| In recent years, data volume in all kinds of large-scale scientific researches, information services, multimedia applications, etc. presents explosive increasing. And the needs for integrated access, transfer, management of geographically distributed mass datasets are also increasing. The data grid technology is an effective solution to this problem and is also a research hotspot in computer field in the world. Federated data service is one of the core services in data grid, which provides uniform data access service to wide-area, distributed and heterogeneous srorage resources.Our project has studied the key technologies of data grid, and has designed and implemented a general data grid middleware called GridDaEn, which can achieve uniform access, transfer and management of distributed, heterogeneous mass datasets and provide a high-performance platform for data-intensive applications and researches over wide area networks.This paper focuses on the key technologies of federated data service in data grid. Firstly, we study the seamless integration of distributed and heterogeneous storage resources in wide area network, and propose the autonomous federated data service model, in which model roles are described in detail on behavior, feature, organization, management and interaction. Secondly, we do research on the coordination of multiple domains, and present an algorithm based on service reassemble, which can improve the system performance by reducing communication frequency. And then, we research the cache management mechanism, session management mechanism and security mechanism. Based on which, we design and implement FDSS, the core of GridDaEn data grid system, and DRB, the basic data service provider of FDSS.The research in this paper is not only implemented in GridDaEn data grid system, but also tested widely under the China National Grid environment.The results of tests indicate that FDSS can achieve uniform and high-efficient coordination of multiple domains. |
PDF Full Text Request