Analyzing the power consumption behavior of a large scale data center

Research output: Contribution to journalArticleScientificpeer-review

Researchers

  • Kashif Nizam Khan
  • Sanja Scepanovic
  • Tapio Niemi
  • Jukka K. Nurminen
  • Sebastian von Alfthan
  • Olli Pekka Lehto

Research units

  • Helsinki Institute of Physics
  • CSC - IT Center for Science Ltd.
  • Aalto University

Abstract

The aim of this paper is to illustrate the use of application and system level logs to better understand scientific data center behavior and energy-spending. Analyzing a data center log of 900 nodes (Sandy Bridge and Haswell), we study node power consumption and describe approaches to estimate and forecast it. Our results include methods to cluster nodes based on different vmstat and RAPL measurements as well as Gaussian and GAM models for estimating the plug power consumption. We also analyze failed jobs and find that non-successfully terminated jobs consume around 40% of computing time. While the actual numbers are likely to vary in different data centers at different times, the purpose of the paper is to share ideas of what can be found by statistical and machine learning analysis of large amount of log data.

Details

Original languageEnglish
Pages (from-to)61–70
Number of pages10
JournalComputer Science - Research and Development
Volume34
Issue number1
Early online date29 May 2018
Publication statusPublished - Mar 2019
MoE publication typeA1 Journal article-refereed

    Research areas

  • Data center log analysis, Energy efficiency, Energy modeling, RAPL

ID: 29744331