Intelligent Methods for File System Optimization

The speed of I/O components is it major limitation of the speed of all other major components in today's computer systems. Motivated by this, we investigated several algorithms for efficient and intelligent organization of files on a hard disk. Total access time may be decreased if files with temporal locality also have spatial locality. Three intelligent methods based on file type, frequency, and transition probabilities information showed up to 60% savings of total I/O time over the naive placement of files. More computationally intensive hill climbing and genetic algorithms approaches did not outperform statistical methods. The experiments were run on a real and simulated hard drive in single and multiple user environments.

[1]  Mendel Rosenblum,et al.  The design and implementation of a log-structured file system , 1991, SOSP '91.

[2]  Alan Jay Smith,et al.  Input/output optimization and disk architectures: A survey , 1981, Perform. Evaluation.

[3]  Tze Chiang Lee,et al.  A file-based adaptive prefetch caching design , 1990, Proceedings., 1990 IEEE International Conference on Computer Design: VLSI in Computers and Processors.

[4]  Robert S. Fabry,et al.  A fast file system for UNIX , 1984, TOCS.

[5]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[6]  William G. Tuel.  Optimum reorganization points for linearly growing files , 1978, TODS.

[7]  Alexander A. Stepanov,et al.  Loge: A Self-Organizing Disk Controller , 1991 .

[8]  Yale N. Patt,et al.  Disk subsystem load balancing: disk striping vs. conventional data placement , 1993, [1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences.

[9]  T.M. Madhyastha,et al.  Intelligent, adaptive file system policy selection , 1996, Proceedings of 6th Symposium on the Frontiers of Massively Parallel Computation (Frontiers '96).