Energy Efficiency in Web Server Clusters Aiming for Large-Scale Application: A Hierarchical Architecture
Abstract
The growth in the demand for web services requires a larger processing capacity and, consequently, an increase in the energy consumption to support this infrastructure. The reduction of this consumption involves technical challenges and environmental aspects, because in the energy generation tons of carbon are thrown in the atmosphere. As additional restriction, the quality of service, offered to the customers, should be maintained above an acceptable minimum level. This work is directed to the energy saving in web server clusters, in the direction of the “green” data centers’ construction. Our solution involves optimization techniques, the Dynamic Voltage Scaling technology (DVS), and the application of an hierarchical architecture on the support of the decision making process for large scale clusters.
References
E.N. (Mootaz) Elnozahy, M. Kistler, and R. Rajamony (Fevereiro, 2002). Energy-efficient server clusters. Workshop on Power-Aware Computing Systems.
EPA (Agosto, 2007). Report to congress on server and data center energy efficiency. Technical report, Environmental Protection Agency, EUA.
GLPK (2010). Gnu linear programming kit, free software foudation, gnu. [link] acessado em 12/11/2009.
HTTPERF (2010). httperf documentation. [link].
J. Huang, H. Jin, X. Xie, and Q. Zhang (Agosto, 2007). Using NARX neural network based load prediction to improve scheduling decision in grid environments. 3rd International Conference on Natural Computation, Wuhan, China, pages 718–724.
L.Bertini, J.C.B. Leite, and D. Mossé (Julho, 2007). Statistical QoS guarantee and energy-efficiency in web clusters. 19th Euromicro Conference on Real-Time Systems, Pisa, Itália, pages 83–92.
Linux (2010). Linux kernel cpufreq subsystem. [link].
L.S. Sousa, J.C.B. Leite, and J.C.S. Souza (2008). Aplicação de redes neurais na construção de servidores web verdes. In XXXIV Conferência Latinoamericana de Informática, Santa Fe, Argentina.
M. Elnozahy, M. Kistler, and R. Rajamony (Março, 2003). Energy conservation policies for web servers. 4th USENIX Symposium on Internet Technologies and Systems, Seattle, WA, EUA.
M.R. Garey and D.S. Johnson (1979). Computers and intractability - a guide to theory of np-completeness. In Freeman, San Francisco.
P. Pillai and K. G. Shin (Outubro, 2001). Real-time dynamic voltage scaling for low-power embedded operating systems. 18th Symposium on Operating Systems Principles, Banff, Alberta, Canadá, pages 89–102.
Rountree, B., Lowenthal, D. K., Funk, S., Freeh, V. W., de Supinski, B. R., and Schulz, M. (2007). Bounding energy consumption in large-scale mpi programs. In SC ’07: Proceedings of the 2007 ACM/IEEE conference on Supercomputing, pages 1–9, New York, NY, USA. ACM.
Rusu, C., Ferreira, A., Scordino, C., and Watson, A. (2006). Energy-efficient real-time heterogeneous server clusters. In RTAS ’06: Proceedings of the 12th IEEE Real-Time and Embedded Technology and Applications Symposium, pages 418–428, Washington, DC, USA. IEEE Computer Society.
T. Heath, B. Diniz, E.V. Carrera, W. Meira Jr., and R. Bianchini (Junho, 2005). Energy conservation in heterogeneous server clusters. 10th ACM Symposium on Principles and Practice of Parallel Programming, Chicago, IL, EUA, pages 186–195.
