The Community for Technology Leaders
RSS Icon
Issue No.07 - July (2012 vol.23)
pp: 1178-1192
Dong Lin , The Hong Kong University of Science and Technology, Hong Kong
Mounir Hamdi , The Hong Kong University of Science and Technology, Hong Kong
Jogesh K. Muppala , The Hong Kong University of Science and Technology, Hong Kong
High-speed routers rely on well-designed packet buffers that support multiple queues, provide large capacity and short response times. Some researchers suggested combined SRAM/DRAM hierarchical buffer architectures to meet these challenges. However, these architectures suffer from either large SRAM requirement or high time-complexity in the memory management. In this paper, we present scalable, efficient, and novel distributed packet buffer architecture. Two fundamental issues need to be addressed to make this architecture feasible: 1) how to minimize the overhead of an individual packet buffer; and 2) how to design scalable packet buffers using independent buffer subsystems. We address these issues by first designing an efficient compact buffer that reduces the SRAM size requirement by (k-1)/k. Then, we introduce a feasible way of coordinating multiple subsystems with a load-balancing algorithm that maximizes the overall system performance. Both theoretical analysis and experimental results demonstrate that our load-balancing algorithm and the distributed packet buffer architecture can easily scale to meet the buffering needs of high bandwidth links and satisfy the requirements of scale and support for multiple queues.
Router memory, SRAM/DRAM, packet scheduling.
Dong Lin, Mounir Hamdi, Jogesh K. Muppala, "Distributed Packet Buffers for High-Bandwidth Switches and Routers", IEEE Transactions on Parallel & Distributed Systems, vol.23, no. 7, pp. 1178-1192, July 2012, doi:10.1109/TPDS.2011.276
[1] A. Willig, A Short Introduction to Queueing Theory, Telecom Networks Group, pp. 19-27, 1999.
[2] B. Agrawal and T. Sherwood, "Virtually Pipelined Network Memory," Proc. IEEE/ACM 39th Ann. Int'l Symp. Microarchitecture (Micro '06), pp. 197-207, Dec. 2006.
[3] B.S. Arnaud, "Scaling Issues on Internet Networks," , 2001.
[4] Cisco, "Cisco Carrier Router System," index.html, 2011.
[5] D. Lin, M. Hamdi, and J. Muppala, "Designing Packet Buffers in High Bandwidth Switches and Routers," Proc. Int'l Conf. High Performance Switching and Routing (HPSR '10), pp. 32-37, June 2010.
[6] D. Lin, M. Hamdi, and J. Muppala, "Designing Packet Buffers Using Random Round Robin," Proc. IEEE GlobeCom '10, pp. 1-5, Dec. 2010.
[7] D. Lin and M. Hamdi, "Two-Stage Fair Queuing Using Budget Round-Robin," Proc. IEEE Int'l Conf. Comm. (ICC '10), pp. 1-5, May 2010.
[8] DRAMeXchange,, 2011.
[9] F. Wang and M. Hamdi, "Scalable Router Memory Architecture Based on Interleaved DRAM," Proc. Workshop High Performance Switching and Routing (HPSR '06), pp. 6-10, May 2006.
[10] F. Wang, M. Hamdi, and J. Muppala, "Using Parallel DRAM to Scale Router Buffers," IEEE Trans. Parallel and Distributed Systems, vol. 20, no. 5, pp. 710-724, May 2009.
[11] G. Appenzeler, I. Keslassy, and N. McKeown, "Sizing Router Buffers," ACM SIGCOMM Computer Comm. Rev., vol. 34, no. 4, pp. 281-292, Oct. 2004.
[12] G. Shrimali and N. McKeown, "Building Packet Buffers with Interleaved Memories," Proc. Workshop High Performance Switching and Routing (HPSR '05), pp. 1-5, May 2005.
[13] H. Wang and B. Lin, "Block-Based Buffer with Deterministic Packet Departure," Proc. Int'l Conf. High Performance Switching and Routing (HPSR '10), pp. 38-43, June 2010.
[14] H. Wang, H. Zhao, B. Lin, and J. Xu, "Design and Analysis of a Robust Pipelined Memory System," Proc. IEEE INFOCOM '10, pp. 1-9, Mar. 2010.
[15] J. Corbal, R. Espasa, and M. Valero, "Command Vector Memory Systems: High performance at Low Cost," Proc. Int'l Conf. Parallel Architectures and Compilation Techniques, pp. 68-77, Oct. 1998.
[16] J. Garcia, J. Corbal, L. Cerda, and M. Valero, "Design and Implementation of High-Performance Memory Systems for Future Packet Buffers," Proc. IEEE/ACM 36th Ann. Int'l Symp. Microarchitecture (Micro '03), pp. 372-384, Dec. 2003.
[17] J. Garcia, M. March, L. Cerda, J. Corbal, and M. Valero, "A DRAM/SRAM Memory Scheme for Fast Packet Buffers," IEEE Trans. Computers, vol. 55, no. 5, pp. 588-602, May 2006.
[18] J. Kleinberg and E. Tardos, Algorithm Design, pp. 758-760. Prentice Hall, 2006.
[19] Juniper E Series Router,, 2011.
[20] K.G. Coffman and A.M. Odlyzko, "Is There a Moore's Law for Data Traffic?," Handbook of Massive Data Sets, pp. 47-93, Kluwer, 2002.
[21] M. Kabra, S. Saha, and B. Lin, "Fast Buffer Memory with Deterministic Packet Departures," Proc. 14th IEEE Symp. High Performance Interconnects '06, pp. 67-72, 2006.
[22] Micron Reduced Latency DRAM MT49H16M36 Datasheet, rldramMT49 H16M36A.pdf, 2009.
[23] N. Beheshti, E. Burmeister, Y. Ganjali, J. Bowers, D. Blumenthal, and N. McKeown, "Optical Packet Buffers for Backbone Internet Routers," IEEE/ACM Trans. Networking, vol. 18, no. 5, pp. 1599-1609, Oct. 2010.
[24] N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner, "OpenFlow: Enabling Innovation in Campus Networks," SIGCOMM Computer Comm. Rev., vol. 38, no. 2, pp. 69-74, 2008.
[25] Phoenics Electronics, http:/, 2011.
[26] R. Prasad, C. Dovrolis, and M. Thottan, "Router Buffer Sizing for TCP Traffic and the Role of the Output/Input Capacity Ratio," IEEE/ACM Trans. Networking, vol. 17, no. 5, pp. 1645-1658, Oct. 2009.
[27] S. Iyer, R. Kompella, and N. McKeown, "Designing Packet Buffers for Router Linecards," IEEE Trans. Networking, vol. 16, no. 3, pp. 705-717, June 2008.
[28] Samsung Product SRAM/DRAM Chips, com/global/business/ semiconductor/productsProducts.html, 2011.
[29] Samsung DDR3 chip K4B4G0446B Datasheet, http://www. semiconductor/ product/ 2009/6/11366219ds_k4b4gxx46b_rev10.pdf, 2009.
[30] W. Fang and L. Peterson, "Inter-as Traffic Patterns and Their Implications," Proc. GlobeCom '99, pp. 1859-1868, Dec. 1999.
43 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool