Search the Dagstuhl Website
Looking for information on the websites of the individual seminars? - Then please:
Not found what you are looking for? - Some of our services have separate websites, each with its own search option. Please check the following list:
Schloss Dagstuhl - LZI - Logo
Schloss Dagstuhl Services
Within this website:
External resources:
  • DOOR (for registering your stay at Dagstuhl)
  • DOSA (for proposing future Dagstuhl Seminars or Dagstuhl Perspectives Workshops)
Within this website:
External resources:
Within this website:
External resources:
  • the dblp Computer Science Bibliography

Dagstuhl Seminar 09131

Service Level Agreements in Grids

( Mar 22 – Mar 27, 2009 )

(Click in the middle of the image to enlarge)

Please use the following short url to reference this page:




Grid computing allows virtual organizations to share resources across administrative domains. In its early days, Grid computing was inspired by the need for transparent access to supercomputing resources and by the idea to even couple the resources in a metacomputing environment to create even more powerful compute resources. Currently the focus is on service-oriented architectures (SOA) where a wide variety of services from multiple administrative domains can be accessed by service clients.

One of the most important tasks of current Grid middleware centers on efficient resource management. Resource providers offer their resource to virtual organizations and publish detailed information about the resources. Recent efforts have also focused on exposing computational and data resources as “services” – thereby providing a single abstraction that could be applied at different levels of software deployment. Based on this information appropriate resources for Grid applications are selected, and jobs are finally submitted to these resources.

Service Level Agreements (SLA) are attracting more and more attention in Grids as a means to guarantee quality of service terms for grid applications and to enable the establishment of novel business models. A wide range of research and development questions have to be addressed in this context. This covers the creation of languages for formulating SLAs that are powerful enough to express the relevant QoS terms, but can also be used to automatically manage the negotiation, execution, and monitoring of SLAs. Brokering systems are required that can select resources for job execution based on the SLA templates offered by the resource owners. Scheduling algorithms that can optimize for different goals in the context of multi-item, multi-attribute, and multi-unit optimization problems are also necessary. Flexible local resource management algorithms are required for provisioning the resources at the provider’s side to meet signed SLAs.

The seminar brought together people working on SLAs in the context of grid computing mainly from computer science, but also from information systems and application areas. These researchers come from different areas and bring in a wide range of research work. The topics covered by people on the invitation list include but are not limited to the following areas:

  • Languages and protocols for creation of SLA
  • Business models
  • Grid economy
  • SLA management
  • Resource management
  • Job scheduling
  • Application deployment mechanisms
  • Negotiation strategies

  • Dominic Battré (TU Berlin, DE)
  • Ivona Brandic (TU Wien, AT) [dblp]
  • Frances Brazier (VU University Amsterdam, NL) [dblp]
  • Marian Bubak (ACK Cyfronet AGH, PL) [dblp]
  • Simon Caton (Cardiff University, GB) [dblp]
  • Donal Fellows (University of Manchester, GB)
  • Michael Gerndt (TU München, DE) [dblp]
  • Cecilia Gomes (Universidade Nova de Lisboa, PT) [dblp]
  • Houssam Haitof (TU München, DE)
  • Markus Hedwig (Universität Freiburg, DE)
  • Matthias Hovestadt (TU Berlin, DE)
  • Sebastian Hudert (Universität Bayreuth, DE)
  • Bastian Koller (Universität Stuttgart, DE)
  • Tianchao Li (IBM Deutschland - Böblingen, DE)
  • Marcel Meyer (TU München, DE)
  • Julian Padget (University of Bath, GB) [dblp]
  • Michael Parkin (Tilburg University, NL)
  • Shamima Paurobally (University of Westminster - London, GB)
  • Kassian Plankensteiner (Universität Innsbruck, AT)
  • Tim Püschel (Universität Freiburg, DE)
  • Thomas Quillinan (Thales Netherlands - Delft, NL)
  • Rizos Sakellariou (University of Manchester, GB) [dblp]
  • Gregor von Laszewski (Rochester Institute of Technology, US)
  • Oliver Wäldrich (Fraunhofer SCAI - St. Augustin, DE)
  • Philipp Wieder (TU Dortmund, DE)
  • Ramin Yahyapour (TU Dortmund, DE) [dblp]
  • Wolfgang Ziegler (Fraunhofer SCAI - St. Augustin, DE)

  • optimization / scheduling
  • Distributed Systems

  • Grid Computing
  • Resource Management
  • Scheduling