摘要：It is very complex and of low efficiency for grid users to access heterogeneous diverse data resources distributed over the whole wide area network. Data Grid has denoted a network of storage resources, from archival systems, to caches, to databases, that are linked across a distributed network. And it should provide integrated, scalable data services which implement more wide range of transparent access to data resources in Data Grid, such as location transparency, time transparency. I n this paper, we describe a SDS system which can implement integrated , scalable data services. We have implemented o ne of the important building blocks for SDS is the server called DSB which can provide integrated data services. The DSB bases on cluster and agent technologies. Agent-based DSB can cleverly prefetch required data, replicate them among DSBs. Each DSB based on cluster implements a single entry and a virtual i ntegrated storage system in a data domain. As far as whole SDS, Multiple DSBs are formed cluster data services, which are scalable, and provide a single entry for all data grid users, and provide a virtual i ntegrated mass storage system, and hide distributed heterogeneous low-level data resources, and insure load balance of each server. SDS architecture supporting these various scenarios, are also described.
