Removing bias from the judgment day: A Ravenscar-based toolbox for quantitative comparison of EDF-to-RM uniprocessor scheduling

Abstract

Abstract Since 1973, Earliest Deadline First (EDF) uniprocessor scheduling has been known to be superior to its Rate Monotonic (Fixed-Priority, FPS) counterpart for its capacity to feasibly sustain full utilization, which FPS can only achieve in certain favorable circumstances. In 2005, further research results illustrated EDF’s superiority in a number of finer-grained performance indicators, such as preemption count, release and response-time jitter, and resilience to transient over+load. Recent work allowed EDF uniprocessor scheduling to be used in place of default FPS in Ada Ravenscar systems with unchanged application code: this development provides an interesting and practical avenue for empirical EDF-to-RM performance comparisons in an especially lean and efficient embedded setting. We leveraged that opportunity to develop a toolbox that enables quantitative per-application comparison of EDF-to-RM uniprocessor scheduling on common embedded targets, using lightweight run-time tracing and offline analytic. Using that toolbox, we performed a vast range of experiments to examine how EDF and RM uniprocessor scheduling operate quantitatively in situations of interest to system design, at a level much deeper than classic utilization tests and their ramifications. Interestingly, the surge of attention around the Edge Computing paradigm makes simple yet efficient and predictable embedded technology that targets Edge-friendly processors, such as our Ravenscar runtime, especially attractive for future use.