Towards Decentralized Load Balancing in a Computational Grid Environment

  • Kai Lu
  • Riky Subrata
  • Albert Y. Zomaya
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3947)


Load balancing has been a key concern for locally distributed multiprocessor systems. The emergence of computational grid extends this problem, such as scalability, heterogeneity of computing resources and considerable communication delay. In this paper, we study the problem of scheduling a large number of CPU-intensive jobs on such systems. The time spent by a job in the system is considered as the main issue that needs to be minimized. The proposed dynamic algorithm of scheduling jobs consists of two policies: Instantaneous Distribution Policy (IDP) and Load Adjustment Policy (LAP). Our algorithm does not address directly the load balancing problem since it is completely unrealistic in such large environments, but we will show that even a non-perfectly load balanced system can behave reasonably well by taking into account the jobs’ time demands. The proposed algorithm is evaluated by a series of simulations.


Load Balance Transmission Delay Computing Node Average Response Time Communication Delay 
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.
    Foster, I., Kesselman, C. (eds.): The Grid: Blueprint for a New Computing Infrastructure. Morgan Kaufmann, San Francisco (1999)Google Scholar
  2. 2.
    El-Ghazawi, T., Gaj, K., Alexandridis, N., Vroman, F., Nguyen, N., Radzikowski, J., Samipagdi, P., Suboh, S.: A Performance Study of Job Management Systems. Concurrency and Computation: Practice and Experience 16(13), 1229–1246 (2004)CrossRefGoogle Scholar
  3. 3.
    Casavant, T.L., Kuhl, J.G.: A taxonomy of scheduling in general-purpose distributed computing systems. IEEE Transactions on Software Engineering 14(2), 141–154 (1988)CrossRefGoogle Scholar
  4. 4.
    Kim, C., Kameda, H.: An algorithm for optimal static load balancing in distributed computer systems. IEEE Trans. Comput. 41(3), 381–384 (1992)CrossRefGoogle Scholar
  5. 5.
    Lin, H.-C., Raghavendra, C.S.: A dynamic load-balancing policy with a central job dispatcher (LBC). IEEE Transactions on Software Engineering 18(2), 145–158 (1992)CrossRefGoogle Scholar
  6. 6.
    Mitzenmacher, M.: The power of Two Choices in Randomized Load Balancing. IEEE Trans. Parallel and Distributed Systems 12(10), 1094–1104 (2001)CrossRefGoogle Scholar
  7. 7.
    Shivaratri, N.G., Krueger, P., Singhal, M.: Load distributing for locally distributed systems. Computer, 33–44 (1992)Google Scholar
  8. 8.
    Barak, A., La’adan, O.: The MOSIX Multicomputer Operating System for High Performance Cluster Computing. Journal of Future Generation Computer Systems 13(4–5), 361–372 (1998)CrossRefGoogle Scholar
  9. 9.
    Sanders, P.: Analysis of nearest neighbor load balancing algorithms for random loads. Parallel Computing 25(80) (1999)Google Scholar
  10. 10.
    Xu, C., Lau, F., Monien, B., Luling, R.: Nearest neighbor algorithms for load balancing in parallel computers. Concurrency, Practice and Experience 7, 736 (1995)CrossRefGoogle Scholar
  11. 11.
    Zhou, S.: A trace-driven simulation study of dynamic load balancing. IEEE Transactions on Software Engineering 14(9), 1327–1341 (1988)CrossRefGoogle Scholar
  12. 12.
    Wolski, R., Spring, N., Hayes, J.: The network weather service: A distributed resource performance forecasting service for metacomputing. Journal of Future Generation Computing Systems 15, 757–768 (1999)CrossRefGoogle Scholar
  13. 13.
    Francis, P., Jamin, S., Jin, C., Jin, Y., Raz, D., Shavitt, Y., Zhang, L.: IDMaps: a global internet host distance estimation service. IEEE/ACM Transactions on Networking (TON) 9(5), 525–540 (2001)CrossRefGoogle Scholar
  14. 14.
    Agrawal, A., Casanova, H.: Clustering hosts in P2P and global computing platforms. In: 3rd IEEE/ACM International Symposium on CCGrid 2003, 12-15 May 2003, pp. 367–373 (2003)Google Scholar
  15. 15.
    Theilmann, W., Rothermel, K.: Dynamic distance maps of the Internet. INFOCOM 2000. In: Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings, March 26-30, vol. 1, pp. 275–284. IEEE, Los Alamitos (2000)Google Scholar
  16. 16.
    Xian-He, S., Ming, W.: GHS: A performance prediction and task scheduling system for Grid computing. In: IEEE International Parallel and Distributed Processing Symposium, IPDPS 2003 (2003)Google Scholar
  17. 17.
    Nudd, G.R., Kerbyson, D.J., Papaefstathiou, E., Perry, S.C., Harper, J.S., Wilcox, D.V.: PACE – a toolset for the performance prediction of parallel and distributed systems. Int. J. High Performance Computing Applications 3, 228–251 (2000)CrossRefGoogle Scholar
  18. 18.
    Amir, Y., Awerbuch, B., Barak, A., Borgstrom, S., Keren, A.: An opportunity cost approach for job assignment in a scalable computing cluster. IEEE Transactions on Parallel and Distributed Systems 11(7), 760–768 (2000)CrossRefGoogle Scholar
  19. 19.
    Harchol-Balter, M., Downey, A.: Exploiting Process Lifetime Distributions for Dynamic Load Balancing. In: Proceedings of ACM sigmetrics 1998 Conference on Measurement and Modeling of Computer Systems, May 1997, pp. 115–126 (1997)Google Scholar
  20. 20.
    Eager, D.L., Lazowska, E.D., Zahorjan, J.: The limited performance benefits of migrating active processes for load sharing. In: Proceedings of the 12th ACM Symposium on Operating Systems Principles, pp. 63–72 (1988)Google Scholar
  21. 21.
    Zhu, W., Socko, P., Kiepuszewski, B.: Migration impact on load balancing—an experience on amoeba. Operating Systems Review 31(1), 43–53 (1997)CrossRefGoogle Scholar
  22. 22.
    Krueger, P., Shivaratri, N.G.: Adaptive location policies for global scheduling. IEEE Transactions on Software Engineering 20(6), 432–444 (1994)CrossRefGoogle Scholar
  23. 23.
    Eager, D.L., Lazowska, E.D., Zahorjan, J.: A comparison of receiver initiated and sender initiated adaptive load sharing. Performance Evaluation 6, 53–68 (1986)CrossRefGoogle Scholar
  24. 24.
    Kunz, T.: The influence of different workload descriptions on a heuristic load balancing scheme. IEEE Transactions on Software Engineering 17(7), 725–730 (1991)CrossRefGoogle Scholar
  25. 25.
    Thanalapati, T., Dandamudi, S.: An efficient adaptive scheduling scheme for distributed memory multicomputers. IEEE Transactions on Parallel and Distributed Systems 12(7), 758–768 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kai Lu
    • 1
  • Riky Subrata
    • 1
  • Albert Y. Zomaya
    • 1
  1. 1.Networks & Systems Lab, School of Information TechnologiesUniversity of SydneyAustralia

Personalised recommendations