CoreGRID Network of Excellence - European Grid Research

The primary objective of this institute is the development of general and scalable approaches to an information and monitoring infrastructure for large scale heterogeneous Grids. The resources on a Grid are under the control of different entities and are heterogeneous. The useful integration of these resources and related services is impossible without access to relevant information about their accessibility and state. Also, this information must be properly collected, merged, filtered, and delivered to users, either for other services like resource brokers or to end users and their programs. In addition, to the resource and service oriented point of view, job centred collection of information is important for the better understanding of the general state and behaviour of a Grid.

Current Grid information and monitoring frameworks have identifiable drawbacks, as they are either too focused to specific aspects or do not scale enough. The performance of the infrastructures is also not satisfactory, especially when security and reliability are required. The institute will focus its research to better understand the reasons and to find models and frameworks to overcome these limitations. In close collaboration with the institute on system architectures, appropriate architectures for scalable and dependable information and monitoring infrastructures will be investigated and deployed. A possibility for convergence of currently distinct approaches to information services and monitoring services will also be taken into account, with the aim to identify a unified framework.

The information provided by the monitoring services will be used to get a better understanding of Grid behaviour. However, the current lack of understanding of grid performance in general, and the non-existence of generally accepted set of metrics to evaluate Grid performance, makes the task of Grid evaluation and performance comparison not possible. The institute will focus on the development of new Grid performance models that will provide the means and tools for the evaluation of services deployed on the Grid.

Complex job workflows represent another challenge, as the monitoring information must be synchronously gathered from many different sources and appropriately processed to provide a coherent view (state information) of the whole workflow and its components. The job workflow itself must be extracted from programming models and the monitoring and information services must be tightly coupled with job checkpointing and migration support to provide an environment where even complex job workflows could be easily deployed, executed, and monitored. Models and methods to provide a virtualized end user account system are a specific part of the combined job flow support and information services.