Hint-based cooperative caching

  • Authors:
  • Prasenjit Sarkar;John H. Hartman

  • Affiliations:
  • IBM Almaden Research Center, Tucson, AZ;Univ. of Arizona, Tucson, AZ

  • Venue:
  • ACM Transactions on Computer Systems (TOCS)
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

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.