Assessing the Pessimism of Current Multicore Global Fixed-Priority Schedulability Analysis
Résumé
This work provides a formal assessment on the pessimism of existing methods for the schedulability analysis of multicores with global fixed priority (FP) scheduling. We show how according to the existing analysis methods for FP scheduling, it is relatively easy to define a simple task allocation strategy followed by local analysis that dominates the existing global-FP feasibility analysis algorithms, in terms of deadline guarantees. Rather than being an indication of a true comparison between the effectiveness of local and global policies, we consider the result as an indication of the limited maturity of multicore global analysis (and its outstanding pessimism). Additionally, we show how a simple change in the task model, consisting in splitting the task execution and performing the analysis in two stages, allows to provide a better global schedulability analysis that overcomes this limitation. However, the new analysis mainly aims to show where the demonstrated pessimism most likely comes from. Due to the huge pessimism pointed out on existing analyses and the limited improvement from the new analysis, more efforts from the community are needed to enhance the multicore global scheduling works.
Origine : Fichiers produits par l'(les) auteur(s)