More data points: RHEL9 (kernel 5.14.0) w/ HT: 22s RHEL9 (kernel 5.14.0) w/o HT: 22s Slackware (kernel 5.15.161) w/ HT: 155s Slackware (kernel 5.15.161) w/o HT: 22s ubuntu20 (kernel 5.4.0-196-generic) w/ HT: 14s ubuntu20 (UPGRADED kernel 5.11.0-22-generic) w/ HT: 19s ubuntu20 (UPGRADED kernel 5.13.0-21-generic) w/ HT: 19s ubuntu20 (UPGRADED kernel 5.15.0-33-generic) w/ HT: 19s ubuntu20 (UPGRADED kernel 5.15.0-43-generic) w/ HT: 19s ubuntu20 (UPGRADED kernel 5.15.0-46-generic) w/ HT: 84s ubuntu20 (UPGRADED kernel 5.15.0-50-generic) w/ HT: 84s ubuntu20 (UPGRADED kernel 5.15.0-75-generic) w/ HT: 84s ubuntu20 (UPGRADED kernel 5.15.0-100-generic) w/ HT: 84s ubuntu20 (UPGRADED kernel 5.15.0-122-generic) w/ HT: 84s
This confirms that changing the kernel version while leaving other packages alone introduces the regression, so I have assigned this bug to the linux package. The various kernels were installed using apt install. At this point, it looks like I may need to look into how to reproduce these kernel builds so I can start trying to build intermediate commits from source. ** Package changed: ubuntu => linux (Ubuntu) -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2083077 Title: python3 counting 6x slowdown with ubuntu22 on cisco ucs hardware with hyperthreading To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2083077/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
