Study of Virtualization Energy-efficiency in High-energy Physics Computing

Jukka Kommeri, Marko Niinimaki, Tapio Niemi

Abstract

Modern multi-core servers are able to run growing amount of physics analysis tasks. As the count of CPU cores keep growing, a need for sharing a single server among several analysis tasks becomes more difficult. The need for varying analysis environments increase the complexity of an computing node software collection. In this paper we study how virtual machines should be deployed and loaded when running high-energy physics analysis applications to achieve high throughput and minimal energy consumption. We build a test environment using a realistic data analysis software and performed a large set of test runs. We used both 4 core single processor and two processor 12 core servers to evaluate bottlenecks of physics analysis software. Our results indicate that both throughput and energy efficiency strongly depend on how many virtual machines (VM) are run in a computing node and how many analysis applications are processed in parallel in a VM: It is more efficient to have less VMs with more parallel applications than one application in each VM. Thus, we suggest that jobs of the same user running in the same environment should be combined to the same VMs instead of running each job in a different VM.

References

  1. Anderson, E., Bai, Z., Dongarra, J., Greenbaum, A., McKenney, A., Du Croz, J., Hammerling, S., Demmel, J., Bischof, C., and Sorensen, D. (1990). Lapack: a portable linear algebra library for high-performance computers. In Proceedings of the 1990 ACM/IEEE conference on Supercomputing, Supercomputing 7890, pages 2-11, Los Alamitos, CA, USA. IEEE Computer Society Press.
  2. Antcheva, I. and et al. (2009). Root a c++ framework for petabyte data storage, statistical analysis and visualization. Computer Physics Communications, 180(12):2499 - 2512.
  3. Buyya, R., Yeo, C. S., and Venugopal, S. (2008). Marketoriented cloud computing: Vision, hype, and reality for delivering it services as computing utilities. In High Performance Computing and Communications, 2008. HPCC 7808. 10th IEEE International Conference on, pages 5 -13.
  4. Chaudhary, V., Cha, M., Walters, J., Guercio, S., and Gallo, S. (2008). A comparison of virtualization technologies for hpc. In Advanced Information Networking and Applications, 2008. AINA 2008. 22nd International Conference on, pages 861 -868.
  5. Fabozzi, F., Jones, C., Hegner, B., and Lista, L. (2008). Physics analysis tools for the cms experiment at lhc. Nuclear Science, IEEE Transactions on, 55:3539- 3543.
  6. Fenn, M., Murphy, M. A., and Goasguen, S. (2009). A study of a kvm-based cluster for grid computing. In Proceedings of the 47th Annual Southeast Regional Conference, ACM-SE 47, pages 34:1-34:6, New York, NY, USA. ACM.
  7. Kivity, A., Lublin, U., and Liguori, A. (2007). kvm : the linux virtual machine monitor. In Proceedings of the Linux Symposium, pages 225-230.
  8. Kommeri, J., Niemi, T., and Helin, O. (2012). Energy efficiency of server virtualization. In Proc. Energy 2012.
  9. Niemi, T., Kommeri, J., and Ari-Pekka, H. (2009a). Energyefficient scheduling of grid computing clusters. In Proceedings of the 17th Annual International Conference on Advanced Computing and Communications (ADCOM 2009), Bengaluru, India.
  10. Niemi, T., Kommeri, J., Happonen, K., Klem, J., and Hameri, A.-P. (2009b). Improving energy-efficiency of grid computing clusters. In Advances in Grid and Pervasive Computing, 4th International Conference, GPC 2009, Geneva, Switzerland, pages 110-118.
  11. Nussbaum, L., Anhalt, F., Mornard, O., and Gelas, J.-P. (2009). Linux-based virtualization for hpc clusters. Network, pages 221-234.
  12. Padala, P., Zhu, X., Wang, Z., Singhal, S., and Shin, K., G. (2007). Performance evaluation of virtualization technologies for server consolidation. Work, (HPL2007-59):15.
  13. Regola, N. and Ducom, J.-C. (2010). Recommendations for virtualization technologies in high performance computing. In Cloud Computing Technology and Science (CloudCom), 2010 IEEE Second International Conference on, pages 409-416.
  14. Sch├Ąppi, B., Bellosa, F., Przywara, B., Bogner, T., Weeren, S., and Anglade, A. (2007). Energy efficient servers in europe. Technical Report October, Austrian Energy Agency.
  15. STAR, E. (2007). Report to congress on server and data center energy efficiency. Technical report, U.S. Environmental Protection Agency ENERGY STAR Program.
  16. Verma, A., Ahuja, P., and Neogi, A. (2008). Power-aware dynamic placement of hpc applications. In Proceedings of the 22nd annual international conference on Supercomputing, ICS 7808, pages 175-184, New York, NY, USA. ACM.
  17. Xu, M., Hu, Z., Long, W., and Liu, W. (2004). Service virtualization: Infrastructure and applications. In The grid: blueprint for a new computing infrastructure, chapter 14. Wiley.
Download


Paper Citation


in Harvard Style

Niemi T., Niinimaki M. and Kommeri J. (2012). Study of Virtualization Energy-efficiency in High-energy Physics Computing . In Proceedings of the Sixth International Symposium on e-Health Services and Technologies and the Third International Conference on Green IT Solutions - Volume 1: ICGREEN, ISBN 978-989-8565-27-3, pages 77-82. DOI: 10.5220/0004474800770082


in Bibtex Style

@conference{icgreen12,
author={Tapio Niemi and Marko Niinimaki and Jukka Kommeri},
title={Study of Virtualization Energy-efficiency in High-energy Physics Computing},
booktitle={Proceedings of the Sixth International Symposium on e-Health Services and Technologies and the Third International Conference on Green IT Solutions - Volume 1: ICGREEN,},
year={2012},
pages={77-82},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004474800770082},
isbn={978-989-8565-27-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Sixth International Symposium on e-Health Services and Technologies and the Third International Conference on Green IT Solutions - Volume 1: ICGREEN,
TI - Study of Virtualization Energy-efficiency in High-energy Physics Computing
SN - 978-989-8565-27-3
AU - Niemi T.
AU - Niinimaki M.
AU - Kommeri J.
PY - 2012
SP - 77
EP - 82
DO - 10.5220/0004474800770082