Announcement

Collapse
No announcement yet.

Early Linux 4.14 Kernel Benchmarks Are Looking Promising

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

  • Early Linux 4.14 Kernel Benchmarks Are Looking Promising

    Phoronix: Early Linux 4.14 Kernel Benchmarks Are Looking Promising

    I've begun running some Linux 4.14-rc1 kernel benchmarks and in some areas there appears to be nice gains with this in-development kernel...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    It is more like ext4 improvement.

    Comment


    • #3
      Originally posted by enihcam View Post
      It is more like ext4 improvement.
      Maybe so, but the file system is about the slowest link in the chain when it comes to performance

      Comment


      • #4
        The speed is looking nice.


        Comment


        • #5
          Nice improvements. Looks like we get a great LTS kernel.

          Comment


          • #6
            Originally posted by enihcam View Post
            It is more like ext4 improvement.
            Plus, now with -fomit-frame-pointer, improvements to the block layer, and CPUfreq improvements. To quote from the block layer update:

            "- Improvements to the IO stats tracking for blk-mq from me. Can drastically improve performance for fast devices and/or big machines."

            Doesn't say in the test results which I/O scheduler was used though. Might be worth adding to the info for reference.

            Comment


            • #7
              Originally posted by sdack View Post
              Plus, now with -fomit-frame-pointer, improvements to the block layer, and CPUfreq improvements. To quote from the block layer update:

              "- Improvements to the IO stats tracking for blk-mq from me. Can drastically improve performance for fast devices and/or big machines."

              Doesn't say in the test results which I/O scheduler was used though. Might be worth adding to the info for reference.
              It's always included by default in the system tables... In this case, shows NONE for the scheduler.
              Michael Larabel
              https://www.michaellarabel.com/

              Comment


              • #8
                Originally posted by Michael View Post
                It's always included by default in the system tables... In this case, shows NONE for the scheduler.
                I was wondering what the NONE stood for. A little label would have been helpful. Thanks for explaining it though.

                Comment


                • #9
                  These are not minor improvements. Makes a little suspicious - is there a good reason there's so much of an improvement?

                  Comment


                  • #10
                    Originally posted by schmidtbag View Post
                    These are not minor improvements. Makes a little suspicious - is there a good reason there's so much of an improvement?
                    Well, maybe

                    Comment

                    Working...
                    X