The main objective of the Intelligent GRID Scheduling System (ISS) project is to provide a middleware infrastructure allowing a good positioning and scheduling of real life applications in a computational GRID. According to data collected on the machines in the GRID, on the behaviour of the applications, and on the performance requirements demanded by the user, a heuristic cost function is evaluated by means of which a well suited computational resource is detected and allocated to execute his application. The monitoring information collected during execution is put into a database and reused for the next resource allocation decision. In addition to providing scheduling information, the collected data allows to detect overloaded resources and to pin-point inefficient applications that could be further optimised.
Olaf Blanke, Emanuela De Falco, Louis Philippe Albert, Hyeongdong Park, Baptiste Gauthier, Hyukjun Moon, Corentin Marie Hervé Robert Tasu
Danick Briand, Nicolas Francis Fumeaux