Replication in the Harp File System

Download: pdf.

“Replication in the Harp File System” by Barbara Liskov, Sanjay Ghemawat, Robert Gruber, Paul Johnson, Liuba Shrira, and Michael Williams. In 13th ACM Symposium on Operating Systems Principles (SOSP), (Pacific Grove, CA), Oct. 1991. Also as Technical Memo MIT/LCS/TM-456, MIT Laboratory for Computer Science, Cambridge, MA, August 1991.

Abstract

This paper describes the design and implementation of the Harp file system. Harp is a replicated Unix file system accessible via the VFS interface. It provides highly available and reliable storage for files and guarantees that file operations are executed atomically in spite of concurrency and failures. It uses a novel variation of the primary copy replication technique that provides good performance because it allows us to trade disk accesses for network communication. Harp is intended to be used within a file service in a distributed network; in our current implementation, it is accessed via NFS. Preliminary performance results indicate that Harp provides equal or better response time and system capacity than an unreplicated implementation of NFS that uses Unix files directly.

Download: pdf.

BibTeX entry:

@inproceedings{liskov91replication,
   author = {Barbara Liskov and Sanjay Ghemawat and Robert Gruber and Paul
	Johnson and Liuba Shrira and Michael Williams},
   title = {Replication in the Harp File System},
   booktitle = {13th ACM Symposium on Operating Systems Principles (SOSP)},
   address = {Pacific Grove, CA},
   month = oct,
   year = {1991},
   note = {Also as Technical Memo MIT/LCS/TM-456, MIT Laboratory for
	Computer Science, Cambridge, MA, August 1991}
}