Opportunistic Admission and Scheduling of Remote Processes in Large Scale Distributed Systems

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 260)


The large scale loosely-coupled distributed systems such as, grid and cloud computing systems employ opportunistic execution mechanism of remote processes in order to utilize computing resources of idle nodes. The opportunistic admission and scheduling of remote processes at a node need to balance the enhanced resource utilization and the performance of local processes at the node. This paper proposes the design and implementation of a novel Admission Control and Scheduling (ACS) algorithm for opportunistic execution of remote processes in a distributed system based on online estimation method. The experimental results illustrate that the algorithm can schedule the CPU-bound and IO-bound remote processes without degrading overall performance of a node. The CPU-utilization and memory-utilization of a node are enhanced by 26.65 and 24.5 % respectively on the average without degrading the performance of local processes executing at the node.


Distributed systems Opportunistic scheduling Online estimation 


  1. 1.
    Lin CC, Shih CW (2008) An efficient scheduling algorithm for grid computing with periodical resource reallocation. In: 8th IEEE International Conference on Computer and Information Technology, IEEEGoogle Scholar
  2. 2.
    Tang X, Li K, Qiu M, Sha EHM (2011) A hierarchical reliability-driven scheduling algorithm in grid systems. J Parallel Distribut Comput 72(4):525–535Google Scholar
  3. 3.
    Shah SNM, Mahmood AKB, Oxley A (2010) Analysis and evaluation of grid scheduling algorithms using real workload traces. In: ACM MEDES’10, ACMGoogle Scholar
  4. 4.
    Wieczoreka M et al (2009) Towards a general model of the multi-criteria workflow scheduling on the grid. Future Generation Computer Systems Journal, Vol. 25, No. 3, Elsevier (2009)Google Scholar
  5. 5.
    Fan H, Sun X (2010) A multi-state reliability evaluation model for P2P networks. Reliab Eng Syst Saf J 95(4): 402–411Google Scholar
  6. 6.
    Fernandez-Baca D (1989) Allocating modules to processors in a distributed system. IEEE Transact Softw Eng 15(11): 1427–1436Google Scholar
  7. 7.
    Litzkow MJ, Livny M, Mutka MW (1988) Condor: a hunter of idle workstations. In: 8th IEEE International Conference on Distributed Computing Systems, IEEEGoogle Scholar
  8. 8.
    Ghare GD, Leutenegger ST (2000) Improving small job response time for opportunistic scheduling. In: 8th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, IEEEGoogle Scholar
  9. 9.
    Mutka M, Livny M (1991) The available capacity of a privately owned workstation environment. Perform Eval J 12(4), 269–284Google Scholar
  10. 10.
    Tchernykh A et al (2009) Idle regulation in non-clairvoyant scheduling of parallel jobs. Discrete Appl Math J 157(2): 364–376Google Scholar
  11. 11.
    Livny M, Basney J, Raman R, Tannenbaum T (1997) Mechanisms for high throughput computing. SPEEDUP J 11(1)Google Scholar
  12. 12.
    Zhihong X, Xiangdan H, Jizhou S (2003) Ant algorithm-based task scheduling in grid computing. In: CCECE’03, IEEEGoogle Scholar
  13. 13.
    Kiran N, Maheswaran V, Shyam M, Narayanasamy P (2007) A novel task replica based resource scheduling algorithm in grid computing. In: The 14th HiPC ConferenceGoogle Scholar
  14. 14.
    Li H (2009) Workload dynamics on clusters and grids. J Supercomputing 47(1): 1–20Google Scholar
  15. 15.
    Abdulal W, Ramachandran S (2011) Reliability-aware genetic scheduling algorithm in grid environment. In: International Conference on Communication Systems and Network Technologies, IEEEGoogle Scholar
  16. 16.
    Abawajy JH (2002) Job scheduling policy for high throughput computing environments. In: 9th International Conference on Parallel and Distributed Systems, IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  1. 1.Department of InformaticsGyeongsang National UniversityJinjuSouth Korea

Personalised recommendations