This years RT-Summit is mostly in a workshop format. Short introductory talks to get the discussion rolling and deep diving into technical issues.
| Time | Topic | Session lead, presenter |
|---|---|---|
| 9:00 | Introduction | |
| 9:15 | Preempt-RT - State of the union | Thomas Gleixner |
| 10:00 | Mind the gap - between real-time Linux and real-time theory | Daniel Bristot de Oliveira |
| 11:00 | Break | |
| 11:30 | Printk | John Ogness |
| 12:30 | Lunch | |
| 13:30 | Scheduler and related RT pitfalls | Peter Zijlstra |
| 15:00 | Break | |
| 15:30 | Softirq handling | Thomas Gleixner |
| 16:30 | Open discussion and wrap up | |
| 17:30 | Beerstorming |
It is common to see RT Linux being used on research projects. However, the assumptions made in papers are very often unrealistic. In contrast, researchers argue that the latency metric, although useful, is an oversimplification of the problem.
It is a consensus that the academic research helps to improve Linux’s state-of-art, and vice versa. So how can we reduce the gap between these task forces? The real-time researchers start papers with a clear definition of the task model. But we do not have a task model for Linux: this is where the gap is.
This talk presents effort on establishing the task model for the PREEMPT RT Linux. Starting with the description of the operations that influence the timing behavior of tasks, passing by the definition of the relationships of the operations. Finally, the outcomes for Linux, like new metrics and a model validator for the kernel, are discussed.
Daniel Bristot de Oliveira is a Senior Software Engineer Red Hat. He is also a last year Ph.D. candidate at the Scuola Superiore Sant'Anna (ITA) and Universidade Federal de Santa Catarina (BRA). In all cases, working with real-time related subjects.