Abstract
Network virtualization has gained much popularity with the advent of datacenter networking. The hardware aspect of network virtualization, router virtualization, allows network service providers to consolidate network hardware, reducing equipment cost and management overhead. Several approaches have been proposed to achieve router virtualization to support several virtual networks on a single hardware platform. However, their performance has not been analyzed quantitatively to understand the benefits of each approach. In this work, we perform a comprehensive analysis of performance of these approaches on Field Programmable Gate Array (FPGA) with respect to memory consumption, throughput, and power consumption. Generalized versions of virtualization approaches are evaluated based on post place-and-route results on a state-of-the-art FPGA. Grouping of routing tables is proposed as a novel approach to improve scalability (i.e., the number of virtual networks hosted on a single chip) of virtual routers on FPGA with respect to memory requirement. Further, we employ floor-planning techniques to efficiently utilize chip resources and achieve high performance for virtualized, pipelined architectures, resulting in 1.6× speedup on the average compared with the non-floor-planned approach. The results indicate that the proposed solution is able to support 100+ and 50 virtual routers per chip in the near-best and near-worst case scenarios, while operating at 20+ Gbps rates.
- Alcatel-Lucent. 2013. Alcatel-lucent fps 400G network processor. http://www.alcatel-lucent.com/fp3/.Google Scholar
- Attig, M. and Brebner, G. 2011. 400 Gb/s programmable packet parsing on a single fpga. In Proceedings of the 7th ACM/IEEE Symposium on Architectures for Networking and Communications Systems. 12--22. Google Scholar
Digital Library
- Baroncelli, F., Martini, B., and Castoldi, P. 2010. Network virtualization for cloud computing. Ann. Telecomm. 65, 11, 713--721.Google Scholar
Cross Ref
- Chowdhury, N. M. M. K. and boutaba, R. 2009. Network virtualization: State of the art and research challenges. IEEE Comm. Mag. 47, 7, 20--26. Google Scholar
Digital Library
- Chu, Y.-S., Lin, P.-F., Lin, J.-H., Su, H.-K., and Chen, M.-J. 2005. ASIC design of fast ip lookup for next generation ip router. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS'05). Vol. 4, IEEE, 3825--3828.Google Scholar
- Cisco. 2013a. Cisco catalyst 6500 virtual switching system 1440. http://www.cisco.com/en/US/products/ps9336/index.html.Google Scholar
- Cisco. 2013b. Cisco nexus 1000V switch. http://www.cisco.com/en/US/prod/collateral/switches/ps9441/ps9902/dmzvirtualization vsphere4 nexus1000V.pdf.Google Scholar
- Cisco. 2013c. Data center designs: Network virtualization. http://www.cisco.com/en/US/netsol/ns1002/index.html.Google Scholar
- Cisco. 2013d. Evaluating and enhancing green practices with cisco catalyst switching. http://www.cisco.com.Google Scholar
- Cisco. 2013e. Hardware and software virtualized routers. http://www.cisco.com/en/US/solutions/collateral/ns341/ns524/ns562/ns573/white paper c11-512753 ns573 Networking Solutions White Paper.html.Google Scholar
- Fu, J. and Rexford, J. 2008. Efficient ip-address lookup with a shared forwarding table for multiple virtual routers. In Proceedings of the ACM CoNEXT Conference (CoNEXT'08). ACM Press, New York. Google Scholar
Digital Library
- Ganegedara, T., Jiang, W., and Prasanna, V. 2010. FRuG: A benchmark for packet forwarding in future networks. In Proceedings of the 29th International Performance Computing and Communications Conference (IPCCC'10). IEEE, 231--238.Google Scholar
- Ganegedara, T., Le, H., and Prasanna, V. K. 2011. Towards on-the-fly incremental updates for virtualized routers on fpga - Unpublished article. In International Conference on Field Programmable Logic and Applications (FPL'11). Google Scholar
Digital Library
- Ganegedara, T. and Prasanna. V. K. 2012a. FPGA-based router virtualization: A power perspective. In Proceedings of the 26th IEEE International Parallel and Distributed Processing Symposium Workshops and PhD Forum (IPDPSW'12). 360--367. Google Scholar
Digital Library
- Ganegedara, T. and Prasanna, V. K. 2012b. StrideBV: Single chip 400G+ packet classification. In Proceedings of the 13th IEEE International Conference on High Performance Switching and Routing (HPSR'12). 1--6.Google Scholar
- Jiang, W. and Prasanna, V. K. 2008. Towards green routers: Depth-bounded multi-pipeline architecture for power-efficient ip lookup. In Proceedings of the Performance, Computing and Communications Conference (IPCCC'08). 185--192.Google Scholar
