Disk space guarantees as a distributed resource management problem: a case study

Murthy Devarakonda; Ananda Rao Ladi; Andy Zlotek; Ajay Mohindra

Disk space guarantees as a distributed resource management problem: a case study

Murthy Devarakonda, Ananda Rao Ladi, Andy Zlotek, Ajay Mohindra

Research output: Contribution to journal › Conference article › peer-review

Abstract

In the single system UNIX, successful completion of a write system call implies a guarantee of adequate disk space for any new pages created by the system call. To support such a guarantee in a distributed file system designers need to solve the problems of accurately estimating the space needed, communication overhead, and fault tolerance. In the Calypso file system, which is a cluster-optimized, distributed UNIX file system, we solve these problems using an advance-reservation scheme. Measurements show that the overhead of this scheme for typical UNIX usage patterns is 1% to 3%.

Original language	English (US)
Pages (from-to)	289-292
Number of pages	4
Journal	IEEE Symposium on Parallel and Distributed Processing - Proceedings
State	Published - Dec 1 1995
Externally published	Yes
Event	Proceedings of the 1995 7th IEEE Symposium on Parallel and Distributed Processing - San Antonio, TX, USA Duration: Oct 25 1995 → Oct 28 1995

ASJC Scopus subject areas

General Engineering

Cite this

@article{76ed8f99e2c04caa9e5f2116a049f14a,

title = "Disk space guarantees as a distributed resource management problem: a case study",

abstract = "In the single system UNIX, successful completion of a write system call implies a guarantee of adequate disk space for any new pages created by the system call. To support such a guarantee in a distributed file system designers need to solve the problems of accurately estimating the space needed, communication overhead, and fault tolerance. In the Calypso file system, which is a cluster-optimized, distributed UNIX file system, we solve these problems using an advance-reservation scheme. Measurements show that the overhead of this scheme for typical UNIX usage patterns is 1% to 3%.",

author = "Murthy Devarakonda and Ladi, {Ananda Rao} and Andy Zlotek and Ajay Mohindra",

year = "1995",

month = dec,

day = "1",

language = "English (US)",

pages = "289--292",

journal = "IEEE Symposium on Parallel and Distributed Processing - Proceedings",

issn = "1063-6374",

note = "Proceedings of the 1995 7th IEEE Symposium on Parallel and Distributed Processing ; Conference date: 25-10-1995 Through 28-10-1995",

}

TY - JOUR

T1 - Disk space guarantees as a distributed resource management problem

T2 - Proceedings of the 1995 7th IEEE Symposium on Parallel and Distributed Processing

AU - Devarakonda, Murthy

AU - Ladi, Ananda Rao

AU - Zlotek, Andy

AU - Mohindra, Ajay

PY - 1995/12/1

Y1 - 1995/12/1

N2 - In the single system UNIX, successful completion of a write system call implies a guarantee of adequate disk space for any new pages created by the system call. To support such a guarantee in a distributed file system designers need to solve the problems of accurately estimating the space needed, communication overhead, and fault tolerance. In the Calypso file system, which is a cluster-optimized, distributed UNIX file system, we solve these problems using an advance-reservation scheme. Measurements show that the overhead of this scheme for typical UNIX usage patterns is 1% to 3%.

AB - In the single system UNIX, successful completion of a write system call implies a guarantee of adequate disk space for any new pages created by the system call. To support such a guarantee in a distributed file system designers need to solve the problems of accurately estimating the space needed, communication overhead, and fault tolerance. In the Calypso file system, which is a cluster-optimized, distributed UNIX file system, we solve these problems using an advance-reservation scheme. Measurements show that the overhead of this scheme for typical UNIX usage patterns is 1% to 3%.

UR - http://www.scopus.com/inward/record.url?scp=0029530487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029530487&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0029530487

SN - 1063-6374

SP - 289

EP - 292

JO - IEEE Symposium on Parallel and Distributed Processing - Proceedings

JF - IEEE Symposium on Parallel and Distributed Processing - Proceedings

Y2 - 25 October 1995 through 28 October 1995

ER -

Disk space guarantees as a distributed resource management problem: a case study

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this