SRPT Scheduling for Web Servers

  • Mor Harchol-Balter
  • Nikhil Bansal
  • Bianca Schroeder
  • Mukesh Agrawal
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2221)


This note briefly summarizes some results from two papers: [4] and [23]. These papers pose the following question: Is it possible to reduce the expected response time of every request at a web server, simply by changing the order in which we schedule the requests? In [4] we approach this question analytically via an M/G/1 queue. In [23] we approach the same question via implementation involving an Apache web server running on Linux.


Access Link Fair Schedule Static Request Bottleneck Resource Large Request 
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.
    J. Almeida, M. Dabu, A. Manikutty, and P. Cao. Providing di.erentiated quality of-service inWeb hosting services. In Proceedings of the First Workshop on Internet Server Performance, June 1998.Google Scholar
  2. 2.
    Bruce Maggs at Akamai. Personal communication., 2001.Google Scholar
  3. 3.
    G. Banga, P. Druschel, and J. Mogul. Better operating system features for faster network servers. In Proc. Workshop on Internet Server Performance, June 1998.Google Scholar
  4. 4.
    Nikhil Bansal and Mor Harchol-Balter. Analysis of SRPT scheduling: Investigating unfairness. In Proceeding of ACM Sigmetrics Conference on Measurement and Modeling of Computer Systems (SIGMETRICS’ 01), June 2001.Google Scholar
  5. 5.
    Paul Barford and M. E. Crovella. Measuring web performance in the wide area. Performance Evaluation Review - Special Issue on Network Trafic Measurement and Workload Characterization, August 1999.Google Scholar
  6. 6.
    Paul Barford and Mark Crovella. Critical path analysis of tcp transactions. In SIGCOMM, 2000.Google Scholar
  7. 7.
    Paul Barford and Mark E. Crovella. Generating representative Web workloads for network and server performance evaluation. In Proceedings of SIGMETRICS’ 98, pages 151–160, July 1998.Google Scholar
  8. 8.
    M. Bender, S. Chakrabarti, and S. Muthukrishnan. Flow and stretch metrics for scheduling continous job streams. In Proceedings of the 9th Annual ACM-SIAM Symposium on Discrete Algorithms, 1998.Google Scholar
  9. 9.
    Michael Bender, Soumen Chakrabarti, and S. Muthukrishnan. Flow and stretch metrics for scheduling continuous job streams. In Proceedings of the 9th Annual ACM-SIAM Symposium on Discrete Algorithms, 1998.Google Scholar
  10. 10.
    Azer Bestavros, Robert L. Carter, Mark E. Crovella, Carlos R. Cunha, Abdelsalam Heddaya, and Sulaiman A. Mirdad. Application-level document caching in the internet. In Proceedings of the Second International Workshop on Services in Distributed and Networked Environments (SDNE’95), June 1995.Google Scholar
  11. 11.
    H. Braun and K. Claffy. Web trafic characterization: an assessment of the impact of caching documents from NCSA’s Web server. In Proceedings of the Second International WWW Conference, 1994.Google Scholar
  12. 12.
    Adrian Cockcroft. Watching your web server. The Unix Insider at, April 1996.
  13. 13.
    Mark E. Crovella and Azer Bestavros. Self-similarity in World Wide Web trafic: Evidence and possible causes. In Proceedings of the 1996 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, pages 160–169, May 1996.Google Scholar
  14. 14.
    Mark E. Crovella and Azer Bestavros. Self-similarity in World Wide Web trafic: Evidence and possible causes. IEEE/ACM Transactions on Networking, 5(6):835–846, December 1997.CrossRefGoogle Scholar
  15. 15.
    Mark E. Crovella, Robert Frangioso, and Mor Harchol-Balter. Connection scheduling in web servers. In USENIX Symposium on Internet Technologies and Systems, October 1999.Google Scholar
  16. 16.
    Mark E. Crovella, Murad S. Taqqu, and Azer Bestavros. Heavy-tailed probability distributions in the World Wide Web. In A Practical Guide To Heavy Tails, pages 3–26. Chapman & Hall, New York, 1998.Google Scholar
  17. 17.
    Peter Druschel and Gaurav Banga. Lazy receiver processing (LRP): A network subsystem architecture for server systems. In Proceedings of OSDI’ 96, October 1996Google Scholar
  18. 18.
    Fielding, Gettys, Mogul, Frystyk, and Berners-lee. DNS support for load balancing. RFC 2068, April 1997.Google Scholar
  19. 19.
    J.E. Gehrke, S. Muthukrishnan, R. Rajaraman, and A. Shaheen. Scheduling to minimize average stretch online. In 40th Annual symposium on Foundation of Computer Science, pages 433–422, 1999.Google Scholar
