Perspectives Workshop: The Future of Grid Computing

Motivation

For more than ten years Grid computing has been promoted as the global computing infrastructure of the future. From a user’s perspective, this claim is based on the observation that large scale simulation and computer usage is spreading fast in many disciplines, from natural sciences via engineering even to the humanities. Therefore, the use of large computing systems has reached areas whose members have traditionally little experience in administrating and managing these systems. To these areas, the concept of a computing infrastructure similar to the electrical power infrastructure is particularly appealing. Similar to many electrical power plants, larger compute centres are more efficient with respect to administration and operation than many smaller distributed installations.

The prospect of Grid computing has convinced many countries to provide significant investments into the generation of a Grid infrastructure during the past years, like, for instance, the D-Grid initiative in Germany. Undoubtedly, Grid computing has reached production status in Enterprise Grids and in some communities that require huge amounts of data and use a hierarchical storage concept, like particle physics. But the number of users is still small compared to the forecasts often publicly announced in project descriptions and vision publications. Are these expectations realistic in the long run or will Grid computing remain a niche for relatively few users with special demands and for large enterprises? Do we simply need to wait until sufficient users acquire a taste for Grid computing or shall we develop an appropriate strategy to accelerate this process? We like to address these und some of the following questions in a Dagstuhl Perspectives Seminar.

In general, computer users will move to a new paradigm if the expected benefits dwarf the transition costs. Therefore, we need to address both sides of the coin. While already many publications present approaches to enhance the eventual benefits of Grid computing shall we also increase our efforts to reduce transition costs for the user? Can we identify user groups that are very eager to use Grid computing and may help us to quickly reach system maturity thus reducing transition costs? However, this approach may automatically focus on core services and may create obstacles for building a general Grid with many higher level services. But do most users actually need such a Grid with many high level services or is the cloud computing concept sufficient for the majority of applications?

We believe that these questions can only be answered by examining the foundations of Grid computing. As Grid computing touches many areas of computer science there is an increasing number of computer scientists who pick their favourite research topics to produce some more or less Grid related results. This uncoordinated type of research is likely to produce good results in the long run as most niches are eventually covered by experts in the corresponding fields. However, it may take a long time to achieve a solution for a complex system like an efficiently working production Grid with many interacting services. Can we accelerate this process by identifying the key problems of Grid computing and by convince our colleagues to address them in a systematic and coordinated manner incorporating existing research in related areas of computer science?

We have listed some examples of these key problems that may serve as a starting point:

1. Execution of complex applications (with parallelism or complex workflows) on different platforms, for instance by using virtualization techniques.
2. Programming of Grid applications by people without knowledge of the used middleware, system software, and hardware.
3. Protection of data and software independent of the execution site.
4. Interoperability of different Grid systems to allow the exchange of resources and jobs.
5. Organizational structure of a Grid system to assure long term sustainability.

As related problems have already been addressed in different computer science areas, the state of the art in related fields of computer science and the experience with existing Grid systems must be taken into account when identifying the key problems. This particularly applies to distributed systems as Grid systems can be seen as an extension to them with additional new properties, like independent resource ownership and virtual organizations. Therefore, most problems of distributed computing, like security, programming paradigms, resource management, networks are also highly relevant for Grid computing. However due to their potential size and their new properties, Grid systems may need new approaches to solve these problems. Additionally, new problems like the efficient handling of huge data sets must be addressed. Further, a sustained operation of a large Grid organization may require new concepts to ensure cost recovery.

Contrary to many other workshops or seminars with the topic Grid, we do not strive to solve individual Grid related problems but to discuss which problems must be solved in order to create a sustainable Grid infrastructure. We strongly believe that it is time to determine some kind of research roadmap towards mature Grid systems. These results can help when actually building the Grid infrastructure on a national or international scale. Unfortunately, Grid requirements of two different communities are usually not the same leading to the identification of different problems. Therefore, we plan to bring together representatives of different Grid systems in science and business as well as computer scientists from different areas. We believe that our Dagstuhl Perspectives Seminar will provide the opportunity for a fruitful exchange of concepts and ideas based on the different background of the participants.