High occupancy resource allocation for grid and cloud systems

Economic models have long been advocated as a means of efficient resource allocation, however they are often criticized due to a lack of performance and high overheads. The widespread adoption of utility computing models as seen in commercial Cloud providers has re-motivated the need for economic allocation mechanisms. The aim of this work is to address some of the performance limitations of existing economic allocation models, by reducing the failure/reallocation rate, increasing occupancy and thereby increasing the obtainable utilization of the system. This paper is a study of high performance resource utilization strategies that can be employed in Grid and Cloud systems. In particular we have implemented and quantified the results for strategies including overbooking, advanced reservation, justin-time bidding and using substitute providers for service delivery. These strategies are analyzed in a meta-scheduling context using synthetic workloads derived from a production Grid trace to quantify the performance benefits obtained