Power consumption out of box

Alan Pope alan at popey.com
Mon Oct 15 11:07:37 BST 2007

Hi Justin,

On Mon, 2007-10-15 at 04:31 -0500, Justin Dugger wrote:
> I don't think people will be doing heavy file / number crunching, but
> there is a slightly more valid use case: video games.

Sure there are other use cases, I was just outlining mine. I guess we
could come up with typical uses that people have for their laptops, ways
in which they use their machines off the battery. This is actually
partly what I was suggesting the wiki for. Not for collecting the
statistical data, I agree that could be presented in a much better form.
More for the continuation of this very discussion. Putting together the
aims and objectives, the lists of use cases, and ultimately
scripts/programs for performing the tests. 

If we had a robust system of test scripts then it's entirely plausible
that any ubuntu user could benchmark their laptop and contribute back
their results. This would give a much better overall result than the
"one thinkpad benchmark" performed in the study your referred to.

>   I kind of take
> issue with glxgears as somehow 3d representative. As the nouveau
> people pointed out, it is a benchmark, but only of buffer clearing
> speed.  It doesn't put texture rendering to work, or much of the rest
> of the 3d chipset.  Everyone says it's not a valid 3d benchmark, and I
> suspect for power consumption purposes this is true.

Of course it depends _what_ we want to test. I'd suggest we look at that
first before picking and choosing tools/apps/test-suites and trying to
mould them into the use case. I'd start with a dozen or so laptop use
cases, using "basic browsing, email, IM", "watching DVD full screen" and
so on as a starter. Then figure out what tests we might perform

> That sounds like a nifty endeavor. What do you think of the 'stress'
> package?

Never used it, but having just installed and played it looks like
another way of putting a non-use-case load on the system. Of course if
you _do_ use that and you use that on every system then you're comparing
like for like. Just not real-world performance. It depends what you want
to achieve.

> Has anyone actually gone about seeing to the powertop suggestions?

I fired up powertop when on battery and took note of the suggestions it
made. I get about 3 hours out of my laptop where previously I think I
would get about 2-2.5. That's of course just finger in the air, but
could be nailed down with some numbers if we went through this process.

> Some of them aren't user friendly, but some seem fairly innocuous.
> It'd be nice to document an opinion if a set of suggestions haven't
> been included for sound reasons.

I collated the suggestions into a script which I just run when I "go

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
Url : https://lists.ubuntu.com/archives/laptop-devel/attachments/20071015/c6c46d98/attachment.pgp 

More information about the laptop-devel mailing list