Using Split Queues to Improve the Performance of Parallel Switch

  • Xiaofeng Hu
  • Zhigang Sun
  • Xicheng Lu
  • Jinshu Su
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2834)

Abstract

Parallel switch scales well with the growth of port density and line rate. PSIQC (Parallel Switch based on Input-Queued Crossbar) is a parallel switch that is scalable and simple to implement. But it needs large capacity high-speed memories to store cells, and the average cell latency is high under heavy load. This paper presents a revised version of PSIQC based on split queues that is initialed as SQ-PSIQC (Split Queued Parallel Switch based on Input-Queued Crossbar), and its scheduling algorithm SQ-RRDS (Split Queued Round Robin and Deterministic Sequence). SQ-PSIQC not only has all of the original characteristics, but also solves the two above-mentioned problems. In SQ-PSIQC the memory buffers are required to operate only at 1/m of the line rate, where m is the number of the middle switches. The simulation results show that SQ-PSIQC performs better than PSIQC in the average latency and throughput under any load, especially heavy load.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    McKeown, N.: A fast switched backplane for a gigabit switched router. Business Communications Review (December 1997)Google Scholar
  2. 2.
    McKeown, N., Izzard, M., Mekkittikul, A., Ellersick, W., Horowitz, M.: Tiny Tera: a packet switch core. IEEE Micro 17(1), 26–33 (1997)CrossRefGoogle Scholar
  3. 3.
    Partidge, C., Carvey, P., Burgess, E., et al.: A 50Gb/s IP router. IEEE/ACM Transactions on Networking 6(3), 237–248 (1998)CrossRefGoogle Scholar
  4. 4.
    Arpaci, M., Copeland, J.: Buffer Management for Shared-Memory ATM Switches. IEEE Communications Surveys, 1Q (2000)Google Scholar
  5. 5.
    Semeria, C.: Internet backbone routers and evolving Internet design. White paper, http://www.juniper.com
  6. 6.
    Iyer, S., Zhang, R., McKeown, N.: Routers with a Single Stage of Buffering. In: Proc. of ACM SIGCOMM 2002, Pittsburgh (September 2002)Google Scholar
  7. 7.
    Iyer, S., Awadallah, A., McKeown, N.: Analysis of a packet switch with memories running slower than the line rate. In: Proc. of IEEE Infocom 2000, Tel-Aviv, Israel (March 2000)Google Scholar
  8. 8.
    Iyer, S., McKeown, N.: Making Parallel Packet Switches Practical. In: Proc. of IEEE Infocom 2001, Alaska (April 2001)Google Scholar
  9. 9.
    Wang, W., Dong, L., Wolf, W.: A Distributed Switch Architecture with Dynamic Loadbalancing and Parallel Input-Queued Crossbars for Terabit Switch Fabrics. In: Proc. Of IEEE Infocom 2002, New York (June 2002)Google Scholar
  10. 10.
    Keslassy, I., McKeown, N.: Maintaining Packet Order in Two-Stage Switches. In: Proc. of IEEE Infocom 2002, New York (June 2002)Google Scholar
  11. 11.
    Chiussi, F., Khotimsky, D., Krishnan, S.: Generalized Inverse Multiplexing of Switched ATM Connections. In: Proc. of IEEE Globecom 1998, Sydney, Australia (November 1998)Google Scholar
  12. 12.
    Bennett, J., Partridge, C., Shectman, N.: Packet Reordering is not Pathological Network Behavior. IEEE/ACM Transactions on Networking 7(6), 789–798 (1999)CrossRefGoogle Scholar
  13. 13.
    McKeown, N.: iSLIP: a scheduling algorithm for input-queued switches. IEEE/ACM Transactions on Networking 7(2), 188–201 (1999)CrossRefGoogle Scholar
  14. 14.
    Zhigang, S., Jinshu, S., Xicheng, L.: ISP: a high performance crossbar arbitrating algorithm. Journal of Computer Research and Development (In Chinese) 23(10), 1078–1082 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Xiaofeng Hu
    • 1
  • Zhigang Sun
    • 1
  • Xicheng Lu
    • 1
  • Jinshu Su
    • 1
  1. 1.School of ComputerNational University of Defense TechnologyChangshaP.R. China

Personalised recommendations