Checkpointing and Rollback-Recovery for Distributed Systems
IEEE Transactions on Software Engineering - Special issue on distributed systems
On Coordinated Checkpointing in Distributed Systems
IEEE Transactions on Parallel and Distributed Systems
A survey of rollback-recovery protocols in message-passing systems
ACM Computing Surveys (CSUR)
Message Logging: Pessimistic, Optimistic, Causal, and Optimal
IEEE Transactions on Software Engineering
An Efficient Optimistic Message Logging Scheme for Recoverable Mobile Computing Systems
IEEE Transactions on Mobile Computing
Distributed Snapshots for Mobile Computing Systems
PERCOM '04 Proceedings of the Second IEEE International Conference on Pervasive Computing and Communications (PerCom'04)
A novel min-process checkpointing scheme for mobile computing systems
Journal of Systems Architecture: the EUROMICRO Journal
Checkpointing and rollback-recovery protocol for mobile systems with MW session guarantee
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Hi-index | 0.00 |
The fundamental goal of the log-based fault-tolerant scheme is to bring the system into a consistent global state without any orphan inconsistence. However, the existing Alvisi's No-Orphans Consistency Condition is only sufficient on condition that the set of local checkpoints of failure processes keep consistent always. Independent of the specific log-based checkpointing and rollback-recovery fault tolerant scheme, an extended orphan-free consistency condition is derived based on PWD assumption in this paper. The definitions of the orphan inconsistence among the process state and the nondeterministic event during a rollback recovery were extended. Finally the essential requirement for message logs was specified to eliminate the possible orphan inconsistence among the process state during a rollback recovery. By contrast, the proposal is a practical and efficient constraint for the orphan-free recovery.