Affordable Access

Access to the full text

How much power does your server consume? Estimating wall socket power using RAPL measurements

Authors
  • Khan, Kashif Nizam1, 2
  • Ou, Zhonghong3
  • Hirki, Mikael1, 2
  • Nurminen, Jukka K.2, 4
  • Niemi, Tapio2
  • 1 Aalto University, Department of Computer Science, Espoo, Finland , Espoo (Finland)
  • 2 Helsinki Institute of Physics, Helsinki, Finland , Helsinki (Finland)
  • 3 Beijing University of Posts and Telecommunications, Beijing, China , Beijing (China)
  • 4 VTT Technical Research Centre of Finland, Helsinki, Finland , Helsinki (Finland)
Type
Published Article
Journal
Computer Science - Research and Development
Publisher
Springer Berlin Heidelberg
Publication Date
Aug 08, 2016
Volume
31
Issue
4
Pages
207–214
Identifiers
DOI: 10.1007/s00450-016-0325-4
Source
Springer Nature
Keywords
License
Yellow

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.

Report this publication

Statistics

Seen <100 times