Hint-based cooperative caching

Prasenjit Sarkar, John H Hartman

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

This article presents the design, implementation, and measurement of a hint-based cooperative caching file system. Hints allow clients to make decisions based on local state, enabling a loosely coordinated system that is simple to implement. The resulting performance is comparable to that of existing tightly coordinated algorithms that use global state, but with less overhead. Simulations show that the block access times of our system are as good as those of the existing algorithms, while reducing manager load by more than a factor of seven, block lookup traffic by nearly a factor of two-thirds, and replacement traffic a factor of five. To verify our simulation results in a real system with real users, we implemented a prototype and measured its performance for one week. Although the simulation and prototype environments were very different, the prototype system mirrored the simulation results by exhibiting reduced overhead and high hint accuracy. Furthermore, hint-based cooperative caching reduced the average block access time to almost half that of NFS.

Original languageEnglish (US)
Pages (from-to)387-419
Number of pages33
JournalACM Transactions on Computer Systems
Volume18
Issue number4
StatePublished - Nov 2000

Fingerprint

Cooperative Caching
Prototype
Simulation
Managers
Traffic
File System
Replacement
High Accuracy
Verify

Keywords

  • Algorithms
  • Cooperative caching
  • D.4.3 [Operating Systems]
  • Design
  • File Systems Management
  • Hints
  • Measurement
  • Performance

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Hint-based cooperative caching. / Sarkar, Prasenjit; Hartman, John H.

In: ACM Transactions on Computer Systems, Vol. 18, No. 4, 11.2000, p. 387-419.

Research output: Contribution to journalArticle

Sarkar, Prasenjit ; Hartman, John H. / Hint-based cooperative caching. In: ACM Transactions on Computer Systems. 2000 ; Vol. 18, No. 4. pp. 387-419.
@article{b1c080d4623a40328c0e955663bb0946,
title = "Hint-based cooperative caching",
abstract = "This article presents the design, implementation, and measurement of a hint-based cooperative caching file system. Hints allow clients to make decisions based on local state, enabling a loosely coordinated system that is simple to implement. The resulting performance is comparable to that of existing tightly coordinated algorithms that use global state, but with less overhead. Simulations show that the block access times of our system are as good as those of the existing algorithms, while reducing manager load by more than a factor of seven, block lookup traffic by nearly a factor of two-thirds, and replacement traffic a factor of five. To verify our simulation results in a real system with real users, we implemented a prototype and measured its performance for one week. Although the simulation and prototype environments were very different, the prototype system mirrored the simulation results by exhibiting reduced overhead and high hint accuracy. Furthermore, hint-based cooperative caching reduced the average block access time to almost half that of NFS.",
keywords = "Algorithms, Cooperative caching, D.4.3 [Operating Systems], Design, File Systems Management, Hints, Measurement, Performance",
author = "Prasenjit Sarkar and Hartman, {John H}",
year = "2000",
month = "11",
language = "English (US)",
volume = "18",
pages = "387--419",
journal = "ACM Transactions on Computer Systems",
issn = "0734-2071",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Hint-based cooperative caching

AU - Sarkar, Prasenjit

AU - Hartman, John H

PY - 2000/11

Y1 - 2000/11

N2 - This article presents the design, implementation, and measurement of a hint-based cooperative caching file system. Hints allow clients to make decisions based on local state, enabling a loosely coordinated system that is simple to implement. The resulting performance is comparable to that of existing tightly coordinated algorithms that use global state, but with less overhead. Simulations show that the block access times of our system are as good as those of the existing algorithms, while reducing manager load by more than a factor of seven, block lookup traffic by nearly a factor of two-thirds, and replacement traffic a factor of five. To verify our simulation results in a real system with real users, we implemented a prototype and measured its performance for one week. Although the simulation and prototype environments were very different, the prototype system mirrored the simulation results by exhibiting reduced overhead and high hint accuracy. Furthermore, hint-based cooperative caching reduced the average block access time to almost half that of NFS.

AB - This article presents the design, implementation, and measurement of a hint-based cooperative caching file system. Hints allow clients to make decisions based on local state, enabling a loosely coordinated system that is simple to implement. The resulting performance is comparable to that of existing tightly coordinated algorithms that use global state, but with less overhead. Simulations show that the block access times of our system are as good as those of the existing algorithms, while reducing manager load by more than a factor of seven, block lookup traffic by nearly a factor of two-thirds, and replacement traffic a factor of five. To verify our simulation results in a real system with real users, we implemented a prototype and measured its performance for one week. Although the simulation and prototype environments were very different, the prototype system mirrored the simulation results by exhibiting reduced overhead and high hint accuracy. Furthermore, hint-based cooperative caching reduced the average block access time to almost half that of NFS.

KW - Algorithms

KW - Cooperative caching

KW - D.4.3 [Operating Systems]

KW - Design

KW - File Systems Management

KW - Hints

KW - Measurement

KW - Performance

UR - http://www.scopus.com/inward/record.url?scp=0038023772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038023772&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0038023772

VL - 18

SP - 387

EP - 419

JO - ACM Transactions on Computer Systems

JF - ACM Transactions on Computer Systems

SN - 0734-2071

IS - 4

ER -