Algorithm and complexity for the global scheduling of sporadic tasks on multiprocessors with work-limited parallelism

Sébastien Collette (1) , Liliana Cucu (2) , Joël Goossens

1 ULB - Université libre de Bruxelles
2 TRIO - Real time and interoperability

We investigate the global scheduling of sporadic, implicit deadline, real-time task systems on identical multiprocessor platforms. We provide a task model which integrates work-limited job parallelism. For work-limited parallelism, we prove that the time-complexity of deciding if a task set is feasible is linear relatively to the number of (sporadic) tasks for a fixed number of processors. Based on this proof, we propose an optimal scheduling algorithm. Moreover, we provide an \emph{exact} feasibility utilization bound.

Domaines: Systèmes embarqués

Sébastien Collette, Liliana Cucu, Joël Goossens. Algorithm and complexity for the global scheduling of sporadic tasks on multiprocessors with work-limited parallelism. 15th International Conference on Real-Time and Network systems - RTNS'07, Mar 2007, Nancy, France. pp.123-128. ⟨inria-00192213⟩