Announcement

Collapse
No announcement yet.

The Linux Kernel Power Problems On Older Desktop Hardware

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

  • The Linux Kernel Power Problems On Older Desktop Hardware

    Phoronix: The Linux Kernel Power Problems On Older Desktop Hardware

    As mentioned last week, a plethora of Linux power tests are on the way now that we have found an AC power meter with USB interface that works under Linux and we've been able to integrate nicely into the Phoronix Test Suite and its sensor monitoring framework. In this article is one of the first tests that have been completed using this power-measuring device as we monitored the Linux kernel power consumption for an old Intel Pentium 4 and ATI Radeon 9200 system for the past several kernel releases. Even this very old desktop system looks to be affected by the kernel power problems.

    http://www.phoronix.com/vr.php?view=16164

  • #2
    Something looks very wrong here...

    First: Graph says milliwatts. I suspect that's a mistake, or you've just discovered a pretty amazing system.

    Second on the first graph:
    In terms of the power regressions that we have been tracking down, they are confirmed by this test.
    I don't see it. The way I read that graph is that in .32 and .33 the desktop was not stepping down the power, and was going full bore all the time. In .34 this power management was introduced for the desktop. Then it looks like, from .35 onwards, the stepping up was made more sensitive to increased performance needs, going to full power. This would be to prevent people experiencing stutter, or poor experience with the system stepping up and down constantly.

    Comment


    • #3
      Originally posted by kiwi_kid_aka_bod View Post
      First: Graph says milliwatts. I suspect that's a mistake, or you've just discovered a pretty amazing system.
      That's actually only on the first graph.

      Comment


      • #4
        For p4 the p4-clockmod module only manipulates the fsb. This is not the way as more current cpus work, there the fsb is not changed but the multiplyer in the cpu together with the vcore - these features are called (E)IST/(Enhanced) Intel Speed Step or Powernow (for AMD). Most likely the fsb change did not work on your system with kernel .32/.33, but using intel core cpus it should work - or amd athlon 64 and newer. You should take this info into account when you look at the values.

        Comment


        • #5
          Originally posted by kiwi_kid_aka_bod View Post

          Second on the first graph:

          I don't see it. The way I read that graph is that in .32 and .33 the desktop was not stepping down the power, and was going full bore all the time. In .34 this power management was introduced for the desktop. Then it looks like, from .35 onwards, the stepping up was made more sensitive to increased performance needs, going to full power. This would be to prevent people experiencing stutter, or poor experience with the system stepping up and down constantly.
          I totally agree
          Netrunner Linux - Rolling Release ; Nexus 5 ROM Chroma 5.1 ; NAS 6TB on FreeNAS

          Comment


          • #6
            Originally posted by kiwi_kid_aka_bod View Post
            I don't see it. The way I read that graph is that in .32 and .33 the desktop was not stepping down the power, and was going full bore all the time. In .34 this power management was introduced for the desktop. Then it looks like, from .35 onwards, the stepping up was made more sensitive to increased performance needs, going to full power. This would be to prevent people experiencing stutter, or poor experience with the system stepping up and down constantly.
            Had the exact same thought

            Comment


            • #7
              typo

              you wrote: "it shows the pre-2.5.34 kernels are consuming a vicious amount of power."

              I think you meant "the pre-2.6.34 kernels"

              ?

              Comment


              • #8
                Useless

                The first graph is completely meaningless because it seems that there are different numbers of idle samples to busy samples between kernels.

                Of course if you have more idle points than busy points you're going to have a lower average power. The idle points vs the Busy points are easy to see from the graph. Now look at the ratio of I to B:

                Code:
                KV      I to B     I/B     Av pwr
                ------===========================
                2.6.34  14 to 1    14      54
                2.6.35  10 to 3     3.3    59.3
                2.6.36   9 to 1     9      57.6
                2.6.37   8 to 3     2.6    60.4
                2.6.38   9 to 4     2.25   65.6
                2.6.39  10 to 4     2.5    66.4
                3.0.00   8 to 5     1.6    70.5
                Now sort them by the I/B and notice the average power magically gets sorted too (except for one point which is probably close enough to be within the margin of error).

                Code:
                KV      I to B     I/B     Av pwr
                ===================-----=========
                2.6.34  14 to 1    14      54
                2.6.36   9 to 1     9      57.6
                2.6.35  10 to 3     3.3    59.3
                2.6.37   8 to 3     2.6    60.4
                2.6.39  10 to 4     2.5    66.4
                2.6.38   9 to 4     2.25   65.6
                3.0.00   8 to 5     1.6    70.5
                [sarcasm]OMG the ones with a lower I/B are on a power binge!!![/sarcasm] Completely useless.

                The rest of the graphs are more interesting, mostly because they don't seem to be fundamentally flawed. However, they don't really show that power consumption is that much worse off.

                Of course since the entire article seems to hinge on the first graph...

