Response-Time Analysis and Optimization for Probabilistic Conditional Parallel DAG Tasks

TL;DR

This paper introduces a reservation-based scheduling method for probabilistic parallel DAG tasks in multicore real-time systems, ensuring bounded tardiness and deadline misses with probabilistic guarantees.

Contribution

It proposes a novel scheduling algorithm and analysis framework for probabilistic conditional DAG tasks, addressing bounded tardiness and deadline misses without immediate job abortion.

Findings

Guarantees bounded tardiness with specified probability.

Supports applications tolerating limited deadline misses.

Provides design rules for probabilistic real-time scheduling.

Abstract

Real-time systems increasingly use multicore processors in order to satisfy thermal, power, and computational requirements. To exploit the architectural parallelism offered by the multicore processors, parallel task models, scheduling algorithms and response-time analyses with respect to real-time constraints have to be provided. In this paper, we propose a reservation-based scheduling algorithm for sporadic constrained-deadline parallel conditional DAG tasks with probabilistic execution behaviour for applications that can tolerate bounded number of deadline misses and bounded tardiness. We devise design rules and analyses to guarantee bounded tardiness for a specified bounded probability for $k$-consecutive deadline misses without enforcing late jobs to be immediately aborted.