- Jiang, W., Wang, Q., and Prasanna, V. K. 2008. Beyond tcams: An sram-based parallel multi-pipeline architecture for terabit ip lookup. In Proceedings of the 27th IEEE Conference on Computer Communications (INFOCOM'08). 1786--1794.Google Scholar
- Juniper. 2008. Control plance scaling and router virtualization. http://support.neoteris.com/solutions/literature/white papers/200261.pdf.Google Scholar
- Juniper. 2009. JCS1200 control system. http://www.juniper.net/us/en/local/pdf/whitepapers/2000261-en.pdf.Google Scholar
- Kaxiras, S. and G. Keramidas, G. 2003. IPStash: A power-efficient memory architecture for ip-lookup. In Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'03). 361--372. Google Scholar
Digital Library
- Le, H., Ganegedara, T., and Prasanna, V. K. 2011. Memory-efficient and scalable virtual routers using fpga. In Proceedings of the International Symposium on Field Programmable Gate Arrays (FPGA'11). Google Scholar
Digital Library
- Lyons, A. M., Neilson, D. T., and Salamon, T. R. 2008a. Energy efficient strategies for high density telecom applications. http://imsresearch.com/press-release/Internet Connected Devices About to Pass the 5 Billion Milestone&from=all pr.Google Scholar
- Lyons, A. M., Neilson, D. T., and Salamon, T. R. 2008b. Energy efficient strategies for high density telecom applications. In Princeton University, Supelec, Ecole Centrale Paris and Alcatel-Lucent Bell Labs Workshop on Information, Energy and Environment.Google Scholar
- Netfpga. 2013. NetFPGA boards. http://netfpga.org/.Google Scholar
- Potaroo. 2013. BGP analysis reports. http://bgp.potaroo.net/.Google Scholar
- Song, H., Kodialam, M., Hao, F., and Lakshman, T. V. 2010. Building scalable virtual routers with trie braiding. In Proceedings of the 29th IEEE Conference on Information Communications (INFOCOM'10). 1--9. Google Scholar
Digital Library
- Open Networking Summit. 2013. Why software defined networking (sdn)? http://opennetsummit.org/why.html.Google Scholar
- Unnikrishnan, D., Vadlamani, R., Liao, Y., Dwaraki, A., Crenne, J., Gao, L., and TESSIER, R. 2010. Scalable network virtualization using fpgas. In Proceedings of the 18th Annual ACM/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA'10). ACM Press, New York, 219--228. Google Scholar
Digital Library
- Wikipedia. 2013a. Longest prefix matching. http://en.wikipedia.org/wiki/Longest prefix match.Google Scholar
- Wikipedia. 2013b. Multiprotocol label switching. http://en.wikipedia.org/wiki/Multiprotocol Label Switching.Google Scholar
- Wikipedia. 2013c. Software defined networking. http://en.wikipedia.org/wiki/Software_Defined_Networking.Google Scholar
- Xilinx. 2013a. Virtex 7 fpgas. http://www.xilinx.com/products/silicon-devices/fpga/virtex-7/index.htm.Google Scholar
- Xilinx. 2013b. Xilinx xcell journal. http://www.xilinx.com/publications/xcellonline/.Google Scholar
- Zheng, K., Hu, C., Liu, H., and Liu, B. 2004. An ultra high throughput and power efficient tcam-based ip lookup engine. In Proceedings of the 23rd Annual Joint Conference of the IEEE Computer and Communications Societies. Vol. 3. IEEE, 1984--1994.Google Scholar
- Zheng, K., Hu, C., Lu, H., and Liu, B. 2006. A TCAM-based distributed parallel ip lookup scheme and performance analysis. IEEE/ACM Trans. Netw.14, 4, 863--875. Google Scholar
Digital Library
Index Terms
A comprehensive performance analysis of virtual routers on FPGA
Recommendations
Fairness issues in software virtual routers
PRESTO '08: Proceedings of the ACM workshop on Programmable routers for extensible services of tomorrowIn this paper we investigate the building of a virtual router platform that ensures isolation and fairness between concurrent virtual routers. Recent developments in commodity x86 hardware enable us to take advantage of the flexibility and wealth of ...
FPGA-based Router Virtualization: A Power Perspective
IPDPSW '12: Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD ForumBoth Internet and semiconductor technology have advanced dramatically over the past decade. These advancements have made great impact on the conventional Internet infrastructure where networking equipment is dedicated on a per network basis. Router ...
Towards On-the-Fly Incremental Updates for Virtualized Routers on FPGA
FPL '11: Proceedings of the 2011 21st International Conference on Field Programmable Logic and ApplicationsRecently, router virtualization has gained much interest in networking community. However, hardware support for router virtualization is still in its primitive stages. One of the major problems in a virtualized router is how to support frequent routing ...






Comments