Revenue driven resource allocation for virtualized data centers

Sajib Kundu; Raju Rangaswami; Ming Zhao; Ajay Gulati; Kaushik Dutta

doi:10.1109/ICAC.2015.40

Revenue driven resource allocation for virtualized data centers

Sajib Kundu, Raju Rangaswami, Ming Zhao, Ajay Gulati, Kaushik Dutta

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

7 Scopus citations

Abstract

The increasing VM density in cloud hosting services makes careful management of physical resources such as CPU, memory, and I/O bandwidth within individual virtualized servers a priority. To maximize cost-efficiency, resource management needs to be coupled with the revenue generating mechanisms of cloud hosting: the service level agreements (SLAs) of hosted client applications. In this paper, we develop a server resource management framework that reduces data center resource management complexity substantially. Our solution implements revenue-driven dynamic resource allocation which continuously steers the resource distribution across hosted VMs within a server such as to maximize the SLA-generated revenue from the server. Our experimental evaluation for a VMware ESX hyper visor highlights the importance of both resource isolation and resource sharing across VMs. The empirical data shows a 7%-54% increase in total revenue generated for a mix of 10-25 VMs hosting either similar or diverse workloads when compared to using the currently available resource distribution mechanisms in ESX.

Original language	English (US)
Title of host publication	Proceedings - IEEE International Conference on Autonomic Computing, ICAC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	197-206
Number of pages	10
ISBN (Print)	9781467369701
DOIs	https://doi.org/10.1109/ICAC.2015.40
State	Published - Sep 14 2015
Externally published	Yes
Event	12th IEEE International Conference on Autonomic Computing, ICAC 2015 - Grenoble, France Duration: Jul 7 2015 → Jul 10 2015

Other

Other	12th IEEE International Conference on Autonomic Computing, ICAC 2015
Country	France
City	Grenoble
Period	7/7/15 → 7/10/15

Keywords

Cloud computing
Data centers
Resource allocation
SLA
Virtualization

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Software
Control and Systems Engineering

Access to Document

10.1109/ICAC.2015.40

Fingerprint Dive into the research topics of 'Revenue driven resource allocation for virtualized data centers'. Together they form a unique fingerprint.

Cite this

Revenue driven resource allocation for virtualized data centers. / Kundu, Sajib; Rangaswami, Raju; Zhao, Ming; Gulati, Ajay; Dutta, Kaushik.

Proceedings - IEEE International Conference on Autonomic Computing, ICAC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 197-206 7266964.

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

Kundu, S, Rangaswami, R, Zhao, M, Gulati, A & Dutta, K 2015, Revenue driven resource allocation for virtualized data centers. in Proceedings - IEEE International Conference on Autonomic Computing, ICAC 2015., 7266964, Institute of Electrical and Electronics Engineers Inc., pp. 197-206, 12th IEEE International Conference on Autonomic Computing, ICAC 2015, Grenoble, France, 7/7/15. https://doi.org/10.1109/ICAC.2015.40

@inproceedings{861e3c0137254934ac8ae43e0f8ef1b8,

title = "Revenue driven resource allocation for virtualized data centers",

abstract = "The increasing VM density in cloud hosting services makes careful management of physical resources such as CPU, memory, and I/O bandwidth within individual virtualized servers a priority. To maximize cost-efficiency, resource management needs to be coupled with the revenue generating mechanisms of cloud hosting: the service level agreements (SLAs) of hosted client applications. In this paper, we develop a server resource management framework that reduces data center resource management complexity substantially. Our solution implements revenue-driven dynamic resource allocation which continuously steers the resource distribution across hosted VMs within a server such as to maximize the SLA-generated revenue from the server. Our experimental evaluation for a VMware ESX hyper visor highlights the importance of both resource isolation and resource sharing across VMs. The empirical data shows a 7%-54% increase in total revenue generated for a mix of 10-25 VMs hosting either similar or diverse workloads when compared to using the currently available resource distribution mechanisms in ESX.",

keywords = "Cloud computing, Data centers, Resource allocation, SLA, Virtualization",

author = "Sajib Kundu and Raju Rangaswami and Ming Zhao and Ajay Gulati and Kaushik Dutta",

year = "2015",

month = sep,

day = "14",

doi = "10.1109/ICAC.2015.40",

language = "English (US)",

isbn = "9781467369701",

pages = "197--206",

booktitle = "Proceedings - IEEE International Conference on Autonomic Computing, ICAC 2015",

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

note = "12th IEEE International Conference on Autonomic Computing, ICAC 2015 ; Conference date: 07-07-2015 Through 10-07-2015",

}

TY - GEN

T1 - Revenue driven resource allocation for virtualized data centers

AU - Kundu, Sajib

AU - Rangaswami, Raju

AU - Zhao, Ming

AU - Gulati, Ajay

AU - Dutta, Kaushik

PY - 2015/9/14

Y1 - 2015/9/14

N2 - The increasing VM density in cloud hosting services makes careful management of physical resources such as CPU, memory, and I/O bandwidth within individual virtualized servers a priority. To maximize cost-efficiency, resource management needs to be coupled with the revenue generating mechanisms of cloud hosting: the service level agreements (SLAs) of hosted client applications. In this paper, we develop a server resource management framework that reduces data center resource management complexity substantially. Our solution implements revenue-driven dynamic resource allocation which continuously steers the resource distribution across hosted VMs within a server such as to maximize the SLA-generated revenue from the server. Our experimental evaluation for a VMware ESX hyper visor highlights the importance of both resource isolation and resource sharing across VMs. The empirical data shows a 7%-54% increase in total revenue generated for a mix of 10-25 VMs hosting either similar or diverse workloads when compared to using the currently available resource distribution mechanisms in ESX.

AB - The increasing VM density in cloud hosting services makes careful management of physical resources such as CPU, memory, and I/O bandwidth within individual virtualized servers a priority. To maximize cost-efficiency, resource management needs to be coupled with the revenue generating mechanisms of cloud hosting: the service level agreements (SLAs) of hosted client applications. In this paper, we develop a server resource management framework that reduces data center resource management complexity substantially. Our solution implements revenue-driven dynamic resource allocation which continuously steers the resource distribution across hosted VMs within a server such as to maximize the SLA-generated revenue from the server. Our experimental evaluation for a VMware ESX hyper visor highlights the importance of both resource isolation and resource sharing across VMs. The empirical data shows a 7%-54% increase in total revenue generated for a mix of 10-25 VMs hosting either similar or diverse workloads when compared to using the currently available resource distribution mechanisms in ESX.

KW - Cloud computing

KW - Data centers

KW - Resource allocation

KW - SLA

KW - Virtualization

UR - http://www.scopus.com/inward/record.url?scp=84961774349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961774349&partnerID=8YFLogxK

U2 - 10.1109/ICAC.2015.40

DO - 10.1109/ICAC.2015.40

M3 - Conference contribution

AN - SCOPUS:84961774349

SN - 9781467369701

SP - 197

EP - 206

BT - Proceedings - IEEE International Conference on Autonomic Computing, ICAC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Autonomic Computing, ICAC 2015

Y2 - 7 July 2015 through 10 July 2015

ER -