Announcement

Collapse
No announcement yet.

Linux 5.11 Is Regressing Hard For AMD Performance With Schedutil

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

  • #31
    Grinch, just because Michael mentioned a Grinch stealing Christmas doesn't mean that you need to get huffy and defend against the entire article.

    We all know what in-development means.

    This wouldn't be the first time Michael's tests have prevented an otherwise unnoticed regression from making it to release.

    Chill.

    Comment


    • #32
      Originally posted by ssokolow View Post
      That's why it's important to test them. To make sure bad defaults get called out.
      Reality is kernel developers don't care. intel_pstate=powersave has been such a gigantic mess for years, it's hopeless. Similar things seem to apply to schedutil, after many years of work it's still far worse than Windows balanced power plan.

      Comment


      • #33
        Maybe next time you could also compare how the latest clear os kernel is doing and the latest oracle uek kernel is doing in these graphs so we could see how far away 5.11/5.12 are ? are we in a sand pit or are we on the green?

        Comment

        Working...
        X