Approach for Processor to Dispatcher Load Balancing in Distributed Networks

##plugins.themes.academic_pro.article.main##

Kuldeep Sharma
Deepak Garg

Abstract

Load balancing is extensively used in distributed network applications to decrease the response times. In this paper, the focus is on backend load balancing (processor-to-dispatcher). Many algorithms are devised for front end load balancing e.g. JSQ, SQ(d) and JIQ. Join-Idle-Queue(JIQ) goes well in a distributed environment like cloud computing. In JIQ approach, at the backend, a processor joins the queue on either random or sampled basis. In both the cases, I-Queue of any dispatcher might remain empty resulting in degrading the performance. After finishing the job, the processor should join the dispatcher whose I-Queue is empty. To achieve this, we have used a dequeue to track the dispatcher with empty I-Queue. As the processor finishes the current job and reaches the idle state, it should refer the dequeue and join the dispatcher whose I-Queue is empty.

##plugins.themes.academic_pro.article.details##

How to Cite
Kuldeep Sharma, & Deepak Garg. (2016). Approach for Processor to Dispatcher Load Balancing in Distributed Networks. International Journal of Next-Generation Computing, 7(1), 69–77. https://doi.org/10.47164/ijngc.v7i1.105

References

  1. Applewhite, H. L., Garg, R., Jensen, E. D., Northcutt, J. D., and Sha, L. 1982. Decentralized resource management in distributed computer systems. Technical report, DTIC Document.
  2. Bramson, M., Lu, Y., and Prabhakar, B. 2010. Randomized load balancing with general service time distributions. ACM SIGMETRICS Performance Evaluation Review 38, 275–286.
  3. Chou, T. C. and Abraham, J. A. 1982. Load balancing in distributed systems. Software Engineering, IEEE Transactions on 4, 401–412.
  4. Gupta, V., Balter, M. H., Sigman, K., and Whitt, W. 2007. Analysis of join-the-shortest-queue routing for web server farms. Performance Evaluation 64, 9, 1062–1081.
  5. Lu, Y., Xie, Q., Kliot, G., Geller, A., Larus, J. R., and Greenberg, A. 2011. Join-idle-queue: A novel load balancing algorithm for dynamically scalable web services. Performance Evaluation 68, 11, 1056–1071.
  6. Squillante, M. S. and Nelson, R. D. 1991. Analysis of task migration in shared-memory multiprocessor scheduling. ACM 19.
  7. Vvedenskaya, N. D., Dobrushin, R. L., and Karpelevich, F. I. 1996. Queueing system with selection of the shortest of two queues: An asymptotic approach. Problemy Peredachi Informatsii 32, 1, 20–34.
  8. Wang, Y.-T. and Morris, R. J. 1985. Load sharing in distributed systems. Computers, IEEE Transactions on 100, 3, 204–217.