Abstract
This paper deals with the static task-assignment problem in a cluster computing system as follows: Given a task composed of a number of interacting modules, assign the task modules to the processors in the system to minimize the communication cost while balancing the processors’ loads. Because these two optimization criteria conflict with each other, a compromise needs to be made between them according to the given task type. This paper proposes a new cost function to evaluate the static task assignments and a heuristic algorithm for solving the transformed problem explicitly describing the tradeoff between the two goals. The simulation results showed that this approach outperforms the existing representative approach for a range of tasks and processing systems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bokhari, S.H.: Dual process scheduling with dynamic reassignment. IEEE Trans. Softw. Eng. SE-5, 341–349 (1979)
Bokhari, S.H.: A shortest tree algorithm for optimal assignment across space and time in a distributed processor systems. IEEE Trans. Softw. Eng. SE-7, 583–589 (1981)
Bokhari, S.H.: Assignment Problems in Parallel and Distributed Computing. Kluwer Academic, Boston (1987)
Bokhari, S.H.: Partitioning problems in parallel, pipelined and distributed computing. IEEE Trans. Comput. C-37, 48–57 (1988)
Chan, S.Y., Ling, T.C., Aubanel, E.: The impacr of heterogeneous multi-core clusters on graph partitioning. Clust. Comput. 15(3), 281–302 (2012)
Chu, W.W., Leung, K.K.: Module replication and assignment for real-time distributed processing systems. Proc. IEEE 75, 547–562 (1987)
Eager, D.L., Lazowska, E.D., Zahorjan, J.: Adaptive load sharing in homogeneous distributed systems. IEEE Trans. Softw. Eng. SE-12, 662–675 (1986)
Efe, K.: Heuristic models of task assignment scheduling in distributed systems. IEEE Comput., 50–56 (1982)
Kernighan, B.W., Lin, S.: An efficient heuristic procedure for partitioning graphs. Bell Syst. Tech. J. 49, 291–307 (1970)
Kim, C.-H., Lee, J.-M.: A repeated mapping scheme of task modules with minimum communication cost in hypercube multicomputers. ETRI J. 20(4), 327–345 (1998)
Lee, C.-H., Shin, K.G.: Optimal task assignment in homogeneous networks. IEEE Trans. Parallel Distrib. Syst. 8(2), 119–129 (1997)
Lo, V.M.: Heuristic algorithms for task assignment in distributed systems. IEEE Trans. Comput. C-37, 1384–1397 (1988)
Moharil, S., Lee, S.-Y.: Load balancing on temporally heterogeneous cluster of workstations for parallel simulated annealing. Clust. Comput. 14, 295–310 (2011)
Pulidas, S., Towsley, D., Stankovic, J.A.: Embedding gradient estimators in load balancing algorithms. In: Proc. 8th Int. Conf. Distributed Comput. Syst., pp. 482–490 (1988)
Qin, J., Bauer, M.A.: Job co-allocation strategies for multiple high performance computing clusters. Clust. Comput. 12, 323–340 (2009)
Acknowledgements
This research was supported by the MSIP (Ministry of Science, ICT & Future Planning), Korea, under IT/SW Creative research program supervised by the NIPA (National IT Industry Promotion Agency)” (NIPA-2013-(H0502-0901-0009)).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kang, Y.H., Choi, W.J., Kim, B.C. et al. On tradeoff between the two compromise factors in assigning tasks on a cluster computing. Cluster Comput 17, 861–870 (2014). https://doi.org/10.1007/s10586-013-0301-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-013-0301-8