Announcement

Collapse
No announcement yet.

Linux 5.9 To Allow Controlling Page Lock Unfairness In Addressing Performance Regression

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

  • Linux 5.9 To Allow Controlling Page Lock Unfairness In Addressing Performance Regression

    Phoronix: Linux 5.9 To Allow Controlling Page Lock Unfairness In Addressing Performance Regression

    Following the Linux 5.0 to 5.9 kernel benchmarks on AMD EPYC and it showing the in-development Linux 5.9 kernel regressing in some workloads, bisecting that issue, and that bringing up the issue of the performance regression over page lock fairness a solution for Linux 5.9 has now landed.

    http://www.phoronix.com/vr.php?view=29508

  • #2
    Great to see Michael's investigation have such a positive impact on the linux kernel!

    Comment


    • #3
      The positive impact is huge. Now Linus and the community are seriously rethinking this code, the old design, the new, the way forward. We can look forward to some big change in the near future.

      Comment


      • #4
        Originally posted by dxin View Post
        The positive impact is huge. Now Linus and the community are seriously rethinking this code, the old design, the new, the way forward. We can look forward to some big change in the near future.
        Very well said.


        I remember when I first entered the Linux scene. There were a lot of people taking negative runs at Phoronix and Micheal. Other content creators were jealous.
        Getting lots of praise now.
        You earned it Big Mike.

        Comment


        • #5
          Can someone explain why 'fairness' could trump performance in a CS setting? Is this a buzzword change or a real engineering improvement?

          Comment


          • #6
            Originally posted by down1 View Post
            Can someone explain why 'fairness' could trump performance in a CS setting? Is this a buzzword change or a real engineering improvement?
            It becomes important when you juggle lots of balls at the same time. Imagine you gotta juggle 5 balls at the same time. But well, one ball is super fast, so instead of slowing down and juggling all balls you just put the other 4 down and juggle that single ball. I mean, yeah it's faster? But you were asked to juggle 5 balls, not one. Here's the isssue with the fairness. In essence, the kernel would allow only one ball to get past over and over while the other 4 would stay still. Overall, performance is greater, but the kernel was asked to juggle 5 balls, not one.

            Comment


            • #7
              Originally posted by down1 View Post
              Can someone explain why 'fairness' could trump performance in a CS setting? Is this a buzzword change or a real engineering improvement?
              https://www.phoronix.com/scan.php?pa...fairness&num=1

              Comment


              • #8
                Well, this seemingly small change certainly opened up a large can of worms! But that's part of the awesomeness of Linux. With so many talented people tackling issues like this they are found and remedied rather quickly.

                And wow Michael, I sure hope to heck the Linux Foundation is at least paying you a bounty for uncovering problems like this. Fantastic job!

                Comment


                • #9
                  Originally posted by HighValueWarrior View Post

                  Very well said.


                  I remember when I first entered the Linux scene. There were a lot of people taking negative runs at Phoronix and Micheal. Other content creators were jealous.
                  Getting lots of praise now.
                  You earned it Big Mike.
                  In some 'serious' linux forums, Phoronix articles and comments were treated dismissively and even contemptuously, but I haven't seen much of that attitude in the past year or so. I think partly that's because the insights have matured, but significantly because the standard of these conversation threads has improved a lot. Subjectively, I think the level of commentary is much more informed.
                  I am pleased to subscribe to help support the work. This regression was a good catch.

                  Comment


                  • #10
                    In some 'serious' linux forums, Phoronix articles and comments were treated dismissively and even contemptuously, but I haven't seen much of that attitude in the past year or so. I think partly that's because the insights have matured, but significantly because the standard of these conversation threads has improved a lot.
                    We seem to be living in Clown World these days, at least when viewed from many of today's so-called "news" sources (more like sold off, propaganda outlets now). Phoronix is a breath of fresh air, a place to go where all that nonsense is ignored and real Linux news continues to thrive.

                    Comment

                    Working...
                    X