[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: Bug#110273: ITP: lvcool -- "cools" the AMD K7 (Athlon/Duron) CPU



On Mon, Aug 27, 2001 at 01:08:53PM -0400, Noah Meyerhans wrote:
> On Mon, Aug 27, 2001 at 03:08:21PM +0200, Eduard Bloch wrote:
> > Package: lvcool
> > Description: "cools" the AMD K7 (Athlon/Duron) CPU
> >  This little utility will cool your Athlon/Duron processor on Via
> >  KT133 or KX133(A) (VT8363 or VT8371/VT82C686x) chipsets during idle
> >  states. It switches to STPGNT mode and works "more effective" than
> >  kernels HLT command.

That's not the point.  I expect ACPI to do STPGNT in addition to halt.
The additional power saving comes from enabling the frontside bus
disconnect on STPGNT.  When disconnected the Athlon can save a lot more
power.

> This tool is not necessary; ACPI support in the kernel will do it
> automatically.

No, it won't.  The disconnect is disabled by most BIOSes for various
reasons[1] and ACPI essentially just executes BIOS provided bytecode.

However the general idea of lvcool is bullshit.  Linux doesn't need
stupid idle loop programs, it's open source for hell's sake!  All we
need is a one line patch (or two line, to include the conditional
checking for right chipset) to the kernel to set that one bit to enable
disconnect.  That's all.

I oppose the packaging of lvcool.  It's a totally wrong approach due to
being written by a person who is "not a Linux guy" (his own words).


[1] Reasons include marketing (benchmarks) and the fact that many
    cheaper power supplies and motherboards are not up to the task.  And
    some Athlon errata for some runs and certain circumstances.

-- 
Andreas E. Bombe <andreas.bombe@munich.netsurf.de>    DSA key 0x04880A44



Reply to: