CAREER: Cost-Effective Application Deployments Spanning Multiple Cloud Services

Regents Of The University Of Michigan - Ann Arbor, Ann Arbor MI

Investigators

Abstract

The use of cloud computing services---services that host infrastructure on which third-parties can run applications and store data---has skyrocketed in the last few years. However, despite the growing number of cloud services, most applications are deployed today on a single cloud service. This status quo has several drawbacks---availability and performance offered by an application are limited by the cloud service on which the application is deployed, and cost borne by an application provider to meet performance goals is limited by the types and pricing of resources offered by that service. This research project will enable distributed applications to obtain better availability and performance at lower cost by planning and managing application deployments that span multiple cloud services. Recognizing the fact that different components of an application have different characteristics, this project will enable cost-effective multi-cloud deployments by matching the heterogeneity of an application's components with the diversity of resources offered by different cloud services. The research in this project involves three main tasks---1) the development of algorithms to choose cost-effectively among the myriad candidate configurations for deploying an application across cloud services, 2) the design and implementation of a distributed measurement and monitoring framework to dynamically reconfigure an application's deployment as the state of cloud services and of the Internet change over time, and 3) the development of tools and techniques that enable legacy applications implemented for deployment on a single cloud service to be easily ported to multi-cloud deployments. The research will involve significant systems-building and experimentation with the proposed techniques applied to deployments of popular applications on real cloud services. Broader Impact: In spite of the increasing popularity of cloud services, there remain several concerns about their use. The algorithms and software systems developed as part of this research may transform the ways in which application providers use cloud services, thus easing concerns with respect to availability and performance. The project also has a significant education component with the introduction of new graduate and undergraduate classes, and public talks to increase awareness about cloud services among small and non-profit businesses.