put cpu-load and gpu-laod simultaneously 1. cpu-load, phoronix-test-suite benchmark compress-7zip 2. gpu-load, phoronix-test-suite benchmark unigine-super resolution: 2560*, full-screen, ultra quality.
use nvidia-smi to monitor gpu temperature, performance and utilization #sudo nvidia-smi -pm 1, watch -n 1 nvidia-smi kernel, ~~~ $ uname -a Linux u 6.0.0-1020-oem #20-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul 14 13:12:17 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux ~~~ With 2.4.9-1ubuntu0.2, observed the gpu was put into P3(performance state), the max power watt is limited under 30W. the gpu temperature is under 70 and lower. even cpu load is finished, the p state of gpu is still P3 and gpu performance is limited. gpu load is still running after cpu load is finished. With 2.4.9-1ubuntu0.3, didn't observe the throttled symptom during run cpu&gpu load. gpu is keepin in P0 and max power watt, 80w. the gpu temperature is over 70 and higher. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to thermald in Ubuntu. https://bugs.launchpad.net/bugs/1981087 Title: thermald prematurely throttling GPU Status in thermald package in Ubuntu: Fix Released Status in thermald source package in Jammy: Fix Committed Bug description: [Impact] * thermald prematurely throttling GPU [Fix] This fix is removed the code refactoring part and keep the necessary. (patch: 0009-Install-passive-default.patch) 82609c7) Separate Adaptive engine and GDDV [Test Plan] Test1, * Run game on the target machine. * the FPS must not be significantly reduced. Test2, * Run on others platform, ADL/TGL/CML/CFL/KBL. * Use monitoring tool(e.g. s-tui) and stress-ng to verify if the machine runs normally. [Where problems could occur] * better support for Passive Policy. currently passive policy 1 is supported and it should have a bug if the machine only enable pssive policy 2. ~~~ I got a new game and started playing it It would run at over 100 FPS solidly some of the time and then cyclically dip down to below 20 FPS for a few minutes I determined that it was thermald trying to keep my GPU below 70°C to determine this I sudo systemctl stop thermald The game ran solidly and consistently with the GPU at 75°C This is well below the specs set by the manufacturer and perhaps unreasonably low for a laptop But more importantly I was given no indication this was happening. I had to sleuth it out myself. Perhaps it is impossible to determine good defaults for all hardware, I don't know. However without an indication that this is happening there will be a lot of people with a mysteriously broken experience. This was extremely difficult for me to find and I had several friend who are experts on linux gaming and video drivers trying to track this down. I discovered it by luck and perseverance. This absolutely needs some sort of indication and hopefully a way to remedy it from the GUI. ideally it would set thermal limits that are more in line with what the device is designed for and not a conservative default if at all possible. ProblemType: Bug DistroRelease: Ubuntu 22.04 Package: thermald 2.4.9-1 ProcVersionSignature: Ubuntu 5.15.0-40.43-generic 5.15.35 Uname: Linux 5.15.0-40-generic x86_64 NonfreeKernelModules: nvidia_modeset nvidia ApportVersion: 2.20.11-0ubuntu82.1 Architecture: amd64 CasperMD5CheckResult: unknown CurrentDesktop: XFCE Date: Fri Jul 8 16:08:55 2022 InstallationDate: Installed on 2020-10-19 (626 days ago) InstallationMedia: Xubuntu 20.04.1 LTS "Focal Fossa" - Release amd64 (20200731) SourcePackage: thermald UpgradeStatus: Upgraded to jammy on 2022-06-17 (20 days ago) To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/thermald/+bug/1981087/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
