Efficient Data Allocation for a Cluster of Workstations

The development and use of cluster based computing is increasingly becoming an effective approach for solving high performance computing problems. The trend of moving away from specialized traditional supercomputing platforms such as Cray / SGI T3E to cheap and general-purpose systems consisting of loosely coupled components is expected to continue. In [1], we presented an analytical model for evaluating the performance of such platforms. The model covers the effect of storage limitations, interconnection networks and the impact of data partitioning and allocation. The model can also detect the bottlenecks in the system, which can lead to a more effective utilization of the available resources. In this paper, we use our model to find the best data allocation method that maximizes the throughput of the system based on the cluster architecture. Key words: Cluster Computing; Queueing Analysis; Performance Modeling; Distributed Computing.

• Type: Conference
• Year: 2003
• Where: ISCAPDCS
• Authors: Ahmed M. Mohamed, Reda A. Ammar, Lester Lipsky
• Keywords: Cluster Based Computing, ISCAPDCS 2003, ISCAPDCS 2007, Model, Performance Computing Problems