Scheduling Distributed Resources in Heterogeneous Private Clouds

TL;DR

This paper investigates resource scheduling in heterogeneous private clouds, extending fair scheduling algorithms to multiple resources and servers, and compares their efficiencies through illustrative examples.

Contribution

It extends max-min and proportional fair scheduling to complex multi-resource, multi-server private cloud environments, analyzing their efficiency and fairness.

Findings

Server-specific fairness criteria are more efficient.

Residual resource-based fairness improves efficiency.

Max-min fair allocations can be effectively computed by progressive filling.

Abstract

We first consider the static problem of allocating resources to ( i.e. , scheduling) multiple distributed application framework s, possibly with different priorities and server preferences , in a private cloud with heterogeneous servers. Several fai r scheduling mechanisms have been proposed for this purpose. We extend pr ior results on max-min and proportional fair scheduling to t his constrained multiresource and multiserver case for generi c fair scheduling criteria. The task efficiencies (a metric r elated to proportional fairness) of max-min fair allocations found b y progressive filling are compared by illustrative examples . They show that "server specific" fairness criteria and those that are b ased on residual (unreserved) resources are more efficient.