摘要
针对数据中心网络(data center network,DCN)动态调度导致的负载不均衡问题,提出了基于流调度选择的动态负载均衡(dynamic load balancing based on flow scheduling selection,DLBFSS)算法。该算法首先计算拥塞链路上各条大流的等价最短路径,并删除不满足流带宽需求的路径;然后计算剩余路径的可用吞吐量,选择可用吞吐量最大的路径作为最优调度路径;最后根据大流的带宽和最优路径的负载定义调度的拥塞概率,将拥塞概率作为大流调度选择的依据。实验结果表明,与传统ECMP(equal-cost multi-path)路由和现有大流调度算法相比,DLBFSS能够减小网络时延,提高流的带宽利用率,保证了更好的负载均衡。
In order to solve the problems of poor load balancing caused by dynamic scheduling in data center networks( DCN),this paper proposed a dynamic load balancing algorithm based on flow scheduling selection( DLBFSS). Firstly,DLBFSS calculated the equal-cost shortest path for each large flow on the congested link and removed the path with insufficient bandwidth. Then,the available throughput of each remaining path for large flows was calculated,and the path with maximum available throughput was selected as the optimal scheduling path. Finally,the congestion probability of each large flow was defined by considering the flow bandwidth and the load of the optimal path,and the congestion probability was used for large flow scheduling selection. The experimental results show that DLBFSS can reduce the network delay,improves the flow bandwidth utilization and ensures load balancing compared with ECMP( equal-cost multi-path) and typical large flow scheduling algorithms.
引文
[1] Veena S,Rustagi R P,Murthy K N B. Network management and performance monitoring using software defined networks[C]//Proc of the 20th Annual International Conference on Advanced Computing and Communications. Washington DC:IEEE Computer Society,2014:29-31.
[2] Gholami M,Akbari B. Congestion control in software defined data center network through flow rerouting[C]//Proc of the 23rd Iranian Conference on Electrical Engineering. Piscataway,NJ:IEEE Press,2015:654-657.
[3] Sehery W,Clancy T C. Load balancing in data center networks with folded-clos architectures[C]//Proc of the 1st IEEE Conference on Network Softwarization. Piscataway,NJ:IEEE Press,2015:1-6.
[4] Jo E,Pan Deng,Liu J,et al. A simulation and emulation study of SDNbased multipath routing for fat-tree data center networks[C]//Proc of Winter Simulation Conference. Piscataway,NJ:IEEE Press,2014:3072-3083.
[5] Wojcik R,Domzal J,Dulinski Z. Flow-aware multi-topology adaptive routing[J]. IEEE Communications Letters,2014,18(9):1539-1542.
[6]杨洋,杨家海,秦董洪.数据中心网络多路径路由算法[J].清华大学学报:自然科学版,2016,56(3):262-268.(Yang Yang,Yang Jiahai,Qin Donghong. Multipath routing algorithm for data center networks[J]. Journal of Tsinghua University(Science and Technology),2016,56(3):262-268.)
[7] Chiesa M,Kindler G,Schapira M. Traffic engineering with equalcost-multipath:an algorithmic perspective[J]. IEEE/ACM Trans on Networking,2017,25(2):779-792.
[8] Li Yu,Pan Deng. Open Flow based load balancing for fat-tree networks with multipath support[C]//Proc of the 12th IEEE International Conference on Communications. Piscataway,NJ:IEEE Press,2013:1-5.
[9] Shah S A R,Seok W,Kim J,et al. CAMOR:congestion aware multipath optimal routing solution by using software-defined networking[C]//Proc of International Conference on Platform Technology and Service. Piscataway,NJ:IEEE Press,2017:1-6.
[10]Long Hui,Shen Yao,Guo Minyi,et al. Dynamic load-balanced routing in Open Flow-enabled networks[C]//Proc of the 27th International Conference on Advanced Information Networking and Applications. Piscataway,NJ:IEEE Press,2013:290-297.
[11] Project Floodlight. Floodlight[EB/OL].[2017-06-05]. http://www. projectfloodlight. org/.
[12]Benson T,Akella A,Maltz D A. Network traffic characteristics of data centers in the wild[C]//Proc of the 10th ACM SIGCOMM Conference on Internet Measurement. New York:ACM Press,2010:267-280.
[13]Deng Gang,Gong Zhenghu,Wang Hong. Characteristics research on modern data center network[J]. Journal of Computer Research and Development,2014,51(2):395-407.
[14]Mininet Team. Mininet[EB/OL].[2017-06-05]. http://mininet.org/.