Advertisement

Performance-Adaptive Prediction-Based Transport Control over Dedicated Links

  • Xukang Lu
  • Qishi Wu
  • Nageswara S. V. Rao
  • Zongmin Wang
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 22)

Abstract

Several research and production networks now provide multiple Gbps dedicated connections to meet the demands of large data transfers over wide-area networks. End users, however, have not been able to see corresponding increase in application goodputs mainly because (i) such rates have pushed the bottleneck from the network to the end system, and (ii) the traditional transport methods are not optimized for handling host dynamics. Due to the sharing with unknown background workloads, the data receiver oftentimes lacks sufficient system resources to process packets arriving from high-speed dedicated links, therefore leading to significant packet drops at the end system. We propose a rigorous design approach for a new class of transport protocols that explicitly account for the dynamics of the running environment to maximize application goodputs over dedicated connections. The control strategy of the proposed transport method combines two aspects: (i) the receiving bottleneck rate is predicted based on performance modeling, and (ii) the sending rate is stabilized at the estimated bottleneck rate based on stochastic approximation. We test the proposed method on a local dedicated connection and the experimental results illustrate its superior performance over existing methods.

Keywords

Transport control dedicated networks performance modeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    DRAGON: Dynamic Resource Allocation via GMPLS Optical Networks, http://dragon.maxgigapop.net
  2. 2.
  3. 3.
    Beltran, M., Guzman, A.: A new cpu availability prediction model for time-shared systems. IEEE Transaction 2009 57, 865–875 (2009)MathSciNetGoogle Scholar
  4. 4.
    Benveniste, A., Metivier, M.: Adaptive Algorithms and Stochastic Approximation. Springer, New York (1990)CrossRefzbMATHGoogle Scholar
  5. 5.
    Brakmo, L., O’Malley, S., Peterson, L.: Tcp vegas: new techniques for congestion detection and avoidance. In: SIGCOMM 1994 Conf. on Communications Architectures and Protocols, London, United Kingdom, October 1994, pp. 24–35 (1994)Google Scholar
  6. 6.
    Dinda, P., OHallaron, D.: Host load prediction using linear models. Cluster Computing 3(4), 265–280 (2000)CrossRefGoogle Scholar
  7. 7.
    Rio, M., et al.: A map of the networking code in linux kernel 2.4.20. Technical Report DataTAG-2004-1 (March 2004)Google Scholar
  8. 8.
    Floyd, S.: Highspeed tcp for large congestion windows, Internet Draft (February 2003)Google Scholar
  9. 9.
    Gu, Y., Hong, X., Mazzucco, M., Grossman, R.L.: SABUL: A high performance data transfer protocol. Submitted to IEEE Communications Letters (2004)Google Scholar
  10. 10.
    He, E., Leigh, J., Yu, O., DeFanti, T.: Reliable blast udp: predictable high performance bulk data transfer. In: IEEE Int. Conf. on Cluster Computing, Chicago, Illinois, September 23-26 (2002)Google Scholar
  11. 11.
    Katabi, D., Handley, M., Rohrs, C.: Internet congestion control for future high-bandwidth-delay product environments. In: Proc. of ACM SIGCOMM 2002, Pittsburgh, PA, August 19-21 (2002), http://www.acm.org/sigcomm/sigcomm2002/papers/xcp.pdf
  12. 12.
    Kelly, T.: Scalable tcp: Improving performance in highspeed wide area networks. In: Workshop on Protocols for Fast Long-Distance Networks (Februrary 2003)Google Scholar
  13. 13.
    Kushner, H.J., Yin, C.G.: Stochastic Approximation Algorithms and Applications. Springer, New York (1997)CrossRefzbMATHGoogle Scholar
  14. 14.
    Kuzmanovic, A., Knightly, E., Cottrell, R.L.: Hstcp-lp: A protocol for low-priority bulk data transfer in high-speed high-rtt networks. In: The Second Int. Workshop on Protocols for Fast Long-Distance Networks (February 2004)Google Scholar
  15. 15.
    Love, R.: CPU Scheduler. Sams (2003)Google Scholar
  16. 16.
    Low, S., Peterson, L., Wang, L.: Understanding vegas: a duality model. J. of the ACM 49(2), 207–235 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Rao, N., Wing, W., Carter, S., Wu, Q.: Ultrascience net: Network testbed for large-scale science applications. IEEE Communications Magazine 43(11), s12–s17 (2005), http://www.csm.ornl.gov/ultranet Google Scholar
  18. 18.
    Wu, Q., Rao, N.: Protocol for high-speed data transport over dedicated channels. In: Proc. of the 3rd Int. Workshop on Protocols for Fast Long-Distance Networks, February 3-4, pp. 155–162 (2005)Google Scholar
  19. 19.
    Zheng, X., Mudambi, A., Veeraraghavan, M.: Frtp: Fixed rate transport protocol – a modified version of sabul for end-to-end circuits. In: Proc. of Broadnets (2004)Google Scholar
  20. 20.
    Zheng, X., Veeraraghavan, M., Rao, N., Wu, Q., Zhu, M.: Cheetah: Circuit-switched high-speed end-to-end transport architecture testbed. IEEE Communications Magazine 43(11), s11–s17 (2005)Google Scholar

Copyright information

© ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering 2009

Authors and Affiliations

  • Xukang Lu
    • 1
  • Qishi Wu
    • 1
  • Nageswara S. V. Rao
    • 2
  • Zongmin Wang
    • 3
  1. 1.Dept of Computer ScienceUniversity of MemphisMemphisUSA
  2. 2.Computer Sci. Math. Div.Oak Ridge National Lab.Oak RidgeUSA
  3. 3.Henan Key Lab On Info. Net.Zhengzhou Univ.ZhengzhouChina

Personalised recommendations