Scheduling algorithms for Elastic Mixed-Criticality tasks in multicore systems

Abstract

Abstract-The Elastic Mixed-Criticality (E-MC) task model and an Early-Release EDF (ER-EDF)scheduling algorithm have been studied to address the service interruption problem for lowcriticality tasks in uniprocessor systems, where the minimum service requirements of low-criticality tasks are guaranteed by their maximum periods. In this paper, focusing on multicore systems, we first investigate and empirically evaluate the schedulability of E-MC tasks under partitioned-EDF (P-EDF) by considering various task-to-core mapping heuristics. Then, to improve the service levels of low-criticality tasks by exploiting slack at runtime, with and without task migrations being considered, we study both global and local early-release schemes. Moreover, considering varied migration overheads between different cores, we propose the multicore-aware and migration constrained global-ER schemes. The simulation results show that, compared to the state-of-the-art Global EDF-VD scheduler, P-EDF with various partitioning heuristics can lead to many more schedulable E-MC task sets. Moreover, our proposed global and local ER schemes can significantly improve the execution frequencies (and thus service levels) of low-criticality tasks, while Global EDF-VD may severely affect them by discarding most of their task instances at runtime (especially for systems with more cores). Furthermore, by allowing task migrations, global-ER schemes can dramatically improve low-criticality tasks' service levels for partitionings that do not balance high-and low-criticality tasks among the cores.

Adaptive Mixed Criticality Scheduling with Deferred Preemption

“…This transition can, however, only occur if all newly released LO-criticality jobs can be guaranteed. This issue, of reimposing the pre-conditions on the system for LO-criticality behaviour, is essentially orthogonal to the topics addressed in this paper, and is therefore not considered further here (it is discussed in [3], [21], [22], [30], [29], [23], [14]). …”

“…This abstract behavioural model has been very useful in allowing key properties of mixed criticality systems to be derived, but it has been necessary to extend the model to allow for more realistic characteristics such as allowing some LO-criticality work to execute in the HI-criticality mode and for the LO-criticality mode itself to be reinstated [5], [30], [29], [23], [14]. Work has also focused on criticality-aware resource control protocols that allow resource sharing between tasks [13], [32], [25].…”

Two-Phase Low-Energy N-Modular Redundancy for Hard Real-Time Multi-Core Systems

“…Many previous works in the context of multi-processor systems either propose energy reduction management techniques without considering reliability (e.g., [14], [15], [32], [33]) or consider reliability without considering energy consumption (e.g., [4], [30], [34]). [14] has considered variation in execution times to propose a scheduling algorithm based on dynamic voltage scaling (DVS) [12] for multi-processor systems.…”

“…ULTI-CORE platforms have emerged to be popular and powerful computing engines for many recent embedded systems [1], [2], [3], [4], [5]. While such architectures have been employed for embedded applications that require high performance computing, we believe they also offer new considerable opportunities for designing embedded systems where hard real-time operation, high reliability in the presence of transient faults, and low energy consumption are required [6], [7], [8].…”

Mixed-Criticality Scheduling on Multiprocessors Using Task Grouping

“…For instance, Su et al [17], [26] studied an elastic mixed-criticality task model that allows low-criticality task to have different periods in different system modes. To maximize the execution rate of low-criticality tasks, Jan et al [18] introduced stretching factors and proposed an associated online decision algorithm based on the existing elastic task model.…”