Slashdot Mirror

← Back to Stories (view on slashdot.org)

Intel's PowerTOP Extends Linux Battery Life

Posted by kdawson on from the using-the-hooks dept.

DuracellFan writes "Intel recently released its PowerTOP utility, which builds on work done by kernel developers to make the Linux kernel power-efficient. PowerTOP gives a snapshot of what apps are consuming the most power. The PowerTOP website also hosts patches for several Linux apps and the kernel. In the Linux.com article, lead PowerTOP developer Arjan van de Ven of Intel says that PowerTOP could soon show which applications keep the disk busy." Linux.com and Slashdot are both part of OSTG.

7 of 113 comments (clear)

  1. Re:How stable is CONFIG_NO_HZ? by VON-MAN · · Score: 2, Informative

    Doesn't really matter. You can make yourself a custom kernel just to check your apps and services with NO_HZ. Then when you've identified the misbehaving processes you can fix them and start using your old kernel again.

  2. How about hours? by eddy · · Score: 5, Informative

    Success Stories

    "With PowerTOP, I managed to increase the battery life of my Panasonic R4 laptop from 4 to almost 7 hours" -- Keith Packard, Principal Engineer at Intel

    Guess you could accuse him of bias...

    --
    Belief is the currency of delusion.
    1. Re:How about hours? by eddy · · Score: 3, Informative

      If you just read the site (it's very small) you'll see that there are many no-obvious things you can detect with it. I personally do however consider it primarily a developer tool, but that might change. But even non-coding users can find out that the CDROM automounting polling is waking the CPU a lot, and disable that in battery mode, etc.

      --
      Belief is the currency of delusion.
    2. Re:How about hours? by caseih · · Score: 2, Informative

      Kieth was well-known in the Linux world before he went to work for Intel. He's largely responsible for the composite X extension, and even the Xorg fork. I also believe he had some influence on the technology responsible for making compiz work. I remember using an early version of his experimental, fancy rendering X server. Also, notably, he created the kdrive mini x server for embedded environments. So he's got a lot of low-level linux experience.

      Getting 7 hours of battery life is indeed impressive. Does anyone know what the Panasonic R4 gets when running windows?

      Maybe Apple will take some of this work and apply it to their OS. MacBook and MacBook Pro battery life is dismal compared to your average Dell business laptop running Windows.

  3. Re:Linux does not consume power! by Anonymous Coward · · Score: 1, Informative

    Definitely hard disk's activity is not a major contributor to power consumption. CPU usage is. Disks do require some juice to spin up (not that much though), but it's the CPU that makes the difference once the system is up and running. I know because this week I benchmarked precisely this issue: searching a file throughout the filesystem only raised consumption from 0.6 A to 0.65 A, but it went all the way up to 1.0 A when the CPU was at 100% (and at that point running the filesystem search did not raise consumption at all, indicating that the 0.05 A were due to CPU activity during file search and not to disk head moving or data flowing through the SCSI bus).

  4. Re:Laptops??? What about my server farm? by Spoke · · Score: 2, Informative

    C'mon what are we talking about here, a few minutes? AFAIK, better power savings comes through a good acpi config, which I don't see a whole lot of discussion on.

    The biggest and easiest power savings come from CPU frequency scaling (if your processor supports it). Linux has long done a good pretty good job of putting the CPU to sleep and low power states when it can.

    For older Athlon/Duron processors installing/running athcool makes a significant difference in power consumption (as long as it runs stable on your hardware, which it isn't guaranteed to do). On one of our old servers it reduced idle power draw from 100w to 65w.

    My guess is where this kind of thing would make a dollars/cents difference is in the NOC. But this kind of detail isn't very sexy or very high on most NOC operators radar.

    It might depending on how idle your servers are. The more idle they are, the bigger the possibility for power savings. While they are obviously targeting laptop battery consumption, all Linux machines running this tool (and kernel 2.6.21 or later which has the dynticks feature) will be identify what is waking up their processor from low power states.

    Much of the work put into optimizing battery life on laptops will also apply to desktops and servers alike.
  5. Re:How stable is CONFIG_NO_HZ? by Ant+P. · · Score: 4, Informative

    I'm using NO_HZ on my P4 desktop. It was horrible in old patches, but the version in the mainline kernel (>= .20) is solid as a rock.

    I gave the powertop thing a try the other day. Seems the worst offender on my machine is MPD, even when it's not doing anything.