Real-Time OS Scheduling
Discussions focus on real-time scheduling in Linux and other OSes, including preemptive vs. cooperative multitasking, PREEMPT_RT patches, SCHED_DEADLINE, kernel/user-space preemption, and latency guarantees compared to dedicated RTOS.
Activity Over Time
Top Contributors
Keywords
Sample Comments
Doesn't source love CPU and linux would have had a better scheduler?
That would require a real-time OS, I suppose.
Linux has real time scheduling available though.
This is a common misconception about RTOSes, or at least needs to be further qualified with soft real time vs hard real time OSes. RTOSes provide schedulers and multitasking mechanisms for context switching between tasks. Tasks can be assigned priorities. A higher priority task can pre-empt a lower priority task (depending on the RTOSβ scheduler implementation). In that case, you may never get your cycles, or at least not deterministically. tl;dr, depends on the scheduler implementation.
Doesn't this already exist for processor scheduling?
Because you are likely still running a preemptive multitasking operating system.
You only need a real-time os if you're guaranteeing maximum latency.
From what I understand, it is about interrupts being handled in real-time. For example see the famous PREEMPT_RT Linux patch.
You can, at least in Linux. But in general the OS will do a better scheduling job than you will.
The scheduler that puts your program on a CPU works probabilistically. There are no rigid guarentees of workloads in Linux. Those only exist in real time operating systems.