A Cost-Benefit Approach to Resource Allocation in Scalable Metacomputers
The Center for Networking and Distributed Systems
The Johns Hopkins University
Notes:
Summary of Thesis on Resource Allocation in Metacomputers
A metacomputer is a set of machines networked together for increased computational performance. To build an efficient metacomputer, one must assign jobs to the various networked machines intelligently. With a good strategy for job assignment, the metacomputer completes all of its work swiftly. With a poor job assignment strategy, the metacomputer does little better than its individual machines.
Resource heterogeneity makes job assignment more complex. Placing a job on one machine might risk depleting its small memory. Another machine might have more free memory but a heavily burdened CPU. Bin packing on memory protects the system against thrashing. Load balancing protects the system against high CPU loads. Combining the two approaches, however, gives a heuristic algorithm with no clear theoretical merit.
The Cost-Benefit Framework, developed in this work, offers a new approach to job assignment on metacomputers. It smoothly handles heterogeneous resources by converting them into a unitless cost. This work extends that research. It makes practical implementation of this approach both a possibility and an actuality.