Re: long delays (possibly infinite) in time_interpolator_get_counter

[Bjorn Helgaas <bjorn.helgaas@hp.com>]

On Saturday 30 July 2005 12:10 pm, Christoph Lameter wrote:
> On Sat, 30 Jul 2005, Alex Williamson wrote:
> 
> > On Fri, 2005-07-29 at 16:31 -0700, Christoph Lameter wrote:
> > > What you are dealing with is a machine that is using ITC as a time bases. 
> > > That is a special case.
> > 
> >    The default time source for ia64 systems is a "special case"?  4
> > socket and smaller boxes typically do not have any other time source.
> 
> It is a special case because we typically use other time sources.

Maybe you==SGI typically use other time sources, but most other
ia64 boxes have synchronized ITCs.  There's no reason such machines
should have to use the slower and lower precision HPET.

> If it is really synchronized then you can run with "nojitter" without any 
> issue. Then you wont have to deal with the cmpxchg and everything is fine. 
> But I suspect that the ITC are NOT truly synchronized (it has an 
> "offset" that may be nonzero right?) otherwise you would have used nojitter.

And why should everyday users have to be concerned with "nojitter"?

> Extra timer hardware is necessary to fix the ITC deficiency. You are at 
> the source of the problem. Fix the damn hardware to provide a standardized 
> synchronized clock or provide a truly synchronized ITC.

The "ITC deficiency" is a platform design issue.  Most small SMP platforms
*do* synchronize the clocks of all processors.  Obviously that's difficult
on large boxes, and then you may need extra timers in the platform.