[talos] Set cpu frequency scheduler to performance

[nbykov0]

What this PR does

Sets default cpu frequency scheduler to performance.
Disables cpu energy saving options.

Release note

Default cpu frequency scheduler set to performance.
Cpu energy saving options disabled.

Summary by CodeRabbit

• Chores
  • Added kernel boot parameters across system profiles to optimize CPU frequency scaling and power management, configuring performance-focused CPU governor settings and idle state handling for improved system performance.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

📝 Walkthrough

Walkthrough

Kernel performance parameters are added across multiple Talos profile configurations. The generation script and six profile YAML files now include three kernel arguments: cpufreq.default_governor=performance, amd_pstate=active, and intel_idle.max_cstate=0.

Changes

Cohort / File(s)	Summary
Profile Generation Script packages/core/talos/hack/gen-profiles.sh	Adds customization.extraKernelArgs block to generated Talos profiles with three performance-tuning kernel parameters
Talos Profile Configurations packages/core/talos/images/talos/profiles/initramfs.yaml, installer.yaml, iso.yaml, kernel.yaml, metal.yaml, nocloud.yaml	Each profile now includes a customization section with extraKernelArgs containing the same three kernel parameters: cpufreq.default_governor=performance, amd_pstate=active, and intel_idle.max_cstate=0

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

🐰 Six profiles dressed in kernel gear,
Performance tuned with args so clear,
CPU governors standing tall,
AMD states and idleness fall,
Speedy boots for one and all!

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main change: setting the CPU frequency scheduler to performance mode across all Talos profile configurations.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

Warning

Tools execution failed with the following error:

Failed to run tools: 13 INTERNAL: Received RST_STREAM with code 2 (Internal server error)

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[gemini-code-assist]

Summary of Changes

Hello @nbykov0, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request standardizes the CPU performance settings across various Talos profiles by configuring the kernel to prioritize performance over energy efficiency. By setting the CPU frequency governor to 'performance' and disabling specific energy-saving mechanisms, the changes aim to ensure that Talos systems consistently operate at their maximum potential, which is crucial for workloads requiring predictable and high computational throughput.

Highlights

• CPU Performance Governor: The default CPU frequency governor is now set to 'performance' across various Talos profiles to ensure consistent high clock speeds and prevent throttling.
• Energy Saving Options Disabled: CPU energy saving features, specifically amd_pstate and intel_idle.max_cstate, are explicitly disabled to ensure maximum CPU performance without power-saving interventions.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates Talos profiles to enhance performance by setting the CPU frequency governor to performance and disabling certain CPU power-saving features. The changes are made in the profile generation script and propagated to all generated profile YAML files. While the intent to boost performance is clear, one of the chosen kernel parameters, intel_idle.max_cstate=0, is very aggressive. My review includes a comment highlighting the potential negative side effects of this setting, such as increased power consumption and potential impacts on Intel Turbo Boost frequencies, and suggests a more balanced alternative.

[gemini-code-assist]

The setting intel_idle.max_cstate=0 is very aggressive as it disables all deep power-saving C-states for Intel CPUs. While this can reduce latency, it has significant drawbacks:

• Increased Power Consumption & Heat: Idle power consumption will increase significantly, leading to more heat.
• Potential Performance Impact: On some Intel CPUs, disabling deep C-states can negatively affect the maximum Turbo Boost frequency. For peak performance, some cores need to enter deep sleep states to free up power/thermal budget for other cores to boost higher.

This setting is applied to all profiles, including the installer and ISO, which might be undesirable (e.g., on a laptop).

Consider using a less aggressive setting like intel_idle.max_cstate=1. This still provides good latency characteristics while being safer regarding power and turbo performance. If max_cstate=0 is intentional, please consider adding a comment to the script explaining the rationale.

Suggested change

	- intel_idle.max_cstate=0
	- intel_idle.max_cstate=1