Comparative analysis of different virtual switches to improve the efficiency of networks of different configurations
Abstract
The aim of the study was to determine the optimal type of virtual switch to ensure maximum efficiency of computer networks of various configurations, taking into account their technical characteristics, capabilities, and level of integration. A comparative analysis of the performance and functionality of virtual switches was conducted. The main results showed that the Cisco Nexus 1000V provides excellent performance and low latency (0.5-2 milliseconds), making it ideal for environments where network speed and responsiveness are critical. Open vSwitch is highly scalable and memory efficient, with up to 9 gigabits per second of bandwidth and moderate Central Processing Unit usage, making it suitable for scalable virtualised environments. VMware vSwitch, with a bandwidth of 6-8 gigabits per second, has good integration into the VMware environment and easy configuration. Moreover, Virtual Packet Processing was found to provide the best throughput, reaching values between 20 and 50 gigabits per second, and also exhibits low latency in the range of 0.3-0.5 milliseconds, making it the optimal choice for environments with high bandwidth requirements. At the same time, the Bridge Virtual Switch has the lowest Central Processing Unit load (5-10%), which allows maintaining performance even with limited hardware resources. The other switches, namely Hyper-V Virtual Switch, Juniper Contrail Virtual Router, CloudStack Virtual Router, and Huawei CloudEngine vSwitch, demonstrated good performance and can be useful for environments with lower bandwidth and scalability requirements. The results showed that the choice of a virtual switch depends on specific requirements, as each switch has its own advantages and limitations that determine its optimality for different network configurations
Keywords
bandwidth; component scalability; system integration and performance; data processing; latency reduction
References
[1] Abdou, A., van Oorschot, P.C., & Wan, T. (2018). Comparative analysis of control plane security of SDN and conventional networks. IEEE Communications Surveys & Tutorials, 20(4), 3542-3559. doi: 10.1109/ COMST.2018.2839348.
[2] Ahmmed, F., Rahman, A., Hossain Emon, M., & Rahman Enam, M. (2024). Enhancing energy efficiency in wireless sensor networks using virtual MIMO technology. Global Mainstream Journal of Innovation, Engineering & Emerging Technology, 3(2), 27-42. doi: 10.62304/jieet.v3i02.93.
[3] Alam, I., Sharif, K., Li, F., Latif, Z., Karim, M.M., Biswas, S., Nour, B., & Wang, Y. (2020). A survey of network virtualization techniques for Internet of Things using SDN and NFV. ACM Computing Surveys, 53(2), article number 35. doi: 10.1145/3379444.
[4] Alnaim, A.K. (2024). Securing 5G virtual networks: A critical analysis of SDN, NFV, and network slicing security. International Journal of Information Security, 23(6), 3569-3589. doi: 10.1007/s10207-024-00900-5.
[5] Bringhenti, D., Marchetto, G., Sisto, R., Valenza, F., & Yusupov, J. (2023). Automated firewall configuration in virtual networks. IEEE Transactions on Dependable and Secure Computing, 20(2), 1559-1576. doi: 10.1109/ TDSC.2022.3160293.
[6] Bueno, G., Saquetti, M., Rodrigues, P., Lamb, I., Gaspary, L., Luizelli, M.C., Zhani, M.F., Azambuja, J.R., & Cordeiro, W. (2022). Managing virtual programmable switches: Principles, requirements, and design directions. IEEE Communications Magazine, 60(2), 53-59. doi: 10.1109/MCOM.001.2100363.
[7] CloudEngine 1800V virtual switch. (2018). Retrieved from https://carrier.huawei.com/~/media/CNBG/ Downloads/Product/Fixed%20Network/b2b/0920/1800-en.pdf.
[8] Configuring AutoScale with using CloudStack virtual router. (n.d.). Retrieved from https://docs.cloudstack. apache.org/en/4.19.1.3/adminguide/autoscale_with_virtual_router.html.
[9] Contrail Networking and Security User Guide. (2023). Retrieved from https://www.juniper.net/documentation/ us/en/software/contrail-networking19/contrail-networking-security-user-guide/contrail-networkingsecurity-user-guide.pdf.
[10] De Oliveira, J.V.G., Bellotti, P.C.P., de Oliveira, R.M., Borges Vieira, A., & Chaves, L.J. (2021). Virtualizing packetprocessing network functions over heterogeneous OpenFlow switches. IEEE Transactions on Network and Service Management, 19(1), 485-496. doi: 10.1109/TNSM.2021.3112403.
[11] Detecting bottlenecks in a virtualized environment. (2022). Retrieved from https://learn.microsoft.com/en-us/ windows-server/administration/performance-tuning/role/hyper-v-server/detecting-virtualized-environmentbottlenecks.
[12] Dumitrak, V. (2020). Methods and means of increasing the efficiency of implementing virtualisation of network functions in modern network infrastructures. (Master’s dissertation, Ternopil Ivan Puluj National Technical University, Ternopil, Ukraine).
[13] Guo, Z., Li, F., Shen, J., Xie, T., Jiang, S., & Wang, X. (2023). ConfigReco: Network configuration recommendation with graph neural networks. IEEE Network, 38(1), 7-14. doi: 10.1109/MNET.2023.3336239.
[14] Lira, O.G., Caicedo, O.M., & da Fonseca, N.L.S. (2024). Large language models for zero touch network configuration management. ArXiv. doi: 10.48550/arXiv.2408.13298.
