The implementation of service monitoring system in scientific data grid

Weizhong Lv^1,2, Yuanchun Zhou¹, Kaichao Wu¹, Baoping Yan¹

¹Computer Network Information Center, Chinese Academy of Sciences, Beijing, China

²Graduate University of Chinese Academy of Sciences, Beijing, China

Email： lvweizhong@sdb.cnic.cn

The Scientific Data Grid (SDG) of Chinese Academy of Sciences (CAS) is aimed at connecting mass data resources in scientific databases hosted and supported by different institutes, realizing effective sharing of those geographically distributed and heterogeneous multidisciplinary data resources among research groups from different locations via grid technology. The availability and efficiency of scientific databases is critical to gain better performance because that the scientific database is the major scientific and technological information resources with a total data volume of hundreds of terabytes. It is emergent and significant to develop a real-time service monitoring system in SDG to improve its stability and availability. First, this paper presents a framework of service monitoring system in SDG. And then, a detailed resolution to implement the monitoring system in SDG environment is proposed. Furthermore, we have designed and implemented an extensible agent-based prototype of the monitoring system. This paper describes the deployment of the prototype. The status information of the portal of SDG, the www service, the database service, and the middleware components is collected from the grid nodes based on agent technology, aggregated and stored in a special database for statistically analyzing. The status information of services in SDG is then transformed to real-time operational pictures for administrative or management staff. This service monitoring system enhances the availability and improves the performance of the SDG service.