Re: Runtime power management for network interfaces

[David Brownell <david-b@pacbell.net>]

On Monday 31 July 2006 9:17 am, Stephen Hemminger wrote:
> On Tue, 25 Jul 2006 11:59:52 -0400 (EDT)
> Alan Stern <stern@rowland.harvard.edu> wrote:
> 
> > During a Power Management session at the Ottawa Linux Symposium, it was
> > generally agreed that network interface drivers ought to automatically
> > suspend their devices (if possible) whenever:
> > 
> >     (1) The interface is ifconfig'ed down, or
> > 
> >     (2) No link is available.
> 
> This is hard because most of the power may be consumed by the PHY interface
> and it needs to be alive to see link.

True only for #2, yes?  I think #1 could be adopted pretty widely, but
no driver I've yet come across implements that policy.  I think maybe
Don Becker didn't have power management on the brain nearly enough.  :)


> > Has any progress been made in this direction?  If not, a natural approach 
> > would be to start with a reference implementation in one driver which 
> > could then be copied to other drivers.
> > 
> 
> The problem is not generic, it really is specific to each device.

For #2, yes.  Much less so for #1; if the hardware has a low power mode,
there's no point in being in any other mode when the interface is down.

This might actually be a good time to start rethinking power management for
network interfaces.  Upcoming kernels (see the MM tree) have new class
methods for suspend() and resume(), with the notion that they should be
offloading tasks from drivers.  For network links, that would most
naturally be netif_device_detach() on suspend, etc; if netdevices were
to provide suspend() and resume() methods, those could be called via
class suspend/resume as well as when they're configured down/up.  Just
an idea of course ... but it might well be possible that some changes
like that would be a nice incremental power savings on many systems,
while simplifying some tasks that often confuse driver writers.


> We have all the necessary infrastructure to do the right thing in the network
> device driver, but in many cases we don't have the code or the technical information
> to do proper power management.

I think that's more true for wakeup events than for PM in general.  After
all, quite a lot of network drivers do have suspend() methods that do
something even if it's just going into PCI_D3, and resume() methods that
are fully capable of re-initializing from power-off.

- Dave