节点文献

实时内存数据库分区模糊检验点策略

A Partition Fuzzy Checkpointing Strategy for Real-Time Main Memory Databases

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 廖国琼刘云生肖迎元

【Author】 Liao Guoqiong 1,2, Liu Yunsheng1, and Xiao Yingyuan1 1(School of Computer Science & Technology, Huazhong University of Science & Technology, Wuhan 430074) 2(Corporation Technology, Siemens Limited China, Beijing 100102)

【机构】 华中科技大学计算机科学与技术学院华中科技大学计算机科学与技术学院 武汉430074西门子(中国)有限公司西门子中国研究院北京100102武汉430074

【摘要】 检验点技术是实时内存数据库恢复的关键技术之一.在分析实时内存数据库数据特征基础上,给出了综合考虑数据和事务定时约束的数据检验点优先级计算方法.然后,结合内存数据库段式存储结构,讨论了一种基于数据段检验点优先级的分区模糊检验点策略PFCSSCP.通过性能测试,表明所提出的检验点策略能减低超截止期事务比率.

【Abstract】 Checkpointing is one of the important recovery techniques of real-time main memory database systems (RTMMDBS). Through analyzing the data characteristics in RTMMDBS, a method to calculate data checkpointing priorities is presented, which takes the timing constraints of both data and transactions into consideration. A partition fuzzy checkpionting strategy based on data segment checkpointing priority—PFCS?-SCP is suggested, and the correctness of PFCE-SCP is also discussed. It is shown through performance testing that PFCS-SCP strategy can decrease the missing ratio of transactions in RTMMDBS.

【基金】 中国博士后科学基金项目(2003034482)
  • 【文献出处】 计算机研究与发展 ,Journal of Computer Research and Development , 编辑部邮箱 ,2006年07期
  • 【分类号】TP311.13
  • 【被引频次】20
  • 【下载频次】238
节点文献中: 

本文链接的文献网络图示:

本文的引文网络