Answers are grounded in this paper and cite their sources.
We develop a testbed for multiprocessor real-time scheduling algorithms based on Linux and implement it on an Apalis iMX6 quad computer on module. This provides an interface to support different real-time task scheduling policies and a mechanism for managing the schedulers that can be used at runtime. Three built-in schedulers are currently available: GEDF, G-RM and DP-WRAP. With the proposed framework, periodic synchronous tasks with implicit deadlines can easily be generated using configuration files in JSON format, and parallel DAG tasks can be supported for G-EDF and G-RM, which can be used for evaluation of the schedulers. The open source tools trace-cmd and kernelshark are integrated into the testbed for task tracing and overhead recording. Unlike existing testbeds, ours is developed and tested based on the embedded platform, meaning that it is closer to a practical environment. Support for parallel DAG tasks is also a major feature of this testbed.
No takes yet. Share an insight, caveat, or question.
Qiao et al. (2021) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: