Quorum-based protocol for group communication

Objects in distributed systems are replicated to make the systems fault-tolerant. Traditional group protocols support the ordered delivery of messages transmitted in the network. Only messages significant for the applications should be causally ordered in order to reduce the computation and communication overheads. In this paper a precedent relation among messages is for replicas which are locked in a quorum-based scheme. We discuss a group protocol which supports the precedency.

[1]  Tomoya Enokido,et al.  Group protocol for distributed replicated objects , 1998, Proceedings. 1998 International Conference on Parallel Processing (Cat. No.98EX205).

[2]  Akihito Nakamura,et al.  Causally ordering broadcast protocol , 1994, 14th International Conference on Distributed Computing Systems.

[3]  Divyakant Agrawal,et al.  Using message semantics to reduce rollback in optimistic message logging recovery schemes , 1994, 14th International Conference on Distributed Computing Systems.

[4]  K. Ravindran,et al.  Causal broadcasting and consistency of distributed shared data , 1994, 14th International Conference on Distributed Computing Systems.

[5]  Michel Raynal,et al.  An adaptive protocol for implementing causally consistent distributed services , 1998, Proceedings. 18th International Conference on Distributed Computing Systems (Cat. No.98CB36183).

[6]  Robbert van Renesse,et al.  Reliable Distributed Computing with the Isis Toolkit , 1994 .

[7]  Tomoya Enokido,et al.  Transaction-based causally ordered protocol for distributed replicated objects , 1997, Proceedings 1997 International Conference on Parallel and Distributed Systems.

[8]  André Schiper,et al.  Lightweight causal and atomic group multicast , 1991, TOCS.

[9]  Makoto Takizawa,et al.  Significantly ordered delivery of messages in group communication , 1997, Comput. Commun..

[10]  Makoto Takizawa,et al.  Object-based checkpoints in distributed systems , 1997, Proceedings Third International Workshop on Object-Oriented Real-Time Dependable Systems.