Advertisement

Cluster Computing

, Volume 3, Issue 2, pp 95–112 | Cite as

A comparative study of online scheduling algorithms for networks of workstations

  • Olaf Arndt
  • Bernd Freisleben
  • Thilo Kielmann
  • Frank Thilo
Article

Abstract

Networks of workstations offer large amounts of unused processing time. Resource management systems are able to exploit this computing capacity by assigning compute-intensive tasks to idle workstations. To avoid interferences between multiple, concurrently running applications, such resource management systems have to schedule application jobs carefully. Continuously arriving jobs and dynamically changing amounts of available CPU capacity make traditional scheduling algorithms difficult to apply in workstation networks. Online scheduling algorithms promise better results by adapting schedules to changing situations. This paper compares six online scheduling algorithms by simulating several workload scenarios. Based on the insights gained by simulation, the three online scheduling algorithms performing best were implemented in the Winner resource management system. Experiments conducted with Winner in a real workstation network confirm the simulation results obtained.

Keywords

Schedule Algorithm Resource Management System Online Schedule Fuzzy Processing Time Online Schedule Algorithm 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    O. Arndt, B. Freisleben, T. Kielmann and F. Thilo, Scheduling parallel applications in networks of mixed uniprocessor/multiprocessor workstations, in: Proc. ISCA 11th International Conference on Parallel and Distributed Computing Systems (PDCS-98), Chicago, IL (September 1998) pp. 190-197.Google Scholar
  2. [2]
    O. Arndt, B. Freisleben, T. Kielmann and F. Thilo, Batch queueing in the Winner resource management system, in: Proc. 1999 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'99), Vol. V, Las Vegas, NV (June/July 1999) pp. 2523–2529.Google Scholar
  3. [3]
    A.C. Arpaci-Dusseau and D.E. Culler, Extending proportional-share scheduling to a network of workstations, in: Proc. 1997 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'97), Las Vegas, NV (July 1997).Google Scholar
  4. [4]
    M.A. Baker, G.C. Fox and H.W. Yau, A Review of Commercial and Research Cluster Management Software, Technical Report NPAC TR SCCS-748, NPAC, Syracuse University, New York (November 1995).Google Scholar
  5. [5]
    F. Berman, R. Wolski, S. Figueira, J. Schopf and G. Shao, Application-level scheduling on distributed heterogeneous networks, in: Proc. Supercomputing 96 (November 1996).Google Scholar
  6. [6]
    P. Brucker, Scheduling Algorithms (Springer, Berlin, 1998).zbMATHGoogle Scholar
  7. [7]
    B. Chen and A.P.A. Vestjens, Scheduling on Identical Parallel Machines: How Good is LPT in an On-line Setting?, Technical Report Memorandum COSOR 96-11, Eindhoven University of Technology (1996).Google Scholar
  8. [8]
    CODINE 4.1.1, Computing in Networked Environments, Technical Overview, GENIAS Software GmbH (1996).Google Scholar
  9. [9]
    A.B. Downey, Using queue time predictions for processor allocation, in: Proc. International Parallel Processing Symposium (IPPS'97) O. Arndt et al. / Online scheduling algorithms for networks of workstations 111 Workshop on Job Scheduling Strategies for Parallel Processing (1997).Google Scholar
  10. [10]
    A. Enzmann, L. Kretzschmar and C. Young, Ray Tracing Worlds with POV-Ray (The Waite Group, 1994).Google Scholar
  11. [11]
