go directly to the contents
EUChinaGRID

application repository

  • name: Scientific Data Grid
  • domain: information retrieval/data repositories
  • country: China
  • author:
  • institute:
  • contacts:
  • description: Scientific Data Grid, SDG, is a representative application grid in science research area of China National Grid, CNGrid, and gets long-term support from CNGrid. Based on mass scientific data resources in Scientific Databases, Scientific Data Grid is equipped with 20TB network storage, 50TB tape system and 1 TFLOP computing abilities (Figure 5). Service-oriented architecture is adopted while developing Scientific Data Grid software. SDG supports several appilot applications including:
    • China Virtual Observatory. developed with the collaboration between Computer Network Information Center (CNIC) and National Astronomical Observatories (NAO) of CAS and prioviding several services, including Statistical Analysis of Fe Abundances Gradients in the Galaxy, The Decoding Grid Service and Query Grid Service for some catalogue, DSS image retrieval grid service and Basic Astronomical Computing Service.
    • High Energy Physics: YBJ International Cosmic Ray Data Pre-processing Center. The ARGO -YBJ Aiming at researching the origin of high energy cosmic rays, the observatory (located at 90°26'E and 30°13'N in YangBaJing (YBJ) valley of Tibetan highland) generates more than 200TB raw data each year, that are transferred  to Beijing and processed into reconstructed data. For this purpose a grid-based computing system will be built with about 400 CPUs, mass storage system and broad band network links among Tibet, Beijing and institutes in Italy. See ARGO application in EUChinaGRID >>
    • Avian Flu – Integrated Information Platform, Predicting & Alarming System for Avian Influenza. Major tasks of this project include integrating databases of avian flu, investigating epidemiology of avian flu, setting up comprehensive analyzing system of biological information, building predicting and alarming system, constructing collaboration research grid and information publication system for avian flu.
    • functionalities: Via the standardization of metadata and resource discovery based on metadata, Scientific Data Grid software makes it easy for users to implement uniform access of distributed and heterogeneous data resource by two-step search.　Up till now, 3 versions of Scientific Data Grid software package, SDG 1.0, SDG 2.0 and SDG 3.0, have been released and deployed in 45 institutes of Chinese Academy of Sciences, which participate in Scientific Databases project. In the fields of astronomy and high energy physics, we developed applications such as virtual observatory and cosmic ray data pre-processing system, providing research-oriented data service for relevant principles and further collaborating with scientists to develop other application tools and services specific for science problems. SDG provides the following resources:
      • Scientific Database [45 Institutes of CAS, 503 Specialized Databases, Data Volume 16.6 TB (by Oct. 2005)]
      • SDB6800 Super Server [59 nodes / 236 CPUs   , Official Service Started in Apr. 2005, Node Usage 79.7%, Storage Usage 87% (by Sept. 2005)
      • SDG Storage System [Tape System 50TB, Disk Array 20TB, Backbone Netvault]
      • SDG portal
      • Visualization System [5×4 Tiles, 6400×4096 Pixels, 21-Node Cluster]
    • middleware requirements: Several funtionalities were implemented in the SDG middleware, to meet the application requirements:
      • Uniform Data Access to geographycally disstributed and eterogeneous DBs - Data Access Service (DAS), one of the central services in SDG middleware, is designed to provide uniform data access to geographically distributed, heterogeneous and autonomous databases for users and allows accessing several types of relational databases, including Oracle, Microsoft SQL Server, MySQL and even file systems.
      • Information retrieval via metadata and web-based tools - Based on the metadata designed and constructed for Scientific Database, Information Service provides resource discovery and locating for Scientific Data Grid and advanced application systems via Information and Metadata Service (IMS) and SDGFinder, a web-based resource finding tool.
      • Secure and Authorized Access to Resources - Functionality that has been implemented for Security Infrastructure of SDG includes Access Control and Certificate Administration by which the administrator can easily issue, manage, suspend, revoke or renew certificates and users can apply and get digital certificates in practical and efficient manner.
      • Easy use of Shared Storage resources - To facilitate and promote usage of shared storage resources in SDG, Storage Service is made available on the basis of file storage service, database service, Internet publishing service and a set of client tools named SSTools with utilities of data transfer, quota assignment and storage management.

      • resources requirements:

      Back to list of applications >>

powered by
Consortium GARR