Abstract
Full system electricity intake from the wall socket is important for understanding and budgeting the power consumption of large scale data centers. Measuring full system power, however, requires extra instrumentation with external physical devices, which is not only cumbersome, but also expensive and time consuming. To tackle this problem, in this paper, we propose to model wall socket power from processor package power obtained from the running average power limit (RAPL) interface, which is available on the latest Intel processors. Our experimental results demonstrate a strong correlation between RAPL package power and wall socket power consumption. Based on the observations, we propose an empirical power model to predict the full system power. We verify the model using multiple synthetic benchmarks (Stress-ng, STREAM), high energy physics benchmark (ParFullCMS), and non-trivial application benchmarks (Parsec). Experimental results show that the prediction model achieves good accuracy, which is maximum 5.6 % error rate.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agostinelli S et al (2003) GEANT4: A simulation toolkit. Nucl Instrum Methods A506:250–303
Bienia C, Kumar S, Singh JP, Li K (2008) The parsec benchmark suite: characterization and architectural implications. In: Proceedings of the 17th international conference on parallel architectures and compilation techniques
Bircher W, John L (2012) Complete system power estimation using processor performance events. Comput IEEE Trans 61(4):563–577
Castano M, Catalan S, Mayo R, Quintana-Orti E (2015) Reducing the cost of power monitoring with DC wattmeters. Comput Sci Res Dev 30(2):107–114
David H, Gorbatov E, Hanebutte UR, Khanna R, Le C (2010) Rapl: memory power estimation and capping. In: Low-power electronics and design (ISLPED), 2010 ACM/IEEE international symposium on, pp 189–194
Economou D, Rivoire S, Kozyrakis C (2006) Full-system power analysis and modeling for server environments. In: Workshop on Modeling Benchmarking and Simulation (MOBS)
Hackenberg D, Ilsche T, Schone R, Molka D, Schmidt M, Nagel W (2013) Power measurement techniques on standard compute nodes: a quantitative comparison. In: Performance analysis of systems and software (ISPASS), 2013 IEEE international symposium on, pp 194–204
Hackenberg D, Schöne R, Ilsche T, Molka D, Schuchart J, Geyer R (2015) An energy efficiency feature survey of the intel haswell processor. In: 2015 IEEE international parallel and distributed processing symposium workshop, IPDPS 2015, Hyderabad, India, May 25–29, 2015, pp 896–904
Hähnel M, Döbel B, Völp M, Härtig H (2012) Measuring energy consumption for short code paths using RAPL. ACM SIGMETRICS Perform Eval Rev 40(3):13–17
Huang S, Lang M, Pakin S, Fu S (2015) Measurement and characterization of haswell power and energy consumption. In: Proceedings of the 3rd international workshop on energy efficient supercomputing, E2SC ’15. ACM, New York, pp 7:1–7:10
Intel: Intel 64 and IA-32 Architectures Software Developer’s Manual Volume 3 (3A, 3B & 3C): System Programming Guide (2014). http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64- ia-32-architectures-software-developer-system-programming-manual-325384.pdf. Accessed 6 Aug 2015
Lightweight performance tools, Likwid. https://code.google.com/p/likwid/. Accessed 6 Aug 2015
McCalpin JD. STREAM: sustainable memory bandwidth in high performance computers. http://www.cs.virginia.edu/stream/. Accessed 21 Sep 2015
McCullough JC, Agarwal Y, Chandrashekar J, Kuppuswamy S, Snoeren AC, Gupta RK (2011) Evaluating the effectiveness of model-based power characterization. Proceedings of the 2011 USENIX conference on USENIX annual technical conference., USENIXATC’11USENIX Association, Berkeley, pp 12–12
Orgerie AC, Assuncao MDd, Lefevre L (2014) A survey on techniques for improving the energy efficiency of large-scale distributed systems. ACM Comput Surv 46(4) 47:1–47:31
Piga L, Bergamaschi R, Rigo S (2014) Empirical and analytical approaches for web server power modeling. Clust Comput 17(4):1279–1293
Plugwise. https://www.plugwise.com/. Accessed 6 Aug 2015
Qureshi A, Weber R, Balakrishnan H, Guttag J, Maggs B (2009) Cutting the electric bill for internet-scale systems. SIGCOMM Comput Commun Rev 39(4):123–134
Stress-ng. http://kernel.ubuntu.com/~cking/stress-ng/. Accessed 21 Sep 2015
Subramaniam B, Feng W (2013) Towards energy-proportional computing for enterprise-class server workloads. In: Proceedings of the 4th ACM/SPEC international conference on performance engineering., ICPE ’13ACM, New York, pp 15–26
Venkatesh A, Kandalla K, Panda D (2013) Evaluation of energy characteristics of MPI communication primitives with RAPL. In: Parallel and distributed processing symposium workshops PhD Forum (IPDPSW), 2013 IEEE 27th International, pp 938–945
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Khan, K.N., Ou, Z., Hirki, M. et al. How much power does your server consume? Estimating wall socket power using RAPL measurements. Comput Sci Res Dev 31, 207–214 (2016). https://doi.org/10.1007/s00450-016-0325-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00450-016-0325-4