Application-tailored cache consistency for wide-area file systems

Ming Zhao, Renato J. Figueiredo

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

5 Citations (Scopus)

Abstract

The inability to perform optimizations based on application-specific information presents a hurdle to the deployment of pervasive LAN file systems across WAN environments. This paper proposes a novel approach addressing this problem through application-tailored caching and consistency in wide-area file systems. It leverages widely available Network File System (NFS) deployments without any modifications to kernels nor applications, and employs middleware to dynamically establish Grid-wide Virtual File System (GVFS) sessions with application-tailored cache consistency. Two consistency models are discussed in this paper: a relaxed model based on invalidation polling, and a stronger model based on delegation and callback. Experimental evaluation based on microbenchmarks and scientific applications show that with application-tailored cache consistency, GVFS is able to both improve application runtimes and reduce server load significantly, compared to kernel-level NFS in WAN.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Distributed Computing Systems
Volume2006
DOIs
StatePublished - 2006
Externally publishedYes
Event26th IEEE Internationa26th IEEE International Conference on Distributed Computing Systems, ICDCS 2006 - Lisboa, Portugal
Duration: Jul 4 2006Jul 7 2006

Other

Other26th IEEE Internationa26th IEEE International Conference on Distributed Computing Systems, ICDCS 2006
CountryPortugal
CityLisboa
Period7/4/067/7/06

Fingerprint

Wide area networks
Middleware
Local area networks
Computer systems
Servers

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Zhao, M., & Figueiredo, R. J. (2006). Application-tailored cache consistency for wide-area file systems. In Proceedings - International Conference on Distributed Computing Systems (Vol. 2006). [1648828] https://doi.org/10.1109/ICDCS.2006.17

Application-tailored cache consistency for wide-area file systems. / Zhao, Ming; Figueiredo, Renato J.

Proceedings - International Conference on Distributed Computing Systems. Vol. 2006 2006. 1648828.

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

Zhao, M & Figueiredo, RJ 2006, Application-tailored cache consistency for wide-area file systems. in Proceedings - International Conference on Distributed Computing Systems. vol. 2006, 1648828, 26th IEEE Internationa26th IEEE International Conference on Distributed Computing Systems, ICDCS 2006, Lisboa, Portugal, 7/4/06. https://doi.org/10.1109/ICDCS.2006.17
Zhao M, Figueiredo RJ. Application-tailored cache consistency for wide-area file systems. In Proceedings - International Conference on Distributed Computing Systems. Vol. 2006. 2006. 1648828 https://doi.org/10.1109/ICDCS.2006.17
Zhao, Ming ; Figueiredo, Renato J. / Application-tailored cache consistency for wide-area file systems. Proceedings - International Conference on Distributed Computing Systems. Vol. 2006 2006.
@inproceedings{0d4fcabd843048a0871622b5597a32e9,
title = "Application-tailored cache consistency for wide-area file systems",
abstract = "The inability to perform optimizations based on application-specific information presents a hurdle to the deployment of pervasive LAN file systems across WAN environments. This paper proposes a novel approach addressing this problem through application-tailored caching and consistency in wide-area file systems. It leverages widely available Network File System (NFS) deployments without any modifications to kernels nor applications, and employs middleware to dynamically establish Grid-wide Virtual File System (GVFS) sessions with application-tailored cache consistency. Two consistency models are discussed in this paper: a relaxed model based on invalidation polling, and a stronger model based on delegation and callback. Experimental evaluation based on microbenchmarks and scientific applications show that with application-tailored cache consistency, GVFS is able to both improve application runtimes and reduce server load significantly, compared to kernel-level NFS in WAN.",
author = "Ming Zhao and Figueiredo, {Renato J.}",
year = "2006",
doi = "10.1109/ICDCS.2006.17",
language = "English (US)",
isbn = "0769525407",
volume = "2006",
booktitle = "Proceedings - International Conference on Distributed Computing Systems",

}

TY - GEN

T1 - Application-tailored cache consistency for wide-area file systems

AU - Zhao, Ming

AU - Figueiredo, Renato J.

PY - 2006

Y1 - 2006

N2 - The inability to perform optimizations based on application-specific information presents a hurdle to the deployment of pervasive LAN file systems across WAN environments. This paper proposes a novel approach addressing this problem through application-tailored caching and consistency in wide-area file systems. It leverages widely available Network File System (NFS) deployments without any modifications to kernels nor applications, and employs middleware to dynamically establish Grid-wide Virtual File System (GVFS) sessions with application-tailored cache consistency. Two consistency models are discussed in this paper: a relaxed model based on invalidation polling, and a stronger model based on delegation and callback. Experimental evaluation based on microbenchmarks and scientific applications show that with application-tailored cache consistency, GVFS is able to both improve application runtimes and reduce server load significantly, compared to kernel-level NFS in WAN.

AB - The inability to perform optimizations based on application-specific information presents a hurdle to the deployment of pervasive LAN file systems across WAN environments. This paper proposes a novel approach addressing this problem through application-tailored caching and consistency in wide-area file systems. It leverages widely available Network File System (NFS) deployments without any modifications to kernels nor applications, and employs middleware to dynamically establish Grid-wide Virtual File System (GVFS) sessions with application-tailored cache consistency. Two consistency models are discussed in this paper: a relaxed model based on invalidation polling, and a stronger model based on delegation and callback. Experimental evaluation based on microbenchmarks and scientific applications show that with application-tailored cache consistency, GVFS is able to both improve application runtimes and reduce server load significantly, compared to kernel-level NFS in WAN.

UR - http://www.scopus.com/inward/record.url?scp=33947669951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947669951&partnerID=8YFLogxK

U2 - 10.1109/ICDCS.2006.17

DO - 10.1109/ICDCS.2006.17

M3 - Conference contribution

AN - SCOPUS:33947669951

SN - 0769525407

SN - 9780769525402

VL - 2006

BT - Proceedings - International Conference on Distributed Computing Systems

ER -