Implementing a caching service a distributed COBRA objects
IFIP/ACM International Conference on Distributed systems platforms
A survey of rollback-recovery protocols in message-passing systems
ACM Computing Surveys (CSUR)
Session Guarantees for Weakly Consistent Replicated Data
PDIS '94 Proceedings of the Third International Conference on Parallel and Distributed Information Systems
A Framework for Consistent, Replicated Web Objects
ICDCS '98 Proceedings of the The 18th International Conference on Distributed Computing Systems
Safety of a server-based version vector protocol implementing session guarantees
ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part III
DAIS'06 Proceedings of the 6th IFIP WG 6.1 international conference on Distributed Applications and Interoperable Systems
Pastis: a highly-scalable multi-user peer-to-peer file system
Euro-Par'05 Proceedings of the 11th international Euro-Par conference on Parallel Processing
Hi-index | 0.00 |
The rVsAll rollback-recovery protocol assures that consistency models, called session guarantees, are provided for mobile clients and unreliable servers. The protocol is optimized according to the required consistency model by taking into account properties of session guarantees and integrating their consistency management with known rollback-recovery techniques: message-logging and checkpointing. We have proved the correctness of rVsAll protocol in terms of safety and liveness properties. These properties assert that clients access object replicas maintained by servers according to the required session guarantee regardless of server's failures, and state that each access operation issued by clients will eventually be performed (in a finite time), even in the presence of server's failures. In this paper, we show that the proposed protocol is also optimal, in the sense that, the consistent global checkpoint taken in rVsAll protocol contains the minimal number of operations indispensable to fulfill the required session guarantees after server's failure and its recovery. The paper presents the proof of the optimality property of the proposed protocol.