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

[Nigel Cunningham <ncunningham@crca.org.au>]

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!

I'll see if I can find the time to do the other computers, then. We're
going away for a couple of weeks on Monday, though, so I'm not sure that
I'll get the time beforehand.

Nigel