An optimistic replication algorithm to improve consistency for massive data

Authors:
Jing Zhou;Yijie Wang;Sikun Li
Affiliations:
School of Computer Science, National University of Defense Technology, China;School of Computer Science, National University of Defense Technology, China;School of Computer Science, National University of Defense Technology, China
Venue:
GCC'05 Proceedings of the 4th international conference on Grid and Cooperative Computing
Year:
2005

Citing 6
Cited 0

Managing update conflicts in Bayou, a weakly connected replicated storage system

SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
Flexible update propagation for weakly consistent replication

Proceedings of the sixteenth ACM symposium on Operating systems principles
OceanStore: an architecture for global-scale persistent storage

ASPLOS IX Proceedings of the ninth international conference on Architectural support for programming languages and operating systems
Towards an Economy-Based Optimisation of File Access and Replication on a Data Grid

CCGRID '02 Proceedings of the 2nd IEEE/ACM International Symposium on Cluster Computing and the Grid
Data Replication Strategies in Grid Environments

ICA3PP '02 Proceedings of the Fifth International Conference on Algorithms and Architectures for Parallel Processing
Farsite: federated, available, and reliable storage for an incompletely trusted environment

OSDI '02 Proceedings of the 5th symposium on Operating systems design and implementationCopyright restrictions prevent ACM from being able to make the PDFs for this conference available for downloading

Quantified Score

Hi-index	0.00

Visualization

Abstract

Data replication introduces well-known consistency issues. For massive data, how to improve update propagation and how to minimizing space overhead effectually are important. An optimistic replication algorithm is proposed. In our algorithm, home replica is used to resolve updates conflict and pair-wise communication supports the reconciliation of any two replicas. A new anti-entropy partner selection method based on the distribution of updates and the information of local write-log is presented. The algorithm uses write-log truncation appropriately during updates propagation to remove out-of-date updates in time. The simulation results show that the partner selection mechanism can achieve good scalability and adaptability, the average number of updates in write-log does not exceed the number of replicas, and the variety for running different numbers of updates is not obvious.