Scafida

A scale-free network inspired data center architecture

Laszlo Gyarmati, Tuan Anh Trinh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

Data centers have a crucial role in current Internet architecture supporting content-centric networking. State-of-the-art data centers have different architectures like fat-tree [16, 10], DCell [12], or BCube [11]. However, their architectures share a common property: symmetry. Due to their symmetric nature, a tricky point with these architectures is that they are hard to be extended in small quantities. Contrary to state-of-the-art data center architectures, we propose an asymmetric data center topology generation method called Scafida inspired by scale-free networks; these data centers have not only small diameters and high fault tolerance, inherited by scale-free networks, but can also be scaled in smaller and less homogenous increments. We extend the original scale-free network generation algorithm of Barabási and Albert [5] to meet the physical constraints of switches and routers. Despite the fact that our method artificially limits the node degrees in the network, our data center architectures keep the preferable properties of scale-free networks. Based on extensive simulations we present preliminary results that are promising regarding the error tolerance, scalability, and flexibility of the architecture.

Original languageEnglish
Title of host publicationSIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference
Pages5-12
Number of pages8
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event7th International Conference on Autonomic Computing, SIGCOMM 2010 - New Delhi, India
Duration: 30 Aug 20103 Sep 2010

Other

Other7th International Conference on Autonomic Computing, SIGCOMM 2010
CountryIndia
CityNew Delhi
Period30/8/103/9/10

Fingerprint

Data Center
Scale-free Networks
Complex networks
Fault tolerance
Oils and fats
Routers
Scalability
Switches
Topology
Internet
Architecture
Router
Fault Tolerance
Networking
Increment
Tolerance
Switch
Flexibility
Symmetry
Vertex of a graph

Keywords

  • Data center
  • Scale-free network

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Gyarmati, L., & Trinh, T. A. (2010). Scafida: A scale-free network inspired data center architecture. In SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference (pp. 5-12)

Scafida : A scale-free network inspired data center architecture. / Gyarmati, Laszlo; Trinh, Tuan Anh.

SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference. 2010. p. 5-12.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gyarmati, L & Trinh, TA 2010, Scafida: A scale-free network inspired data center architecture. in SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference. pp. 5-12, 7th International Conference on Autonomic Computing, SIGCOMM 2010, New Delhi, India, 30/8/10.
Gyarmati L, Trinh TA. Scafida: A scale-free network inspired data center architecture. In SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference. 2010. p. 5-12
Gyarmati, Laszlo ; Trinh, Tuan Anh. / Scafida : A scale-free network inspired data center architecture. SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference. 2010. pp. 5-12
@inproceedings{0822b0422f32428c90e5537d7bafb2a5,
title = "Scafida: A scale-free network inspired data center architecture",
abstract = "Data centers have a crucial role in current Internet architecture supporting content-centric networking. State-of-the-art data centers have different architectures like fat-tree [16, 10], DCell [12], or BCube [11]. However, their architectures share a common property: symmetry. Due to their symmetric nature, a tricky point with these architectures is that they are hard to be extended in small quantities. Contrary to state-of-the-art data center architectures, we propose an asymmetric data center topology generation method called Scafida inspired by scale-free networks; these data centers have not only small diameters and high fault tolerance, inherited by scale-free networks, but can also be scaled in smaller and less homogenous increments. We extend the original scale-free network generation algorithm of Barab{\'a}si and Albert [5] to meet the physical constraints of switches and routers. Despite the fact that our method artificially limits the node degrees in the network, our data center architectures keep the preferable properties of scale-free networks. Based on extensive simulations we present preliminary results that are promising regarding the error tolerance, scalability, and flexibility of the architecture.",
keywords = "Data center, Scale-free network",
author = "Laszlo Gyarmati and Trinh, {Tuan Anh}",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "9781450302012",
pages = "5--12",
booktitle = "SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference",

}

TY - GEN

T1 - Scafida

T2 - A scale-free network inspired data center architecture

AU - Gyarmati, Laszlo

AU - Trinh, Tuan Anh

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Data centers have a crucial role in current Internet architecture supporting content-centric networking. State-of-the-art data centers have different architectures like fat-tree [16, 10], DCell [12], or BCube [11]. However, their architectures share a common property: symmetry. Due to their symmetric nature, a tricky point with these architectures is that they are hard to be extended in small quantities. Contrary to state-of-the-art data center architectures, we propose an asymmetric data center topology generation method called Scafida inspired by scale-free networks; these data centers have not only small diameters and high fault tolerance, inherited by scale-free networks, but can also be scaled in smaller and less homogenous increments. We extend the original scale-free network generation algorithm of Barabási and Albert [5] to meet the physical constraints of switches and routers. Despite the fact that our method artificially limits the node degrees in the network, our data center architectures keep the preferable properties of scale-free networks. Based on extensive simulations we present preliminary results that are promising regarding the error tolerance, scalability, and flexibility of the architecture.

AB - Data centers have a crucial role in current Internet architecture supporting content-centric networking. State-of-the-art data centers have different architectures like fat-tree [16, 10], DCell [12], or BCube [11]. However, their architectures share a common property: symmetry. Due to their symmetric nature, a tricky point with these architectures is that they are hard to be extended in small quantities. Contrary to state-of-the-art data center architectures, we propose an asymmetric data center topology generation method called Scafida inspired by scale-free networks; these data centers have not only small diameters and high fault tolerance, inherited by scale-free networks, but can also be scaled in smaller and less homogenous increments. We extend the original scale-free network generation algorithm of Barabási and Albert [5] to meet the physical constraints of switches and routers. Despite the fact that our method artificially limits the node degrees in the network, our data center architectures keep the preferable properties of scale-free networks. Based on extensive simulations we present preliminary results that are promising regarding the error tolerance, scalability, and flexibility of the architecture.

KW - Data center

KW - Scale-free network

UR - http://www.scopus.com/inward/record.url?scp=82155173979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82155173979&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781450302012

SP - 5

EP - 12

BT - SIGCOMM'10 - Proceedings of the SIGCOMM 2010 Conference

ER -