On the Consolidation of Data-Centers with Performance Constraints
We address the data-center consolidation problem: given a working data-center, the goal of the problem is to choose which software applications must be deployed on which servers in order to minimize the number of servers to use while avoiding the overloading of system resources and satisfying availability constraints. This in order to tradeoff between quality of service issues and data-center costs. The problem is approached through a robust model of the data-center which exploits queueing networks theory. Then, we propose two mixed integer linear programming formulations of the problem able to capture novel aspects such as workload partitioning (load-balancing) and availability issues. A simple heuristic is proposed to compute solutions in a short time. Experimental results illustrate the impact of our approach with respect to a real-world consolidation project.
KeywordsServer Utilization Mixed Integer Linear Programming Performance Constraint Service Demand Deployment Scheme
Unable to display preview. Download preview PDF.
- 1.Anselmi, J., Amaldi, E., Cremonesi, P.: Service consolidation with end-to-end response time constraints. In: Software Engineering and Advanced Applications, 2008. SEAA 2008. 34th Euromicro Conference, September 3-5, pp. 345–352 (2008)Google Scholar
- 3.Bichler, M., Setzer, T., Speitkamp, B.: Capacity planning for virtualized servers. In: Proceedings of the Workshop on Information Technologies and Systems, Milwaukee, Wisconsin, USA (2006)Google Scholar
- 4.Cardellini, V., Casalicchio, E., Grassi, V., Mirandola, R.: A framework for optimal service selection in broker-based architectures with multiple qos classes. In: SCW 2006: Proceedings of the IEEE Services Computing Workshops, pp. 105–112. IEEE Computer Society, Washington (2006)CrossRefGoogle Scholar
- 5.Fourer, R., Gay, D.M., Kernighan, B.W.: AMPL: A Modeling Language for Mathematical Programming. Duxbury Press (November 2002)Google Scholar
- 6.Lazowska, E.D., Zahorjan, J., Graham, G.S., Sevcik, K.C.: Quantitative system performance: computer system analysis using queueing network models. Prentice-Hall, Inc., Upper Saddle River (1984)Google Scholar
- 8.Martello, S., Pisinger, D., Toth, P.: New trends in exact algorithms for the 0-1 knapsack problem (1997)Google Scholar
- 9.Menasce, D.A.: Virtualization: Concepts, applications, and performance modeling. The volgenau school of information technology and engineering (2005)Google Scholar
- 10.Menasce, D.A., Almeida, V.A.F., Dowdy, L.W.: Performance by Design: Computer Capacity Planning by Example: Computer Capacity Planning. Prentice Hall International, Englewood CliffsGoogle Scholar
- 11.Menasce, D.A., Dowdy, L.W., Almeida, V.A.F.: Performance by Design: Computer Capacity Planning By Example. Prentice Hall PTR, Upper Saddle River (2004)Google Scholar