Balanceamento de carga entre caminhos utilizando redes definidas por software

• Alisson Cavalcante e Silva Universidade do Estado do Rio de Janeiro http://orcid.org/0000-0001-6489-0039
• Marcelo Gonçalves Rubinstein Universidade do Estado do Rio de Janeiro https://orcid.org/0000-0002-2509-4010

DOI: https://doi.org/10.5753/wgrs.2020.12455

Abstract

It is common for datacenter networks to use the Ethernet network model with packet forwarding by a single path based on the Spanning Tree Protocol (STP), to avoid loops on the network. However, this fact does not allow the use of idle links to reduce congestion and increase the aggregate bandwidth of the network. One solution would be to divide the network into subnets connected by routers. However, the use of routers would considerably increase the final cost of the network [Costa et al. 2012]. One way to get around this problem is to perform load balancing between links. This work presents a proposal for a load balancing mechanism between paths using Software Defined Networks (SDNs). The proposed mechanism, named MLB (Multipath Load Balance), was implemented in Python and submitted to a performance evaluation, in which the results showed that it is possible to increase the aggregate bandwidth by 95% and decrease the packet loss by about 95.5% compared to the standard OpenDaylight SDN controller operating mode.

Keywords: Redes definidas por software, SDN, Balanceamento de carga, Roteamento multicaminhos

References

Bhandarkar, S. and Khan, K. A. (2015). Load balancing in software-defined network (SDN) based on traffic volume. Advances in Computer Science and Information Technology (ACSIT), 47):12-16.

Bredel, M., Bozakov, Z., Barczyk, A., and Newman, H. (2014). Flow-based load balan-cing in multipathed layer-2 networks using openflow and multipath-TCP. In Workshopon Hot Topics in Software Defined Networking (HotSDN), pages 213-214, New York,NY, USA. ACM.

Cormen, T. H., Leiserson, C. E., Rivest, R. L., and Stein, C. (2012). Algoritmos Teoria e Prática. Elsevier, Rio de Janeiro. Tradução da 3º edição americana.

Costa, L. H. M. K., de Amorim, M. D., Campista, M. E. M., Rubinstein, M. G., Florissi, P., and Duarte, O. C. M. B. (2012). Grandes massas de dados na nuvem: Desafios e técnicas para inovação. In Minicurso apresentado no XXX Simpósio Brasileiro deRedes de Computadores e Sistemas Distribuídos, SBRC. SBC.

Hagberg, A. A., Schult, D. A., and Swart, P. J. (2008). Exploring network structure, dynamics, and function using NetworkX. In Varoquaux, G., Vaught, T., and Millman,J., editors, Proceedings of the 7th Python in Science Conference (SciPy), pages 11-15, Pasadena, CA USA.

Hassan, M. H. O. (2017). Implementing Nayan Seth's dynamic load balancing algorithmin software-defined networks: A case study. Dissertação de Mestrado, Sudan University of Science and Technology, Sudan.

Jain, R. (1991). The art of computer systems performance analysis: techniques for experimental design, measurement, simulation, and modeling. John Wiley & Sons, 1º edition.

Kreutz, D., Ramos, F. M. V., Veríssimo, P. E., Rothenberg, C. E., Azodolmolky, S., andUhlig, S. (2015). Software-Defined Networking: A comprehensive survey. Proceedings of the IEEE, 103(1):14-76.

Lantz, B., Heller, B., and McKeown, N. (2010). A network in a laptop: Rapid prototyping for software-defined networks. In Proceedings of Workshop on Hot Topics in Networks(SIGCOMM), Hotnets-IX, pages 1-6, New York, NY, USA. ACM.

Mallik, A. and Hegde, S. (2014). A novel proposal to effectively combine multipathdata forwarding for data center networks with congestion control and load balancing using Software-Defined Networking approach. In International Conference on RecentTrends in Information Technology (ICRTIT), pages 1-7, Chennai, India. IEEE.

OpenDaylight (2017). Opendaylight - The L2 Switch project provides Layer2 switch functionality. https://docs.opendaylight.org/en/stable-fluorine/user-guide/12switch-user-guide.html. Acesso em: 03 de dezembro de 2019.

Prabhavat, S., Nishiyama, H., Ansari, N., and Kato, N. (2012). On load distribution overmultipath networks. IEEE Communications Surveys & Tutorials, 14(3):662-680.

Ramdhani, M. F., Hertiana, S. N., and Dirgantara, B. (2016). Multipath routing with load balancing and admission control in software-defined networking (SDN). In International Conference on Information and Communication Technology (IColCT), pages 1-6,Bandung, Indonesia. IEEE.

Seth, N. (2016). SDN load balancing. https://github.com/nayanseth/sdn-loadbalancing. Acesso em: 16 de abril de 2019.

Singh, S. K., Das, T., and Jukan, A. (2015). A survey on internet multipath routing and provisioning. IEEE Communications Surveys & Tutorials, 17(4):2157-2175.

Sun, Z., Xie, Z., Chen, Z., and Dai, L. (2012). An algorithm for the shortest pairsof arc-disjoint paths problem. In International Conference on Natural Computation (ICNC2012), pages 1001-1006, Chongging, China. IEEE.

Tsai, J. and Moors, T. (2006). A review of multipath routing protocols: From wirelessad hoc to mesh networks. In ACORN Early Career Researcher Workshop on Wireless Multihop Networking, volume 30, Sydney, Australia.