Data Management Services in ChinaGrid for Data Mining Applications

摘要

Grid systems, as large-scale distributed computing environments, are widely used by data mining communities. This paper proposes a set of system-level Grid services to form an infrastructure supporting data-intensive applications and data mining. ChinaGrid, aiming at integrate heterogeneous massive resources distributed on China Education and Research Network (CERNET), is a national-wide Grid project supported by the Chinese government. ChinaGrid Supporting Platform (CGSP) is a Grid middleware developed for the ChinaGrid. It provides a series of system-level services of the ChinaGrid, helps to build application portals and integrate Grid resources, and supports the secondary development of Grid services. The Data Management Services (DMS) is a group of Grid services in CGSP to manage storage and data resources, support transparent data access, and guarantee high-performance data transfer on the Grid. It consists of metadata management service, storage resource management service, replication management service, storage agent and transfer client. It offers the fundamental support for data mining applications on ChinaGrid. In this paper, we introduce the design principle and implementation of DMS.