Announcement

Collapse
No announcement yet.

Benchmarking 11 Linux Distributions Across Dozens Of Workloads On The Intel Core i9 10980XE

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

  • Benchmarking 11 Linux Distributions Across Dozens Of Workloads On The Intel Core i9 10980XE

    Phoronix: Benchmarking 11 Linux Distributions Across Dozens Of Workloads On The Intel Core i9 10980XE

    If opting for a high-end desktop/workstation like the Intel Core i9 10980XE and even for smaller systems, your choice of Linux distribution can be a big factor in the performance potential out of the system. In benchmarking eleven modern Linux distributions across dozens of benchmarks, the performance difference can be more than 30% for the out-of-the-box Linux performance. Benchmarked this round on the i9-10980XE were multiple versions of CentOS, Clear Linux, Debian, Fedora Workstation, Manjaro, openSUSE Tumbleweed, Solus, and Ubuntu.

    http://www.phoronix.com/vr.php?view=28648

  • #2
    Fedora slow-down-super-secure compilation flags really make everything ugly. Slower than CentOS 8/RHEL 8 despite using almost the most recent kernel release? Wow.

    Too bad these results won't result in anything on Fedora's side for "the sake of security of our users". Yet, most Fedora users are on the desktop where these security measures are an absolute overkill.

    Comment


    • #3
      Originally posted by birdie View Post
      Fedora slow-down-super-secure compilation flags really make everything ugly. Slower than CentOS 8/RHEL 8 despite using almost the most recent kernel release? Wow.

      Too bad these results won't result in anything on Fedora's side for "the sake of security of our users". Yet, most Fedora users are on the desktop where these security measures are an absolute overkill.
      Perhaps. But you can also say that since these mitigations are in place in the majority of systems: Windows, Linux, OpenBSD, etc, these hardware vulnerabilities are too difficult and too specific to use in widespread exploits.

      The days of easy performance wins are over. The real cost of performance over security choices over the past several decades from hardware architectural decisions to software built using unsafe practices, languages that wrongly assume programmer always know what they're doing, and decades old security paradigms is coming to a painful end.

      Distribution developers are starting to realize that. The safe defaults are literally the safe defaults.

      Obviously you can have performance, but you have to make some very careful choices that almost no one in the general public, even on Phoronix, is qualified to make.

      Comment


      • #4
        I was talking about GCC compilation flags, you countered with ... CPU HW vulnerabilities mitigations which are enabled on all Linux distros by default and all have roughly the same performance impact - actually recent kernels are less affected because some of these mitigations have been optimized unlike RHEL where they use the initial "slow" versions of them.

        Comment


        • #5
          Why is there a Manjaro Release number? Its rolling or didnt you have installed updates for it after installation?

          I also would like to have Arch in there. I mean common, it's a one time setup you have to do. And no, Manjaro is not Arch, also not in performance of some things.

          Comment


          • #6
            Why is anyone benchmarking Intel and not AMD these days? Intel is useless until they come up with something new (and not a rehash). Is Michael an Intel fan?

            Comment


            • #7
              Thank you so much for including Manjaro in these benchmarks Michael! It didn't do as well as I would have expected, but it's good to know the truth of where the distros stand.

              The same benchmarks with a powerful AMD processor would be also be very interesting.
              Last edited by muncrief; 12-15-2019, 11:19 PM.

              Comment


              • #8
                Originally posted by Almindor View Post
                Why is anyone benchmarking Intel and not AMD these days? Intel is useless until they come up with something new (and not a rehash). Is Michael an Intel fan?
                I benchmark both Intel and AMD (and ARM, Power9, etc)... if you look at just an article from a few days ago or so are plenty of Linux distro comparison tests.
                Michael Larabel
                http://www.michaellarabel.com/

                Comment


                • #9
                  Originally posted by birdie View Post
                  I was talking about GCC compilation flags, you countered with ... CPU HW vulnerabilities mitigations which are enabled on all Linux distros by default and all have roughly the same performance impact - actually recent kernels are less affected because some of these mitigations have been optimized unlike RHEL where they use the initial "slow" versions of them.
                  No, I countered with the reality of the situation which is both hardware and software (compiler flags and switches) in tandem.

                  Comment


                  • #10
                    Originally posted by birdie View Post
                    Too bad these results won't result in anything on Fedora's side for "the sake of security of our users". Yet, most Fedora users are on the desktop where these security measures are an absolute overkill.
                    The problem is Fedora is the testbed for an enterprise product. And that will only accelerate under IBM. And canonical's pivot toward enterprise means this trend is likely to pickup even more. We'll soon all be running massively bloated "desktop" editions of code that's meant for hyperscalers.

                    Comment

                    Working...
                    X