>Now, if I understand you well enough David, you'd like an
>algorithm where the less you want the CPU, the more you get
>it.
Exactly. This is the UNIX tradition of static and dynamic priorities. The
more polite you are about yielding the CPU when you don't need it, the more
claim you have to getting it when you do need it.
>I'd love if you could actually give us an outlook of
>your ideal scheduler so I can try my thought experiment on it,
>because from what I've understood so far, your hypothetical
>scheduler would allocate all of the CPU to the yielders.
Not all, just the same share any other process gets. They're all
ready-to-run, they're all at the same priority.
>Also, since it seems to worry you: no I'm not using sched_yield
>to implement pseudo-blocking behaviour.
Then tell us what you are doing so we can tell you the *right* way to do it.
Unless this is just an abstract theoretical exercise, you shouldn't complain
when ready-to-run threads get the CPU.
DS
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Jun 23 2002 - 22:00:17 EST