Skip to content

Disable efficiency cores #190

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Jul 30, 2025
Merged

Disable efficiency cores #190

merged 5 commits into from
Jul 30, 2025

Conversation

vmcj
Copy link
Member

@vmcj vmcj commented Jul 29, 2025

Also clarified the package/socket as package is more correct but socket is better known and fixed a typo.

This does not fix our issue yet but will most likely help us a bit more.

@vmcj vmcj requested a review from tuupke July 29, 2025 19:40
@vmcj vmcj force-pushed the disable_ht_fixes branch from 375c74b to c910e69 Compare July 29, 2025 20:21
Copy link
Contributor

@tuupke tuupke left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTMNITS; one - maybe - slightly bigger issue so putting it on request changes to make sure.

@@ -61,14 +94,18 @@ if [ -d $DIR_INTEL ]; then
# increase freq from powersaving to normal, but don't overclock
echo 100 > $DIR_INTEL/min_perf_pct
echo 100 > $DIR_INTEL/max_perf_pct
elif [ -d $DIR_AMD ]; then
elif [ -f $FILE_AMD && ]; then
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks incorrect to me, but I don't use bash often enough to be sure.

echo "Error: turboboost still enabled!"
exit 1
fi
else
echo "Warning: kernel (turbo) boost config not found in '$DIR_INTEL' or '$DIR_AMD'."
fi

if [ -n "${store_isolcpus_fact}" ]; then
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it on purpose that this is not logged when turboboost cannot be disabled? This is an improvement nonetheless, but probably best to move this to before disabling turboboost.

vmcj added 5 commits July 30, 2025 19:21
We will use those later for a report and to not duplicate the method of disabling.
This is defence in depth by disallowing the kernel to schedule work on the online cpu's before the script disables the CPU's. The script can fail when the CPU taken down is currently working on something.
Package is more correct but socket is better known.

Also fixed a typo.
The boost exists for asahi@M1 laptops but not on a raspberry with ARMv7.
Also clarified the package/socket as package is more correct but socket is better known and fixed a typo.
@vmcj vmcj force-pushed the disable_ht_fixes branch from c910e69 to 1eb5b51 Compare July 30, 2025 17:29
@vmcj vmcj merged commit b7e1e65 into DOMjudge:main Jul 30, 2025
3 checks passed
@vmcj vmcj deleted the disable_ht_fixes branch July 30, 2025 18:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants