Announcement

Collapse
No announcement yet.

Wine Takes Minor Performance Hit Running Windows Programs On Linux With KPTI

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

  • Wine Takes Minor Performance Hit Running Windows Programs On Linux With KPTI

    Phoronix: Wine Takes Minor Performance Hit Running Windows Programs On Linux With KPTI

    With word this morning that Wine performance may be impacted by the Linux KPTI patches stealing the spotlight this week, I ran some basic benchmarks of Wine in different configurations looking at the performance impact of the kernel page table isolation patches.

    http://www.phoronix.com/vr.php?view=25791

  • #2
    For the sake of clarity headline should be specific; minor performance hit on Intel processors.

    Comment


    • #3
      Would be interesting to see the performance hit that STEAM LINK streaming takes! I/O & Networking is supposed to be heavily affected

      Comment


      • #4
        Originally posted by humbug View Post
        For the sake of clarity headline should be specific; minor performance hit on Intel processors.

        No, I think it should be left alone because in 3 months when AMD is forced to turn KPTI on, it will be a more accurate headline.

        Comment


        • #5
          Considering Wine was supposed to be a "worst case" scenario due to all the overhead involved, this just shows that KPTI really isn't that big of a deal.
          Having run a pretty intensive Wine program, Sketchup, with the latest 4.14 kernels there's no perceivable change in performance.

          Comment


          • #6
            Any chance of seeing the impact on Docker containers? I think a lot of desktop users use Docker, Ubuntu Snaps and Fedora's Flatpack containers.

            Comment


            • #7
              Originally posted by gururise View Post
              Any chance of seeing the impact on Docker containers? I think a lot of desktop users use Docker, Ubuntu Snaps and Fedora's Flatpack containers.
              If the term "container" is being used accurately and not as a substitute for "virtualization" then the use of containers shouldn't really impact the performance of the program beyond what would otherwise occur normally if the program was run normally. The kernel-userspace interaction with containers is pretty similar to regular programs, just that the container adds additional restrictions on namespaces, system resources, etc.

              Comment


              • #8
                Originally posted by chuckula View Post


                No, I think it should be left alone because in 3 months when AMD is forced to turn KPTI on, it will be a more accurate headline.
                Any evidence to back that up, as it seems pretty well confirmed at this point that AMD is not vulnerable to Meltdown which KPTI protects against.

                Comment


                • #9
                  Originally posted by bosjc View Post

                  Any evidence to back that up, as it seems pretty well confirmed at this point that AMD is not vulnerable to Meltdown which KPTI protects against.
                  That's lovely. That's like saying that because Microsoft wasn't vulnerable to the Heartbleed bug that input validation on Microsoft products is totally unnecessary. Which it totally stupid but is pretty much the logical position of AMD at this point.

                  Comment


                  • #10
                    I have a question. Say I would like to upgrade my kernel that includes this patch but would like to turn off KPTI to avoid the performance loss, will I be able to do that and if so, can anyone please tell me how? Thanks.

                    I play a few games on Wine and Guild Wars 2 is one of the main reasons, which happens to be very CPU intensive, this might kill its' not-too-shabby performance.

                    Comment

                    Working...
                    X