Modelling Resilience in Cloud-Scale Data Centres

John Cartlidge; Ilango L Sriram

Modelling Resilience in Cloud-Scale Data Centres

John Cartlidge, Ilango L Sriram

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

89 Downloads (Pure)

Abstract

The trend for cloud computing has initiated a race towards data centres (DC) of an ever-increasing size. The largest DCs now contain many hundreds of thousands of virtual machine (VM) services. Given the finite lifespan of hardware, such large DCs are subject to frequent hardware failure events that can lead to disruption of service. To counter this, multiple redundant copies of task threads may be distributed around a DC to ensure that individual hardware failures do not cause entire jobs to fail. Here, we present results demonstrating the resilience of different job scheduling algorithms in a simulated DC with hardware failure. We use a simple model of jobs distributed across a hardware network to demonstrate the relationship between resilience and additional communication costs of different scheduling methods.

Original language	English
Title of host publication	23rd European Modeling and Simulation Symposium (EMSS 2011)
Subtitle of host publication	Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference
Editors	Agostino Bruzzone, Miquel Piera, Francesco Longo, Priscilla Elfrey, Michael Affenzeller, Osman Balci
Publisher	University of Genoa Press
Pages	299-307
Number of pages	9
ISBN (Print)	9788890372445
Publication status	Published - Mar 2014
Event	23rd European Modeling & Simulation Symposium (EMSS-2011) - Rome, Italy Duration: 12 Sept 2011 → 14 Sept 2011

Conference

Conference	23rd European Modeling & Simulation Symposium (EMSS-2011)
Country/Territory	Italy
City	Rome
Period	12/09/11 → 14/09/11

Keywords

cloud computing
cloud middleware
network topology
resilience
simulation

Access to Document

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available via Curran at http://www.proceedings.com/20411.html. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 3.55 MBLicence: Unspecified

Handle.net

Persistent link

Cite this

Cartlidge, J., & Sriram, I. L. (2014). Modelling Resilience in Cloud-Scale Data Centres. In A. Bruzzone, M. Piera, F. Longo, P. Elfrey, M. Affenzeller, & O. Balci (Eds.), 23rd European Modeling and Simulation Symposium (EMSS 2011): Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference (pp. 299-307). University of Genoa Press.

Cartlidge, John ; Sriram, Ilango L. / Modelling Resilience in Cloud-Scale Data Centres. 23rd European Modeling and Simulation Symposium (EMSS 2011): Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference . editor / Agostino Bruzzone ; Miquel Piera ; Francesco Longo ; Priscilla Elfrey ; Michael Affenzeller ; Osman Balci. University of Genoa Press, 2014. pp. 299-307

@inproceedings{a18d7633b76247d09e3a8d05fa67b3a6,

title = "Modelling Resilience in Cloud-Scale Data Centres",

abstract = "The trend for cloud computing has initiated a race towards data centres (DC) of an ever-increasing size. The largest DCs now contain many hundreds of thousands of virtual machine (VM) services. Given the finite lifespan of hardware, such large DCs are subject to frequent hardware failure events that can lead to disruption of service. To counter this, multiple redundant copies of task threads may be distributed around a DC to ensure that individual hardware failures do not cause entire jobs to fail. Here, we present results demonstrating the resilience of different job scheduling algorithms in a simulated DC with hardware failure. We use a simple model of jobs distributed across a hardware network to demonstrate the relationship between resilience and additional communication costs of different scheduling methods.",

keywords = "cloud computing, cloud middleware, network topology, resilience, simulation",

author = "John Cartlidge and Sriram, {Ilango L}",

year = "2014",

month = mar,

language = "English",

isbn = "9788890372445",

pages = "299--307",

editor = "Agostino Bruzzone and Miquel Piera and Francesco Longo and Priscilla Elfrey and Michael Affenzeller and Osman Balci",

booktitle = "23rd European Modeling and Simulation Symposium (EMSS 2011)",

publisher = "University of Genoa Press",

address = "Italy",

note = "23rd European Modeling & Simulation Symposium (EMSS-2011) ; Conference date: 12-09-2011 Through 14-09-2011",

}

Cartlidge, J & Sriram, IL 2014, Modelling Resilience in Cloud-Scale Data Centres. in A Bruzzone, M Piera, F Longo, P Elfrey, M Affenzeller & O Balci (eds), 23rd European Modeling and Simulation Symposium (EMSS 2011): Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference . University of Genoa Press, pp. 299-307, 23rd European Modeling & Simulation Symposium (EMSS-2011), Rome, Italy, 12/09/11.

