Since filing the initial report, I ran a real workload comparison using my full pytest suite.
On this Metabox system running Ubuntu 24.04, the suite takes about 22 minutes. On a less powerful Dell Ubuntu laptop, the same suite takes about 11–12 minutes. The project directory on the Metabox is on the internal NVMe and mounted as ext4 (`df -T .` shows ext4), so this does not appear to be a Windows- mounted filesystem issue. `powerprofilesctl` still reports: `performance -> Degraded: yes (high-operating-temperature)` At the time of sampling, temperatures were moderate rather than near critical: - CPU package: about 60C - GPU: about 49C - NVMe: about 38.9C - fans: about 2200–2700 RPM The filtered kernel log from this boot shows ACPI BIOS errors and NVIDIA ACPI DSM warnings, but I did not see obvious thermal-throttling messages in that filtered output. I have attached the latest outputs of: - `powerprofilesctl list` - `sensors` - `nvidia-smi` - `journalctl -k -b | grep -Ei 'thermal|thrott|tcc|pstate|acpi|NVRM'` No firmware updates are available via `fwupdmgr`. ** Attachment added: "metabox_kernel_log_journalctl_k_b_grep_thermal_acpi.txt" https://bugs.launchpad.net/ubuntu/+source/power-profiles-daemon/+bug/2148099/+attachment/5960538/+files/metabox_kernel_log_journalctl_k_b_grep_thermal_acpi.txt -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2148099 Title: power-profiles-daemon reports high-operating-temperature degradation at moderate temperatures on Ubuntu 24.04 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/power-profiles-daemon/+bug/2148099/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
