Key-Attributes Based Optimistic Data Consistency Maintenance Method

摘要

Peer-to-peer distributed storage systems usually replicate data objects on multi-node to improve the performance and availability. However, updates may be delayed for P2P systems are generally large-scale and strong distributed, and then the performance of resource location in Internet would be depressed. According to that, an optimistic data consistency maintenance method based on key-attributes is proposed. In the method, updates about key-attributes are separated from user request. Key-updates are propagated by latency-overlay update propagation model, that is, updates are always propagated to nodes having maximum or minimal latency, and assured and uncertain propagation paths of updates are all taken into account. Based on classifying key-update conflicts, a double-level reconciling mechanism including the preprocessing of buffer and the processing of update-log is applied to detect and reconcile conflicts, and then conflicts are solved by policies of last-writer-win and divide-and-rule. Lastly, the technique of managing and maintaining update-log is discussed for the above is deployed based on the information storied in update-log. Delaying key-attributes updates cannot occur by the optimistic disposal method, and then it cannot depress efficiency of resource location based on key-attributes, which adapts well to P2P systems in Internet. The simulation results show it is an effective optimistic consistency maintenance method, achieves good consistency overhead, resource location and access overhead, and has strong robustness.