Effective and Efficient Scheduling of Certifiable Mixed-Criticality Sporadic Task Systems

Abstract

Abstract-An increasing trend in embedded system design is to integrate components with different levels of criticality into a shared hardware platform for better cost and power efficiency. Such mixed-criticality systems are subject to certifications at different levels of rigorousness, for validating the correctness of different subsystems on various confidence levels. The realtime scheduling of certifiable mixed-criticality systems has been recognized to be a challenging problem, where using traditional scheduling techniques may result in unacceptable resource waste. In this paper we present an algorithm called PLRS to schedule certifiable mixed-criticality sporadic tasks systems. PLRS uses fixed-job-priority scheduling, and assigns job priorities by exploring and balancing the asymmetric effects between the workload on different criticality levels. Comparing with the state-of-the-art algorithm by Li and Baruah for such systems, which we refer to as LB, PLRS is both more effective and more efficient: (i) The schedulability test of PLRS not only theoretically dominates, but also on average significantly outperforms LB's. (ii) The run-time complexity of PLRS is polynomial (quadratic in the number of tasks), which is much more efficient than the pseudo-polynomial run-time complexity of LB.

Mixed Critical Earliest Deadline First

“…As argued in [10], this assumption applies without restrictions when generating schedules for time-triggered architecture, an important major paradigm for designing safety-critical systems, in particular, in automotive and avionics application domains [12]. Moreover, when applied at run-time, it can be readily imported into computing the dynamic priorities for sporadic tasks [13]. Therefore, this approach is worth considering in many practically relevant RT scheduling contexts.…”

Preemptive Uniprocessor Scheduling of Mixed-Criticality Sporadic Task Systems

“…In Li and Baruah [2010], this result was extended to mixed-criticality sporadic task systems: a scheduling algorithm and associated pseudopolynomial-time schedulability test was proposed that gives the same guarantee. Guan et al [2011] subsequently proposed an algorithm called PLRS that only has quadratic runtime complexity, able to schedule a wider range of instances.…”

“…(5) We provide a schedulability test for EDF-VD having polynomial-time complexity, and also show that the time complexity per scheduling decision is logarithmic in the number of tasks. Based on these runtime properties, it is evident that EDF-VD, in contrast to the algorithms in Li and Baruah [2010] and Guan et al [2011], can be considered suitable for implementation in actual systems. (6) Algorithm EDF-VD sets virtual deadlines in a uniform way for all tasks.…”

A Bailout Protocol for Mixed Criticality Systems

“…Background material on MCS research can be obtained from the following sources [5]- [8], [18], [19], [23], [30]. and from an ongoing survey [14].…”

“…Although the formal study of mixed criticality systems is a relatively new endeavour, starting with the paper by Vestal (Honeywell Aerospace) in 2007 [30], a standard model has emerged (see for example [6], [8], [15], [19], [23], [27]) For dual criticality systems this standard model has the following properties:…”