Re: Which Kernel for soft realtime on ARM 9

That is exactly what I feel:new feature will not be supported by 2.4. So 2.6 is the way to go.

But Wolfgang Denk's arguments _are_ striking: Due to the larger footprint, The O(1) scheduler is a lot slower when there are only a few tasks, especially if there is only a small cache and the time slice interval is small.

So it would be really useful to have a 2.6 version of the O(n) scheduler and define a longer time slice interval. No idea how to do this ?

-Michael
.

Relevant Pages

  • [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm2-V0.7.32-0
    ... latency of RT tasks on SMP systems. ... the new global RT-task balancing feature solves this problem by tracking ... Now on the vanilla 2.6 kernel, if task-C ... on low RT load the scheduler behaves like the stock ...
    (Linux-Kernel)
  • pluggable scheduler flamewar thread (was Re: Volanomark slows by 80% under CFS)
    ... inefficient apps too. ... I'm pretty sure the point of posting a patch that triples CFS performance on a certain benchmark and arguably improves the semantics of sched_yield was to improve CFS. ... We cannot run a fully-functional POSIX OS without a scheduler. ... Any feature without which the OS cannot execute userspace code is sufficiently primitive that somewhere there is a device on which it will be impossible to debug if that feature fails to initialize. ...
    (Linux-Kernel)
  • Re: pluggable scheduler thread (was Re: Volanomark slows by 80% under CFS)
    ... remaining regression without a pluggable scheduler, ... Any feature without which the OS cannot execute userspace code ... And both are switchable at runtime (not just at boot ... but preserving boot-time debugging ...
    (Linux-Kernel)
  • Re: [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm2-V0.7.32-0
    ... I implemented this feature with your workload in mind. ... low-overhead in the common, non-RT case. ... scheduler to fix some RT issue but break the generic scheduler - this ...
    (Linux-Kernel)