An opportunity cost approach for job assignment in a scalable computing cluster

A new method is presented for job assignment to and reassignment between ma chines in a computing cluster. Our method is based on a theoretical framewo rk that has been experimentally tested and shown to be useful in practice. This "opportunity cost" method converts the usage of several heterogeneous resources in a machine to a single homogeneous "cost." Assignment and reass ignment are then performed based on that cost. This is in contrast to tradi tional, ad hoc methods for job assignment and reassignment. These treated e ach resource as an independent entity with its own constraints, as there wa s no clean way to balance one resource against another. Our method has been tested by simulations, as well as real executions, and was found to perfor m well.