Оптимизация пропускной способности SDN посредством управления таблицами потоков: сравнительное исследование и перспективы будущих исследований

Программно-определяемые сети (SDN) изменили подход к управлению сетями, отделив контроль от плоскости передачи данных, что сделало их более гибкими и программируемыми. Однако пропускная способность по-прежнему ограничивается задержкой контроллера и ограниченным размером троичной памяти с адресацией по содержанию (TCAM) в коммутаторах. Для решения этой проблемы схемы сокращения таблиц потоков (FTRS) предлагается простое программное решение. В этой статье  исследовано, как развивалась оптимизация пропускной способности SDN, сравниваются популярные контроллеры и показаны, где FTRS может быть применен. Показаны реальные результаты внедрения FTRS на контроллере Ryu, изучено, почему это важно для стоимости и устойчивости, и описаны будущие направления, такие как использование машинного обучения и настроек с несколькими контроллерами для более умных и быстрых сетей.

1. Alizadeh, M., Edsall, T., Dharmapurikar, S., Vaidyanathan, R., Chu, K., Fingerhut, A., Lam, V. T., Matus, F., Pan, R., Yadav, N., & Varghese, G. (2014). CONGA: Distributed congestion-aware load balancing for datacenters. Proceedings of ACM SIGCOMM, 503–514.

2. Benson, T., Akella, A., & Maltz, D. (2010). Network traffic characteristics of datacenters in the wild. Proceedings of the 10th ACM Internet Measurement Conference (IMC’10), 267–280.

3. Berde, P., Gerola, M., Hart, J., Higuchi, Y., Kobayashi, M., Koide, T., Lantz, B., O'Connor, B., Radoslavov, P., Snow, W., & Parulkar, G. (2014). ONOS: Towards an open, distributed SDN operating system. Proceedings of the 3rd Workshop on Hot Topics in Software Defined Networking (HotSDN), 1–6.

4. Chen, H., Guo, Y., Wu, Z., Liu, Y., & Hu, J. (2021). Entropy-aware wildcard compression for flow-table management. IEEE Transactions on Network and Service Management, 18(4), 3904–3916.

5. Curtis, A. R., Mogul, J. C., Tourrilhes, J., Yalagandula, P., Sharma, P., & Banerjee, S. (2011). DevoFlow: Scaling flow management for high-performance networks. ACM SIGCOMM Computer Communication Review, 41(4), 254–265.

6. Fernández, M., Frangoudis, P., Koutsiamanis, R. A., Dilaveroglu, S., & Tomkos, I. (2018). Performance comparison of open-source SDN controllers. Computer Communications, 128, 36–47.

7. Gao, Z., Lu, C., Zhou, H., & Lei, W. (2022). Aggregated flow-table techniques for scalable SDN. Computer Networks, 210, 108940.

8. Ghobadi, M., Sivaraman, V., Mahimkar, A., Boppana, R., & Alizadeh, M. (2020). Characterizing and optimizing distributed SDN controller coordination. IEEE Transactions on Network and Service Management, 17(3), 1644–1656.

9. Gude, N., Koponen, T., Pettit, J., Pfaff, B., Casado, M., McKeown, N., & Shenker, S. (2008). NOX: Towards an operating system for networks. ACM SIGCOMM Computer Communication Review, 38(3), 105–110.

10. He, Q., Xia, S., Sun, X., & Zhang, X. (2021). Latency-aware flow scheduling in software-defined networks. IEEE Transactions on Network and Service Management, 18(2), 1339–1353.

11. Hu, Y., Wu, J., Yang, W., & Zhang, Y. (2020). Hardware support for efficient SDN rule offloading. IEEE/ACM Transactions on Networking, 28(2), 719–733.

12. Kang, J., Li, Y., Zhang, H., & Zheng, Y. (2021). Lightweight SDN controller architecture for scalable network management. Future Generation Computer Systems, 116, 222–233.

13. Kim, H., & Feamster, N. (2013). Improving network management with SDN. IEEE Communications Magazine, 51(2), 114–119.

14. Kobayashi, M., Muraoka, Y., Shirose, Y., & Yamaguchi, N. (2014). OpenFlow channel latency issues in large-scale deployments. IEEE Communications Magazine, 52(2), 86–92.

15. Kreutz, D., Ramos, F. M. V., & Veríssimo, P. (2015). Software-defined networking: A comprehensive survey. Proceedings of the IEEE, 103(1), 14–76.

