Title
NFS-cc: tuning NFS for concurrent read sharing
Abstract
A common file access pattern found in cluster applications is concurrent read sharing: applications running on multiple sites read access the same data set concurrently. Traditional network file systems are limited by the server's network bandwidth; therefore, it cannot satisfy the high-bandwidth concurrent reads that cluster applications typically require. This paper presents NFS-cc; a cooperative caching file system based on NFS and optimised for concurrent read sharing. Cooperative caching used by NFS-cc is a distributed file caching scheme, which allows file system clients to read data from the memory of other clients, instead of the server. If multiple clients cache the same data, they can supply the data to other clients concurrently, which greatly reduces the contention for the server's network bandwidth. NFS-cc exploits clients' bandwidth and file caches to improve the aggregate read throughput of the file system. Our preliminary performance measurements show that the aggregate read throughput of NFS-cc was increased with the number of clients and reached as high as 42.6 MB/s with 12 clients connected by a fast Ethernet. NFS-cc also reduced the average block read time by a factor of 50 80% under a variety of concurrent read access patterns when compared with NFS.
Year
DOI
Venue
2004
10.1504/IJHPCN.2004.008349
IJHPCN
Keywords
Field
DocType
file system,clients concurrently,index terms—cooperative caching,aggregate read throughput,cluster application,file system client,network file system,cooperative caching file system,network bandwidth,concurrent read access pattern,common file access pattern,cluster,concurrent read sharing,tuning nfs,indexing terms,satisfiability,high performance computing,network file systems
SSH File Transfer Protocol,File system,Virtual file system,Stub file,Computer science,Computer network,Distributed computing,File server,Self-certifying File System,Parallel computing,Versioning file system,Network File System,Operating system
Journal
Volume
Issue
Citations 
1
4
8
PageRank 
References 
Authors
0.58
12
2
Name
Order
Citations
PageRank
Ying Xu1629.43
Brett D. Fleisch220941.08