摘要
数据网格提供了地理分布的大量共享数据资源,然而互联网的高访问延迟降低了数据访问的效率,创建副本是一个有效的方法,而在何处放置副本是一个具有挑战性的问题。从应用环境和用户访问特征出发,讨论了副本创建位置、粒度和时机,提出了一种基于副本共享组的副本创建模型,可以获得优化的副本创建位置,构造了一个副本创建代价函数,由系统的传输速率、拓扑结构和用户访问特征共同决定,并给出了确定副本创建位置的有效算法。分析和仿真实验表明,自适应副本管理方案具有动态性、适应性和可扩展性,能较好地适应数据网格的特性,可以有效降低访问延迟,提高数据访问效率。
Data Grid provides geographically distributed data resources. However, ensuring efficient and fast access to such huge and widely distributed data is hindered by the high latencies of the Internet. Data replication is an effective approach and one of the challenges in data replication is to select the candidate sites to place replicas. To address this problem an adaptive replication strategy RGRS（Replica Group based Replication Strategy） was introduced, which was dynamically depending on current conditions, offering improved scalability of the overall system, and was able to achieve optimized placement location. Replication placement decisions were made based on a cost model that evaluated data access costs and performance gains of creating each replica. Meanwhile, the granularity and creating time of replica were discussed. Through analysis and simulations, the results prove that the replication strategy is dynamic, adaptive and scalable, improving the performance of the data access in Data Grid.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2008年第18期4854-4858,共5页
Journal of System Simulation
基金
重庆市教育委员会2007年科学技术研究项目支持(KJ071503)
关键词
数据网格
副本
动态
可扩展
data grid
replication
dynamic
scalability
