A Measurement Study of the Interplay Between Application Level Restart and Transport Protocol

  • Philipp Reinecke
  • Aad van Moorsel
  • Katinka Wolter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3335)


Restart is an application-level mechanism to speed up the completion of tasks that are subject to failures or unpredictable delays. In this paper we investigate if restart can be beneficial for Internet applications. For that reason we conduct and analyze a measurement study for restart applied to HTTP GET over TCP. Since application-level restart and TCP time-out mechanisms may interfere, we discuss in detail the relation between restart and transport protocol. The analysis shows that restart may especially be beneficial in the TCP set-up phase, in essence tuning TCP time-out values for the application at hand. In addition, we discuss the design of and experimentation with a proxy-based restart tool that includes a statistical oracle module to automatically adapt and optimize the restart time.


Completion Time Autocorrelation Function Measurement Study Download Time Partial Autocorrelation Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alt, H., Guibas, L., Mehlhorn, K., Karp, R., Wigderson, A.: A Method for Obtaining Randomized Algorithms with Small Tail Probabilities. Algorithmica 16(4/5), 543–547 (1996)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Bansal, D., Balakrishnan, H., Floyd, S., Shenker, S.: Dynamic Behavior of Slowly-Responsive Congestion Control Algorithms. In: Proceedings ACM SIGCOMM 2001, San Diego, CA, USA (August 2001)Google Scholar
  3. 3.
    Brockwell, P., Davis, R.: Time Series: Theory and Methods, 2nd edn. Springer, New York (1991)CrossRefGoogle Scholar
  4. 4.
    Chalasani, P., Jha, S., Shehory, O., Sycara, K.: Query Restart Strategies for Web Agents. In: Proceedings of Agents 1998. AAAI Press, Menlo Park (1998)Google Scholar
  5. 5.
    Cochran, W.: Sampling Techniques. John Wiley, New York (1977)zbMATHGoogle Scholar
  6. 6.
    Floyd, S., Fall, K.: Promoting the Use of End-to-End Congestion Control in the Internet. IEEE/ACM Transactions on Networking 7(4), 458–472 (1999)CrossRefGoogle Scholar
  7. 7.
    Krishnamurthy, B., Rexford, J.: Web Protocols and Practice. Addison-Wesley, Reading (2001)Google Scholar
  8. 8.
    Luby, M., Sinclair, A., Zuckerman, D.: Optimal Speedup of Las Vegas Algorithms. In: Israel Symposium on Theory of Computing Systems, pp. 128–133 (1993)Google Scholar
  9. 9.
    Maurer, S.M., Huberman, B.A.: Restart strategies and Internet congestion. Journal of Economic Dynamics and Control 25, 641–654 (2001)zbMATHCrossRefGoogle Scholar
  10. 10.
    van Moorsel, A., Wolter, K.: Optimization of Failure Detection Retry Times. In: Performability workshop, Monticello, IL (October 2003)Google Scholar
  11. 11.
    van Moorsel, A.P.A., Wolter, K.: Analysis and Algorithms for Restart. In: Proceedings of Quantitative Evaluation of Systems, Twente, The Netherlands, September 27–30, pp. 195–204 (2004)Google Scholar
  12. 12.
    R Development Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria (2003),
  13. 13.
    Ruan, Y., Horvitz, E., Kautz, H.: Restart Policies with Dependence among Runs: A Dynamic Programming Approach. In: Van Hentenryck, P. (ed.) CP 2002. LNCS, vol. 2470, p. 573. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  14. 14.
    Schroeder, M., Buro, L.: Does the Restart Method Work? Preliminary Results on Efficiency Improvements for Interactions of Web-Agents. In: Wagner, T., Rana, O. (eds.) Proceedings of the Workshop on Infrastructure for Agents, MAS, and Scalable MAS at the Conference Autonomous Agents 2001. Springer, Montreal (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Philipp Reinecke
    • 1
  • Aad van Moorsel
    • 2
  • Katinka Wolter
    • 1
  1. 1.Institut für InformatikHumboldt-Universität zu BerlinBerlinGermany
  2. 2.School of Computing ScienceUniversity of Newcastle upon TyneNewcastle upon TyneUnited Kingdom

Personalised recommendations