  20. 21.
    James Gwertzman and Margo Seltzer. The case for geographical push-caching. In Proceedings of HotOS’ 94, May 1994.Google Scholar
  21. 23.
    Mor Harchol-Balter, Nikhil Bansal, Bianca Schroeder, and Mukesh Agrawal. Implementation of SRPT scheduling in web servers. Technical Report CMU-CS-00-170, 2000.Google Scholar
  22. 24.
    Mor Harchol-Balter and Allen Downey. Exploiting process lifetime distributions for dynamic load balancing. In Proceedings of SIGMETRICS’ 96, pages 13–24, 1996.Google Scholar
  23. 26.
    Gordon Irlam. Unix file size survey-1993. Available at, September 1994.
  24. 27.
    M. Kaashoek, D. Engler, D. Wallach, and G. Ganger. Server operating systems. In SIGOPS European Workshop, September 1996.Google Scholar
  25. 28.
    L. Kleinrock, R.R. Muntz, and J. Hsu. Tight bounds on average response time for time-shared computer systems. In Proceedings of the IFIP Congress, volume 1, pages 124–133, 1971.Google Scholar
  26. 29.
    Leonard Kleinrock. Queueing Systems, volume II. Computer Applications. John Wiley & Sons, 1976.Google Scholar
  27. 30.
    W. E. Leland and T. J. Ott. Load-balancing heuristics and process behavior. In Proceedings of Performance and ACM Sigmetrics, pages 54–69, 1986.Google Scholar
  28. 31.
    S. Manley and M. Seltzer. Web facts and fantasy. In Proceedings of the 1997 USITS, 1997.Google Scholar
  29. 32.
    Evangelos Markatos. Main memory caching of Web documents. In Proceedings of the Fifth Interntional Conference on the WWW, 1996.Google Scholar
  30. 33.
    J. Mogul. Operating systems support for busy internet servers. Technical Report WRL-Technical-Note-49, Compaq Western Research Lab, May 1995.Google Scholar
  31. 34.
    V. N. Padmanabhan and J. Mogul. Improving HTTP latency. Computer Networks and ISDN Systems, 28:25–35, December 1995.CrossRefGoogle Scholar
  32. 35.
    Vivek S. Pai, Peter Druschel, and W. Zwaenepoel. Flash: An effcient and portable web server. In Proceedings of USENIX 1999, June 1999.Google Scholar
  33. 36.
    A.V. Pechinkin, A.D. Solovyev, and S.F. Yashkov. A system with servicing discipline whereby the order of remaining length is serviced first. Tekhnicheskaya Kibernetika, 17:51–59, 1979.MathSciNetGoogle Scholar
  34. 37.
    R. Perera. The variance of delay time in queueing system M/G/1 with optimal strategy SRPT. Archiv fur Elektronik und Uebertragungstechnik, 47:110–114, 1993.Google Scholar
  35. 38.
    David L. Peterson and David B. Adams. Fractal patterns in DASD I/O trafic. In CMG Proceedings, December 1996.Google Scholar
  36. 39.
    J. Roberts and L. Massoulie. Bandwidth sharing and admission control for elastic trafic. In ITC Specialist Seminar, 1998.Google Scholar
  37. 40.
    R. Schassberger. The steady-state appearance of the M/G/1 queue under the discipline of shortest remaining processing time. Advances in Applied Probability, 22:456–479, 1990.zbMATHCrossRefMathSciNetGoogle Scholar
  38. 41.
    L.E. Schrage. A proof of the optimality of the shortest processing remaining time discipline. Operations Research, 16:678–690, 1968.Google Scholar
  39. 42.
    L.E. Schrage and L.W. Miller. The queue M/G/1 with the shortest processing remaining time discipline. Operations Research, 14:670–684, 1966.zbMATHMathSciNetGoogle Scholar
  40. 43.
    F. Schreiber. Properties and applications of the optimal queueing strategy SRPT-a survey. Archiv fur Elektronik und Uebertragungstechnik, 47:372–378, 1993.Google Scholar
  41. 44.
    Bianca Schroeder and Mor Harchol-Balter. Evaluation of task assignment policies for supercomputing servers: The case for load unbalancing and fairness. In 9th IEEE Symposium on High Performance Distributed Computing (HPDC’ 00), August 2000.Google Scholar
  42. 45.
    A. Silberschatz and P. Galvin. Operating System Concepts, 5th Edition. John Wiley & Sons, 1998.Google Scholar
  43. 46.
    D.R. Smith. A new proof of the optimality of the shortest remaining processing time discipline. Operations Research, 26:197–199, 1976.CrossRefGoogle Scholar
  44. 47.
    W. Stallings. Operating Systems, 2nd Edition. Prentice Hall, 1995.Google Scholar
  45. 48.
    A.S. Tanenbaum. Modern Operating Systems. Prentice Hall, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Mor Harchol-Balter
    • 1
  • Nikhil Bansal
    • 1
  • Bianca Schroeder
    • 1
  • Mukesh Agrawal
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon UniversityPittsburgh

Personalised recommendations