Re: [linux-pm] [RFC] Asynchronous suspend/resume - test results

["Rafael J. Wysocki" <rjw@sisk.pl>]

On Friday 25 December 2009, Nigel Cunningham wrote:
> Rafael J. Wysocki wrote:
> > On Thursday 24 December 2009, Nigel Cunningham wrote:
> >> Hi.
> > 
> > Hi, 
> > 
> >> I built the async branch of your tree and tested it, also running
> >> 2.6.33-rc1 + TuxOnIce for comparison. Dmesg for both are attached. Is
> >> there anything I can/should be doing for you on top of this?
> > 
> > No, thanks a lot.
> > 
> >> I'll try Dmitry's patch on top of this a little later - other things to do first.
> > 
> > No need for that, the patchset contains an equivalent of the Dmitry's patch.
> > 
> >> I noticed that you were doing standard deviations in your stats - how
> >> many runs were you basing them on?
> > 
> > I usually run 10 iterations of suspend-resume for each configuration.
> > The raw data are at http://www.sisk.pl/kernel/data/async-suspend-updated.pdf
> > if you're interested.
> > 
> >> Not sure that I can be bothered to do too many - too much else to do!
> > 
> > Sure, thanks a lot anyway.  Your data confirn that there's a measurable gain
> > from suspending and resuming devices asynchronously.
> 
> It did? I thought it showed no difference at all!

Yes, it did.  Please compare these lines:

(from the "sync" dmesg):
[   31.640676] PM: freeze of devices complete after 709.277 msecs
[   37.087548] PM: restore of devices complete after 4973.508 msecs

(from the "async" dmesg):
[   25.600067] PM: freeze of devices complete after 620.429 msecs
[   29.195366] PM: restore of devices complete after 3057.982 msecs

So clearly, there's a difference. :-)

Of course, in terms of total hibernate/restore time this is only a little
improvement, but if that was suspend to RAM and resume, the reduction of
the device resume time by almost 2 s would be a big deal.

> I'll see if I can find the time to do the other computers, then.

I'd appreciate that very much.

> We're going away for a couple of weeks on Monday, though, so I'm not sure
> that I'll get the time beforehand.

OK

Rafael