The dangers of replication and a solution
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
Fault-tolerant broadcasts and related problems
Distributed systems (2nd Ed.)
Replication management using the state-machine approach
Distributed systems (2nd Ed.)
Distributed systems (2nd Ed.)
Design and evaluation of a conit-based continuous consistency model for replicated services
ACM Transactions on Computer Systems (TOCS)
A Low Latency, Loss Tolerant Architecture and Protocol for Wide Area Group Communication
DSN '00 Proceedings of the 2000 International Conference on Dependable Systems and Networks (formerly FTCS-30 and DCCA-8)
AQuA: An Adaptive Architecture that Provides Dependable Distributed Objects
SRDS '98 Proceedings of the The 17th IEEE Symposium on Reliable Distributed Systems
A System Architecture for Enhanced Availability of Tightly Coupled Distributed Systems
ARES '06 Proceedings of the First International Conference on Availability, Reliability and Security
Using Replication to Build Highly Available .NET Applications
DEXA '06 Proceedings of the 17th International Conference on Database and Expert Systems Applications
Implementing Network Partition-Aware Fault-Tolerant CORBA Systems
ARES '07 Proceedings of the The Second International Conference on Availability, Reliability and Security
Measuring Availability in Optimistic Partition-Tolerant Systems with Data Constraints
DSN '07 Proceedings of the 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
A generic and flexible model for replica consistency management
ICDCIT'04 Proceedings of the First international conference on Distributed Computing and Internet Technology
Increasing availability in a replicated partitionable distributed object system
ISPA'06 Proceedings of the 4th international conference on Parallel and Distributed Processing and Applications
Hi-index | 0.00 |
In decentralised systems, replication is commonly used to provide a certain degree of fault tolerance. Whereas many systems only consider the failure of individual system nodes, partitionable systems also consider network link faults that can cause the system to be divided into isolated parts. Replication in the presence of network partitioning is problematic, as updates to replicas in different partitions can lead to data inconsistencies that are not detected until the partitioning is repaired. The degree to which temporary or permanent inconsistencies can be tolerated depends heavily on the application. We exploit commutativity to define a group of replication protocols that improve the performance for operations without order constraints on replicated objects. The protocols provide a way to trade consistency for improved availability in the presence of partitions and also simplify the reconciliation process, when two or more partitions are merged. The protocols have been implemented in the DeDiSys add-on for the CORBA middleware and some performance results are provided.