The real-time executive daemon, or the “rtxd”, is a set of Linux processes and Linux process APIs providing a high-resolution computing time reference, a shared memory data management architecture, and a comprehensive set of computing services for real-time and accelerated industrial computing applications. The rtxd transforms the standard Linux computing environment into a microsecond resolution, highly instrumented, distributed computing, client-server platform.
This whitepaper introduces the real-time executive daemon and includes the following sections:
- What is the rtxd?
- Who uses the rtxd?
- The rtx daemon – Linux Real-Time Executive
- Real-Time Computing and Data Handling Frameworks
- Real-Time Assemblies
- Framework Client-Server Architecture
- Performance-Optimized Real-Time Computing – Method to the rtxd Madness
- Data Acquisition Services
- Why a “Real-Time” Linux Server?
- Network, Databus, and Serial Communications
- Compatible Modeling Tools
- Real-Time Linux Comes of Age
This whitepaper is 9 pages long and free to download!
Download the whitepaper here
Applied Dynamics International (ADI) has release the first details of the rtxd project. Here are the basics:
What is the rtxd project?
The “rtx daemon” is a Linux service which runs on ARM- and Intel-based computers and transforms them into fully functioning real-time computers that are internally instrumented with performance, latency, jitter, and other precision time-based measurements for all aspects of the computer architecture.
What does it do?
The goal of the rtxd project is to simplify the development and management of time-deterministic programming.
What is so special about time-deterministic programming?
Traditional programming happens in a “main()” function and runs as fast as it can. This is mostly great, but sometimes things get backed up and become unresponsive. This is annoying when it happens on a PC, but when it happens in a device that is directly connected to the real world, such as the engine computer in your car or the automation controller in a factory, things can get bad quickly. Time-deterministic programming assures that things happen when they need to happen.
Time-deterministic programming sounds great. Why aren’t all programs written that way?
Time-determinism is not easy to get right. Time-deterministic programming must be structured in a specific way that allows the right code to run at the right time without interference from anything else in the system. This means that many of the bells and whistles that can be used in traditional programming will break a time-deterministic system. Even the act of monitoring a system to check whether it’s meeting its timing requirements can cause a time-deterministic system to fail.
What does ADI know about time-deterministic programming?
ADI has spent the last twenty years designing and implementing time-deterministic real-time systems for the aerospace and defense industry. Many of the systems that ADI has created are safety critical and extremely complex, including 10,000+ signals, multiple distributed processing nodes, multi-core architectures, high-speed I/O and industrial communication protocols. Over the years, ADI has refined their lessons learned and tuned their real-time framework for performance and flexibility, and this framework is what ADI is using as the basis to kick-start the rtxd project.
For more details, visit ADI’s rtxd whitepaper post: The rtxd Project: Open Source Real-time for the Industrial Internet of Things.