There’s a couple of ways of looking at it; general purpose computers generally implement ‘soft’ real time functionality. It’s usually a requirement for music and video production; if you want to keep to a steady 60fps, then you need to update the screen and the audio buffer absolutely every 16 ms. To achieve that, the AV thread runs at a higher priority than any other thread. The real-time scheduler doesn’t let a lower-priority thread run until every higher-priority thread is finished. Normally that means worse performance overall, and in some cases can softlock the system - if the AV thread gets stuck in a loop, your computer won’t even respond to keyboard input.
Soft real-time is appropriate for when no-one will die if a timeslot is missed. A video stutter won’t kill you. Hard real-time is for things like industrial control. If the anti-lock breaks in your car are meant to evaluate your wheels one hundred times a second, then taking 11 ms to evaluate that is a complete system failure, even if the answer is correct. Note that it doesn’t matter if it gets the right answer in 1 ms or 9 ms, as long as it never ever takes more than 10. Hard real-time performance does not mean good performance, it means predictable performance.
When we program up PLCs in industrial settings, for our ‘critical sections’, we’ll processor interrupts, so that we know our code will absolutely run in time. We use specialised languages as well - no loops, no recursion - that don’t let you do things that can’t be checked for an upper time bound. Lots of finite state machines! But when we’re done, we know that we’ve got code that won’t miss a time slot in the next twenty years of operation.
That does mean, ironically, that my old Amiga was a better music computer than my current desktop, despite being millions of times less powerful. OctaMED could take over the whole CPU whenever it liked. Whereas a modern desktop might always have to respond to a USB device or a hard drive, leading to a potential stutter at any time. Tiny probability, but not an acceptable one.
I imagine something like Fedora with an RT kernel and CPU partitioning could be as reliable as an old Amiga. CPU partitioning would let you reserve one or more cores for specific applications such as music production software. Now, the software in question may not be up to the task but that’s a different problem.
Yeah.
There’s a couple of ways of looking at it; general purpose computers generally implement ‘soft’ real time functionality. It’s usually a requirement for music and video production; if you want to keep to a steady 60fps, then you need to update the screen and the audio buffer absolutely every 16 ms. To achieve that, the AV thread runs at a higher priority than any other thread. The real-time scheduler doesn’t let a lower-priority thread run until every higher-priority thread is finished. Normally that means worse performance overall, and in some cases can softlock the system - if the AV thread gets stuck in a loop, your computer won’t even respond to keyboard input.
Soft real-time is appropriate for when no-one will die if a timeslot is missed. A video stutter won’t kill you. Hard real-time is for things like industrial control. If the anti-lock breaks in your car are meant to evaluate your wheels one hundred times a second, then taking 11 ms to evaluate that is a complete system failure, even if the answer is correct. Note that it doesn’t matter if it gets the right answer in 1 ms or 9 ms, as long as it never ever takes more than 10. Hard real-time performance does not mean good performance, it means predictable performance.
When we program up PLCs in industrial settings, for our ‘critical sections’, we’ll processor interrupts, so that we know our code will absolutely run in time. We use specialised languages as well - no loops, no recursion - that don’t let you do things that can’t be checked for an upper time bound. Lots of finite state machines! But when we’re done, we know that we’ve got code that won’t miss a time slot in the next twenty years of operation.
That does mean, ironically, that my old Amiga was a better music computer than my current desktop, despite being millions of times less powerful. OctaMED could take over the whole CPU whenever it liked. Whereas a modern desktop might always have to respond to a USB device or a hard drive, leading to a potential stutter at any time. Tiny probability, but not an acceptable one.
I imagine something like Fedora with an RT kernel and CPU partitioning could be as reliable as an old Amiga. CPU partitioning would let you reserve one or more cores for specific applications such as music production software. Now, the software in question may not be up to the task but that’s a different problem.