A wide-area distributed system such as a Grid requires that a broad range of resources are monitored and data collected for a variety of tasks such as fault detection and performance monitoring, analysis, prediction and tuning. 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.
The Grid Resource Monitoring (GridRM) project's focus is to provide a generic open-source resource monitoring architecture, designed specifically for the Grid. Unlike many other monitoring systems, GridRM is designed to monitor Grid resources, rather than the applications that execute on a Grid. The GridRM is capable of registering interest in events, remotely observing devices, as well as gathering and displaying monitoring data.
The GridRM architecture has two hierarchical layers, a global layer and a local layer. The global layer uses the standards based Grid Monitoring Architecture (GMA) (from the Global Grid Forum (GGF)) to bind together remote Grid-enabled sites. These sites interact with the GMA via a GridRM Gateway. The Gateway is used internally, to a Grid-enabled site (the local layer), to configure, manage and monitor internal resources, while providing controlled external access to resource information.
The GridRM design employs an extensible framework whereby diverse information providers are plugged into the bottom of the GridRM architecture and at the 'top' equally diverse information consumers query and extract the data they require from multiple Grid sites.
Key infrastructure goals include: