Announcement

Collapse
No announcement yet.

Did Linux Power Consumption Improve At All This Year?

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    with tlp install the power usage is much lower, i test my last laptop with a i7 4720hq, with tlp i have more battery in ubuntu 14.04.3 kernel 4.2 and without thermald than w10 without tlp win10 wins

    Comment


    • #12
      Originally posted by milkylainen View Post
      All Windows and OSX-releases have far more in common regarding user experience than any coherent Linux distribution ever had.
      Lol Good joke!

      Comment


      • #13
        I can admit power management improvement: at least some Allwinner ICs got cpufreq driver in mainline kernel. This improved power management on this platform heck a lot. Because it lacked power management before it happened . This has been a very major improvement, which allowed me to run plenty of ARM systems at lower power, much cooler, yet being able to scale when performance matters. For me it counts as noteworthy power management related achievement this year, any day.
        Last edited by SystemCrasher; 28 December 2015, 02:37 PM.

        Comment


        • #14
          Originally posted by andre30correia View Post
          with tlp install the power usage is much lower, i test my last laptop with a i7 4720hq, with tlp i have more battery in ubuntu 14.04.3 kernel 4.2 and without thermald than w10 without tlp win10 wins
          I can believe this. I have yet to find a distribution with a kernel where all the latest features are enabled. They never are.

          I am also somewhat annoyed by the idea that a comparison of two Ubuntu distributions suddenly would reveal the entirety of improvements made and to call this "Linux Power Consumption". It might be a good idea for Michael to just enjoy the holidays and take some time off instead of aiming for a new low in quality. Seems almost like he himself and his articles ran out of power.

          Comment


          • #15
            Originally posted by caligula View Post
            I'd guess that a smaller kernel has less code to run when idle.
            I just want to point out that this is complete nonsense. The size of the kernel has NOTHING to do with how much code it runs when idling.

            Comment


            • #16
              Originally posted by Michael View Post
              If you set PERFORMANCE_PER_WATT=1 environment variable, it will also calculate performance-per-Watt for each test based upon what it recorded for power consumption. Or if you want other non-power metrics, set MONITOR=all environment variable.
              Thanks. What about power states, frequency, etc.?

              Comment

              Working...
              X