Re: [PATCH 13/39] NLKD/x86-64 - time adjustment

[Vojtech Pavlik]

On Sat, Nov 12, 2005 at 06:21:11PM +0100, Andi Kleen wrote:
> On Saturday 12 November 2005 10:22, Vojtech Pavlik wrote:
> 
> > Is there any advantage to using 64-bit HPET? 
> 
> Yes - it can tolerate long delays between ticks, e.g. caused by noidletick / 
> debuggers / target probes / smm etc. At least the first case will be fairly
> important soon.

A 32-bit 14 MHz HPET counter will overflow in approximately 5 minutes. I
don't think going 64-bit makes sense for noidletick, but for debuggers,
etc, it could make a good sense indeed.

> > It's read is even slower 
> 
> Why? The read should be on cache line granuality and there shouldn't
> be any difference in theory.
 
I'll try to measure this. Indeed, in theory there shouldn't be a
significant difference.

-- 
Vojtech Pavlik
SuSE Labs, SuSE CR
-
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/