Page 4 of 6 FirstFirst ... 23456 LastLast
Results 31 to 40 of 56

Thread: Fenrus Linux: A Distro For Performance, Developers

  1. #31
    Join Date
    Jul 2009
    Posts
    221

    Default

    Quote Originally Posted by fenrus View Post
    If Fenrus Linux would also get 100 FPS, the score would thus be 200%, however, for the purpose of showing a delta, 100% is subtracted (hence the "delta") and the score will 'only' be "100%" in the graph.
    If Fenrus Linux would get 25 FPS, the score would be 50%, but the delta would be 50% - 100% = -50% in the graph.
    Why bother with the subtraction? It doesn't really make the graphs any easier to read. In fact, why not put the result (fenrus's score/best other score) on a log scale? Then some of the results with large changes like noise-level-1.1.0 would be easier to read.

  2. #32
    Join Date
    Mar 2013
    Posts
    21

    Default

    Quote Originally Posted by Cyborg16 View Post
    Why bother with the subtraction? It doesn't really make the graphs any easier to read. In fact, why not put the result (fenrus's score/best other score) on a log scale? Then some of the results with large changes like noise-level-1.1.0 would be easier to read.
    it makes "the same" be "zero".
    A lot of people really do not like graphs without the zero axis there; and if the axis would have to always span 0 - 100 then it becomes useless to see small changes.

  3. #33
    Join Date
    Mar 2013
    Posts
    21

    Default

    Quote Originally Posted by RahulSundaram View Post
    Do you happen to have a link to any video of this talk?
    I don't think this one was recorded unfortunately.

  4. #34
    Join Date
    Mar 2013
    Posts
    21

    Default

    Quote Originally Posted by chrisb View Post
    Are the little hover-dots the test results on Fenrus as someone suggested above? If so, how come the plotted line is smooth? ie. hover on systemd-boot-kernel and you see one single performance jump around Feb 18th or so, but the curve rises up gradually over 2 weeks as if performance was slowly changing every day. It looks like a line of best fit? The problem with that is it doesn't show change very well - in these kind of metrics change tends to be instant rather than gradual.

    So systemd-boot-userspace really is 300 times faster on Fenrus? And systemd-boot-total is 70 times faster?

    Which distributions are you currently testing? Would it be possible to do some graphs directly comparing them, eg. plotting Fenrus vs Ubuntu vs Fedora vs Gentoo, so we can see what the "best of the rest" actually is, and which distributions are best for performance?

    I am curious if there really are significant differences and potential gains to be made, because most benchmarks I have seen suggest there is little real difference between competing modern distros. But this could be because the benchmarks are designed to be tests of the hardware (bound by CPU, GPU, disk IO etc.) rather than tests of distributions.
    the colored dots are the average results for the release in question. there are also tiny black dots which are the results of each individual PTS test (so sometimes you see a "smear" of them, meaning high variation)
    I've been trying various fit functions and am still struggling with finding something sensible that deals with steps well, while still filtering out some of the noise.

  5. #35

    Default

    Quote Originally Posted by fenrus View Post
    I don't think this one was recorded unfortunately.
    It might be useful to replicate the information presented in the talk somewhere in the fenrus linux site then. I am curious to see the technical details.

  6. #36
    Join Date
    Jul 2012
    Location
    SuperUserLand
    Posts
    538

    Default

    waste of time

    this thing is as alpha as alpha gets


    why the fuck is it being promoted in phoronix since it's like 2 years away from being anything decent?


    a better question

    why is intel wasting time experimenting with distros and packages, should be working on the drivers that's what they should be doing, bunch of good for nothings, hey ive me 70% of thw windows driver performance and I won't complain no more

  7. #37
    Join Date
    Mar 2013
    Posts
    21

    Default

    Quote Originally Posted by Pallidus View Post
    waste of time

    this thing is as alpha as alpha gets


    why the fuck is it being promoted in phoronix since it's like 2 years away from being anything decent?


    a better question

    why is intel wasting time experimenting with distros and packages, should be working on the drivers that's what they should be doing, bunch of good for nothings, hey ive me 70% of thw windows driver performance and I won't complain no more
    since you claim it is alpha... I assume you tried it?

    you did not read the website though since this is not an Intel project.

  8. #38
    Join Date
    Nov 2012
    Posts
    633

    Default

    Quote Originally Posted by ryao View Post
    If I recall, the person behind this has a forum account called fenrus. Anyway, he should look into using ZFS and DTrace.
    What for? I can agree (in some part) for zfs, but who needs dtrace?

  9. #39
    Join Date
    Mar 2013
    Posts
    4

    Default

    But how to install fenrus ? I cannot mount that image or write to dvd cause it has 20Gb ...

  10. #40
    Join Date
    Mar 2013
    Posts
    63

    Default Performance a la Intel

    Quote Originally Posted by fenrus View Post
    yeah I'll try to clarify the page tonight, clearly it's not well done right/clear enough right now; thanks for the feedback.

    let me give a specific (but made up) example.
    Say some test gives frames-per-second (e.g. a higher-is-better test).
    And lets say, Fedora 17 is the best-of-the-rest at 50 frames per second.

    If Fenrus Linux would also get 100 FPS, the score would thus be 200%, however, for the purpose of showing a delta, 100% is subtracted (hence the "delta") and the score will 'only' be "100%" in the graph.
    If Fenrus Linux would get 25 FPS, the score would be 50%, but the delta would be 50% - 100% = -50% in the graph.
    Several people is here complaining why you are using this method.

    Well, your combination of a percentage with a baseline has a very interesting result for a distro marketed "for performance". If Fenrus is twice faster than distro B then the graph reads 100%, but if the distro B is twice faster than Fenrus the graph reads -50% (instead of -100%).

    This means that average Joe will be reading on the graphs that Fenrus is, wow!, 100% faster regarding some test but only a 50% slower regarding another test, and he will be taking Fenrus to be a much faster distro when the reality would be that Fenrus and the other distro are on pair 2:1 vs 1:2 regarding both tests.
    Last edited by juanrga; 03-25-2013 at 08:51 PM.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •