When debugging something as involved as kernel scheduler timings, you would typically use one of the software-based debugging mechanisms available. However, in cases when software is close to bare metal, you don’t always need to do that. Instead, you can output a signal to a GPIO, and then use a logic analyzer or a scope to measure signal change timing – which is what [Albert David] did when evaluating Linux kernel’s PREEMPT_RT realtime operation patches.
When you reach for a realtime kernel, latency is what you care about – realtime means that for everything you do, you need to get a response within a certain (hopefully very short) interval. [Albert] wrote a program that reads a changing GPIO input and immediately writes the new state back, and scoped both of the signals to figure out the latency of of the real-time patched kernel as it processes the writes. Overlaying all the incoming and outgoing signals on the same scope screen, you can quickly determine just how suitable a scheduler is when it comes to getting an acceptable response times, and [Albert] also provides a ready-to-go BeagleBone image you can use for your own experiments, or say, in an educational environment.
What could you use this for? A lot of hobbyists use realtime kernels on Linux when building CNC machine controllers and robots, where things like motor control put tight constraints on how quickly a decision in your software is translated into real-world consequences, and if this sounds up your valley, check out this Linux real-time task tutorial from [Andreas]. If things get way too intense for a multi-tasking system like Linux, you might want to use a RTOS to begin with, and we have a guide on that for you, too.
[Andreas] has created this tutorial on real-time (RT) tasks in Linux. At first blush that sounds like a rather dry topic, but [Andreas] makes things interesting by giving us some real-world demos using a Raspberry Pi and a stepper motor. Driving a stepper motor requires relatively accurate timing. Attempting to use a desktop operating system for a task like this is generally ill-advised. Accurate timing is best left to a separate microcontroller. This is why we often see the Raspi paired with an Arduino here on Hackaday. The rationale behind this is not often explained.
[Andreas] connects a common low-cost 28BYJ-48 geared stepper motor with a ULN2003 driver board to a Raspberry Pi’s GPIO pins. These motors originally saw use moving the louvers of air conditioners. In general, they get the job done, but aren’t exactly high quality. [Andreas] uses a simple program to pulse the pins in the correct order to spin the motor. Using an oscilloscope, a split screen display, and a camera on the stepper motor, [Andreas] walks us through several common timing hazards, and how to avoid them.
The most telling hazard is shown last. While running his stepper program, [Andreas] runs a second program which allocates lots of memory. Eventually, Linux swaps out the stepper program’s memory, causing the stepper motor to stop spinning for a couple of seconds. All is not lost though, as the swapping can be prevented with an mlockall() call.
The take away from this is that Linux is not a hard real-time operating system. With a few tricks and extensions, it can do some soft real-time tasks. The best solution is to either use an operating system designed for real-time operation, or offload real-time operations to a separate controller.
Continue reading “A Tutorial On Using Linux For Real-Time Tasks”