MTS-PolKA: Multi-Path Traffic Splitting Proportionally to Weight with Source Routing

• Giancarlo O. dos Santos IFES
• Cristina K. Dominicini IFES
• Gilmar L. Vassoler IFES
• Rafael S. Guimarães IFES
• Isis Oliveira IFES
• Domingos Jose P. Paraiso IFES
• Rodolfo S. Villaca UFES

DOI: https://doi.org/10.5753/sbrc.2024.1263

Abstract

The article presents the innovative proposal called MTS-PolKA to optimize traffic in datacenter networks. Introduces a dynamic method of dividing traffic with labels (routeIDs and weightIDs) in packet headers, using static tables in switches to allow flexible adjustments in real time, eliminating complex reconfigurations. The approach employs source routing with the modified M-Polka Protocol, using a residual number system for stateless source routing and no changes to the final hosts. MTS-PolKA stands out for its agility in (re)configuring paths and weights, with the control plane calculating route identifiers (routeIDs), weight (weightIDs) and node (nodeIDs). Experiments demonstrate the effectiveness of the solution, enabling agile reconfigurations of traffic division profiles at the source, with the potential for improving performance and efficiency in data center networks.

References

Cui, Z., Hu, Y., and Hou, S. (2021). Adaptive weighted cost multipath routing on pisa. In 2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID), pages 541–544.

Dixit, A., Prakash, et al. (2013). On the impact of packet spraying in data center networks. In 2013 Proceedings IEEE INFOCOM, pages 2130–2138.

Dominicini, C. et al. (2020). Polka: Polynomial key-based architecture for source routing in network fabrics. In 2020 6th IEEE Conference on Network Softwarization (NetSoft), pages 326–334.

Guimarães, R. S. et al. (2022). M-polka: Multipath polynomial key-based source routing for reliable communications. IEEE Transactions on Network and Service Management, 19(3):2639–2651.

Hsu, K.-F., Tammana, et al. (2020). Adaptive weighted traffic splitting in programmable data planes. In Proceedings of the Symposium on SDN Research, SOSR ’20, page 103–109, New York, NY, USA. Association for Computing Machinery.

Huang, J., Lyu, et al. (2021). Mitigating packet reordering for random packet spraying in data center networks. IEEE/ACM Transactions on Networking, 29(3):1183–1196.

Jyothi, S. A., Dong, M., and Godfrey, P. B. (2015). Towards a flexible data center fabric with source routing. In Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research, pages 1–8.

Pang, J., Xu, G., and Fu, X. (2017). Sdn-based data center networking with collaboration of multipath tcp and segment routing. IEEE Access, 5:9764–9773.

Robin, D. D. and Khan, J. I. (2022). Clb: Coarse-grained precision traffic-aware weighted cost multipath load balancing on pisa. IEEE Transactions on Network and Service Management, 19(2):784–803.

Rottenstreich, O., Kanizo, et al. (2018). Accurate traffic splitting on commodity switches. In Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures, SPAA ’18, page 311–320, New York, NY, USA. Association for Computing Machinery.

Valentim, R. et al. (2019). Rdna balance: Balanceamento de carga por isolamento de fluxos elefante em data centers com roteamento na origem. In Anais do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 1000–1013, Porto Alegre, RS, Brasil. SBC.

Zhou, J., Tewari, et al. (2014). Wcmp: Weighted cost multipathing for improved fairness in data centers. In Proceedings of the Ninth European Conference on Computer Systems, EuroSys ’14, New York, NY, USA. Association for Computing Machinery.