Power control for Web-based services on multi-core server systems

Minjoong Kim; Moonju Park; Jinseok Chae; Jungsun Kim; Lynn Choi

doi:10.1109/ICCCSN.2012.6215719

Power control for Web-based services on multi-core server systems

Minjoong Kim, Moonju Park, Jinseok Chae, Jungsun Kim, Lynn Choi

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Power consumption in data centers with large number of servers is being issued as energy costs increase. To reduce the energy costs, technologies such as DVFS are adopted to server systems. In this paper, we measure a multi-core server system's power consumption running a HTTP server. To identify the characteristics of multi-core servers' power consumption, we examined CPU-intensive and I/O-intensive synthetic workloads. Experimental results show that we can use DVFS for energy efficient server operation for CPU-intensive load, while parallelizing the interrupt processing helps saving energy for I/O-intensive workloads.

Original language	English
Title of host publication	Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012
DOIs	https://doi.org/10.1109/ICCCSN.2012.6215719
Publication status	Published - 2012 Jul 23
Event	International Conference on Cloud Computing and Social Networking 2012: "Cloud Computing and Social Networking for Smart and Productive Society", ICCCSN 2012 - Bandung, Indonesia Duration: 2012 Apr 26 → 2012 Apr 27

Other

Other	International Conference on Cloud Computing and Social Networking 2012: "Cloud Computing and Social Networking for Smart and Productive Society", ICCCSN 2012
Country	Indonesia
City	Bandung
Period	12/4/26 → 12/4/27

Keywords

Data center
Multi-core server
Power control

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1109/ICCCSN.2012.6215719

Fingerprint Dive into the research topics of 'Power control for Web-based services on multi-core server systems'. Together they form a unique fingerprint.

Cite this

Kim, M., Park, M., Chae, J., Kim, J., & Choi, L. (2012). Power control for Web-based services on multi-core server systems. In Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012 [6215719] https://doi.org/10.1109/ICCCSN.2012.6215719

Power control for Web-based services on multi-core server systems. / Kim, Minjoong; Park, Moonju; Chae, Jinseok; Kim, Jungsun; Choi, Lynn.

Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012. 2012. 6215719.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kim, M, Park, M, Chae, J, Kim, J & Choi, L 2012, Power control for Web-based services on multi-core server systems. in Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012., 6215719, International Conference on Cloud Computing and Social Networking 2012: "Cloud Computing and Social Networking for Smart and Productive Society", ICCCSN 2012, Bandung, Indonesia, 12/4/26. https://doi.org/10.1109/ICCCSN.2012.6215719

@inproceedings{f43cd6b05aff4e3ab88135e7ae6f9ea7,

title = "Power control for Web-based services on multi-core server systems",

abstract = "Power consumption in data centers with large number of servers is being issued as energy costs increase. To reduce the energy costs, technologies such as DVFS are adopted to server systems. In this paper, we measure a multi-core server system's power consumption running a HTTP server. To identify the characteristics of multi-core servers' power consumption, we examined CPU-intensive and I/O-intensive synthetic workloads. Experimental results show that we can use DVFS for energy efficient server operation for CPU-intensive load, while parallelizing the interrupt processing helps saving energy for I/O-intensive workloads.",

keywords = "Data center, Multi-core server, Power control",

author = "Minjoong Kim and Moonju Park and Jinseok Chae and Jungsun Kim and Lynn Choi",

year = "2012",

month = jul,

day = "23",

doi = "10.1109/ICCCSN.2012.6215719",

language = "English",

isbn = "9781467318167",

booktitle = "Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012",

note = "International Conference on Cloud Computing and Social Networking 2012: {"}Cloud Computing and Social Networking for Smart and Productive Society{"}, ICCCSN 2012 ; Conference date: 26-04-2012 Through 27-04-2012",

}

TY - GEN

T1 - Power control for Web-based services on multi-core server systems

AU - Kim, Minjoong

AU - Park, Moonju

AU - Chae, Jinseok

AU - Kim, Jungsun

AU - Choi, Lynn

PY - 2012/7/23

Y1 - 2012/7/23

N2 - Power consumption in data centers with large number of servers is being issued as energy costs increase. To reduce the energy costs, technologies such as DVFS are adopted to server systems. In this paper, we measure a multi-core server system's power consumption running a HTTP server. To identify the characteristics of multi-core servers' power consumption, we examined CPU-intensive and I/O-intensive synthetic workloads. Experimental results show that we can use DVFS for energy efficient server operation for CPU-intensive load, while parallelizing the interrupt processing helps saving energy for I/O-intensive workloads.

AB - Power consumption in data centers with large number of servers is being issued as energy costs increase. To reduce the energy costs, technologies such as DVFS are adopted to server systems. In this paper, we measure a multi-core server system's power consumption running a HTTP server. To identify the characteristics of multi-core servers' power consumption, we examined CPU-intensive and I/O-intensive synthetic workloads. Experimental results show that we can use DVFS for energy efficient server operation for CPU-intensive load, while parallelizing the interrupt processing helps saving energy for I/O-intensive workloads.

KW - Data center

KW - Multi-core server

KW - Power control

UR - http://www.scopus.com/inward/record.url?scp=84863887634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863887634&partnerID=8YFLogxK

U2 - 10.1109/ICCCSN.2012.6215719

DO - 10.1109/ICCCSN.2012.6215719

M3 - Conference contribution

AN - SCOPUS:84863887634

SN - 9781467318167

BT - Proceedings - International Conference on Cloud Computing and Social Networking 2012: Cloud Computing and Social Networking for Smart and Productive Society, ICCCSN 2012

T2 - International Conference on Cloud Computing and Social Networking 2012: "Cloud Computing and Social Networking for Smart and Productive Society", ICCCSN 2012

Y2 - 26 April 2012 through 27 April 2012

ER -