high resolution timers in 2.5? (was: [2.6] The List, pass #2)

high resolution timers in 2.5? (was: [2.6] The List, pass #2)

[dank]

Mark Salisbury wrote:
> On Friday 19 July 2002 00:47, Guillaume Boissiere wrote:
> > Would be nice to have before feature freeze, but most likely 2.7:
> >   o High resolution timers
> 
> this has been done for almost a year now, what is holding it up?

I don't know, but it's about time.  George Anziger should know.

George, 
Have you submitted a high-resolution-timers patch to Linux for 2.5?
I seem to recall he didn't like the patch when he first saw
it, but that was so long ago presumably it's much cleaner now?
- Dan

Re: high resolution timers in 2.5? (was: [2.6] The List, pass #2)

[george anzinger]

dank@kegel.com wrote:
> 
> Mark Salisbury wrote:
> > On Friday 19 July 2002 00:47, Guillaume Boissiere wrote:
> > > Would be nice to have before feature freeze, but most likely 2.7:
> > >   o High resolution timers
> >
> > this has been done for almost a year now, what is holding it up?
> 
> I don't know, but it's about time.  George Anziger should know.
> 
> George,
> Have you submitted a high-resolution-timers patch to Linux for 2.5?
> I seem to recall he didn't like the patch when he first saw
> it, but that was so long ago presumably it's much cleaner now?
> - Dan
That was really a very different patch.  The hang up has
been time to work on the code.  There are a few, minor,
changes, like eliminating nanosleep() (it should call
clock_nanosleep()), and then the code clean up to remove all
the debug cruft.  

The next bit I want to submit is the changes to the timer
queue to allow subjiffie timers...

I am hoping to convince my boss to allow me to work on this
full time so I can make some real progress.  As always, any
help will be gratefully accepted :)

-- 
George Anzinger   george@mvista.com
High-res-timers: 
http://sourceforge.net/projects/high-res-timers/
Real time sched:  http://sourceforge.net/projects/rtsched/
Preemption patch:
http://www.kernel.org/pub/linux/kernel/people/rml