Parallel Job Scheduling Policy for Workstation Cluster Environments

As workstation clusters (WC) become more commonly usedfor parallel jobs, there is a growing awareness for the needof job scheduling policies. There have been a fair number ofstudies on how to schedule parallel applications on parallelsystems and a good survey in the area can be found in [5]. Ithas been shown that the best solution to the processorallocation problem in a distributed multiprocessorenvironment is an adaptive scheduling policy that can adjustload distribution based on runtime scheduling algorithms[2,3]. The main idea of adaptive space-sharing policies isthat the number of processors assigned to a job is acompromise between the user’s request and what the systemcan provide. Note that there are differences in thearchitecture of the multiprocessor systems and WC-baseddistributed systems. For example, the processors in themultiprocessors systems are usually homogenous whereasthose of WC are usually heterogeneous. This change ofarchitectural environment requires important differences inthe decisions made by the system scheduling policy. Mostof adaptive scheduling policies for WC-based systemsprovide only rudimentary facilities for partitioning, i.e.,space sharing, the processors among parallel jobs. Inaddition, parallel applications targeted to WC are typicallyresource-intensive, i.e. they require more resources than areavailable at a single site. However, existing adaptivescheduling policies cannot accommodate this requirement.This is because they may assign 1 processor to a job in theextreme cases [2] or lead to a