RESISTING: Um Novo Mecanismo de Fast-Reroute com Distribuição de Pacotes em Switches Programáveis P4
Abstract
Fast-Reroute (FRR) mechanisms provide failure recovery in different types of network architectures, avoiding application flow performance degradation. Current FRR mechanisms for P4 programmable switches provide fast reroute approaches without considering flow load balancing support. Thus, existing methods do not deliver efficient use of bandwidth resources, resulting in overloaded network links under multiple failure recovery scenarios. This work proposes RESISTING as a new FRR-ECMP (Equal-Cost Multi-Path) mechanism for Programming Protocol-independent Packet Processor (P4) programmable switches, delivering packet flow load balancing and failure recovery. The proposed method is compared against Primitive for Reconfigurable Fast Reroute (PURR) – the state-of-the-art FRR mechanism in P4 – under one, two, and three links failure experiments. The results show that the proposed prototype does not incur packet losses during the experimental evaluation, while PURR presents losses under two or more simultaneous failures.
References
Alizadeh, M. and Edsall, T. (2013). On the data path performance of leaf-spine datacenter fabrics. In 2013 IEEE 21st Annual Symposium on High-Performance Interconnects, pages 71–74.
Bosshart, P., Daly, D., Gibb, G., Izzard, M., McKeown, N., Rexford, J., Schlesinger, C., Talayco, D., Vahdat, A., Varghese, G., and Walker, D. (2014). P4: Programming protocol-independent packet processors. ACM SIGCOMM CCR, 44(3):87–95.
Chiesa, M., Kamisiński, A., Rak, J., Rétvári, G., and Schmid, S. (2021). A survey of fast-recovery mechanisms in packet-switched networks. IEEE Communications Surveys Tutorials, 23(2):1253–1301.
Chiesa, M., Sedar, R., Antichi, G., Borokhovich, M., Kamisiński, A., Nikolaidis, G., and Schmid, S. (2019). PURR: a primitive for reconfigurable fast reroute. In Proceedings of the 15th International Conference on Emerging Networking Experiments And Technologies, CoNEXT ’19, pages 1–14.
Figueira, M. and Vasconcelos, D. E. (2011). Emprego de resiliência na gerência de redes. In Revista Militar de Artigos Ciência e Tecnologia, volume XXXIII, pages 32–41, Rio de Janeiro.
Greenberg, A., Hamilton, J. R., Jain, N., Kandula, S., Kim, C., Lahiri, P., Maltz, D., Patel, P., and Sengupta, S. (2009). Vl2: A scalable and flexible data center network. In SIGCOMM. Association for Computing Machinery, Inc. Recognized as one of ”the most important research results published in CS in recent years”.
Luz, G., Rocha, A., Almeida, L., and Verdi, F. (2022). Infarr: Um algoritmo para reroteamento rápido em planos de dados programáveis. In Anais do XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 154–167, Porto Alegre, RS, Brasil. SBC.
Merling, D., Lindner, S., and Menth, M. (2020). P4-based implementation of BIER and BIER-FRR for scalable and resilient multicast. Journal of Network and Computer Applications, 169:102764.
Omer, M., Nilchiani, R., and Mostashari, A. (2009). Measuring the resilience of the global internet infrastructure system. In 2009 3rd Annual IEEE Syscon, pages 156–162.
Sedar, R., Borokhovich, M., Chiesa, M., Antichi, G., and Schmid, S. (2018). Supporting Emerging Applications With Low-Latency Failover in P4. In Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies, pages 52–57, New York, NY, USA. ACM.
Shand, M. and Bryant, S. (2010). IP Fast Reroute Framework. RFC 5714, RFC Editor https://www.rfc-editor.org/info/rfc5714.
Sivaraman, A., Kim, C., Krishnamoorthy, R., Dixit, A., and Budiu, M. (2015). Dc.p4: Programming the forwarding plane of a data-center switch. In Proceedings of the 1st ACM SIGCOMM SOSR, New York, NY, USA. ACM.
Zhang, M., Liu, B., and Zhang, B. (2008). Load-balanced ip fast failure recovery. In Akar, N., Pioro, M., and Skianis, C., editors, IP Operations and Management, pages 53–65, Berlin, Heidelberg. Springer Berlin Heidelberg.
