Partitioned Scheduling of Parallel Real-time Tasks on Multiprocessor Systems

Frédéric Fauberteau (1) , Serge Midonnet (1) , Manar Qamhieh (2)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 LACSC - Laboratoire d'Analyse et Contrôle des Systèmes Complexes

In this paper, we focus on the scheduling of periodic fork-join real-time tasks on multiprocessor systems. Parallel real-time tasks of fork-join model have strict parallel segments with no laxity. We propose a partitioned scheduling algorithm which increases the laxity of the parallel segments and therefore the schedulability of tasksets of this model. A similar algorithm has been proposed in the literature but it produces job migrations. Ours avoid the use of job migrations in order to create a portable algorithm that can be implemented on a standard Linux kernel. Results of extensive simulations are provided in order to analyze the schedulability of the proposed algorithm compared to the previous one.

Domaines: Algorithme et structure de données [cs.DS]

Frédéric Fauberteau, Serge Midonnet, Manar Qamhieh. Partitioned Scheduling of Parallel Real-time Tasks on Multiprocessor Systems. 23rd Euromicro Conference on Real-Time Systems (ECRTS'11), 2011, United States. pp.1-4. ⟨hal-00620398⟩