Abstract

We investigate the construction of a reliable device. Such a device appears to the file system as an ordinary block-structured device, but is implemented as a set of server processes on several sites. This allows for replication while leaving the operating system kernel and the file system unchanged.

The regular structure of the block-level replication environment allows the use of consistency control algorithms that are simpler and less network intensive. We present three algorithms for maintaining file consistency in a block-level replication environment. The first is a majority consensus voting algorithm that recovers blocks only when required for data access; the second is a variant of the available copy scheme modified for replication at the block level; the third is a naive version of the available copy scheme that does not maintain any failure information.

Each scheme is evaluated in terms of availability and network traffic. While block-level replication is shown to allow improvements in the network traffic burden incurred by voting, available copy schemes are shown to have better availability and require significantly less traffic than voting schemes. The naive available copy variant proposed here is shown to be the algorithm of choice.

BibTeX

@inproceedings{ICDCS-Carroll-1987,
  author       = {John L. Carroll and Darrell D. E. Long and Jehan-François Pâris},
  title        = {Block-Level Consistency of Replicated Files},
  booktitle    = {Proceedings of the International Conference on Distributed Computing Systems},
  month        = sep,
  year         = {1987}
}