HPET on ICH4 and -hrt7 patch

[Andre Müller]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512

Carlos R. Mafra wrote:
> Yes, it is a patch to a vanilla 2.6.22-rc4. I have used it and I got no
> hunks.
> 
> I have a problem with it, tough. Its power usage is almost 3 Watts more
> than
> a vanilla 2.6.22-rc4 or 2.6.22-rc4-hrt2 and it broke powertop´s
> display of C-states info.
> 
> Following Andre´s Muller teaching in the last email, I found out that
> it indeed was using
> hpet as a clocksource. And if I change it on the fly to use tsc my
> desktop becomes very
> slow and it is almost imposible to use.
> 
> So I gave up trying it on my machine, and I am back to 2.6.22-rc4,
> trying to get used to  <extra timer interrupt> being at the top of
> powertop´s listing.
> 
> I wonder if there is a minimal enable-hpet-on-ICH4 patch, without all
> the extra things in
> -hrt7...

There is:
http://www.tglx.de/projects/hrtimers/2.6.22-rc4/broken-out/hpet-force-enable-on-ich34.patch
there is another suspicious name, but if i get it right it is detection
only:
http://www.tglx.de/projects/hrtimers/2.6.22-rc4/broken-out/hpet_ich_force_enable_46.patch

Not that it helped here,
something changed since -hrt2,
but I've still no clue what it is.

Best, Andre


-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (GNU/Linux)

iD8DBQFGcGSWhYOgL/M0VS0RCtaoAJ9Lcc796D0Uh0ML4O0jLPe0PhPRWwCeKhrB
abwZ9o0S6DyL8XtezdgrBhI=
=GHdY
-----END PGP SIGNATURE-----