Software defined deduplicated replica management in scale-out storage systems

Muthukumar Murugan, Krishna Kant, Ajaykrishna Raghavan, David H.C. Du

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Given the unabated growth of storage in data centers, its energy footprint continues to grow, which makes storage energy management a crucial issue. Furthermore, with the emerging trend of underprovisioning of power and cooling infrastructures in large facilities, it is important to flexibly adapt the entire infrastructure of a client, including its storage system, to changing energy limitations. In this paper, we presentan energy-adaptive framework called flexStore that provides a flexible mechanism to specify and control the energy vs. performance tradeoffs. These mechanisms are defined and enforced by a software layer called “Policy Engine” that controls the number of active copies of deduplicated data chunks in storage containers based on energy availability. The mechanism synchronizes data chunks in inactive storage containers with those in the active containers, in the background to enable them to be put into service quickly when needed. We evaluate flexStore with different workloads on a sample data center environment and demonstrate the effectiveness of its control mechanisms in adapting to the performance and energy constraints.

Original languageEnglish (US)
Pages (from-to)340-354
Number of pages15
JournalFuture Generation Computer Systems
Volume97
DOIs
StatePublished - Aug 2019

Fingerprint

Containers
Energy management
Availability
Engines
Cooling

Keywords

  • Adaptive deduplication
  • Energy adaptive storage
  • Flexible distributed storage
  • Software defined energy management

Cite this

Software defined deduplicated replica management in scale-out storage systems. / Murugan, Muthukumar; Kant, Krishna; Raghavan, Ajaykrishna; Du, David H.C.

In: Future Generation Computer Systems, Vol. 97, 08.2019, p. 340-354.

Research output: Contribution to journalArticle

Murugan, Muthukumar ; Kant, Krishna ; Raghavan, Ajaykrishna ; Du, David H.C. / Software defined deduplicated replica management in scale-out storage systems. In: Future Generation Computer Systems. 2019 ; Vol. 97. pp. 340-354.
@article{132e866e8b8e496aadbabbc403c93782,
title = "Software defined deduplicated replica management in scale-out storage systems",
abstract = "Given the unabated growth of storage in data centers, its energy footprint continues to grow, which makes storage energy management a crucial issue. Furthermore, with the emerging trend of underprovisioning of power and cooling infrastructures in large facilities, it is important to flexibly adapt the entire infrastructure of a client, including its storage system, to changing energy limitations. In this paper, we presentan energy-adaptive framework called flexStore that provides a flexible mechanism to specify and control the energy vs. performance tradeoffs. These mechanisms are defined and enforced by a software layer called “Policy Engine” that controls the number of active copies of deduplicated data chunks in storage containers based on energy availability. The mechanism synchronizes data chunks in inactive storage containers with those in the active containers, in the background to enable them to be put into service quickly when needed. We evaluate flexStore with different workloads on a sample data center environment and demonstrate the effectiveness of its control mechanisms in adapting to the performance and energy constraints.",
keywords = "Adaptive deduplication, Energy adaptive storage, Flexible distributed storage, Software defined energy management",
author = "Muthukumar Murugan and Krishna Kant and Ajaykrishna Raghavan and Du, {David H.C.}",
year = "2019",
month = "8",
doi = "10.1016/j.future.2019.02.018",
language = "English (US)",
volume = "97",
pages = "340--354",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Software defined deduplicated replica management in scale-out storage systems

AU - Murugan, Muthukumar

AU - Kant, Krishna

AU - Raghavan, Ajaykrishna

AU - Du, David H.C.

PY - 2019/8

Y1 - 2019/8

N2 - Given the unabated growth of storage in data centers, its energy footprint continues to grow, which makes storage energy management a crucial issue. Furthermore, with the emerging trend of underprovisioning of power and cooling infrastructures in large facilities, it is important to flexibly adapt the entire infrastructure of a client, including its storage system, to changing energy limitations. In this paper, we presentan energy-adaptive framework called flexStore that provides a flexible mechanism to specify and control the energy vs. performance tradeoffs. These mechanisms are defined and enforced by a software layer called “Policy Engine” that controls the number of active copies of deduplicated data chunks in storage containers based on energy availability. The mechanism synchronizes data chunks in inactive storage containers with those in the active containers, in the background to enable them to be put into service quickly when needed. We evaluate flexStore with different workloads on a sample data center environment and demonstrate the effectiveness of its control mechanisms in adapting to the performance and energy constraints.

AB - Given the unabated growth of storage in data centers, its energy footprint continues to grow, which makes storage energy management a crucial issue. Furthermore, with the emerging trend of underprovisioning of power and cooling infrastructures in large facilities, it is important to flexibly adapt the entire infrastructure of a client, including its storage system, to changing energy limitations. In this paper, we presentan energy-adaptive framework called flexStore that provides a flexible mechanism to specify and control the energy vs. performance tradeoffs. These mechanisms are defined and enforced by a software layer called “Policy Engine” that controls the number of active copies of deduplicated data chunks in storage containers based on energy availability. The mechanism synchronizes data chunks in inactive storage containers with those in the active containers, in the background to enable them to be put into service quickly when needed. We evaluate flexStore with different workloads on a sample data center environment and demonstrate the effectiveness of its control mechanisms in adapting to the performance and energy constraints.

KW - Adaptive deduplication

KW - Energy adaptive storage

KW - Flexible distributed storage

KW - Software defined energy management

UR - http://www.scopus.com/inward/record.url?scp=85062857755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062857755&partnerID=8YFLogxK

U2 - 10.1016/j.future.2019.02.018

DO - 10.1016/j.future.2019.02.018

M3 - Article

AN - SCOPUS:85062857755

VL - 97

SP - 340

EP - 354

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

ER -