一种基于结点的分布式合作缓存管理算法DCC

A DISTRIBUTED COOPERATIVE CACHING ALGORITHM FOR WORKSTATION CLUSTER FILE SYSTEM

工作站机群系统需要有一个高性能的并行文件系统以适应高速输入、输出数据处理的要求，而提高并行文件系统性能的关键是合作缓存技术．文中提出了一种基于结点的分布式合作缓存管理算法 Ｄ Ｃ Ｃ．该算法综合了基于全局管理器和基于局部信息两种算法的优点，给出了一种位于结点机上的主块信息站的方法，通过对主块信息站的信息进行维护来达到对全局信息的跟踪．算法采用积极的局部信息维护策略，提高了主块位置判断的准确性．与 Ｇ Ｍ Ｓ算法、 Ｈｉｎｔｓ 算法相比， Ｄ Ｃ

With the development of workstation cluster systems, a high performance file system on such systems is needed. A impotent technology to further improve the performance of cluster file system is cooperation of cache. A distributed cooperative caching algorithm (DCC) is brought forward in this paper. This algorithm combines the advantages of the global manager based algorithms and the local message based algorithms. It gives a concept of master copy message station. This approach uses active safeguard decision of local messages. The judgment of master copy position is more accurate. Consequently, the cost of the algorithm is the lowest among the available algorithms and it also exhibits a good scalability.