[15] Lucas-Estañ, M.C., Coll-Perales, B., Khan, M.I., Gozalvez, J., Avedisov, S.S., Altintas, O., & Sepulcre, M. (2024). 5G network architecture and configuration choices to support teleoperated driving at scale. In Proceedings of the 100th vehicular technology conference (pp. 1-6). Washington: IEEE. doi: 10.1109/VTC2024-Fall63153.2024.10758026.
[16] Marzuki, K., Kholid, M.I., Hariyadi, I.P., & Mardedi, L.Z.A. (2023). Automation of open VSwitch-based virtual network configuration using ansible on Proxmox virtual environment. International Journal of Electronics and Communications Systems, 3(1), 11-20. doi: 10.24042/ijecs.v3i1.16524.
[17] Mehta, R. (2015). Network improvements in vSphere 6 boost performance for 40G NICs. Retrieved from https:// surl.li/pmnzmm.
[18] Olifirenko, R. (2021). An improved way of NFV hypervisor functioning in SDN networks. (Bachelor’s dissertation, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine).
[19] OpenContrail vRouter. (2024). Retrieved from https://docs.mirantis.com/mcp/q4-18/mcp-ref-arch/ opencontrail-plan/contrail-vrouter.html.
[20] Patrão, L. (2024). VMware vSphere essentials: A practical approach to vSphere deployment and management. Berkeley: Apress. doi: 10.1007/979-8-8688-0208-9.
[21] Pfaff, B., et al. (2015). The design and implementation of open vSwitch. In Proceedings of the 12th USENIX symposium on networked systems design and implementation (pp. 117-130). Oakland: USENIX.
[22] Poller, J. (2017). Big switch networks and Dell EMC: Next-generation data center networking. Retrieved from https://i.dell.com/sites/csdocuments/Shared-Content_data-Sheets_Documents/en/ESG-Lab-Review-BigSwitch-and-Dell-April-2017.pdf.
[23] Rashelbach, A., Rottenstreich, O., & Silberstein, M. (2022). Scaling open vSwitch with a computational cache. In Proceedings of the 19th USENIX symposium on networked systems design and implementation (pp. 1359-1374). Renton: USENIX.
[24] Rekha, P.M., & Dakshayini, M. (2015). Dynamic network configuration and virtual management protocol for open switch in cloud environment. In Proceedings of the international advance computing conference (pp. 143-148). Bangalore: IEEE. doi: 10.1109/IADCC.2015.7154687.
[25] Rush, S. (2020). Virtual switches and indicators in automotive displays. SAE International Journal of Advances and Current Practices in Mobility, 2(4), 2418-2424. doi: 10.4271/2020-01-1362.
[26] Sadrhaghighi, S., Dolati, M., Ghaderi, M., & Khonsari, A. (2022). Monitoring OpenFlow virtual networks via coordinated switch-based traffic mirroring. IEEE Transactions on Network and Service Management, 19(3), 22192237. doi: 10.1109/TNSM.2022.3149734.
[27] Singh, A. (2019). Development of Python API for a network switch. (Bachelor’s dissertation, Jaypee University of Information Technology Waknaghat, Waknaghat, India).
[28] Tchendji, V.K., Yankam, Y.F., & Myoupo, J.F. (2018). Conflict-free rerouting scheme through flow splitting for virtual networks using switches. Journal of Internet Services and Applications, 9(1), article number 13. doi: 10.1186/s13174-018-0085-4.
[29] Vector Packet Processing. (n.d.). Retrieved from https://www.netgate.com/resources/articles-vector-packetprocessing.
[30] Wang, C., Scazzariello, M., Farshin, A., Ferlin-Reiter, S., Kostic, D., & Chiesa, M. (2024). NetConfEval: Can LLMs facilitate network configuration? Proceedings of the ACM on Networking, 2, article number 7. doi: 10.1145/3656296.
[31] Wang, K., Zhao, C., Chu, J., Shi, Y., Lu, J., Lyu, B., Zhu, S., Cheng, P., & Chen, J. (2024). LFVeri: Network configuration verification for virtual private cloud networks. IEEE/ACM Transactions on Networking, 32(6), 5475-5490. doi: 10.1109/TNET.2024.3469386.
[32] Wang, Y., Gobriel, S., Wang, R., Tai, T.-Y.C., & Dumitrescu, C. (2018). Hash table design and optimization for software virtual switches. In Proceedings of the 2018 afternoon workshop on Kernel bypassing networks (pp. 22-28). New York: Association for Computing Machinery. doi: 10.1145/3229538.3229542.
[33] Wang, Y., Wang, X., Huang, Z., Li, W., & Xu, S. (2022). Joint optimization of dynamic resource allocation and packet scheduling for virtual switches in cognitive internet of vehicles. EURASIP Journal on Advances in Signal Processing, 2022, article number 32. doi: 10.1186/s13634-022-00862-7.
[34] Yalda, K., Hamad, D.J., & Tapus, N. (2024). Comparative analysis of centralized and distributed SDN environments for IoT networks. Journal of Control Engineering and Applied Informatics, 26(3), 84-91. doi: 10.61416/ceai. v26i3.9164.
[35] Yang, Y., Guo, S., Liu, G., & Yi, L. (2021). Fine granularity resource allocation of virtual data center with consideration of virtual switches. Journal of Network and Computer Applications, 175, article number 102916. doi: 10.1016/j.jnca.2020.102916.
[36] Zhu, L., Karim, M., Sharif, K., Xu, C., Li, F., Du, X., & Guizani, М. (2020). SDN controllers: A comprehensive analysis and performance evaluation study. ACM Computing Surveys, 53(6), article number 133. doi: 10.1145/3421764.