Advertisement

Single Source Divisible Load Scheduling on Distributed Heterogeneous Environments

  • Murugesan GanapathyEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 98)

Abstract

Computing loads which can be arbitrarily divided into number of fractional loads are called divisible loads and each fractional load can be processed independently in parallel. Scheduling divisible loads in distributed heterogeneous environment is a challenging task and most of the works carried out to schedule such type of loads are based on divisible load theory principle. It state that the entire processing element in the distributed environment must be participated in the scheduling process. This work focus on to find out the size of the fractional load that can be assigned to a particular processing elements so that the computation time of the entire workload could be minimum with respect to the availability of the processing element, its computation capacity and within the budget allotted to complete the process in a tree shaped network topology. In this work a mathematical model was developed with an objective of minimize the computing time to find out the portion of load to be assigned to the processing elements and that was solved with sample values and few assumptions. Experimental results proves that the proposed approach outperform compared with the divisible load theory approach.

Keywords

Divisible Load Scheduling Linear programming Resource allocation Task scheduling Single source scheduling 

References

  1. 1.
    Aali, S.N., Shahhosseini, H.S., Bagherzadeh, N.: Divisible load scheduling of image processing applications on the heterogeneous star network using a new genetic algorithm. In: Proceedings of the 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing, UK (2018)Google Scholar
  2. 2.
    Altilar, D., Paker, Y.: An optimal scheduling algorithm for parallel video processing. In: Proceeding of the IEEE International Conference on Multimedia Computing and Systems, pp. 245–248 (1998)Google Scholar
  3. 3.
    Altilar, D., Paker, Y.: Optimal scheduling algorithms for communication constrained parallel processing. In: Proceeding of the Euro-Par 2002, LNCS 2400, pp. 197–206. Springer (2002)Google Scholar
  4. 4.
    Blazewicz, J., Drogdowski, M., Markiwicz, M.: Divisible task scheduling – concept and verification. Parallel Comput. 25(1), 87–98 (1999)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Beaumont, O., Casanova, H., Legrand, A., Robert, Y., Yang, Y.: Scheduling divisible loads on star and tree networks: results and open problem. IEEE Trans. Parallel Distrib. Syst. 16(3), 207–218 (2005)CrossRefGoogle Scholar
  6. 6.
    Bharadwaj, V., Ghose, D., Mani, V., Robertazzi, T.: Scheduling Divisible Loads in Parallel and Distributed Systems. IEEE Computer Society Press, Washington, D.C. (1996)Google Scholar
  7. 7.
    Chan, S., Bharadwaj, V., Ghose, D.: Large matrix-vector products on distributed bus networks with communication delays using the divisible load paradigm: performance and simulation. Math. Comput. Simul. 58(1), 71–92 (2001)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Chin, T.T., Bharadwaj, V., Jia, J.: Handling large-size discrete wavelet transform on network-based computing systems: parallelization via divisible load paradigm. J. Parallel Distrib. Comput. 69(2), 143–152 (2009)CrossRefGoogle Scholar
  9. 9.
    Chen, C.Y.: Scheduling divisible loads on heterogeneous linear networks using pipelined communications. In: Proceedings of the Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, Japan (2017)Google Scholar
  10. 10.
    Drogdowski, M., Wolniewicz, P.: Optimum divisible load scheduling on heterogeneous stars with limited memory. Eur. J. Oper. Res. 172(2), 545–559 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Ghatpande, A., Nakazato, H., Beaumont, O., Watanabe, H.: SPORT: an algorithm for divisible load scheduling with result collection on heterogeneous systems. IEICE Trans. Commun. 91(8), 2571–2588 (2012)CrossRefGoogle Scholar
  12. 12.
    Lawenda, M.: Multi-instalment divisible loads scheduling. A Thesis, Poznan University, Poland (2006)Google Scholar
  13. 13.
    Lee, C., Hamdi, M.: Parallel image processing applications on a network of workstations. Parallel Comput. 21(1), 137–160 (1995)CrossRefGoogle Scholar
  14. 14.
    Legrand, A., Su, A., Vivien, F.: Minimizing the stretch when scheduling flows of biological requests. In: Proceedings of the SPAA 2006, pp. 103–112. ACM Press (2006)Google Scholar
  15. 15.
    Li, X., Bharadwaj, V., Ko, C.: Distributed image processing on a network of workstations. Int. J. Comput. Appl. 25(2), 1–10 (2003)Google Scholar
  16. 16.
    Robertazzi, T.G.: A product form solution for tree networks with divisible loads. Parallel Process. Lett. 21(1), 13–20 (2011)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Suresh, S., Mani, V., Omkar, S.N., Kim, H.J., Sundararajan, N.: A new load distribution strategy for linear network with communication delays. Math. Comput. Simul. 79(5), 1488–1501 (2009)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Suresh, S., Cui, R., Robertazzi, T.: Scheduling nonlinear divisible loads for a single level tree network. J. Supercomputing 61(3), 1068–1088 (2012)CrossRefGoogle Scholar
  19. 19.
    Suresh, S., Cui, R., Kim, H.J., Robertazzi, T., Kim, Y.: Scheduling second order computational loads in master-slave paradigm. IEEE Trans. Aerosp. Electron. Syst. 48(1), 780–793 (2012)CrossRefGoogle Scholar
  20. 20.
    Tong, W., Xiao, S., Li, H.: Fault-tolerant scheduling algorithm with re-allocation for divisible loads on homogeneous distributed system. IAENG Int. J. Comput. Sci. 45(3) (2018)Google Scholar
  21. 21.
    Wang, R., Krishnamurthy, A., Martin, R., Anderson, T., Culler, D.: Modelling communication pipeline latency. In: Proceeding of the Measurement and Modelling of Computer Systems, pp. 22–32 (1998)Google Scholar
  22. 22.
    Wu, F., Cao, Y., Robertazzi, T.: Optimal divisible load scheduling for resource-sharing network. Submitted to J. Distrib. Parallel Cluster Comput. (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringSt. Joseph’s College of EngineeringChennaiIndia

Personalised recommendations