Parallel and Distributed Processing, IEEE Symposium on (1996)
New Orleans, LA
Oct. 23, 1996 to Oct. 26, 1996
Darrell D. E. Long , University of California
Jehan-Francois Paris , University of Houston
Available copy protocols provide the highest data availability and data reliability of all replication protocols that do not regenerate failed replicas. Unfortunately, all existing implementations of available copy protocols either rely on complex procedures for ascertaining which replicas are up to date after a total failure or have to wait for the recovery of all failed sites. We present a simple technique for efficiently implementing the available copy protocol. Our protocol does not require version numbers and maintains only n + log(n) bits of state per replica. We also show under standard Markovian assumptions that our new protocol provides the same data as the best feasible implementations of the available copy protocol.
distributed file systems, data replication, replication control protocols
D. D. Long and J. Paris, "A Leaner, More Efficient, Available Copy Protocol," Parallel and Distributed Processing, IEEE Symposium on(SPDP), New Orleans, LA, 1996, pp. 400.