摘要：Service oriented architectures become more and more popular with the emergence and consolidation of new paradigms such as Clouds and Grids. In this context scheduling becomes an important and difficult problem because the services are abstractions. In this paper I present some of the problems which are encountered when designing a job scheduler for system oriented architectures: estimating the performance of the services, estimating the running time of the jobs , enabling the scalability of the system, and I propose solutions for them.
