RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing

Sisu Xi; Chong Li; Chenyang Lu; Christopher D. Gill; Meng Xu; Linh T.X. Phan; Insup Lee; Oleg Sokolsky

doi:10.1109/CLOUD.2015.33

RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing

Sisu Xi
, Chong Li
, Chenyang Lu
, Christopher D. Gill
, Meng Xu
, Linh T.X. Phan
, Insup Lee
, Oleg Sokolsky

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

49 Scopus citations

Abstract

Clouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through proper resource management at both the cloud and the hyper visor levels. This paper presents RT-Open Stack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-Open Stack entails three main contributions: (1) integration of a real-time hyper visor (RT-Xen) and a cloud management system (Open Stack) through a real-time resource interface, (2) a real-time VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs, and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RT-Open Stack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.

Original language	English
Title of host publication	Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015
Editors	Calton Pu, Ajay Mohindra
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	179-186
Number of pages	8
ISBN (Electronic)	9781467372879
DOIs	https://doi.org/10.1109/CLOUD.2015.33
State	Published - Aug 19 2015
Event	8th IEEE International Conference on Cloud Computing, CLOUD 2015 - New York, United States Duration: Jun 27 2015 → Jul 2 2015

Publication series

Name	Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015

Conference

Conference	8th IEEE International Conference on Cloud Computing, CLOUD 2015
Country/Territory	United States
City	New York
Period	06/27/15 → 07/2/15

Keywords

Openstack
Rt-xen
Scheduling

Access to Document

10.1109/CLOUD.2015.33

Cite this

Xi, S., Li, C., Lu, C., Gill, C. D., Xu, M., Phan, L. T. X., Lee, I., & Sokolsky, O. (2015). RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing. In C. Pu, & A. Mohindra (Eds.), Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015 (pp. 179-186). Article 7214043 (Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLOUD.2015.33

Xi, Sisu ; Li, Chong ; Lu, Chenyang et al. / RT-Open Stack : CPU Resource Management for Real-Time Cloud Computing. Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015. editor / Calton Pu ; Ajay Mohindra. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 179-186 (Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015).

@inproceedings{f76d2c675333434f8ddd441c1aa2d924,

title = "RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing",

abstract = "Clouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through proper resource management at both the cloud and the hyper visor levels. This paper presents RT-Open Stack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-Open Stack entails three main contributions: (1) integration of a real-time hyper visor (RT-Xen) and a cloud management system (Open Stack) through a real-time resource interface, (2) a real-time VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs, and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RT-Open Stack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.",

keywords = "Openstack, Rt-xen, Scheduling",

author = "Sisu Xi and Chong Li and Chenyang Lu and Gill, \{Christopher D.\} and Meng Xu and Phan, \{Linh T.X.\} and Insup Lee and Oleg Sokolsky",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 8th IEEE International Conference on Cloud Computing, CLOUD 2015 ; Conference date: 27-06-2015 Through 02-07-2015",

year = "2015",

month = aug,

day = "19",

doi = "10.1109/CLOUD.2015.33",

language = "English",

series = "Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015",

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

pages = "179--186",

editor = "Calton Pu and Ajay Mohindra",

booktitle = "Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015",

}

Xi, S, Li, C, Lu, C, Gill, CD, Xu, M, Phan, LTX, Lee, I & Sokolsky, O 2015, RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing. in C Pu & A Mohindra (eds), Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015., 7214043, Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015, Institute of Electrical and Electronics Engineers Inc., pp. 179-186, 8th IEEE International Conference on Cloud Computing, CLOUD 2015, New York, United States, 06/27/15. https://doi.org/10.1109/CLOUD.2015.33

RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing. / Xi, Sisu; Li, Chong; Lu, Chenyang et al.
Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015. ed. / Calton Pu; Ajay Mohindra. Institute of Electrical and Electronics Engineers Inc., 2015. p. 179-186 7214043 (Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015).

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

TY - GEN

T1 - RT-Open Stack

T2 - 8th IEEE International Conference on Cloud Computing, CLOUD 2015

AU - Xi, Sisu

AU - Li, Chong

AU - Lu, Chenyang

AU - Gill, Christopher D.

AU - Xu, Meng

AU - Phan, Linh T.X.

AU - Lee, Insup

AU - Sokolsky, Oleg

PY - 2015/8/19

Y1 - 2015/8/19

N2 - Clouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through proper resource management at both the cloud and the hyper visor levels. This paper presents RT-Open Stack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-Open Stack entails three main contributions: (1) integration of a real-time hyper visor (RT-Xen) and a cloud management system (Open Stack) through a real-time resource interface, (2) a real-time VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs, and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RT-Open Stack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.

AB - Clouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through proper resource management at both the cloud and the hyper visor levels. This paper presents RT-Open Stack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-Open Stack entails three main contributions: (1) integration of a real-time hyper visor (RT-Xen) and a cloud management system (Open Stack) through a real-time resource interface, (2) a real-time VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs, and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RT-Open Stack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.

KW - Openstack

KW - Rt-xen

KW - Scheduling

UR - https://www.scopus.com/pages/publications/84960103561

U2 - 10.1109/CLOUD.2015.33

DO - 10.1109/CLOUD.2015.33

M3 - Conference contribution

AN - SCOPUS:84960103561

T3 - Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015

SP - 179

EP - 186

BT - Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015

A2 - Pu, Calton

A2 - Mohindra, Ajay

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 27 June 2015 through 2 July 2015

ER -

Xi S, Li C, Lu C, Gill CD, Xu M, Phan LTX et al. RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing. In Pu C, Mohindra A, editors, Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 179-186. 7214043. (Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015). doi: 10.1109/CLOUD.2015.33

RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this