On Managing Heterogeneity in Production Cloud Computing Environments

Abstract

The past few years have witnessed the rise of cloud computing, a paradigm that harnesses massive resource capacity of data centers to support Internet services and applications in a scalable, flexible, reliable and cost-efficient manner. However, despite its success, recent literature has shown that effectively managing resources in production cloud environments remains to be a difficult challenge. A key reason behind this difficulty is that both resources and workloads found in production environments are heterogeneous. In particular, large cloud data centers often consist of machines with heterogeneous resource capacities and performance characteristics. At the same time, real cloud workloads show significant diversity in terms of priority, resource requirements, demand characteristics and performance objectives. Consequently, finding an effective resource management solution that leverages resource heterogeneity to support diverse application performance objectives becomes a difficult problem.

The focus of this talk will be on understanding the research challenges introduced by resource and workload heterogeneity in production cloud environments. We will first provide a characterization of workload and resource heterogeneities found in production data centers, and highlight the key challenges introduced by them. We will then describe our recent work towards addressing some of these challenges. Finally, we will outline several key directions for future research.