Skip to main navigation Skip to search Skip to main content

Energy and performance evaluation of lossless file data compression on server systems

  • Rachita Kothiyal
  • , Vasily Tarasov
  • , Priya Sehgal
  • , Erez Zadok
  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Scopus citations

Abstract

Data compression has been claimed to be an attractive solution to save energy consumption in high-end servers and data centers. However, there has not been a study to explore this. In this paper, we present a comprehensive evaluation of energy consumption for various f le compression techniques implemented in software. We apply various compression tools available on Linux to a variety of data f les, and we try them on server class and workstation class systems. We compare their energy and performance results against raw reads and writes. Our results reveal that software based data compression cannot be considered as a universal solution to reduce energy consumption. Various factors like the type of the data f le, the compression tool being used, the read-to-write ratio of the workload, and the hardware conf guration of the system impact the eff cacy of this technique. In some cases, however, we found compression to save substantial energy and improve performance.

Original languageEnglish
Title of host publicationProceedings of the Israeli Experimental Systems Conference, SYSTOR 2009
Pages4
Number of pages1
DOIs
StatePublished - 2009
EventSYSTOR 2009: The Israeli Experimental Systems Conference - Haifa, Israel
Duration: May 4 2009May 6 2009

Publication series

NameACM International Conference Proceeding Series

Conference

ConferenceSYSTOR 2009: The Israeli Experimental Systems Conference
Country/TerritoryIsrael
CityHaifa
Period05/4/0905/6/09

Keywords

  • Data compression
  • Energy
  • Performance evaluation
  • Storage

Fingerprint

Dive into the research topics of 'Energy and performance evaluation of lossless file data compression on server systems'. Together they form a unique fingerprint.

Cite this