37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'07) (2007)
June 25, 2007 to June 28, 2007
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/DSN.2007.62
Mikael Asplund , Linkoping University, Sweden
Simin Nadjm-Tehrani , Linkoping University, Sweden
Stefan Beyer , Universidad Politcnica de Valencia, Spain
Pablo Galdamez , Universidad Politcnica de Valencia, Spain
Replicated systems that run over partitionable environments, can exhibit increased availability if isolated partitions are allowed to optimistically continue their execution independently. This availability gain is traded against consistency, since several replicas of the same objects could be updated separately. Once partitioning terminates, divergences in the replicated state needs to be reconciled. One way to reconcile the state consists of letting the application manually solve inconsistencies. However, there are several situations where automatic reconciliation of the replicated state is meaningful. We have implemented replication and automatic reconciliation protocols that can be used as building blocks in a partition-tolerant middleware. The novelty of the protocols is the continuous service of the application even during the reconciliation process. A prototype system is experimentally evaluated to illustrate the increased availability despite network partitions.
S. Nadjm-Tehrani, S. Beyer, P. Galdamez and M. Asplund, "Measuring Availability in Optimistic Partition-Tolerant Systems with Data Constraints," 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'07)(DSN), Edinburgh, UK, 2007, pp. 656-665.