OpenFlow:Enabling innovation in campus networks[J].ACM Sigcomm Computer Communication Review,2008,38(2):69-74.
[2] Hu T,Yi P,Zhang J,Lan J.Reliable and load balance-aware multi-controller deployment in SDN[J].China Communications,2018,15(11):184-198.
[3] Hu T,Guo Z,Yi P,Baker T,Lan J.Multi-controller-based software-defined networking:A survey[J].IEEE Access,2018,06:15980-15996.
[4] Koponen T,Casado M,Gude N,et al.Onix:a distributed control platform for large-scale production networks[A].Proceedings of Usenix Conference on Operating Systems Design and Implementation[C].USENIX Association,2010.351-364.
[5] Hu T,Yi P,Guo Z,Lan J,Zhang J.Bidirectional matching strategy for multi-controller deployment in distributed software defined networking[J].IEEE Access,2018,06:14946-14953.
[6] Guo Z,Xu Y,Cello M,et al.JumpFlow:Reducing flow table usage in software-defined networks[J].Computer Networks,2015,92:300-315.
[7] Sherwood R,Mckeown N.The controller placement problem[A].Proceedings of the Workshop on Hot Topics in Software Defined Networks[C].ACM,2012.7-12.
[8] Hock D,Hartmann M,Gebert S.Pareto-optimal resilient controller placement in SDN-based core networks[A].Proceedings of Teletraffic Congress[C].IEEE,2013.1-9.
[9] Bari M F,Roy A R,Chowdhury S R,et al.Dynamic controller provisioning in software defined networks[A].Proceedings of International Conference on Network and Service Management[C].IEEE,2013.18-25.
[10] Yonghong F U,Jun B I,et al.A dormant multi-controller model for software defined networking[J].China Communications,2014,11(3):45-55.
[11] OpenFlow switch specification version1.4.0[OL].https://www.opennetworking.org/,2018.
[12] Dixit AA,Hao F,Mukherjee S,et al.ElastiCon:an elastic distributed sdn controller[A].Proceedings of Acm Sigcomm Workshop on Hot Topics in Software Defined Networking[C].IEEE,2017.17-28.
[13] Liang C,Kawashima R,Matsuo H.Scalable and crash-tolerant load balancing based on switch migration for multiple open flow controllers[A].Proceedings of Second International Symposium on Computing and Networking[C].IEEE,2014.171-177.
[14] Hu T,Yi P,Zhang J.A distributed decision mechanism for controller load balancing based on switch migration in SDN[J].China Communications,2018,15(10):129-142.
[15] Hu T,Guo Z,Zhang J,Lan J.Adaptive slave controller assignment for fault-tolerant control plane in software-defined networking[A].Proceedings of IEEE International Conference on Communications (ICC)[C].Kansas City,2018.1-6.
[16] Guo Z,Su M,Xu Y,et al.Improving the performance of load balancing in software-defined networks through load variance-based synchronization[J].Computer Networks,2014,68(11):95-109.
[17] Hong chang,et al.A game-theoretic approach to elastic control in software-defined networking[J].China Communications,2016,13(5):103-109.
[18] Qin X L,Zhang W B.Enabling elasticity of key-value stores in the cloud using cost-aware live data migration[J].Journal of Software,2013,24(6):1403-1417.
[19] Sahoo K S,et al.Optimal controller selection in software defined network using a greedy-SA algorithm[A].Proceedings of International Conference on Computing for Sustainable Global Development[C].IEEE,2016.1-6.
[20] OpenDaylight[OL].http://www.opendaylight.org/,2018.
[21] Mininet[OL].http://mininet.org/,2018.
[22] Internet2 Open Science,Scholarship and Services Exchange[OL].http://www.internet2.edu/network/ose/,2018.
[23] Knight S,Nguyen H X,Falkner N,et al.The Internettopology zoo[J].IEEE Journal on Selected Areas in Communications,2011,29(9):1765-1775.