Managing server energy and operational costs in hosting centers

Yiyu Chen, Anand Sivasubramaniam, Amitayu Das, Qian Wang, Wubi Qin, Natarajan Gautam

Research output: Contribution to journalConference article

283 Citations (Scopus)

Abstract

The growing cost of tuning and managing computer systems is leading to out-sourcing of commercial services to hosting centers. These centers provision thousands of dense servers within a relatively small real-estate in order to host the applications/services of different customers who may have been assured by a service-level agreement (SLA). Power consumption of these servers is becoming a serious concern in the design and operation of the hosting centers. The effects of high power consumption manifest not only in the costs spent in designing effective cooling systems to ward off the generated heat, but in the cost of electricity consumption itself. It is crucial to deploy power management strategies in these hosting centers to lower these costs towards enhancing profitability. At the same time, techniques for power management that include shutting down these servers and/or modulating their operational speed, can impact the ability of the hosting center to meet SLAs. In addition, repeated on-off cycles can increase the wear-and-tear of server components, incurring costs for their procurement and replacement. This paper presents a formalism to this problem, and proposes three new online solution strategies based on steady state queuing analysis, feedback control theory, and a hybrid mechanism borrowing ideas from these two. Using real web server traces, we show that these solutions are more adaptive to workload behavior when performing server provisioning and speed control than earlier heuristics towards minimizing operational costs while meeting the SLAs.

Original languageEnglish (US)
Pages (from-to)303-314
Number of pages12
JournalPerformance Evaluation Review
Volume33
Issue number1
DOIs
StatePublished - Dec 1 2005
EventSIGMETRICS 2005: International Conference on Measurement and Modeling of Computer Systems - Banff, AB, Canada
Duration: Jun 6 2005Jun 10 2005

Fingerprint

Servers
Costs
Electric power utilization
Outsourcing
Speed control
Cooling systems
Control theory
Feedback control
Profitability
Computer systems
Electricity
Tuning
Wear of materials
Power management

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Chen, Yiyu ; Sivasubramaniam, Anand ; Das, Amitayu ; Wang, Qian ; Qin, Wubi ; Gautam, Natarajan. / Managing server energy and operational costs in hosting centers. In: Performance Evaluation Review. 2005 ; Vol. 33, No. 1. pp. 303-314.
@article{6231aea21430400197bc36f79b351fa2,
title = "Managing server energy and operational costs in hosting centers",
abstract = "The growing cost of tuning and managing computer systems is leading to out-sourcing of commercial services to hosting centers. These centers provision thousands of dense servers within a relatively small real-estate in order to host the applications/services of different customers who may have been assured by a service-level agreement (SLA). Power consumption of these servers is becoming a serious concern in the design and operation of the hosting centers. The effects of high power consumption manifest not only in the costs spent in designing effective cooling systems to ward off the generated heat, but in the cost of electricity consumption itself. It is crucial to deploy power management strategies in these hosting centers to lower these costs towards enhancing profitability. At the same time, techniques for power management that include shutting down these servers and/or modulating their operational speed, can impact the ability of the hosting center to meet SLAs. In addition, repeated on-off cycles can increase the wear-and-tear of server components, incurring costs for their procurement and replacement. This paper presents a formalism to this problem, and proposes three new online solution strategies based on steady state queuing analysis, feedback control theory, and a hybrid mechanism borrowing ideas from these two. Using real web server traces, we show that these solutions are more adaptive to workload behavior when performing server provisioning and speed control than earlier heuristics towards minimizing operational costs while meeting the SLAs.",
author = "Yiyu Chen and Anand Sivasubramaniam and Amitayu Das and Qian Wang and Wubi Qin and Natarajan Gautam",
year = "2005",
month = "12",
day = "1",
doi = "10.1145/1071690.1064253",
language = "English (US)",
volume = "33",
pages = "303--314",
journal = "Performance Evaluation Review",
issn = "0163-5999",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

Managing server energy and operational costs in hosting centers. / Chen, Yiyu; Sivasubramaniam, Anand; Das, Amitayu; Wang, Qian; Qin, Wubi; Gautam, Natarajan.

In: Performance Evaluation Review, Vol. 33, No. 1, 01.12.2005, p. 303-314.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Managing server energy and operational costs in hosting centers

AU - Chen, Yiyu

AU - Sivasubramaniam, Anand

AU - Das, Amitayu

AU - Wang, Qian

AU - Qin, Wubi

AU - Gautam, Natarajan

PY - 2005/12/1

Y1 - 2005/12/1

N2 - The growing cost of tuning and managing computer systems is leading to out-sourcing of commercial services to hosting centers. These centers provision thousands of dense servers within a relatively small real-estate in order to host the applications/services of different customers who may have been assured by a service-level agreement (SLA). Power consumption of these servers is becoming a serious concern in the design and operation of the hosting centers. The effects of high power consumption manifest not only in the costs spent in designing effective cooling systems to ward off the generated heat, but in the cost of electricity consumption itself. It is crucial to deploy power management strategies in these hosting centers to lower these costs towards enhancing profitability. At the same time, techniques for power management that include shutting down these servers and/or modulating their operational speed, can impact the ability of the hosting center to meet SLAs. In addition, repeated on-off cycles can increase the wear-and-tear of server components, incurring costs for their procurement and replacement. This paper presents a formalism to this problem, and proposes three new online solution strategies based on steady state queuing analysis, feedback control theory, and a hybrid mechanism borrowing ideas from these two. Using real web server traces, we show that these solutions are more adaptive to workload behavior when performing server provisioning and speed control than earlier heuristics towards minimizing operational costs while meeting the SLAs.

AB - The growing cost of tuning and managing computer systems is leading to out-sourcing of commercial services to hosting centers. These centers provision thousands of dense servers within a relatively small real-estate in order to host the applications/services of different customers who may have been assured by a service-level agreement (SLA). Power consumption of these servers is becoming a serious concern in the design and operation of the hosting centers. The effects of high power consumption manifest not only in the costs spent in designing effective cooling systems to ward off the generated heat, but in the cost of electricity consumption itself. It is crucial to deploy power management strategies in these hosting centers to lower these costs towards enhancing profitability. At the same time, techniques for power management that include shutting down these servers and/or modulating their operational speed, can impact the ability of the hosting center to meet SLAs. In addition, repeated on-off cycles can increase the wear-and-tear of server components, incurring costs for their procurement and replacement. This paper presents a formalism to this problem, and proposes three new online solution strategies based on steady state queuing analysis, feedback control theory, and a hybrid mechanism borrowing ideas from these two. Using real web server traces, we show that these solutions are more adaptive to workload behavior when performing server provisioning and speed control than earlier heuristics towards minimizing operational costs while meeting the SLAs.

UR - http://www.scopus.com/inward/record.url?scp=33244478578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33244478578&partnerID=8YFLogxK

U2 - 10.1145/1071690.1064253

DO - 10.1145/1071690.1064253

M3 - Conference article

AN - SCOPUS:33244478578

VL - 33

SP - 303

EP - 314

JO - Performance Evaluation Review

JF - Performance Evaluation Review

SN - 0163-5999

IS - 1

ER -