Abstract
A self-stabilizing distributed file systems is presented. The system constructs and maintains a spanning tree for each file volume. The spanning tree consists of the servers that have volume replicas and caches for the specific file volume. The spanning trees are constructed and maintained by self-stabilizing distributed algorithms. A self-stabilizing synchronizer enforces file system semantics and consistent replications. File system updates use the tree to implement file read and write operations. A prototype of the system based on the Linux operating system has been implemented.
Original language | English |
---|---|
Pages (from-to) | 135-153 |
Number of pages | 19 |
Journal | Journal of High Speed Networks |
Volume | 14 |
Issue number | 2 |
State | Published - 28 Jul 2005 |
ASJC Scopus subject areas
- Information Systems
- Hardware and Architecture
- Computer Networks and Communications