On reducing energy management delays in disks

K. R. Krish, Guanying Wang, Puranjoy Bhattacharjee, Ali R. Butt, Christopher Gniady

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Enterprise computing systems consume a large amount of energy, the cost of which contributes significantly to the operating budget. Consequently, dynamic energy management techniques are prevalent. Unfortunately, dynamic energy management for disks impose delays associated with powering up the disks from a low-power state. Systems designers face a critical trade-off: saving energy reduces operating costs but may increase delays; conversely, reduced access latency makes the systems more responsive but may preclude energy management. In this paper, we propose a System-wide Alternative Retrieval of Data (SARD) scheme. SARD exploits the similarity in software deployment and configuration in enterprise computers to retrieve binaries transparently from other nodes, thus avoiding access delays when the local disk is in a low-power state. SARD uses a software-based approach to reduce spin-up delays while eliminating custom buffering, shared memory infrastructure, or the need for major changes in the operating system. SARD achieves over 71% reduction in delays on trace-driven simulations and in an actual implementation. This will encourage users to utilize energy management techniques more frequently. SARD also achieves an additional 5.1% average reduction in energy consumption for typical desktop applications compared to the widely-used timeout-based disk energy management.

Original languageEnglish (US)
Pages (from-to)823-835
Number of pages13
JournalJournal of Parallel and Distributed Computing
Volume73
Issue number6
DOIs
StatePublished - 2013

Fingerprint

Energy Management
Energy management
Retrieval
Alternatives
Operating costs
Industry
Energy conservation
Energy utilization
Software
Costs
Data storage equipment
Energy Saving
Shared Memory
Operating Systems
Energy Consumption
Latency
Infrastructure
Trade-offs
Trace
Binary

Keywords

  • Spin-up delay reduction Disk energy management Peer memory sharing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software
  • Theoretical Computer Science

Cite this

On reducing energy management delays in disks. / Krish, K. R.; Wang, Guanying; Bhattacharjee, Puranjoy; Butt, Ali R.; Gniady, Christopher.

In: Journal of Parallel and Distributed Computing, Vol. 73, No. 6, 2013, p. 823-835.

Research output: Contribution to journalArticle

Krish, K. R. ; Wang, Guanying ; Bhattacharjee, Puranjoy ; Butt, Ali R. ; Gniady, Christopher. / On reducing energy management delays in disks. In: Journal of Parallel and Distributed Computing. 2013 ; Vol. 73, No. 6. pp. 823-835.
@article{0d3b989891324ecab25ab33ba945c4f5,
title = "On reducing energy management delays in disks",
abstract = "Enterprise computing systems consume a large amount of energy, the cost of which contributes significantly to the operating budget. Consequently, dynamic energy management techniques are prevalent. Unfortunately, dynamic energy management for disks impose delays associated with powering up the disks from a low-power state. Systems designers face a critical trade-off: saving energy reduces operating costs but may increase delays; conversely, reduced access latency makes the systems more responsive but may preclude energy management. In this paper, we propose a System-wide Alternative Retrieval of Data (SARD) scheme. SARD exploits the similarity in software deployment and configuration in enterprise computers to retrieve binaries transparently from other nodes, thus avoiding access delays when the local disk is in a low-power state. SARD uses a software-based approach to reduce spin-up delays while eliminating custom buffering, shared memory infrastructure, or the need for major changes in the operating system. SARD achieves over 71{\%} reduction in delays on trace-driven simulations and in an actual implementation. This will encourage users to utilize energy management techniques more frequently. SARD also achieves an additional 5.1{\%} average reduction in energy consumption for typical desktop applications compared to the widely-used timeout-based disk energy management.",
keywords = "Spin-up delay reduction Disk energy management Peer memory sharing",
author = "Krish, {K. R.} and Guanying Wang and Puranjoy Bhattacharjee and Butt, {Ali R.} and Christopher Gniady",
year = "2013",
doi = "10.1016/j.jpdc.2013.02.011",
language = "English (US)",
volume = "73",
pages = "823--835",
journal = "Journal of Parallel and Distributed Computing",
issn = "0743-7315",
publisher = "Academic Press Inc.",
number = "6",

}

TY - JOUR

T1 - On reducing energy management delays in disks

AU - Krish, K. R.

AU - Wang, Guanying

AU - Bhattacharjee, Puranjoy

AU - Butt, Ali R.

AU - Gniady, Christopher

PY - 2013

Y1 - 2013

N2 - Enterprise computing systems consume a large amount of energy, the cost of which contributes significantly to the operating budget. Consequently, dynamic energy management techniques are prevalent. Unfortunately, dynamic energy management for disks impose delays associated with powering up the disks from a low-power state. Systems designers face a critical trade-off: saving energy reduces operating costs but may increase delays; conversely, reduced access latency makes the systems more responsive but may preclude energy management. In this paper, we propose a System-wide Alternative Retrieval of Data (SARD) scheme. SARD exploits the similarity in software deployment and configuration in enterprise computers to retrieve binaries transparently from other nodes, thus avoiding access delays when the local disk is in a low-power state. SARD uses a software-based approach to reduce spin-up delays while eliminating custom buffering, shared memory infrastructure, or the need for major changes in the operating system. SARD achieves over 71% reduction in delays on trace-driven simulations and in an actual implementation. This will encourage users to utilize energy management techniques more frequently. SARD also achieves an additional 5.1% average reduction in energy consumption for typical desktop applications compared to the widely-used timeout-based disk energy management.

AB - Enterprise computing systems consume a large amount of energy, the cost of which contributes significantly to the operating budget. Consequently, dynamic energy management techniques are prevalent. Unfortunately, dynamic energy management for disks impose delays associated with powering up the disks from a low-power state. Systems designers face a critical trade-off: saving energy reduces operating costs but may increase delays; conversely, reduced access latency makes the systems more responsive but may preclude energy management. In this paper, we propose a System-wide Alternative Retrieval of Data (SARD) scheme. SARD exploits the similarity in software deployment and configuration in enterprise computers to retrieve binaries transparently from other nodes, thus avoiding access delays when the local disk is in a low-power state. SARD uses a software-based approach to reduce spin-up delays while eliminating custom buffering, shared memory infrastructure, or the need for major changes in the operating system. SARD achieves over 71% reduction in delays on trace-driven simulations and in an actual implementation. This will encourage users to utilize energy management techniques more frequently. SARD also achieves an additional 5.1% average reduction in energy consumption for typical desktop applications compared to the widely-used timeout-based disk energy management.

KW - Spin-up delay reduction Disk energy management Peer memory sharing

UR - http://www.scopus.com/inward/record.url?scp=84875692399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875692399&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2013.02.011

DO - 10.1016/j.jpdc.2013.02.011

M3 - Article

AN - SCOPUS:84875692399

VL - 73

SP - 823

EP - 835

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

SN - 0743-7315

IS - 6

ER -