Reliable communication in the presence of failures
ACM Transactions on Computer Systems (TOCS)
Replica control in distributed systems: as asynchronous approach
SIGMOD '91 Proceedings of the 1991 ACM SIGMOD international conference on Management of data
Disconnected operation in the Coda file system
SOSP '91 Proceedings of the thirteenth ACM symposium on Operating systems principles
Distributed algorithms for dynamic replication of data
PODS '92 Proceedings of the eleventh ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Providing high availability using lazy replication
ACM Transactions on Computer Systems (TOCS)
Weak-consistency group communication and membership
Weak-consistency group communication and membership
Bounded ignorance: a technique for increasing concurrency in a replicated system
ACM Transactions on Database Systems (TODS)
Managing update conflicts in Bayou, a weakly connected replicated storage system
SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
The dangers of replication and a solution
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
Temporal notions of synchronization and consistency in Beehive
Proceedings of the ninth annual ACM symposium on Parallel algorithms and architectures
Flexible update propagation for weakly consistent replication
Proceedings of the sixteenth ACM symposium on Operating systems principles
Decentralized replicated-object protocols
Proceedings of the eighteenth annual ACM symposium on Principles of distributed computing
Timed consistency for shared distributed objects
Proceedings of the eighteenth annual ACM symposium on Principles of distributed computing
The costs and limits of availability for replicated services
SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
An Efficient Scheme for Dynamic Data Replication
An Efficient Scheme for Dynamic Data Replication
Design and evaluation of a continuous consistency model for replicated services
OSDI'00 Proceedings of the 4th conference on Symposium on Operating System Design & Implementation - Volume 4
A model for characterizing the scalability of distributed systems
ACM SIGOPS Operating Systems Review
Automating service quality with TOMCAD (Tradeoff Model with Capacity and Demand)
Proceedings of the 2007 workshop on Automating service quality: Held at the International Conference on Automated Software Engineering (ASE)
A balanced consistency maintenance protocol for structured P2P systems
INFOCOM'10 Proceedings of the 29th conference on Information communications
P2P consistency support for large-scale interactive applications
Computer Networks: The International Journal of Computer and Telecommunications Networking
Probabilistically bounded staleness for practical partial quorums
Proceedings of the VLDB Endowment
Toward a principled framework for benchmarking consistency
HotDep'12 Proceedings of the Eighth USENIX conference on Hot Topics in System Dependability
| Hi-index | 0.00 |
Replication system is one of the most fundamental buildingblocks of wide-area applications. Due to the inevitabledependencies on wide-area communication, trade-off betweenperformance, availability and replication consistencyis often a necessity. While a number of proposals havebeen made to provide a tunable consistency bound betweenstrong and weak extremes, many of them rely on a staticallyspecified enforcement across replicas. This approach, whileeasy to implement, neglects the dynamic contexts withinwhich replicas are operating, delivering sub-optimal performanceand/or system availability.In this paper, we analyze the problem of optimal performance/availability for a given consistency level under heterogeneousworkload and network condition. We prove severaloptimization rules for different goals. Based on theseresults, we developed an adaptive update window protocolin which consistency enforcement across replicas is self-tunedto achieve optimal performance/availability. A prototypesystem, FRACS, is built and evaluated in this paper.The experiment results demonstrate significant advantagesof adaptation over static approach for a variety of workloads.