A system for adaptive disk rearrangement
Software—Practice & Experience
The design and implementation of a log-structured file system
ACM Transactions on Computer Systems (TOCS)
The HP AutoRAID hierarchical storage system
ACM Transactions on Computer Systems (TOCS) - Special issue on operating system principles
Adaptive block rearrangement under UNIX
Software—Practice & Experience
Improving the performance of log-structured file systems with adaptive methods
Proceedings of the sixteenth ACM symposium on Operating systems principles
Using data clustering to improve cleaning performance for plash memory
Software—Practice & Experience
Placement of Records on a Secondary Storage Device to Minimize Access Time
Journal of the ACM (JACM)
Cleaning policies in mobile computers using flash memory
Journal of Systems and Software
Minimizing Expected Head Movement in One-Dimensional and Two-Dimensional Mass Storage Systems
ACM Computing Surveys (CSUR)
WOLF - A Novel Reordering Write Buffer to Boost the Performance of Log-Structured File Systems
FAST '02 Proceedings of the Conference on File and Storage Technologies
HyLog: A High Performance Approach to Managing Disk Layout
FAST '04 Proceedings of the 3rd USENIX Conference on File and Storage Technologies
Heuristic cleaning algorithms in log-structured file systems
TCON'95 Proceedings of the USENIX 1995 Technical Conference Proceedings
Online reorganization of databases
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
Log-Structured File System (LFS) is famous for its optimization for write performance. Because of its append-only nature, garbage collection is needed to reclaim the space occupied by the obsolete data. The cleaning overhead could significantly decrease the performance of file system. However, traditional cleaning policies do not consider the storage location where the valid data in the cleaned segments should be placed and rewritten to. In this paper, we propose a new method called R-LFS to dynamically reorganize data in disk to approximate the organ pipe heuristic that can place data in disk optimally. Basically, frequently accessed data are dynamically clustered and placed toward the center of disk, whereas less accessed data are moved and placed toward the edges of disk to reduce disk seek time. The essence of R-LFS is that R-LFS takes advantage of the chance of data reorganization during segment cleaning and data writing, no extra overhead is incurred for this data reorganization. Besides, because hot data and cold data are in nature separately clustered under R-LFS, cleaning overhead can be substantially reduced as well. Performance evaluation under both trace-driven simulation and practical implementation on NetBSD/LFS shows that R-LFS can effectively improve the performance of LFS.