Messages in this thread | | | From | David Howells <> | Subject | Re: [RFC patch 08/18] cnt32_to_63 should use smp_rmb() | Date | Fri, 07 Nov 2008 23:55:05 +0000 |
| |
Nicolas Pitre <nico@cam.org> 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
| |