Cluster delegation: high-performance, fault-tolerant data sharing in NFS

Authors:
A. Batsakis;R. Burns
Affiliations:
Dept. of Comput. Sci., Johns Hopkins Univ., Baltimore, MD, USA;Dept. of Comput. Sci., Johns Hopkins Univ., Baltimore, MD, USA
Venue:
HPDC '05 Proceedings of the High Performance Distributed Computing, 2005. HPDC-14. Proceedings. 14th IEEE International Symposium
Year:
2005

Citing 0
Cited 3

Direct-pNFS: scalable, transparent, and versatile access to parallel file systems

Proceedings of the 16th international symposium on High performance distributed computing
Efficient access to many samall files in a filesystem for grid computing

GRID '07 Proceedings of the 8th IEEE/ACM International Conference on Grid Computing
Load balancing and fault-tolerance for scalable network file systems using by web services

ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present cluster delegation, an enhancement to the NFSv4 file system, that improves both performance and recoverability in computing clusters. Cluster delegation allows data sharing among clients by extending the NFSv4 delegation model so that multiple clients manage a single file without interacting with the server. Based on cluster delegation, we implement a fast commit primitive, cooperative caching, and the ability to recover the uncommitted updates of a failed computer. Cluster delegation supports both read and write operations in the cooperative cache, while preserving the consistency guarantees of NFSv4. We have implemented cluster delegation by modifying the Linux NFSv4 client and show that it improves client performance and reduces server load by more than half.