| 引用本文: | 周婧,王意洁,李思昆,等.一种面向关键属性更新的优化数据一致性算法.[J].国防科技大学学报,2007,29(4):42-46.[点击复制] |
| ZHOU Jing,WANG Yijie,LI Sikun,et al.An Optimistic Data Consistency Algorithm for Update of Key-attributes[J].Journal of National University of Defense Technology,2007,29(4):42-46[点击复制] |
|
| |
|
|
| 本文已被：浏览 6424次 下载 5938次 |
| 一种面向关键属性更新的优化数据一致性算法 |
| 周婧1, 王意洁1, 李思昆1, 王元志2 |
|
(1.国防科技大学 计算机学院，湖南 长沙 410073;2.工程兵指挥学院，江苏 徐州 221004)
|
| 摘要: |
| 规模巨大且分布性强的P2P系统可能导致部分数据副本发布的更新被长时间地延迟，从而降低Internet上资源定位的效率。针对关键属性更新的特点，提出一种解决关键属性更新冲突的优化数据一致性算法。算法中分离出用户提交的更新请求中关于关键属性的更新，在对关键更新冲突分类的基础上，采用更新缓冲预处理和关键更新表两层机制并结合最新写胜出和分而治之规则，优化关键更新冲突的发现和解决。关键属性更新的优化处理使得不会产生因为关键属性更新的延迟而降低系统基于关键属性的资源定位效率，满足面向Internet的P2P系统的要求。模拟测试结果表明该算法在一致性维护开销、资源定位开销与资源访问开销以及鲁棒性方面均具有较好的性能。 |
| 关键词: P2P分布存储系统 数据复制 数据一致性 资源定位 |
| DOI： |
| 投稿日期：2006-10-12 |
| 基金项目:国家自然科学基金重大项目；高等学校全国优秀博士学位论文作者专项资金项目(200141)；国家部委资助项目 |
|
| An Optimistic Data Consistency Algorithm for Update of Key-attributes |
| ZHOU Jing1, WANG Yijie1, LI Sikun1, WANG Yuanzhi2 |
|
(1.College of Computer, National Univ. of Defense Technology, Changsha 410073, China;2.Command Institute of Engineer Corps, Xuzhou 221004, China)
|
| Abstract: |
| In generally large-scale and strong distributed P2P systems, updates issued by replicas may be delayed, and then resource location performance on the Internet may be depressed. According to the characteristics of updates about key-attributes in P2P systems, an optimistic data consistency maintenance algorithm is proposed. The update about key-attributes was separated from user update request, and based on classifying key-update conflicts, a double-level mechanism including preprocessing buffer and key-update table were applied to detect and reconcile conflicts, and then conflicts were solved by policies as last-writer-win and divide-and-rule. 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 for Internet. The simulation results show that it is an effective optimistic data consistency algorithm, achieving good consistency overhead, resource location and resource access overhead, and having strong robustness. |
| Keywords: peer-to-peer distributed storage systems data replication data consistency resource location |
|
|
|
|
|
