Announcement

Collapse
No announcement yet.

Ubuntu 7.04 to 8.10 Benchmarks: Is Ubuntu Getting Slower?

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

  • #46
    Score on Distrowatch

    Originally posted by phoronix View Post
    Phoronix: Ubuntu 7.04 to 8.10 Benchmarks: Is Ubuntu Getting Slower?

    With the release of Ubuntu 8.10 coming out later this week we decided to use this opportunity to explore how the performance of this desktop Linux operating system has evolved over the past few releases. We performed clean installations of Ubuntu 7.04, Ubuntu 7.10, Ubuntu 8.04, and Ubuntu 8.10 on a Lenovo ThinkPad T60 notebook and used the Phoronix Test Suite to run 35 tests on each release that covered nine different areas of the system. After spending well more than 100 hours running these tests, the results are now available and our findings may very well surprise you.

    http://www.phoronix.com/vr.php?view=13022
    If you can benchamark the other 4-5 distros, that will be great. I'm NOT sure if h/w vendors will be interested in this BUT it will be nice to see which h/w performs nice for all the distros. (Most h/w vendors will be interested in server customers rather than desktops because those customers are not too many.)

    It will be nice if distrowatch will start putting down these benchmark numbers next to their ranking so people can decide how they want it. It will even be nice if there is an automatic way to do it on Amazon EC2. Meaning you could have a distro load into one of the 4/5 EC2 instances and see how well it performs on the benchmark and then publish it. (Although EC2 is geared up for server loads and so most of the GUI related benchmarks should NOT be run on it -- not sure if their virtual instances have any Graphics hardware)

    BR,
    ~A

    Comment


    • #47
      I cannot believe the report

      Ubuntu RC released only at the midnight of 23rd that means 24th October, The report says they tested it for 100 Hrs, The test result publication time is 27th . How much ubuntu competitors paid for it.

      see more in

      http://shibuvarkala.blogspot.com

      Comment


      • #48
        Originally posted by Michael View Post
        As said in the article, Compiz was disabled.
        Ahh man, I have to read the article text too? Just kidding, but OK I did miss that part... anyway, that's really interesting then. I wonder if it is the scheduler as some have speculated, or if the compiler makes that big a difference, or what? Those time differences are pretty large for quite a few apps.. I knew from the title that 8.10 was probably slower, but I was expecting a few %, not a drop like that .

        Comment


        • #49
          Originally posted by panayara View Post
          Ubuntu RC released only at the midnight of 23rd that means 24th October, The report says they tested it for 100 Hrs, The test result publication time is 27th . How much ubuntu competitors paid for it.
          Before coming up with such a statement, did you take the time to think that not all testing had to begin after the RC was released? The Ubuntu 7.04, 7.10, and 8.04 testing started earlier in the week and then when the 8.10 release candidate came out, that was tested.
          Michael Larabel
          http://www.michaellarabel.com/

          Comment


          • #50
            I really think you should check your suite or repeat the test on a different machine.

            Those LAME numbers can't be right and are not reproducible (plain encoding, not with the suite) on my machine.

            Comment


            • #51
              Originally posted by trooper09 View Post
              You are right. I thought I read that the Core Duo wasn't a true dual core processor some time ago. This still does not mean the benchmarks used, took advantage of multiprocessing that is available.



              https://help.ubuntu.com/8.04/install...supported.html

              The article makes no mention if the benchmarks are taking advantage if multiprocessing is being used.
              My kernel is SMP by default on my T61 with an 8.04 install:
              Code:
              joshua@laptop:~$ uname -a
              Linux laptop 2.6.24-21-generic #1 SMP Mon Aug 25 17:32:09 UTC 2008 i686 GNU/Linux

              Comment


              • #52
                Originally posted by trooper09 View Post
                You are right. I thought I read that the Core Duo wasn't a true dual core processor some time ago. This still does not mean the benchmarks used, took advantage of multiprocessing that is available.



                https://help.ubuntu.com/8.04/install...supported.html

                The article makes no mention if the benchmarks are taking advantage if multiprocessing is being used.
                PTS by design is written to utilize multithreading for applications that do support it. ie openSSL, compile tests, etc

                Comment


                • #53
                  it doesn't matter what pts is written for, when the kernel is UP.

                  Comment


                  • #54
                    Originally posted by energyman View Post
                    it doesn't matter what pts is written for, when the kernel is UP.
                    Is the default ubuntu kernel not SMP? Thought that was pretty much default on all distro's now.

                    Comment


                    • #55
                      The kernel used was SMP supported.
                      Michael Larabel
                      http://www.michaellarabel.com/

                      Comment


                      • #56
                        Hi,

                        A user at the german forum "www.ubuntuusers.de" did some tests with his Lenovo T60 (same hardware as the one in the Phoronix-test) on Ubuntu 8.10. His scores are dramatically better than the ones from the Phoronix test :

                        LAME-MP3 : 60.62s

                        OGG : 35.05s

                        FLAC : 28.82s

                        WAVPACK : 31.22s

                        FFMPEG : 33.76s

                        SQLITE : 24.21s

                        SCIMARK (composite) : 290.28 Mflops

                        Tandem-XML (write) : 54.22s

                        How can it be that two systems with the same hard -and software got so different test results?

                        Comment


                        • #57
                          Originally posted by glasen View Post
                          How can it be that two systems with the same hard -and software got so different test results?

                          Must be because of language support

                          Comment


                          • #58
                            Originally posted by joshuapurcell
                            My kernel is SMP by default on my T61 with an 8.04 install:

                            Code:
                            joshua@laptop:~$ uname -a
                            Linux laptop 2.6.24-21-generic #1 SMP Mon Aug 25 17:32:09 UTC 2008 i686 GNU/Linux
                            I don't know... I am sorry if I am doubtful, but I typically use this command to ensure I have both core enabled:
                            Code:
                            cat /proc/cpuinfo

                            Originally posted by Michael View Post
                            The kernel used was SMP supported.
                            There is a huge difference between supported and enabled.

                            Comment


                            • #59
                              trooper09: I can assure you both cores were enabled and that cpuinfo reported both cores.
                              Michael Larabel
                              http://www.michaellarabel.com/

                              Comment


                              • #60
                                Originally posted by glasen View Post
                                How can it be that two systems with the same hard -and software got so different test results?
                                There's a few possible reasons... Do you have a link to his post / information?
                                Michael Larabel
                                http://www.michaellarabel.com/

                                Comment

                                Working...
                                X