Feedback Control with Prediction for Thread Allocation in Pipeline Architecture Web Server

  • Peng Shao-Liang
  • Li Shan-Shan
  • Liao Xiang-Ke
  • Peng Yu-Xing
  • Ye Hui
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4308)


With the sharply development of high-speed backbone network and phenomenal growth of Web applications, many kinds of Web server structures have been advanced and implemented to increase the serving ability of Web server. In this paper, we propose a pipeline architecture multi-thread web server open KETA which divides the requests processing into several independent phases. This architecture reduces parallelism granularity and achieves inner-request parallelism to enhance its processing capability. Furthermore, a combined feed-forward/feedback model is designed to manage thread allocation in this special architecture. The feed-forward predictor relates instantaneous measurements of queue length and processing rate of each pipeline phase to the thread allocation over a finite prediction horizon. The feedback controller deals with the uncertainty the predictor brings and improves open KETA’s performance farther. Experimental results show the capability of open KETA and the effectiveness of the thread allocation model.


Queue Length Feedback Controller Data Cache Main Thread Helper Thread 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhi-Guang, S., CHuang, L., et al.: Web Quality of Service: A survey. Journal of Computers (Febuary 2004)Google Scholar
  2. 2.
    Huitema, C.: Network vs. server issues in end-to-end performance. In: Keynote speech at Performance and Architecture of Web Servers 2000, Santa Clara, CA (2000),
  3. 3.
    Gray, J., Shenoy, P.: Rules of thumb in data engineering. In: Proc. of IEEE 16th Int’l Conf. on Data Engineering, San Diego, CA, pp. 3–10 (April 2000)Google Scholar
  4. 4.
    Cardellini, V., Casalicchio, E.: The State of the Art in Locally Distributed Web-server Systems. IBM research report, Computer Science, RC22209 (W0110-048), October 16 (2001)Google Scholar
  5. 5.
    Joubert, P., King, R., Neves, R., Russinovich, M., Tracey, J.: High-performance memory-baxde Web servers: Kernel and user-space performance. In: Proceedings of the USENIX 2001 Annual Technical Conference (2001)Google Scholar
  6. 6.
    Brecht, T., Pariag, D., GammoIn, L.: Proceedings of the USENIX 2004 Annual Technical Conference: General Track (June 2004)Google Scholar
  7. 7.
    de Ven, A.w.: kHTTPd Linux http accelerator,
  8. 8.
    Behren, R.v., Condit, J., Brewer, E.: Why events are a bad idea for highcon-currency servers. In: 9th Workshop on Hot Topics in Operating Systems, HotOS IX (2003)Google Scholar
  9. 9.
    The Apache Group. Apache http server project,
  10. 10.
    Pai, V.S., Druschel, P., Zwaenepoel, W.: Flash:An efficient and portable Web server. In: Proceedings of the USENIX 1999 Annual Technical Conference, Monterey,CA (June 1999)Google Scholar
  11. 11.
    Red Hat, Inc. TUX 2.2 Reference Manual (2002)Google Scholar
  12. 12.
    Abdelzaher, T.F., Shin, K.G., Bhatti, N.: Performance guarantees for web server endsystems: A controltheoretical approach. In: IEEE Transactions on Parallel and Distributed Systems (January 2002)Google Scholar
  13. 13.
    Lu, C., Abdelzaher, T., Stankovic, J., Son, S.: A feedback control approach for guaranteeing relative delays in web servers. In: IEEE Real-Time Technology and Applications Symposium (June 2001)Google Scholar
  14. 14.
    Stankovic, J.A., He, T., Abdelzaher, T.F., Marley, M., Tao, G., Son, S.H., Lu, C.: Feedback control scheduling in distributed systems. In: IEEE Real-Time Systems Symposium, London, UK (December 2001)Google Scholar
  15. 15.
    Henriksson, D., Lu, Y., Abdelzaher, T.: Improved prediction for web server delay control. In: IEEE Real-Time Systems Symposium (2004)Google Scholar
  16. 16.
    Krishnamurthy, B., Rexford, J.: Web Protocols and Practices: HTTP/1.1, Networking Protocols, Caching, and Traffic Measurement. Addison-Wesley, Reading (2001)Google Scholar
  17. 17.
    Feldmann, A.: Web performance characteristics. IETF plenary,
  18. 18.
    Shan-Shan, L., Xiang-Ke, L., Jin-Yuan, L.: Dynamic Thread Management in Kernel Pipeline Web Server. In: The IFIP Network and Parallel Conference (2005)Google Scholar
  19. 19.
    Abdelzaher, T.F., Bhatti, N. (eds.): Web server QOS management by adaptive content deliveryGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Peng Shao-Liang
    • 1
  • Li Shan-Shan
    • 1
  • Liao Xiang-Ke
    • 1
  • Peng Yu-Xing
    • 1
  • Ye Hui
    • 2
  1. 1.School of ComputerNational University of Defense TechnologyChangShaChina
  2. 2.Hunan Science and Technology CollegeChangShaChina

Personalised recommendations