nfsp: a distributed NFS server for clusters of workstations

Lombard, Pierre; Denneulin, Yves

doi:10.1109/ipdps.2002.1015512

Cited by 16 publications

(18 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[14]), so that we argue that the ordering of accesses does not influence the performance significantly. Additionally, by activating the ordering (comparing results of VII-D), we could not notice a significant performance degradation.…”

Section: E Discussionmentioning

confidence: 75%

“…At the current state, fault tolerance is not taken into account but is planned for future developments. nfsp [14] is near to PVFS, but directly compatible to the NFS protocol. Data is stored in stripes over several cluster nodes.…”

Section: Related Workmentioning

confidence: 99%

“…It is feasible to reach faster access by using multiple disk subsystems and file systems in parallel which also provides tolerance against single disk and node failures. Examples for systems applying such a technique are given in [1], [5], [7], [8], [14]. For this study, we used an implementation of a RAID-level-3-like storage scheme which was developed by ourselves, called netRAID.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data consistent up- and downstreaming in a distributed storage system

Sobe

2003

Proceedings of the International Workshop on Storage Network Architecture and Parallel I/Os - SNAPI '03

View full text Add to dashboard Cite

Abstract-Distribution of large data objects among several storage servers is a common technique to speed up access rates. In combination with parity schemes, failures of single server nodes can be tolerated, so that such systems reach a certain degree of fault tolerance. In this paper such a distributed server system is analyzed. Data objects are stored in a data layout according to RAID level 3 among disk subsystems of different computers. An access control provides concurrent up-and down-streaming of data objects to/from the distributed storage system with ensured data consistency. This consistency control is described in combination with the handling of faulty server nodes and faulty clients. Furthermore, performance is measured with several access patterns. An application of that technique is for instance a distributed video server, allowing permanently updates without interrupting access.

show abstract

Section: E Discussionmentioning

confidence: 75%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data consistent up- and downstreaming in a distributed storage system

Sobe

2003

Proceedings of the International Workshop on Storage Network Architecture and Parallel I/Os - SNAPI '03

View full text Add to dashboard Cite

show abstract

“…Parallel file systems try to solve such problem by aggregating the I/O ability of multiple servers. Most parallel file systems [2,4,5] do their best to achieve good scalability and unlimited high aggregated I/O performance. However, in reality, the scale of cluster machine for most scientific computing applications is not so large.…”

Section: Introductionmentioning

confidence: 99%

United-FS: A Logical File System Providing a Single Image of Multiple Physical File Systems on NFS Server

Chen¹,

Zhao²,

Xiong³

et al. 2007

2007 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…Unlike AFS and CODA distributed file system, NFS server was designed to work on a single host resulting in relatively poor scalability. Several research such as NFSp [1] and DirectNFS [2] has been conducted to improve its performance and scalability. Bigfoot-NFS [3] allows multiple NFS file servers to use transparently their aggregate space as a single file system.…”

Section: Introductionmentioning

confidence: 99%

mNFS: Multicast-Based NFS Cluster

Lee

Park

Kim

2004

Computational Science - ICCS 2004

View full text Add to dashboard Cite

Abstract. NFS is a distributed file system which is widely used in UNIX environments. Many studies have been worked to improve its I/O performance and scalability. However, existing architectures, which have either single load balancer or meta server, could suffer from single-pointof-failure and unnecessary network delay. We propose a new NFS architecture called mNFS cluster to improve its scalability. Experimental results show that mNFS outperforms both Linux NFS and NFSp by 64% and 99%, respectively.

show abstract

nfsp: a distributed NFS server for clusters of workstations

Cited by 16 publications

References 5 publications

Data consistent up- and downstreaming in a distributed storage system

Data consistent up- and downstreaming in a distributed storage system

United-FS: A Logical File System Providing a Single Image of Multiple Physical File Systems on NFS Server

mNFS: Multicast-Based NFS Cluster

Contact Info

Product

Resources

About