Pp. 57-71 of the Proceedings

Next: Introduction

Model-Based Resource Provisioning in a Web Service Utility

Ron Doyle*, Jeff Chase, Omer Asad, Wei Jin and Amin Vahdat

IBM, RTP
Research Triangle Park *
rdoyle@us.ibm.com

Department of Computer Science
Duke University
{chase,jin,vahdat}@cs.duke.edu

Internet service utilities host multiple server applications on a shared server cluster. A key challenge for these systems is to provision shared resources on demand to meet service quality targets at least cost. This paper presents a new approach to utility resource management focusing on coordinated provisioning of memory and storage resources. Our approach is model-based: it incorporates internal models of service behavior to predict the value of candidate resource allotments under changing load. The model-based approach enables the system to achieve important resource management goals, including differentiated service quality, performance isolation, storage-aware caching, and proactive allocation of surplus resources to meet performance goals. Experimental results with a prototype demonstrate model-based dynamic provisioning under Web workloads with static content.

• Introduction
• Overview
• Web Service Models
  • Server Memory
  • Storage I/O Rate
  • Storage Response Time
  • Service Response Time
  • Discussion
• A Model-Based Allocator
  • Generating Initial Candidates
  • Local Constraint or Surplus
  • Group Constraint or Surplus
  • Putting It All Together
• Prototype and Results
• Related Work
• Conclusion
  • Acknowledgments
• Bibliography
• About this document ...