Re: [RFC patch 08/18] cnt32_to_63 should use smp_rmb()

[David Howells]

Nicolas Pitre <nico@xxxxxxx> wrote:

> I explained several times already why I disagree.  Preemption is not a 
> problem unless you're preempted away for long enough, or IOW if your 
> counter is too fast.

That's my point.  Say a nice -19 process gets preempted... what guarantees
that it will resume within, the time it takes the counter to wrap?  Even if
the preempting process goes back to sleep, in that time a bunch of other
processes could have woken up and could starve it for a long period of time.

David
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/