On Fully Distributed Adaptive Load Balancing

  • David Breitgand
  • Rami Cohen
  • Amir Nahir
  • Danny Raz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4785)

Abstract

Monitoring is an inherent part of the management loop. This paper studies the problem of quantifying utility of monitoring in a fully distributed load balancing setting. We consider a system where job requests arrive to a collection of n identical servers. The goal is to provide the service with the lowest possible average waiting time in a fully distributed manner (to increase scalability and robustness).

We present a novel adaptive load balancing heuristic that maximizes utility of information sharing between the servers. The main idea is to forward the job request to a randomly chosen server and to collect load information on the request packet as it moves on. Each server decides, based on that information, whether to forward the job request packet to another server, or to execute it locally. Our results show that in many practical scenarios this self-adaptive scheme, which does not require dedicated resources for propagating of load information and decision making, performs extremely well with respect to best known practice.

References

  1. 1.
    Srisuresh, P., Gan, D.: Load Sharing using IP Network Address Translation (LSNAT) (August 1998)Google Scholar
  2. 2.
    Breitgand, D., Cohen, R., Nahir, A., Raz, D.: Cost aware adaptive load sharing. In: IWSOS 2007. The 2nd International Workshop on Self-Organizing Systems, English Lake District, UK (September 2007)Google Scholar
  3. 3.
    Mitzenmacher, M.: The power of two choices in randomized load balancing. IEEE Transactions on Parallel and Distributed Systems 12(10), 1094–1104 (2001)CrossRefGoogle Scholar
  4. 4.
    Breitgand, D., Nahir, A., Raz, D.: To know or not to know: on the needed amount of management information, Tech. Rep. H-0242, IBM T.J. Watson Research Center (2006)Google Scholar
  5. 5.
    Mitzenmacher, M.: How useful is old information? IEEE Transactions on Parallel and Distributed Systems 11(1), 6–20 (2000)CrossRefGoogle Scholar
  6. 6.
    Hui, C.-C., Chanson, S.T.: Improved Strategies for Dynamic Load Balancing. IEEE Concurrency 7(3), 58–67 (1999)CrossRefGoogle Scholar
  7. 7.
    Othman, O., Balasubramanian, J., Schmidt, D.C.: Performance Evaluation of an Adaptive Middleware Load Balancing and Monitoring Service. In: 24th IEEE International Conference on Distributed Computing Systems (ICDCS), Tokyo, Japan (May 2004)Google Scholar
  8. 8.
    Corradi, A., Leonardi, L., Zambonelli, F.: On the Effectiveness of Different Diffusive Load Balancing Policies in Dynamic Applications. IEEE Concurrency 7(1), 22–31 (1999)CrossRefGoogle Scholar
  9. 9.
    Amir, Y., Awerbuch, B., Barak, A., Borgstrom, R.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
  10. 10.
    Adam, C., Stadler, R.: Adaptable Server Clusters with QoS Objectives. In: IM 2005. 9th IFIP/IEEE International Symposium on Integrated Network Management, Nice, France (May 2005)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2007

Authors and Affiliations

  • David Breitgand
    • 1
  • Rami Cohen
    • 2
  • Amir Nahir
    • 1
  • Danny Raz
    • 2
  1. 1.IBM Haifa Research LabIsrael
  2. 2.CS Department, Technion, HaifaIsrael

Personalised recommendations