Announcement

Collapse
No announcement yet.

Benchmarking The Ubuntu "Low-Jitter" Linux Kernel

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

  • Benchmarking The Ubuntu "Low-Jitter" Linux Kernel

    Phoronix: Benchmarking The Ubuntu "Low-Jitter" Linux Kernel

    There's an independently maintained "low-jitter" version of the Linux kernel targeting Ubuntu, which claims to be faster, but is that really the case?..

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

  • #2
    This article made me laugh so much, thanks! Nothing like a good old placebo.

    Comment


    • #3
      missing the point

      the thing is not called low _jitter_ for no reason ... maybe you should actually also benchmark jitter in various fields (eg. std. distribution of apache response times, frame jitter, ...) instead of "raw performance"

      Comment


      • #4
        Missing the point indeed

        The whole point of low jitter is low jitter. Running throughput benchmarks pretty much misses the point.

        Comment


        • #5
          Well that was a joke. Where's the magical 3x performance and amazing desktop responsiveness promised by the posters?

          Compile your own kernel, they said...

          Comment


          • #6
            Check out TechReport's articles on what jitter is... that might help for next time. These benchmarks have absolutely nothing to do with jitter.

            Comment


            • #7
              1. Benchmarks just proved that those patches in fact have impact on the kernel
              2. They are likely actually improve the responsivness as one would except the lower scores that might come cause of extra overhead.
              3, One should be happy that drops in overal performance is hardly noticable

              ps anyone tested the patches and may comment about the "low-jitter"?

              Comment


              • #8
                How is jitter defined in computer kernels. I know what jitter is in electronics but kernels?

                Comment


                • #9
                  Originally posted by 89c51 View Post
                  How is jitter defined in computer kernels. I know what jitter is in electronics but kernels?
                  Delay variation till a process gets the cpu again due to scheduling I think.

                  Comment


                  • #10
                    You should punch some speed holes in your car. I did it. It works.

                    Comment


                    • #11
                      Heh, it's one of those "quality articles" on Phoronix where Michael has no clue what it is he's testing :-P Instead of testing jitter, he tests throughput.

                      Ah, well.

                      Comment


                      • #12
                        Me: I concocted this really great variety of beer that's designed to keep for long periods of time without refrigeration (it's got loads of preservatives) and doesn't lose its flavor or spoil. Good to have with you if you're stranded on an island for months and need some alcohol

                        Michael: Let's try this purported new variety of beer... ech, it tastes nothing like a German beer at all!

                        Me: ...did you miss the point that it keeps for a long time?

                        Comment


                        • #13
                          well, to be fair

                          the poster who keeps talking about his jitter-kernel keeps trying to convince everyone it massively boosts framerates in games. or at least that what it sounds like he is saying. which is ridiculous, of course, as michael has now shown.

                          Comment


                          • #14
                            Ya something measuring jitter would be nice. If it reduces it enough in a 3-d rendering engine, you might notice improved responsiveness and smoothness even though the total number of frames remain the same as the frames are more evenly spaced out.

                            There usually is a trade-off in responsiveness vs throughput.

                            Comment


                            • #15
                              Originally posted by smitty3268 View Post
                              the poster who keeps talking about his jitter-kernel keeps trying to convince everyone it massively boosts framerates in games. or at least that what it sounds like he is saying. which is ridiculous, of course, as michael has now shown.
                              Michael just have no clue he also tested catalyst versions in the past with massive "mouse lag/mouse problems" and then he claimed after the benchmarks the game run well because of the very high FPS rate.

                              But the game was in fact unplayable. I reported that to Michael in the IRC chat via private message and he answers: he don't care he tested the FPS and the FPS is high ....... I think he only don't care because his workstation customers only care about rendering stuff they just don't play and they just don't need interactive mouse input while rendering the stuff.

                              Any serious gaming-computer magazine would put a big fat warning over every FPS result like that: "warning unplayable in any fps rate because of mouse input lag/mouse problems"

                              And now again Michael tested a "interactive-low-latency-low-jitter" kernel and Michael just show to the people that he has no clue what he is testing.

                              You can't test this like THIS! you need a pro-gamer who plays clan-games with both kernels in high responsive high interactive games like: HON or Unreal/UT or stuff like that.

                              Then you play the map "deck16" with 200% speed with a 2400DPI mouse as a input.

                              I'm sure the one with the low-latency/low-Jitter/Real-time kernel will win the pro game match.

                              But sure you can benchmark like a noob and just record the FPS.

                              Comment

                              Working...
                              X