Provisioning Spot Market Cloud Resources to Create Cost-effective Virtual Clusters

TL;DR

This paper introduces a resource allocation policy for running deadline-constrained, compute-intensive jobs on spot instances, leveraging price and performance variations to reduce costs by up to 60%.

Contribution

It presents a novel policy that uses job runtime estimations to optimize the selection and timing of spot instances for cost-effective, deadline-aware job execution.

Findings

Cost savings of up to 60% using spot instances.

Effective job scheduling based on runtime estimations.

Validation with real AWS price traces and workload data.

Abstract

Infrastructure-as-a-Service providers are offering their unused resources in the form of variable-priced virtual machines (VMs), known as "spot instances", at prices significantly lower than their standard fixed-priced resources. To lease spot instances, users specify a maximum price they are willing to pay per hour and VMs will run only when the current price is lower than the user's bid. This paper proposes a resource allocation policy that addresses the problem of running deadline-constrained compute-intensive jobs on a pool of composed solely of spot instances, while exploiting variations in price and performance to run applications in a fast and economical way. Our policy relies on job runtime estimations to decide what are the best types of VMs to run each job and when jobs should run. Several estimation methods are evaluated and compared, using trace-based simulations, which take real price variation traces obtained from Amazon Web Services as input, as well as an application trace from the Parallel Workload Archive. Results demonstrate the effectiveness of running computational jobs on spot instances, at a fraction (up to 60% lower) of the price that would normally cost on fixed priced resources.