Reducing data center power with server consolidation

Approximation and evaluation

Chandrasekar Subramanian, Arunchandar Vasan, Anand Sivasubramaniam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

With the growing costs of powering data centers, power management is gaining importance. Server consolidation in data centers, enabled by virtualization technologies, is becoming a popular option for organizations to reduce costs and improve manageability. While consolidation offers these benefits, it is important to ensure proper resource provisioning so that performance is not compromised. In addition to reducing the number of servers, there are other knobs - such as frequency/voltage scaling - that are being offered by recent hardware for finer granularity of power control. In this paper, we look at exploiting server consolidation and frequency/voltage control to reduce power consumption, while meeting certain provisioning guarantees. We formulate the problem as a variant of variable-sized bin packing. We show that the problem is NP-hard, and present an approximation algorithm for the same. The algorithm takes O(n2 log n) time for n workloads, and has a provable approximation ratio. Experimental evaluation shows that in practice our algorithm obtains solutions very close (< 6.5% difference) to optimal.

Original languageEnglish (US)
Title of host publication17th International Conference on High Performance Computing, HiPC 2010
DOIs
StatePublished - Dec 1 2010
Event17th International Conference on High Performance Computing, HiPC 2010 - Goa, India
Duration: Dec 19 2010Dec 22 2010

Publication series

Name17th International Conference on High Performance Computing, HiPC 2010

Other

Other17th International Conference on High Performance Computing, HiPC 2010
CountryIndia
CityGoa
Period12/19/1012/22/10

Fingerprint

Data Center
Consolidation
Servers
Server
Evaluation
Approximation
Voltage
Knobs
Bin Packing
Power Management
Virtualization
Power Control
Costs
Bins
Approximation algorithms
Granularity
Experimental Evaluation
Power control
Voltage control
Power Consumption

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Subramanian, C., Vasan, A., & Sivasubramaniam, A. (2010). Reducing data center power with server consolidation: Approximation and evaluation. In 17th International Conference on High Performance Computing, HiPC 2010 [5713161] (17th International Conference on High Performance Computing, HiPC 2010). https://doi.org/10.1109/HIPC.2010.5713161
Subramanian, Chandrasekar ; Vasan, Arunchandar ; Sivasubramaniam, Anand. / Reducing data center power with server consolidation : Approximation and evaluation. 17th International Conference on High Performance Computing, HiPC 2010. 2010. (17th International Conference on High Performance Computing, HiPC 2010).
@inproceedings{eb271e3365824240947374858fe73cd4,
title = "Reducing data center power with server consolidation: Approximation and evaluation",
abstract = "With the growing costs of powering data centers, power management is gaining importance. Server consolidation in data centers, enabled by virtualization technologies, is becoming a popular option for organizations to reduce costs and improve manageability. While consolidation offers these benefits, it is important to ensure proper resource provisioning so that performance is not compromised. In addition to reducing the number of servers, there are other knobs - such as frequency/voltage scaling - that are being offered by recent hardware for finer granularity of power control. In this paper, we look at exploiting server consolidation and frequency/voltage control to reduce power consumption, while meeting certain provisioning guarantees. We formulate the problem as a variant of variable-sized bin packing. We show that the problem is NP-hard, and present an approximation algorithm for the same. The algorithm takes O(n2 log n) time for n workloads, and has a provable approximation ratio. Experimental evaluation shows that in practice our algorithm obtains solutions very close (< 6.5{\%} difference) to optimal.",
author = "Chandrasekar Subramanian and Arunchandar Vasan and Anand Sivasubramaniam",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/HIPC.2010.5713161",
language = "English (US)",
isbn = "9781424485185",
series = "17th International Conference on High Performance Computing, HiPC 2010",
booktitle = "17th International Conference on High Performance Computing, HiPC 2010",

}

Subramanian, C, Vasan, A & Sivasubramaniam, A 2010, Reducing data center power with server consolidation: Approximation and evaluation. in 17th International Conference on High Performance Computing, HiPC 2010., 5713161, 17th International Conference on High Performance Computing, HiPC 2010, 17th International Conference on High Performance Computing, HiPC 2010, Goa, India, 12/19/10. https://doi.org/10.1109/HIPC.2010.5713161

Reducing data center power with server consolidation : Approximation and evaluation. / Subramanian, Chandrasekar; Vasan, Arunchandar; Sivasubramaniam, Anand.

17th International Conference on High Performance Computing, HiPC 2010. 2010. 5713161 (17th International Conference on High Performance Computing, HiPC 2010).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Reducing data center power with server consolidation

T2 - Approximation and evaluation

AU - Subramanian, Chandrasekar

AU - Vasan, Arunchandar

AU - Sivasubramaniam, Anand

PY - 2010/12/1

Y1 - 2010/12/1

N2 - With the growing costs of powering data centers, power management is gaining importance. Server consolidation in data centers, enabled by virtualization technologies, is becoming a popular option for organizations to reduce costs and improve manageability. While consolidation offers these benefits, it is important to ensure proper resource provisioning so that performance is not compromised. In addition to reducing the number of servers, there are other knobs - such as frequency/voltage scaling - that are being offered by recent hardware for finer granularity of power control. In this paper, we look at exploiting server consolidation and frequency/voltage control to reduce power consumption, while meeting certain provisioning guarantees. We formulate the problem as a variant of variable-sized bin packing. We show that the problem is NP-hard, and present an approximation algorithm for the same. The algorithm takes O(n2 log n) time for n workloads, and has a provable approximation ratio. Experimental evaluation shows that in practice our algorithm obtains solutions very close (< 6.5% difference) to optimal.

AB - With the growing costs of powering data centers, power management is gaining importance. Server consolidation in data centers, enabled by virtualization technologies, is becoming a popular option for organizations to reduce costs and improve manageability. While consolidation offers these benefits, it is important to ensure proper resource provisioning so that performance is not compromised. In addition to reducing the number of servers, there are other knobs - such as frequency/voltage scaling - that are being offered by recent hardware for finer granularity of power control. In this paper, we look at exploiting server consolidation and frequency/voltage control to reduce power consumption, while meeting certain provisioning guarantees. We formulate the problem as a variant of variable-sized bin packing. We show that the problem is NP-hard, and present an approximation algorithm for the same. The algorithm takes O(n2 log n) time for n workloads, and has a provable approximation ratio. Experimental evaluation shows that in practice our algorithm obtains solutions very close (< 6.5% difference) to optimal.

UR - http://www.scopus.com/inward/record.url?scp=79952779649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952779649&partnerID=8YFLogxK

U2 - 10.1109/HIPC.2010.5713161

DO - 10.1109/HIPC.2010.5713161

M3 - Conference contribution

SN - 9781424485185

T3 - 17th International Conference on High Performance Computing, HiPC 2010

BT - 17th International Conference on High Performance Computing, HiPC 2010

ER -

Subramanian C, Vasan A, Sivasubramaniam A. Reducing data center power with server consolidation: Approximation and evaluation. In 17th International Conference on High Performance Computing, HiPC 2010. 2010. 5713161. (17th International Conference on High Performance Computing, HiPC 2010). https://doi.org/10.1109/HIPC.2010.5713161