Monitoring and analysing a Grid Middleware Node

Distributed grid applications are becoming more and more popular as the use of complex grid middlewares becomes extensive, and more facilities are offered by these complex pieces of software. But as grid middlewares grow and offer more advanced features, they become more complex and weighty, as well as hard to tune. As the performance of a distributed grid applications can be strongly influenced by the operation of the underlying grid middleware, it becomes important to study and analyze their behaviour and performance. In this paper we present the eDragon monitoring framework (eDMF), a set of tools for instrumentation and analysis of grid middleware, that provides an unique environment to study the performance of grid applications. The eDMF is composed of a set of specialised monitoring tools as well as a flexible and powerful performance analysis platform. Additionally we also provide a practical application of the eDMF to the Globus toolkit 4 (GT4), one of the most extended and popular grid middlewares, showing how it helped us in the detection and resolution of several job management problems observed in the GT4 middleware