Heterogeneous Resource Allocation in Shared Datacenters

Allocating heterogeneous resource types among multiple clients in a shared datacenter is challenging. Traditional resource allocation models have largely been designed to provide QoS for a single resource type, and result in poor utilization and fairness when applied to multiple coupled resources. In this paper we present a new formal model for allocating multiple resource types among clients to provide both fairness and high system utilization. The model and algorithms are validated with empirical results.