"With all the tickless [story] and other goodies going into the kernel in the last few months, there is a lot of hope that this helps Linux reduce power consumption," Arjan van de Ven began on the lkml, "and the good news is that it does... once you fix some bugs and fix a bunch of userspace applications." He referred to a promising graph generated utilizing the recently introduced PowerTOP utility [story], measuring power consumption before and after applying a series of related bug fixes.
The tests began with a Lenovo T61 laptop running the stock 32-bit Fedora 7 kernel which includes the tickless kernel. This was compared against the stock 2.6.22-rc4 kernel with a series of improvements including a fix for the Ondemand CPUFREQ governor, the new CPUIDLE infrastructure, the Active Link Power Management patch, disabling the laptop's TV-out capability, and using a cli utility to properly reduce the laptop's backlight. Arjan summarizes, "with kernel fixes and features, the power consumption of this laptop went from 21.06 Watts to 18.25 Watts; with 2 additional userspace fixes the power consumption ended up at 15.5 Watts."
From: Arjan van de Ven [email blocked] To: linux-kernel Subject: Liunx power consumption on laptops -- Enormous progress in the last few months Date: Thu, 05 Jul 2007 12:58:58 -0700 Hi, with all the tickless and other goodies going into the kernel in the last few months, there is a lot of hope that this helps Linux reduce power consumption... and the good news is that it does... once you fix some bugs and fix a bunch of userspace applications. While it's hard to show "one size fits all" number/percentage, we took a bog standard Lenovo T61 laptop (no vendor preference, they just were the first one to deliver a model with the latest Intel chipset to our cubes) and measured the effect. The baseline we used was a 32 bit Fedora 7 installation; note that this already has the tickless kernel, but is lacking several of the key bugfixes that came afterwards. We've put our measurements in a graph at http://www.linuxpowertop.org/results.php With kernel fixes and features, the power consumption of this laptop went from 21.06 Watts to 18.25 Watts; with 2 additional userspace fixes the power consumption ended up at 15.5 Watts. (Don't worry that this is the end of it; there's more stuff in the various project pipelines, and we'll keep measuring the progress over time) All in all, personally I'm very happy to see Linux making such a huge step forward with tickless and can't wait for this step to be available in all distros and for all architectures... Greetings, Arjan van de Ven
Tickless or not?
That's a lot of changes but the headline indicates that tickless is responsible for a power improvement. Do you have data for just this one change? I doubt it's anywhere near as much as the other features mentioned - or was tickless a prerequisite for implementing those things?
It would make no sense to
It would make no sense to track down and fix the top causes of CPU wakeups if we still had the 250 (or worse) HZ timer interrupts: with HZ, the CPU can't stay long enough in deep C-states (C3 or C4) anyway. So yes, tickless is a prerequisite (beside saving power by itself).
By the way, the benefits of tickless and high resolution timers isn't only power savings. They also brings you strong accuracy for multimedia editing (think real time audio/video). Also, it's good for virtualisation: having dynticks guests reduce the interrupt storm presure on the host.
While not entirely true it
While not entirely true it is essentially a prerequisite. If you didn't have tickless, idling properly wouldn't save as much. The backlight probably doesn't have much to do with tickless though.
gnome-power-manager does more than changing pixel colour?
The author of gnome-power-manager argues that it does turn off the backlight and does more than changing pixel colour:
I'd be interested in the
I'd be interested in the power usage of the same laptop when running Windows (XP, Vista). Reducing power usage is good in itself, but if it is another benefit over Windows then it'd be good to know.
If Windows has lower power consumption (which would surprise me) then that would be a good target to beat...
Indeed
That'd be interesting indeed. From what I heard and from what I observed with my Vista laptop, Vista achieves very poor results regarding power consumption. Although my laptop runs Vista a benchmark against XP is more interesting IMO.
comparison to XP
On quite a few laptops WinXP scores a lot better with power consumption, while vista seems to be slightly worse than linux on average. For example on my thinkpad R60 win XP can last up to 4.8 hours (tried) while the best i got under linux (tickless 32bit kernel) was about 3.5h. - Both tuned to minimum power usage.
Yes I've noticed the same
Yes I've noticed the same using Vista laptop. There is an obvious advantage for the XP regarding this matter.