Re: [PATCH 0/3] ata port runtime power management support

[Lin Ming <ming.m.lin@intel.com>]

On Thu, 2011-11-03 at 22:30 +0800, Tejun Heo wrote:
> Hello,
> 
> On Thu, Nov 3, 2011 at 7:21 AM, Lin Ming <ming.m.lin@intel.com> wrote:
> >> * How much does this add on top of hardware timed auto spindown and
> >>   dynamic link power management?
> >
> > Sorry, I don't understand this question.
> > What do you mean?
> 
> I was curious about the amount of additional power saving on top of
> the existing PM features.

I'll measure the power saving.

> 
> >> * Do the added benefits justify yet another runtime powersaving
> >>   mechanism?
> >
> > There will be ACPI firmware which supports ata port runtime D3Cold.
> > To enable ata port runtime PM is the first step.
> 
> libata can already turn off unused ports although it wouldn't go as
> far as putting the whole controller into D3.

At runtime?
Could you point me which piece of code implement this?

> 
> >> * Any way we can tie the other stuff with overall runtime PM?
> >
> > What's the other stuff?
> > Do you mean tie disk/link/port/controller stuff with overall runtime PM?
> 
> Hardware initiated spin-down (hdparm -S) and link power saving (look
> for ata_lpm_*). It would be great if there's an overall design how
> they interact before adding yet another PM vector.

Yes. Need to think about it.

Thanks.