Modelling Resilience in Cloud-Scale Data Centres. / Cartlidge, John; Sriram, Ilango L.
23rd European Modeling and Simulation Symposium (EMSS 2011): Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference . ed. / Agostino Bruzzone; Miquel Piera; Francesco Longo; Priscilla Elfrey; Michael Affenzeller; Osman Balci. University of Genoa Press, 2014. p. 299-307.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Modelling Resilience in Cloud-Scale Data Centres

AU - Cartlidge, John

AU - Sriram, Ilango L

PY - 2014/3

Y1 - 2014/3

N2 - The trend for cloud computing has initiated a race towards data centres (DC) of an ever-increasing size. The largest DCs now contain many hundreds of thousands of virtual machine (VM) services. Given the finite lifespan of hardware, such large DCs are subject to frequent hardware failure events that can lead to disruption of service. To counter this, multiple redundant copies of task threads may be distributed around a DC to ensure that individual hardware failures do not cause entire jobs to fail. Here, we present results demonstrating the resilience of different job scheduling algorithms in a simulated DC with hardware failure. We use a simple model of jobs distributed across a hardware network to demonstrate the relationship between resilience and additional communication costs of different scheduling methods.

AB - The trend for cloud computing has initiated a race towards data centres (DC) of an ever-increasing size. The largest DCs now contain many hundreds of thousands of virtual machine (VM) services. Given the finite lifespan of hardware, such large DCs are subject to frequent hardware failure events that can lead to disruption of service. To counter this, multiple redundant copies of task threads may be distributed around a DC to ensure that individual hardware failures do not cause entire jobs to fail. Here, we present results demonstrating the resilience of different job scheduling algorithms in a simulated DC with hardware failure. We use a simple model of jobs distributed across a hardware network to demonstrate the relationship between resilience and additional communication costs of different scheduling methods.

KW - cloud computing

KW - cloud middleware

KW - network topology

KW - resilience

KW - simulation

UR - http://arxiv.org/pdf/1106.5457

M3 - Conference Contribution (Conference Proceeding)

SN - 9788890372445

SP - 299

EP - 307

BT - 23rd European Modeling and Simulation Symposium (EMSS 2011)

A2 - Bruzzone, Agostino

A2 - Piera, Miquel

A2 - Longo, Francesco

A2 - Elfrey, Priscilla

A2 - Affenzeller, Michael

A2 - Balci, Osman

PB - University of Genoa Press

T2 - 23rd European Modeling & Simulation Symposium (EMSS-2011)

Y2 - 12 September 2011 through 14 September 2011

ER -

Cartlidge J, Sriram IL. Modelling Resilience in Cloud-Scale Data Centres. In Bruzzone A, Piera M, Longo F, Elfrey P, Affenzeller M, Balci O, editors, 23rd European Modeling and Simulation Symposium (EMSS 2011): Proceedings of a meeting held 12-14 September 2011, Rome, Italy. Held at the International Mediterranean and Latin American Modeling Multiconference . University of Genoa Press. 2014. p. 299-307 Epub 2011 Sept 12.

Modelling Resilience in Cloud-Scale Data Centres

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cloud computing for large scale complex IT systems.

LSCITS-RPV2: LARGE SCALE COMPLEX IT SYSTEMS INITIATIVE

Cite this

Modelling Resilience in Cloud-Scale Data Centres

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

Cloud computing for large scale complex IT systems.

LSCITS-RPV2: LARGE SCALE COMPLEX IT SYSTEMS INITIATIVE

Cite this