A New Duplication-Based Approach for Scheduling Tasks to a Heterogeneous Workstation Cluster

摘要

Triggered by the ever increasing advancements in processor and networking technology, a cluster of workstations and/or PCs connected by a high-speed network has become a viable and cost-effective platform for the execution of computation intensive parallel applications. However, realizing the goal of efficient cluster computing entails handling a number of resource management chores. In particular, the problem of scheduling tasks to a cluster is a relatively less explored topic. Specifically, there are two difficult research issues to be tackled in the scheduling problem for cluster computing: (1) how to reduce the communication overhead of executing a parallel application on a workstations cluster; (2) how to exploit the benefits of heterogeneity in a cluster of machines for a parallel application. In this paper, we propose a duplication based approach in scheduling tasks to a heterogeneous cluster of workstations. In duplication based scheduling, critical tasks are redundantly scheduled to more than one machines in order to reduce the number of inter-task communication operations. The start times of the succeeding tasks are also reduced. The task duplication process is guided given the system heterogeneity in that the critical tasks are scheduled or replicated in faster machines. Task duplication is indeed particularly effective for heterogeneous systems because the overall completion time of an application is usually determined by a set of tasks on the criticalpath which can be scheduled to execute efficiently on the faster machines. The algorithm has been implemented in our prototype program parallelization tool for generating MPI code executable on a cluster of Sun workstations. Our experiments using three numerical applications have indicated that heterogeneity of workstations cluster is indeed useful for optimizing the execution of parallel programs.