16. Leng, J., Liu, X., & Li, F. (2017). Flow-table reduction in SDN. Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI’17), 1–13.

17. Li, J., Zhao, W., Wang, Y., & Li, Q. (2021). Lightweight machine learning for real-time SDN control. Journal of Network and Computer Applications, 194, 103224.

18. Liu, H., Hu, Y., & Wang, H. (2020). Adaptive flow classification for hybrid SDN traffic engineering. IEEE Access, 8, 198544–198554.

19. McCauley, M., Smith, D., Miller, E., & Timm, J. (2013). POX: Python-based SDN controller for rapid prototyping. Open Networking Summit (ONS), 1–6.

20. McKeown, N., Anderson, T., Balakrishnan, H., Parulkar, G., Peterson, L., Rexford, J., Shenker, S., & Turner, J. (2008). OpenFlow: Enabling innovation in campus networks. ACM SIGCOMM Computer Communication Review, 38(2), 69–74.

21. Medved, J., Varga, R., Gondzio, J., & Zimalyaev, N. (2014). OpenDaylight: Towards a model-driven SDN controller architecture. IEEE/IFIP Network Operations and Management Symposium (NOMS), 1–6.

22. Monsanto, C., Reich, J., Foster, N., Walker, D., & Zeng, H. (2013). Composing software-defined networks. Proceedings of the 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI’13), 1–13.

23. Qin, X., Huang, Y., Liu, P., Jiang, S., Ma, S., & Li, Z. (2023). Flow optimization for 5G edge SDN networks with TCAM limitations. IEEE Communications Surveys & Tutorials, 25(2), 901–924.

24. Shalimov, A., Petrov, I., Yegorov, I., Moiseenko, I., & Khakupov, R. (2013). Ryu SDN framework: Architecture and performance evaluation. ACM Symposium on SDN Research (SOSR), 1–6.

25. Sheikh, M., Abdullah, N. A., Hameed, S., & Wan, K. H. (2024). Comparative evaluation of open-source SDN controllers. Journal of Network and Systems Management, 32(1), 95–112.

26. Singh, A., Ong, J., Agarwal, A., Anderson, G., Armistead, A., Bannon, R., Boving, S., Desai, G., Felderman, B., & Meloy, S. (2015). Jupiter rising: A decade of datacenter network innovation. Proceedings of ACM SIGCOMM, 45(4), 183–197.

27. Tootoonchian, A., Ganjali, Y., Sherwani, J., & Firooz, M. (2012). On controller performance in software-defined networks. Proceedings of the 2nd USENIX Workshop on Hot Topics in Management of Internet, Cloud, and Enterprise Networks and Services (Hot-ICE), 1–6.

28. Trent, L. (2023). Memory efficiency of SDN controllers. Future Generation Computer Systems, 141, 356–367.

29. Tsai, Y., Huang, C., & Chang, Y. (2022). Transformer-based prediction for network traffic. IEEE Access, 10, 93465–93477.

30. Wang, X., Zhao, D., Liu, J., & Xu, Y. (2022). RL-Flow: Reinforcement learning-based flow rule optimisation in SDN. IEEE Transactions on Network and Service Management, 19(1), 91–102.

31. Wang, Y., Chen, X., Wu, Y., & Zhang, Z. (2020). Hierarchical flow aggregation for SDN. Computer Networks, 176, 107290.

32. Yang, X., Li, P., Zhao, J., & Wang, L. (2022). Dynamic flow aggregation based on field correlation in SDN data planes. IEEE Access, 10, 12498–12509.

33. Yeganeh, S. H., Tootoonchian, A., Ganjali, Y., & Sherwani, J. (2013). Kandoo: A framework for efficient and scalable offloading in SDN controllers. Proceedings of the 2nd ACM SIGCOMM Workshop on Hot Topics in Software Defined Networking (HotSDN), 19–24.

34. Zahavi, E., & Zilberman, N. (2021). TCAM scaling challenges in modern networks. IEEE Micro, 41(2), 14–24.

35. Zhang, C., Wang, Y., Liu, X., & Chen, H. (2021). Predictive control-plane scheduling for SDN using machine learning. Computer Networks, 197, 108283.

36. Zhao, Y., Wu, Z., Wang, X., & Peng, Q. (2020). Deep reinforcement learning for intelligent SDN traffic control. IEEE Access, 8, 182010–182021.