On 1/31/2007, "Pavel Machek" <pavel at suse.cz> wrote: >On Wed 2007-01-31 13:53:20, Amit Kucheria wrote: >> On Wed, 2007-01-31 at 11:48 +0100, ext Andi Kleen wrote: >> > On Wednesday 31 January 2007 11:27, Matthew Garrett wrote: >> > > On Wed, Jan 31, 2007 at 12:13:04PM +0100, Andi Kleen wrote: >> > > > Matthew Garrett <mjg59 at srcf.ucam.org> writes: >> > > > > >> > > > > PCI seems to require a delay of 10ms when sequencing from D3 to D0, >> > > > > which probably isn't acceptable latency for an "up" state. >> > > > >> > > > It might be if the interface has been idle for some time >> > > > (and the delay is not busy looping of course) >> > > >> > > Hm. How would this interact with receiving packets? >> > >> > The hardware will hopefully have support to wake itself up when that >> > happens. >> >> Yes. Low power states without ability to respond to wakeup interrupts >> would be broken behaviour generally. > >Do you realy expect wifi to save significant ammount of power, while >still listening for packets on wireless network? Yes, that's what 802.11 PSM is for: your 802.11 hardware can sleep for significant amounts of time and wake up periodically, then check from the beacons if the AP has been buffering some frames for it. The duty cycle can be quite low, depending on how often you decide to wake up and catch beacon frames. Cheers, Samuel.
