Two stage optimization of job scheduling and assignment in heterogeneous compute farms

Distributed networked computing in a compute farm environment has attracted great attention in recent years. Specialized management system for a compute farm enables heterogeneous distributed resources to be shared in a seamless way between various competing jobs. A key functionality of such system is a scheduler that controls the assignment of jobs to resources. This paper outlines a range of scheduling constrains as well as a list of required scheduling features for a state-of-the-art management system in distributed farm computing. It also presents a novel two stage static-dynamic scheduling algorithm to deal with the scheduling complexity.