Adaptive Divisible Load Scheduling Strategies for Workstation Clusters with Unknown Network Resources
Issue No. 10 - October (2005 vol. 16)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPDS.2005.117
Debasish Ghose , IEEE
Hyoung Joong Kim , IEEE
<p><b>Abstract</b>—Conventional divisible load scheduling algorithms attempt to achieve optimal partitioning of massive loads to be distributed among processors in a distributed computing system in the presence of communication delays in the network. However, these algorithms depend strongly upon the assumption of prior knowledge of network parameters and cannot handle variations or lack of information about these parameters. In this paper, we present an adaptive strategy that estimates network parameter values using a probing technique and uses them to obtain optimal load partitioning. Three algorithms, based on the same strategy, are presented in the paper, incorporating the ability to cope with unknown network parameters. Several illustrative numerical examples are given. Finally, we implement the adaptive algorithms on an actual network of processor nodes using MPI implementation and demonstrate the feasibility of the adaptive approach.</p>
Scheduling and task partitioning, divisible loads, distributed applications, workstations, multiprocessor systems.
D. Ghose, T. H. Kim and H. J. Kim, "Adaptive Divisible Load Scheduling Strategies for Workstation Clusters with Unknown Network Resources," in IEEE Transactions on Parallel & Distributed Systems, vol. 16, no. , pp. 897-907, 2005.