Group-based management of distributed file caches

Appeared in Proceedings of the 22nd International Conference on Distributed Computing Systems (ICDCS '02).

Abstract

We describe how to manage distributed file system caches based upon groups of files that are accessed together. We use file access patterns to automatically construct dynamic groupings of files and then manage our cache by fetching groups, rather than single files. We present experimental results, based on trace-driven workloads, demonstrating that grouping improves cache performance. At the file system client, grouping can reduce LRU demand fetches by 50 to 60%. At the server, cache hit rate improvements are much more pronounced, but vary widely (20 to over 1200%) depending upon the capacity of intervening caches. Our treatment includes information theoretic results that justify our approach to file grouping

Publication date:
July 2002

Authors:
Ahmed Amer
Darrell D. E. Long
Randal Burns

Projects:
Prediction and Grouping

Available media

Full paper text: PDF

Bibtex entry

@inproceedings{amer-icdcs02,
  author       = {Ahmed Amer and Darrell D. E. Long and Randal Burns},
  title        = {Group-based management of distributed file caches},
  booktitle    = {Proceedings of the 22nd International Conference on Distributed Computing Systems (ICDCS '02)},
  month        = jul,
  year         = {2002},
}