    D.G. Feitelson and A. Muàlem Weil, Utilization and predictability in scheduling the IBM SP2 with backfilling, in: Proc. 12th International Parallel Processing Symposium (IPPS'98) (April 1998) pp. 542-546.Google Scholar
  12. [12]
    D.G. Feitelson and L. Rudolph (eds.), Job Scheduling Strategies for Parallel Processing, Lecture Notes in Computer Science, Vol. 1459, Springer, 1998.Google Scholar
  13. [13]
    H. Franke, J. Jann, J.E. Moreira, P. Pattnaik and M.A. Jette, An evaluation of parallel job scheduling for ASCI Blue-Pacific, in: Proc. Supercomputing 99 (November 1999).Google Scholar
  14. [14]
    A. Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek and V. Sunderam, PVM: Parallel Virtual Machine-A Users Guide and Tutorial for Network Parallel Computing (MIT Press, 1994).Google Scholar
  15. [15]
    D.P. Ghormley, D. Petrou, S.H. Rodigues, A.M. Vahdat and T.E. Anderson, GLUnix: a Global Layer Unix for a Network of Workstations, Software: Practice & Experience 28(9) (1998) 929–961.CrossRefGoogle Scholar
  16. [16]
    R.L. Graham, Bounds for certain multiprocessor anomalies, Bell System Technical Journal 45 (November 1966) 1563–1581.Google Scholar
  17. [17]
    T.P. Green, DQS 3.0.2 Readme/Installation Manual, Supercomputer Computations Research Institute, Florida State University, Tallahassee (June 1995).Google Scholar
  18. [18]
    W. Gropp, E. Lusk and A. Skjellum, Using MPI: Portable Parallel Programming with the Message-Passing Interface (MIT Press, Cambridge, MA, 1994).Google Scholar
  19. [19]
    J.L. Gustafson and R. Todi, Conventional benchmarks as a sample of the performance spectrum, in: Proc. 31st Hawaii International Conference on System Sciences (1998).Google Scholar
  20. [20]
    L.A. Hall, A.S. Schulz, D.B. Shmoys and J. Wein, Scheduling to minimize average completion time: Off-line and on-line approximation algorithms, Mathematics of Operations Research 22 (August 1997) 513–544.zbMATHMathSciNetCrossRefGoogle Scholar
  21. [21]
    S. Herbert, Generic NQS-free batch processing for UNIX, Academic Computing Services, The University of Sheffield, UK, http://www.shef.ac.uk/uni/projects/nqs/Generic-NQS/.Google Scholar
  22. [22]
    M.A. Iverson, F. Özgüner and L.C. Potter, Statistical prediction of task execution times through analytic benchmarking for scheduling in a heterogeneous environment, in: Proc. 8th Heterogeneous Computing Workshop (HCW), San Juan, Puerto Rico (April 1999).Google Scholar
  23. [23]
    D. Karger, C. Stein and J. Wein, Scheduling algorithms, in: Handbook of Algorithms and Theory of Computation, ed. M.J. Atallah (CRC Press, 1997).Google Scholar
  24. [24]
    T. Kielmann, Programming heterogeneous workstation clusters based on coordination, in: Proc. 8th International Conference of Computing and Information, Waterloo, Ontario, Canada (June 1996). Published as special issue of the CD-ROM Journal of Computing and Information (JCI).Google Scholar
  25. [25]
    P. Krueger and R. Chawla, The stealth distributed scheduler, in: Proc. IEEE 11th International Conference on Distributed Computing Systems (ICDCS) (1991) pp. 336-343.Google Scholar
  26. [26]
    S. Leonardi and D. Raz, Approximating total flow time with preemption, in: Proc. of the 29th Annual ACM Symposium on Theory of Computing (ACM, 1997) pp. 110-119.Google Scholar
  27. [27]
    D.A. Lifka, M.W. Henderson and K. Rayl, Users guide to the argonne SP scheduling system, Mathematics and Computer Science Division Technical Memorandum No. ANL/MCS-TM-201, Argonne National Laboratory, USA (May 1995).Google Scholar
  28. [28]
