Workload-aware resource management for energy efficient heterogeneous Docker containers

Dong Ki Kang; Gyu Beom Choi; Seong Hwan Kim; Il Sun Hwang; Chan Hyun Youn

doi:10.1109/TENCON.2016.7848467

Workload-aware resource management for energy efficient heterogeneous Docker containers

Dong Ki Kang
, Gyu Beom Choi
, Seong Hwan Kim
, Il Sun Hwang
, Chan Hyun Youn^*

^*Corresponding author for this work

Department of Computer Science & Artificial Intelligence

Korea Advanced Institute of Science and Technology

Research output: Contribution to conference › Conference paper › peer-review

21 Scopus citations

Abstract

Recently, containerization has received a lot of attention from world's major vendors such as Google, Amazon, and Microsoft as a good alternative to traditional hypervisor based virtualization for clouds because of its lightweight and rapid deployment of multi-tenant services. Especially, Docker container is the most noteworthy one among serveral container technologies including Linux container (LXC), Warden container, OpenVZ and so on. Similar to the traditional cloud environments, the energy consumption is still a large part of the overall operating expense of Docker container based cloud datacenters. In this paper, we propose Workload aware Energy Efficient Container (WEEC) brokering system to save the energy consumption caused by running container applications while guaranteeing acceptable performance level. In addition, we show the power and performance heterogeneity of several Docker container servers from experimental results with physical power metering devices to identify the performance benefits of our proposed system.

Original language	English
Title of host publication	Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2428-2431
Number of pages	4
ISBN (Electronic)	9781509025961
DOIs	https://doi.org/10.1109/TENCON.2016.7848467
State	Published - 2017.02.8
Event	2016 IEEE Region 10 Conference, TENCON 2016 - Singapore, Singapore Duration: 2016.11.22 → 2016.11.25

Publication series

Name	IEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)	2159-3442
ISSN (Electronic)	2159-3450

Conference

Conference	2016 IEEE Region 10 Conference, TENCON 2016
Country/Territory	Singapore
City	Singapore
Period	16.11.22 → 16.11.25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

cloud datacenters
containers
Docker
energy efficient
heterogeneity

Access to Document

10.1109/TENCON.2016.7848467

Cite this

Kang, D. K., Choi, G. B., Kim, S. H., Hwang, I. S., & Youn, C. H. (2017). Workload-aware resource management for energy efficient heterogeneous Docker containers. In Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016 (pp. 2428-2431). Article 7848467 (IEEE Region 10 Annual International Conference, Proceedings/TENCON). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TENCON.2016.7848467

@inproceedings{11ce69d2d57945a0906ec91061729f29,

title = "Workload-aware resource management for energy efficient heterogeneous Docker containers",

abstract = "Recently, containerization has received a lot of attention from world's major vendors such as Google, Amazon, and Microsoft as a good alternative to traditional hypervisor based virtualization for clouds because of its lightweight and rapid deployment of multi-tenant services. Especially, Docker container is the most noteworthy one among serveral container technologies including Linux container (LXC), Warden container, OpenVZ and so on. Similar to the traditional cloud environments, the energy consumption is still a large part of the overall operating expense of Docker container based cloud datacenters. In this paper, we propose Workload aware Energy Efficient Container (WEEC) brokering system to save the energy consumption caused by running container applications while guaranteeing acceptable performance level. In addition, we show the power and performance heterogeneity of several Docker container servers from experimental results with physical power metering devices to identify the performance benefits of our proposed system.",

keywords = "cloud datacenters, containers, Docker, energy efficient, heterogeneity",

author = "Kang, \{Dong Ki\} and Choi, \{Gyu Beom\} and Kim, \{Seong Hwan\} and Hwang, \{Il Sun\} and Youn, \{Chan Hyun\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE Region 10 Conference, TENCON 2016 ; Conference date: 22-11-2016 Through 25-11-2016",

year = "2017",

month = feb,

day = "8",

doi = "10.1109/TENCON.2016.7848467",

language = "English",

series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2428--2431",

booktitle = "Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016",

}

Kang, DK, Choi, GB, Kim, SH, Hwang, IS & Youn, CH 2017, Workload-aware resource management for energy efficient heterogeneous Docker containers. in Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016., 7848467, IEEE Region 10 Annual International Conference, Proceedings/TENCON, Institute of Electrical and Electronics Engineers Inc., pp. 2428-2431, 2016 IEEE Region 10 Conference, TENCON 2016, Singapore, Singapore, 16.11.22. https://doi.org/10.1109/TENCON.2016.7848467

Workload-aware resource management for energy efficient heterogeneous Docker containers. / Kang, Dong Ki; Choi, Gyu Beom; Kim, Seong Hwan et al.
Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2428-2431 7848467 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - Workload-aware resource management for energy efficient heterogeneous Docker containers

AU - Kang, Dong Ki

AU - Choi, Gyu Beom

AU - Kim, Seong Hwan

AU - Hwang, Il Sun

AU - Youn, Chan Hyun

PY - 2017/2/8

Y1 - 2017/2/8

N2 - Recently, containerization has received a lot of attention from world's major vendors such as Google, Amazon, and Microsoft as a good alternative to traditional hypervisor based virtualization for clouds because of its lightweight and rapid deployment of multi-tenant services. Especially, Docker container is the most noteworthy one among serveral container technologies including Linux container (LXC), Warden container, OpenVZ and so on. Similar to the traditional cloud environments, the energy consumption is still a large part of the overall operating expense of Docker container based cloud datacenters. In this paper, we propose Workload aware Energy Efficient Container (WEEC) brokering system to save the energy consumption caused by running container applications while guaranteeing acceptable performance level. In addition, we show the power and performance heterogeneity of several Docker container servers from experimental results with physical power metering devices to identify the performance benefits of our proposed system.

AB - Recently, containerization has received a lot of attention from world's major vendors such as Google, Amazon, and Microsoft as a good alternative to traditional hypervisor based virtualization for clouds because of its lightweight and rapid deployment of multi-tenant services. Especially, Docker container is the most noteworthy one among serveral container technologies including Linux container (LXC), Warden container, OpenVZ and so on. Similar to the traditional cloud environments, the energy consumption is still a large part of the overall operating expense of Docker container based cloud datacenters. In this paper, we propose Workload aware Energy Efficient Container (WEEC) brokering system to save the energy consumption caused by running container applications while guaranteeing acceptable performance level. In addition, we show the power and performance heterogeneity of several Docker container servers from experimental results with physical power metering devices to identify the performance benefits of our proposed system.

KW - cloud datacenters

KW - containers

KW - Docker

KW - energy efficient

KW - heterogeneity

UR - https://www.scopus.com/pages/publications/85015423417

U2 - 10.1109/TENCON.2016.7848467

DO - 10.1109/TENCON.2016.7848467

M3 - Conference paper

AN - SCOPUS:85015423417

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 2428

EP - 2431

BT - Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE Region 10 Conference, TENCON 2016

Y2 - 22 November 2016 through 25 November 2016

ER -

Kang DK, Choi GB, Kim SH, Hwang IS, Youn CH. Workload-aware resource management for energy efficient heterogeneous Docker containers. In Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2428-2431. 7848467. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). doi: 10.1109/TENCON.2016.7848467

Workload-aware resource management for energy efficient heterogeneous Docker containers

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this