Fault-tolerant bandwidth reservation strategies for data transfers in high-performance networks

Liudong Zuo, Michelle Zhu, Chase Q. Wu, Jason Zurawski

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

Many next-generation e-science applications require fast and reliable transfer of large volumes of data with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks. One prominent issue in such network environments with large footprints is that node and link failures are inevitable, hence potentially degrading the quality of data transfer. We consider two generic types of bandwidth reservation requests (BRRs) concerning data transfer reliability: (i) to achieve the highest data transfer reliability under a given data transfer deadline, and (ii) to achieve the earliest data transfer completion time while satisfying a given data transfer reliability requirement. We propose two periodic bandwidth reservation algorithms with rigorous optimality proofs to optimize the scheduling of individual BRRs within BRR batches. The efficacy of the proposed algorithms is illustrated through extensive simulations in comparison with scheduling algorithms widely adopted in production networks in terms of various performance metrics.

Original languageEnglish
Pages (from-to)1-16
Number of pages16
JournalComputer Networks
Volume113
DOIs
StatePublished - 11 Feb 2017

Fingerprint

Data transfer
Network performance
Bandwidth
Scheduling algorithms
Scheduling

Keywords

  • Bandwidth reservation
  • Bandwidth scheduling
  • Dynamic provisioning
  • Fault tolerance
  • High-performance networks

Cite this

@article{aaec489d5da94be7bf794ebca332d15d,
title = "Fault-tolerant bandwidth reservation strategies for data transfers in high-performance networks",
abstract = "Many next-generation e-science applications require fast and reliable transfer of large volumes of data with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks. One prominent issue in such network environments with large footprints is that node and link failures are inevitable, hence potentially degrading the quality of data transfer. We consider two generic types of bandwidth reservation requests (BRRs) concerning data transfer reliability: (i) to achieve the highest data transfer reliability under a given data transfer deadline, and (ii) to achieve the earliest data transfer completion time while satisfying a given data transfer reliability requirement. We propose two periodic bandwidth reservation algorithms with rigorous optimality proofs to optimize the scheduling of individual BRRs within BRR batches. The efficacy of the proposed algorithms is illustrated through extensive simulations in comparison with scheduling algorithms widely adopted in production networks in terms of various performance metrics.",
keywords = "Bandwidth reservation, Bandwidth scheduling, Dynamic provisioning, Fault tolerance, High-performance networks",
author = "Liudong Zuo and Michelle Zhu and Wu, {Chase Q.} and Jason Zurawski",
year = "2017",
month = "2",
day = "11",
doi = "10.1016/j.comnet.2016.11.003",
language = "English",
volume = "113",
pages = "1--16",
journal = "Computer Networks",
issn = "1389-1286",
publisher = "Elsevier",

}

Fault-tolerant bandwidth reservation strategies for data transfers in high-performance networks. / Zuo, Liudong; Zhu, Michelle; Wu, Chase Q.; Zurawski, Jason.

In: Computer Networks, Vol. 113, 11.02.2017, p. 1-16.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Fault-tolerant bandwidth reservation strategies for data transfers in high-performance networks

AU - Zuo, Liudong

AU - Zhu, Michelle

AU - Wu, Chase Q.

AU - Zurawski, Jason

PY - 2017/2/11

Y1 - 2017/2/11

N2 - Many next-generation e-science applications require fast and reliable transfer of large volumes of data with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks. One prominent issue in such network environments with large footprints is that node and link failures are inevitable, hence potentially degrading the quality of data transfer. We consider two generic types of bandwidth reservation requests (BRRs) concerning data transfer reliability: (i) to achieve the highest data transfer reliability under a given data transfer deadline, and (ii) to achieve the earliest data transfer completion time while satisfying a given data transfer reliability requirement. We propose two periodic bandwidth reservation algorithms with rigorous optimality proofs to optimize the scheduling of individual BRRs within BRR batches. The efficacy of the proposed algorithms is illustrated through extensive simulations in comparison with scheduling algorithms widely adopted in production networks in terms of various performance metrics.

AB - Many next-generation e-science applications require fast and reliable transfer of large volumes of data with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks. One prominent issue in such network environments with large footprints is that node and link failures are inevitable, hence potentially degrading the quality of data transfer. We consider two generic types of bandwidth reservation requests (BRRs) concerning data transfer reliability: (i) to achieve the highest data transfer reliability under a given data transfer deadline, and (ii) to achieve the earliest data transfer completion time while satisfying a given data transfer reliability requirement. We propose two periodic bandwidth reservation algorithms with rigorous optimality proofs to optimize the scheduling of individual BRRs within BRR batches. The efficacy of the proposed algorithms is illustrated through extensive simulations in comparison with scheduling algorithms widely adopted in production networks in terms of various performance metrics.

KW - Bandwidth reservation

KW - Bandwidth scheduling

KW - Dynamic provisioning

KW - Fault tolerance

KW - High-performance networks

UR - http://www.scopus.com/inward/record.url?scp=85000893445&partnerID=8YFLogxK

U2 - 10.1016/j.comnet.2016.11.003

DO - 10.1016/j.comnet.2016.11.003

M3 - Article

VL - 113

SP - 1

EP - 16

JO - Computer Networks

JF - Computer Networks

SN - 1389-1286

ER -