Removing the need for state dissemination in grid resource brokering

ABSTRACT

Resource brokering in Grids is nowadays handled by resource brokers that require detailed knowledge of the state of the resources that they broker. In business settings, surrendering internal information on resources to an outside party is not an option. The traditional resource brokering method based on intimate resource knowledge is therefore not a viable possibility.

This paper argues that the publication of resource state data is not needed for resource brokering. Instead, we advocate the use of service level agreements (SLAs). The use of SLAs for brokering lets providers keep state information internal and at the same time provides customers with guarantees on the used services.

The proposed model has been implemented in the form of a resource broker that is based on Web Service technology. It shows that the approach of using SLAs for scheduling is a possible solution to keeping resource state private.

REFERENCES

• 1: Amazon.com. Amazon Elastic Compute Cloud (Amazon EC2), 2007. http://aws.amazon.com/ec2.
• 2: Karl Czajkowski , Ian T. Foster , Carl Kesselman , Volker Sander , Steven Tuecke, SNAP: A Protocol for Negotiating Service Level Agreements and Coordinating Resource Management in Distributed Systems, Revised Papers from the 8th International Workshop on Job Scheduling Strategies for Parallel Processing, p.153-183, July 24, 2002
• 3: Catalin L. Dumitrescu and Ian Foster. GRUBER: A Grid Resource Usage SLA Broker. In: Euro-Par 2005 Parallel Processing. Springer Verlag, 2005.
• 4: Erik Elmroth , Johan Tordsson, An Interoperable, Standards-Based Grid Resource Broker and Job Submission Service, Proceedings of the First International Conference on e-Science and Grid Computing, p.212-220, December 05-08, 2005 [doi>10.1109/E-SCIENCE.2005.17]
• 5: Erik Elmroth and Johan Tordsson. A Grid Resource Broker Supporting Advance Reservations and Benchmark-based Resource Selection. In: Applied Parallel Computing -- State of the Art in Scientific Computing. Springer Verlag, 2006.
• 6: Ian Foster, Carl Kesselman, Craig Lee, Bob Lindell, Klara Nahrstedt, and Alain Roy. A Distributed Resource Management Architecture that Supports Advance Reservations and Co-Allocation. In: Proceedings of the 7th International Workshop on Quality of Service (IWQoS '99), London, England, June 1999.
• 7: G. Avellino et al. The EU DataGrid Workload Management System: towards the second major release. In: Proceedings of the International Conference on Computing in High Energy and Nuclear Physics (CHEP 2003), San Diego, CA, March 2003.
• 8: Kamel Haddadou, Samir Ghamri-Doudane, Yacine Ghamri-Doudane, and Nazim Agoulmine. Designing Scalable On-Demand Policy-Based Resource Allocation in IP Networks. IEEE Communications Magazine, 44(3):142--149, March 2006.
• 9: Peer Hasselmeyer, Changtao Qu, Lutz Schubert, Bastian Koller, and Philipp Wieder. Towards Autonomous Brokered SLA Negotiation. In: Proceedings of the eChallenges e-2006 Conference, Barcelona, Spain, October 2006.
• 10: Dean Kuo , Mark Mckeown, Advance Reservation and Co-Allocation Protocol for Grid Computing, Proceedings of the First International Conference on e-Science and Grid Computing, p.164-171, December 05-08, 2005 [doi>10.1109/E-SCIENCE.2005.13]
• 11: Hui Li , D. Groep , J. Templon , L. Wolters, Predicting job start times on clusters, Proceedings of the 2004 IEEE International Symposium on Cluster Computing and the Grid, p.301-308, April 19-22, 2004
• 12: Jarek Nabrzyski , Jennifer M. Schopf , Jan Weglarz, Grid resource management: state of the art and future trends, Kluwer Academic Publishers, Norwell, MA, 2004
• 13: NextGRID Consortium. NextGRID Homepage. http://www.nextgrid.org/.
• 14: Open Grid Forum. Web Services Agreement Specification (WS-Agreement), March 2007. http://www.ogf.org/documents/GFD.107.pdf.
• 15: Todd Tannenbaum, Derek Wright, Karen Miller, and Miron Livny. Condor: a distributed job scheduler. MIT Press, 2001.

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.7 Organization and Design

Additional Classification:
  C. Computer Systems Organization
  C.2 COMPUTER-COMMUNICATION NETWORKS
      C.2.4 Distributed Systems

General Terms:
Algorithms, Design, Experimentation

Keywords:
e-commerce, grid, resource brokering, service level agreements