Enterprises increasingly run their analytical workloads in cloud environments, where they must provision both compute and storage resources before any query processing can begin. Infrastructure provisioning, however, can be difficult for these workloads because they are often unpredictable and ad-hoc in nature. To avoid underprovisioning and consequent performance disruption, cloud customers overprovision their resources conservatively, giving up on cost efficiency. Recently, cloud providers introduced means to allocate and bill fine-granular units of resources with function as a service (FaaS) platforms and shared cloud storage. We are building an elastic query processor called Skyrise that embraces this so called serverless cloud infrastructure for improved cost characteristics. In the context of the Skyrise project, we offer Master's thesis topics in the following broad areas:
- Query optimization
- Query execution
Contact: Thomas Bodner