The future of European grids

By Danielle Venton, EGEE.

Back to index page

Previous article: Social simulation could help answer the difficult questions

Next article: OMII-UK principle investigator appointed e-Social Science National strategic Director

Enabling Grids for E-sciencE ’09 (EGEE’09) gathered 631 people from 43 countries. The week was exceptional for its rich scientific and technical presentations: attendees chose from 108 programme sessions and were shown 57 posters and 22 demonstrations. Delegates came from a wider-than-usual selection of the Grid community. To take advantage of this expertise, the EGEE communications team held a series of interviews to discover the delegates’ perspectives on a few issues. Some of the delegates’ views are transcribed in the inset boxes to the right.

If you would like to share your perspective, write to project-eu-egee-dissemination@cern.ch.

Where will grids be in 5-10 years?

‘In the future, I'd like to see grids supporting as wide a range of researchers as possible in a variety of fields… at the EGI conferences, instead of having several hundred people, we'd see several thousand,’ David Fergusson, National e-Science Centre.

‘Grids or e-Infrastructure will become the underpinning on which all research will be done, whether or not it is high-throughput computing, high-performance computing, remote instrumentation, visualisation. All of these things should be available quickly and easily to the research communities,’ David Wallom, Oxford e-Research Centre.

‘I hope they will still be there – but I think they will look quite a bit different. What we are already discussing at this and other conferences is how to incorporate new technologies and new ways of using computing resources in the grid. And I think there are two areas where things will look very different: at the infrastructure level where I think we will see a lot of virtualisation and cloud-linked technologies and at the user level where we will see things like Hadoop and other service platforms and application platforms,’ Cal Loomis, EGEE applications.

‘Well, I'm not sure we are going to be using the same name. I think that we will use more cloud-type technology as it shapes up and matures. I think that the whole landscape of computing will be combined, loosely-coupled clusters, integrated with high-performance resources, and we'll see something much bigger and more unified,’ Vangelis Floros, EGEE.

Did grids develop they way you expected?

‘No – I think the dream of the early pioneers was to implement a pervasive, worldwide, unique computing infrastructure. That was simply too difficult for the technology we had available,’ Fabrizio Gagliardi, Microsoft Research.

‘I think yes, but more slowly than I expected,’ John Gordon, STFC-Rutherford Appleton Laboratory. ‘Grids have unfortunately not developed the way I thought they would. I was really hoping grids would become 'real infrastructure' supporting all research, connecting all communities together. We still haven't achieved that yet,’ David Wallom.

‘Yes, I think grids developed in a direction I thought they would, albeit in a much slower way than I expected. I expected they would come along technolocially much faster and I thought we would have a much bigger grid with more usage earlier – like just after European DataGrid. But I think more or less they've developed along the lines of what was foreseen in the beginning,’ Cal Loomis

EGEE’s main achievement?

‘By and far, is the production grid infrastructure that is used all over Europe by many users,’ Cal Loomis.

‘To pull together all these countries so that you can easily and seamlessly submit jobs across national lines,’ John Gordon.

‘I think EGEE has demonstrated that you can take these basic technologies that were theoretical six years ago and you can deploy them to do something which goes well beyond Web or basic internet technology,’ Manuel Delfino, PIC.

‘To continue holding a very disparate community together to build an infrastructure that is now in production,’ David Wallom.

‘The greatest achievement of EGEE is that it became real – out of so many initiatives in the early 90s, only EGEE has grown to production quality with a user community,’ Fabrizio Gagliardi.