Re: [RFC] sched_clock: Track monotonic raw clock

[Pawel Moll]

On Fri, 2014-07-18 at 18:51 +0100, John Stultz wrote:
> Very cool work! 

Glad that it doesn't sound too ridiculous :-)

> I've not been able to review it carefully, but one good
> stress test would be to pick a system where the hardware used for
> sched_clock is different from the hardware used for timekeeping.

Actually I've got exactly this situation on my board. I've got two
sources, and actually the worse (narrower and more expensive) one is
getting eventually used (because it's registered later - separate patch
to follow).

> Although, looking again, this looks like it only works on the "generic"
> sched_clock (so ARM/ARM64?)...

... and microblaze and xtensa right now, yes. This was just the simplest
thing for me to start with, but I appreciate it doesn't cover all
possible cases. Thus the debugfs attribute to tell userspace what can it
expect from the sched_clock. A hack it is, yes.

Pawel

--
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/