Separating Data From Function in a Distributed File System

IP.com Prior Art Database Disclosure
IP.com Disclosure Number: IPCOM000128883D
Publication Date: 31-Dec-1978
Find Similar Download

Publishing Venue

Software Patent Institute

Related People

Jay E. Israel - Author [+3] [-3]
James G. Mitchell - Author
Massachusetts Institute of Technology - Owner
Yale University Computer Science Library

Abstract

This paper discusses an independent file facility, one that is not embedded in an operating system. The distributed file system (DFS) is so named because it is implemented on a cooperating set of server computers connected by a communications network, w hich together create the illusion of a single, logical system for the creation, deletion, and random accessing of data. Access to the DFS can only be accomplished over the network; a computer (or, more precisely, a program running on orre) that uses the DFS is called a client. This paper describes the division of responsibility between servers and clients. We discuss examples of situations in which a client is expected to take prescribed steps in order to achieve its intended result. The basic tool for maintaining data consistency in these situations is the atomic property of file actions. This is a DFS feature that protects clients from system malfunctions and from the competing activities of other clients. We have implemented an experimental system based on these concepts.

Language

English (United States)

Country

United States

Document File

12 pages / 43.1 KB

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 9% of the total text.

Page 1 of 12

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

Separating Data From Function in a Distributed File System

by Jay E. Israel, James G. Mitchell and Howard E. Sturgis

CSL-78-5 September 1978

This paper discusses an independent file facility, one that is not embedded in an operating system. The distributed file system (DFS) is so named because it is implemented on a cooperating set of server computers connected by a communications network, w hich together create the illusion of a single, logical system for the creation, deletion, and random accessing of data. Access to the DFS can only be accomplished over the network; a computer (or, more precisely, a program running on orre) that uses the DFS is called a client. This paper describes the division of responsibility between servers and clients. We discuss examples of situations in which a client is expected to take prescribed steps in order to achieve its intended result. The basic tool for maintaining data consistency in these situations is the atomic property of file actions. This is a DFS feature that protects clients from system malfunctions and from the competing activities of other clients. We have implemented an experimental system based on these concepts.

KEY WORDS AND PHRASES:

file systems, computer networks, databases, distributed systems, file structures

CR CATEGORIES.-

3.73,4.33

XEROX PALO ALTO RESEARCH CENTER 3333 Coyote Hill Road / Palo Alto / California 94304

1. Introduction

One of the primary functions of an operating system is providing a file storage capability (as well as allocating processor and memory resources, etc.); this paper discusses an independent file facility that is not embedded in an operating system, This file system operates in a distributed environment with a number of computers of several types connected by a high-bandwidth, communications network [1] and can only be accessed over this network., We have implemented an experimental version of ~ the system.

The distributed file system (DFS) is so named because it is impleme nted on a cooperating set of server computers which together create the illusion of a single, logical system. The other computers in the network that use the DFS for creating, destroying, and randomly accessing files are called its clients (we employ the term "user" to stand only for human users; programs that access the DFS are always called clients).

Structuring the DIFS using a set of servers is partly motivated by the economics of disk storage devices. Using rather small computers as file servers permits a wide range of file storage capacity because it is possible to expand a DFS from a single minicomputer with one disk drive,

Massachusetts Institute of Technology Page 1 Dec 31, 1978

Page 2 of 12

Separating Data From Function in a Distributed File System

to many servers, each with a number of disks. It also allows one to vary the ratio of processing power to disk capacity over a wide range to suit a variety of...

First page image
You are not signed in. If you have an IP.com account, your download price may be lower or waived. Click here if you want to sign-in now.
Loading PayPal...
The full document comprises 12 pages and is available as a PDF document as well as a ZIP archive. The cost is $40.00 USD (depending on your billing address, sales tax may apply); payment may be made directly using your credit card or your PayPal account.

If you've already purchased this document, and wish to download it now you may enter the download access code you received in your original email receipt.