Grid2003 Monitoring, Metrics, and Grid Cataloging System

Grid computing involves the close coordination of many different sites which offer distinct computational and storage resources to the Grid user community. The resources at each site need to be monitored continuously. Static and dynamic site information needs to be presented to the user community in a simple and efficient manner. This paper will present both the design and implementation of the Grid3 monitoring infrastructure and the design details and the functionalities of a new application called the GridCat. The Grid3 monitoring architecture follows a useroriented design that specifies standard metrics and utilizes underlying monitoring tools to collect them into a diversified framework. Then existing tools can be integrated, their functionality extended and new tools developed. The primary tools used include the ACDC Job Monitoring system from University at Buffalo, Ganglia, a preliminary version of GridCat, Globus MDS, the University of Chicago Grid telemetry MDViewer, and US CMS MonALISA. Information of interest for a particular VO can be extracted from archives of collected data. For example, sufficient information necessary to associate resources provided and used for each VOs, and job statistics for each VO. GridCat provides a service giving status information through a web interface with a database backend that collects and stores a site’s configuration and dynamic information. It is simple and powerful enough to determine the site's readiness to accept grid applications. The status information displayed by the prototype GridCat was used extensively by the Grid2003 project as a coordination point for the iVDGL Grid Operations Center (iGOC).