An efficient data management system with high scalability for chinagrid support platform

  • Authors:
  • Hai Jin;Wenjun Gong;Song Wu;Muzhou Xiong;Li Qi;Chengwei Wang

  • Affiliations:
  • Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China;Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China;Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China;Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China;Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China;Cluster and Grid Computing Lab., Huazhong University of Science and Technology, Wuhan, China

  • Venue:
  • APPT'05 Proceedings of the 6th international conference on Advanced Parallel Processing Technologies
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

There are a great number of data intensive applications in ChinaGrid. They require an efficient and high performance data management. The data management in ChinaGrid Support Platform (CGSP) supplies a data access mechanism with location transparency, name transparency, and protocol transparency as while as ensuring the transfer efficiency. The data management system consists of five parts: the storage data server based on Global Distributed Storage System to guarantee the reliability and performance of data transfer; the storage resource agent to discover, publish and catalog the storage resources; the data logical domain management to enable applications to select specific storage resources; the metadata management to publish, query and access metadata; and the uniform data access entry to organize grid users’ data space. We present the design philosophy of the efficient data management system with high scalability for CGSP and also give preliminary performance results.