    M.J. Litzkow, M. Livny and M.W. Mutka, Condor-a hunter of idle workstations, in: Proc. of the 8th International Conference on Distributed Computer Systems (ICDCS) (IEEE, 1988) pp. 104-111.Google Scholar
  29. [29]
    M. Livny and R. Raman, High-throughput resource management, in: The GRID: Blueprint for a New Computing Infrastructure (Morgan Kaufmann, San Mateo, CA, 1998) pp. 311-337.Google Scholar
  30. [30]
    C.A. Phillips, C. Stein and J. Wein, Scheduling jobs that arrive over time, in: Algorithms and Data Structures, ed. S.G. Akl, Lecture Notes in Computer Science, Vol. 955 (Springer, Berlin, 1995) pp. 86–97.Google Scholar
  31. [31]
    C.D. Polychronopoulos and D.J. Kuck, Guided self-scheduling: A practical scheduling scheme for parallel supercomputers, IEEE Transactions on Computers 36(12) (1987) 1425–1439.CrossRefGoogle Scholar
  32. [32]
    S.R. Presnell, The Batch Reference Guide, 3rd edition, Batch Version 4.0, Department of Pharmaceutical Chemistry, University of California (March 1994).Google Scholar
  33. [33]
    J. Pruyne and M. Livny, Parallel processing on dynamic resources with CARMI, in: Proc. International Parallel Processing Symposium (IPPS'95) Workshop on Job Scheduling Strategies for Parallel Processing, Lecture Notes in Computer Science, Vol. 949 (Springer, Berlin, 1995) pp. 259–278.Google Scholar
  34. [34]
    J. Sgall, On-line scheduling-A survey, in: Lecture Notes in Computer Science, Vol. 1442, eds. A. Fiat and G.J. Woeginger (Springer, Berlin, 1996) pp. 196–231.Google Scholar
  35. [35]
    D.B. Shmoys, J. Wein and D.P. Williamson, Scheduling parallel machines on-line, SIAM Journal on Computing 24 (1995) 1313–1331.zbMATHMathSciNetCrossRefGoogle Scholar
  36. [36]
    W. Smith, I. Foster and V. Taylor, Predicting application run times using historical information, in: Proc. Joint International Parallel Processing Symposium, Symposium on Parallel & Distributed Processing (IPPS/SPDP '98), Workshop on Job Scheduling Strategies for Parallel Processing (1998).Google Scholar
  37. [37]
    Q. Snell, G. Judd and M. Clement, Load balancing in a heterogeneous supercomputing environment, in: Proc. 1998 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'98), Vol. II (1998) pp. 951–957.Google Scholar
  38. [38]
    D. Talby and D.G. Feitelson, Supporting priorities and improving utilization of the IBM SP scheduler using slack-based backfilling, in: Proc. Joint International Parallel Processing Symposium, Symposium on Parallel & Distributed Processing (IPPS/SPDP '99), San Juan, Puerto Rico (April 1999).Google Scholar
  39. [39]
    T.H. Tzen and L.M. Ni, Trapezoid self-scheduling: A practical scheduling scheme for parallel compilers, IEEE Transactions on Parallel and Distributed Systems 4(1) (1995) 87–98.CrossRefGoogle Scholar
  40. [40]
    A.P.A. Vestjens, On-line machine scheduling, Ph.D. thesis, Eindhoven University of Technology (1997).Google Scholar
  41. [41]
    S. White, A. Alund and V.S. Sunderam, Performance of the NAS parallel benchmarks on PVM-based networks, Journal of Parallel and Distributed Computing 26 (1995) 61–71.CrossRefGoogle Scholar
  42. [42]
    S. Zhou, LSF: Load sharing in large-scale heterogeneous distributed systems, University of Toronto (December 1992).Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Olaf Arndt
    • 1
  • Bernd Freisleben
    • 1
  • Thilo Kielmann
    • 2
  • Frank Thilo
    • 1
  1. 1.Department of Electrical Engineering and Computer ScienceUniversity of SiegenGermany
  2. 2.Department of Mathematics and Computer ScienceVrije UniversiteitAmsterdamThe Netherlands

Personalised recommendations