An Isolation Scheduling Model for Multicores

Abstract

Efficiently exploiting multicore processors for real-time applications is challenging because jobs that run concurrently on different cores can interfere on shared resources, severely complicating precise timing analysis. We propose a new scheduling model called Isolation Scheduling (IS), IS provides a framework to exploiting multicores for real-time applications where tasks are grouped in classes. IS enforces mutually exclusive execution among different task classes, thus avoiding inter-class interference by construction. We show that IS encompasses several recent advances in real-time scheduling as special cases and we propose global and partitioned scheduling algorithms based on this model. Specific results are provided if the task classes correspond to different safety criticality levels.