Taking account of operators needs of CPU and disk I/O into account, we focus our research on processor allocation of parallel query on Shared Nothing execution environment.

In order to improve the performance and accuracy of user querying(refer to multi-heterogeneous data sources) in grid environment,the paper presents a parallel querying solution based on multi-ontology.

In this paper,a query complete-including method is proposed based on data stream sharing,and then it is optimized to a query combining method with its cost model.