Re: [gcv v3 06/35] scheduler: Replace __get_cpu_var uses

[Christoph Lameter]

On Thu, 29 Aug 2013, Steven Rostedt wrote:

> On Thu, Aug 29, 2013 at 04:57:43PM +0000, Christoph Lameter wrote:
> >
> > We could add a ____this_cpu variant that would be used in the cases we do
> > not want preemption checks? There should not be too many but it will
> > mean a whole lot of new definitions in percpu.h.
>
> Let's get away from underscores as they are meaningless.
>
> A this_cpu_atomic() or other descriptive name would be much more
> appropriate.

Its not really an atomic operation in the classic sense.

this_cpu_no_preempt_check_read ?

The problem that I have is also that a kernel with preemption is not
something that see anywhere these days. Looks more like an academic
exercise? Does this really matter? All the distro I see use
PREEMPT_VOLUNTARY. Performance degradation is significant if massive
amounts of checks and preempt disable/enable points are added to the
kernel.

Do we agree that it is necessary and useful to add another variant of
this_cpu ops for this? The concern of having too many variants is no
longer there? Adding another variant is not that difficult just code
intensive.

--
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/