1           Project Summary

Project Abstract

Several major international Grid development projects are underway at present both within the European Community, and in the USA. All of these projects are working towards the common goal of providing transparent access to the massively distributed computing infrastructure that is needed to meet the challenges of modern experiments such as the data intensive LHC applications, as well as applications in other disciplines such as Earth Sciences and Bio-informatics. The DataTAG project will create a large-scale intercontinental Grid testbed that will focus upon advanced networking issues and interoperability between these intercontinental Grid domains, hence extending the capabilities of each and enhancing the worldwide programme of Grid development. The project will address the issues which arise in the sector of high performance inter-Grid networking, including sustained and reliable high performance data replication, end-to-end advanced network services, and novel monitoring techniques. The project will also directly address the issues which arise in the sector of interoperability between the Grid middleware layers such as information and security services. The advance made will be disseminated into each of the associated Grid projects.

Objectives

The fundamental objective of the DataTAG project is to create a large-scale intercontinental Grid testbed involving the DataGrid project, several national projects in Europe,  and related Grid  projects in the USA. This will allow to explore advanced networking technologies and interoperability issues between different Grid domains..

Description of the Work

The work is split into six work packages as follows:

• WP1: Establishment of a high performance intercontinental Grid testbed  – To provision the necessary network components to enable the creation of an intercontinental high bandwidth Grid testbed in connection with other US Grid projects such as GriPhyN, PPDG and  iVDGL.
• WP2: High performance networking  – To demonstrate and make available – through the middleware layers – the high performance data transport and advanced traffic management services required for Grid operations.
• WP3: Bulk data transfer validations and application performance monitoring –  To evaluate existing monitoring tools and if necessary adapt them. To study, and design  new tools to validate the intercontinental infrastructure and provide information to understand user perceived performance.
• WP4: Interoperability between Grid domains –  To address issues of  middleware interoperability between the European and US Grid domains and to enable a selected set of applications to run on the transatlantic Grid test bed.
• WP5: Information dissemination and exploitation –  To ensure that the results of the project are widely disseminated and that the results are exploited by existing and future Grid development projects.
• WP6: Project Management – To put in place the necessary structures to ensure the appropriate management of the DataTAG project and the successful delivery of its proposed work.

2           Project Objectives

This project aims to enhance the EU programme of development of Grid enabled technologies through research and development in the sectors relevant to interoperation of Grid domains on a Global scale. In fact, the main goal of this project is the implementation of an experimental network infrastructure for a truly high-speed interconnection between individual GRID domains  in Europe and in the US to be shared with a number of EU projects. However, the availability of a high-speed infrastructure is not sufficient. This is why the project is proposing to explore some forefront research topics like the design and implementation of advanced network services for guaranteed traffic delivery, transport protocol optimisation, efficiency and reliability of network resource utilization, user-perceived application performance, middleware interoperability in multi domain scenarios, etc.

Several major international Grid development projects are underway at present. Within Europe these are spearheaded by the DataGRID project, with many national programmes in partner states forming an integral part of the programme (e.g. GridPP in the UK, INFN-Grid in Italy and NL-Data-Grid in the Netherlands). Major Grid efforts in the US are DTF, GriPhyN, PPDG and  iVDGL. All of these projects are working towards the common goal of providing transparent access to the massively distributed computing infrastructure that is needed to meet the challenges of modern data intensive applications.

To achieve the aim of this project the overall objective is to create a large-scale intercontinental Grid testbed that will link these Grid domains, and allow us to address and solve the problems encountered in the high performance networking sector and the interoperation of middleware services in the context of large scale data intensive applications.

The major operational goals are:

• To establish a global high performance intercontinental Grid testbed based on a high speed transatlantic link connecting existing high-speed national and international GRID testbeds. This infrastructure will be made available to  other EU GRID projects with similar requirements through the GÉANT backbone and National Research Network infrastructure.
• To demonstrate advanced end-to-end network services across multiple domains, including:
• Demonstration and optimisation of reliable high performance data transfer over long distance high bandwidth-delay network connections, aiming for a minimum of 100 Mbit/s end-to-end throughput in the early stages and  Nx100 Mbit/s in  later stages ( where 5 < N < 10 at least).
• Provisioning and demonstration in a multi-domain network scenario of effective and consistent end-to-end network “value added” services including Quality of Service (QoS), managed bandwidth and advance network reservation.
• Estimation of the real usefulness of methodologies for traffic differentiation through tools for user-perceived performance measurement.
• To develop bulk data transfer validation and applications performance monitoring tools including:
• Long-term infrastructure monitoring;
• Monitoring of network performance delivered to the user (throughput and delay);
• Application-level performance monitoring;
• To insure interoperability mechanisms between US and Europe Grid domains, and study the scalability issues which arise, including:
• Interoperation of Grid security mechanisms;
• Interoperation of information services to permit inter-Grid resource discovery.
• To provide the European research community with an intercontinental test infrastructure for advanced network and application test.

Two types of intercontinental network connections will be used: a new  link for high performance network service and data transfer application development, and the other a set of existing production links for interoperability test activities which do not require separation from production traffic. The new intercontinental connection proposed in this project will be a European counter-part of GriPhyN, PPDG  and iVDGL projects. This infrastructure will be made available to other EU Grid projects with similar requirements.

This work will be set firmly in the context of the applications which are part of each of the collaborating Grid projects. In this way the project will be able to demonstrate network services and interoperability so that the practical issues which arise in a production setting are addressed