Abstract:
Monitoring resources is an important aspect of the overall efficient usage and
control of any distributed system. The resources of interest can include all
manner of networked devices, from a remote sensor or satellite feed through to a
computational node or a communications link. This generic, open-source
resource monitoring architecture has been specifically designed for the Grid
being an ultimate implementation yet defined for distributed architecture. A widearea
distributed system such as a Grid requires that a broad range of data be
monitored and collected for a variety of tasks such as fault detection and
performance monitoring, analysis, prediction and tuning. A range of tools has
been developed for monitoring distributed resources.
The system is based on the basics of Services Oriented Architecture, Java
technologies (jini, applets, servlets and JDBC) a SQL database and SNMP
(agents and objects). Unlike many other monitoring systems, it is designed to
monitor both Grid resources and processes, rather than only the applications that
execute on a Grid. It is capable of registering interest in events, remotely
observing devices, as well as gathering and displaying monitoring data.