                Comment


                • #9
                  Michael, with respect: You are doing binary bisecting, right?

                  I mean, you've been "tracking down" this issue for ... I don't know, more than a month now. The fact that you're compiling the kernel on a slow laptop really doesn't sound like a fair excuse anymore. Or are you just still keeping the results for yourself?

                  Comment


                  • #10
                    Originally posted by NeoBrain View Post
                    Michael, with respect: You are doing binary bisecting, right?

                    I mean, you've been "tracking down" this issue for ... I don't know, more than a month now. The fact that you're compiling the kernel on a slow laptop really doesn't sound like a fair excuse anymore. Or are you just still keeping the results for yourself?
                    He wanted to wait til he got the power meter (last weekend) to finish bisecting all the power issues. Hopefully that also means he wants to do it properly, because then the kernel dudes might take it seriously and fix it (and I could move away from 2.6.37...)

                    Comment


                    • #11
                      oh my

                      Are we still beating this dead horse? This power bug doesn't exist, and sadly I'm starting to believe it is being reported on for the sole purpose of driving hits.

                      No, the sky is not falling. Yes, I have used my netbook for 10 hours with kernel 2.6.39 and yes I still had battery left afterwards.

                      Time to let it go and move on, or actually spend time finding the problem instead of writing articles about it.

                      Sorry to be so blunt, but people are actually believing this even though there is NO evidence that it's real.

                      Comment


                      • #12
                        Originally posted by Jimmy View Post
                        The first graph is completely meaningless because it seems that there are different numbers of idle samples to busy samples between kernels.

                        Of course if you have more idle points than busy points you're going to have a lower average power. The idle points vs the Busy points are easy to see from the graph. Now look at the ratio of I to B:

                        Code:
                        KV      I to B     I/B     Av pwr
                        ------===========================
                        2.6.34  14 to 1    14      54
                        2.6.35  10 to 3     3.3    59.3
                        2.6.36   9 to 1     9      57.6
                        2.6.37   8 to 3     2.6    60.4
                        2.6.38   9 to 4     2.25   65.6
                        2.6.39  10 to 4     2.5    66.4
                        3.0.00   8 to 5     1.6    70.5
                        Now sort them by the I/B and notice the average power magically gets sorted too (except for one point which is probably close enough to be within the margin of error).

                        Code:
                        KV      I to B     I/B     Av pwr
                        ===================-----=========
                        2.6.34  14 to 1    14      54
                        2.6.36   9 to 1     9      57.6
                        2.6.35  10 to 3     3.3    59.3
                        2.6.37   8 to 3     2.6    60.4
                        2.6.39  10 to 4     2.5    66.4
                        2.6.38   9 to 4     2.25   65.6
                        3.0.00   8 to 5     1.6    70.5
                        [sarcasm]OMG the ones with a lower I/B are on a power binge!!![/sarcasm] Completely useless.

                        The rest of the graphs are more interesting, mostly because they don't seem to be fundamentally flawed. However, they don't really show that power consumption is that much worse off.

                        Of course since the entire article seems to hinge on the first graph...

                        Exactly!!!

                        and as someone else pointed out, looking at the first graph, it looks like a difference in how the speedstep is being used, i.e. enabled post 2.6.34 and tune/tweaked afterwords. Seems that 3.0 has a more 'aggressive' response to load. I don't actually see any so called power regression on the 2.6.38, at least on this hardware. If anything, .38 seems to have a more 'relaxed' recovery from idle.

                        Comment


                        • #13
                          Originally posted by fewt View Post
                          Yes, I have used my netbook for 10 hours with kernel 2.6.39 and yes I still had battery left afterwards.
                          "Works for me" is never proof of something working fine for everyone and the people that are experiencing the issue are seeing differences in battery life by simply swapping the kernel for an older one.

                          Comment


                          • #14
                            Originally posted by deanjo View Post
                            "Works for me" is never proof of something working fine for everyone and the people that are experiencing the issue are seeing differences in battery life by simply swapping the kernel for an older one.
                            I agree, however "WorksForMe" isn't at play here, since I have pretty extensive knowledge of power saving techniques on this platform.

                            I did write Jupiter after all.

                            People aren't seeing differences in battery life by simply swapping the kernel, if you look at the bug report on Launchpad the majority of them would save battery life simply by properly testing.

                            Most of the people confirming the "bug" have web browsers and other applications open that of course cause wakeups. That's simply what applications do.

                            Don't make assumptions.

                            Comment


                            • #15
                              Originally posted by fewt View Post
                              Most of the people confirming the "bug" have web browsers and other applications open that of course cause wakeups. That's simply what applications do.

                              Don't make assumptions.
                              "Most" are not all. Don't make assumptions. It is however reasonable to think that those that did have browsers open also had them open in both instances, with older kernel and new.
                              Last edited by deanjo; 06-22-2011, 08:13 PM.

                              Comment

                              Working...
                              X