KEP-6232: Tolerate benign per-NUMA memory drift in the Memory Manager

[AI-Armless]

This is the initial (provisional) KEP for tolerating a benign, bounded per-NUMA
memory drift in the kubelet Memory Manager Static policy (and the delegating
BestEffort policy), so kubelet does not crash-loop after a reboot when a node's
per-NUMA MemTotal shifts benignly and the node otherwise stays NotReady until
an operator deletes the checkpoint by hand.

The background section works through the two independent causes, both confirmed
against real node data on the tracking issue:

• KASLR relocation of the kernel image (MB-scale, needs more than one NUMA node), and
• variable boot-time reserved-memory freeing (KiB-scale, hits even single-NUMA nodes).

The design is in three parts: a bounded tolerance + conservation + re-baseline
(already implemented in the linked code PR), an auto-detected bound derived from
the running kernel image size in /proc/iomem, and an operator policy option to
disable or override it.

• Enhancement issue: Tolerate benign per-NUMA memory drift in the Memory Manager #6232
• Related code PR (part 1, the bounded tolerance): node: mm-mgr: tolerate small NUMA node memory drift on restart kubernetes#140473
• Root-cause discussion: Kubelet failed to start on reboot with memory manager's Static policy kubernetes#131253

/sig node
/cc @ffromani

[kubernetes-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: AI-Armless
Once this PR has been reviewed and has the lgtm label, please assign derekwaynecarr, soltysh for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• keps/prod-readiness/OWNERS
• keps/sig-node/OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[kubernetes-prow]

Welcome @AI-Armless!

It looks like this is your first PR to kubernetes/enhancements 🎉. Please refer to our pull request process documentation to help your PR have a smooth ride to approval.

You will be prompted by a bot to use commands during the review process. Do not be afraid to follow the prompts! It is okay to experiment. Here is the bot commands documentation.

You can also check if kubernetes/enhancements has its own contribution guidelines.

You may want to refer to our testing guide if you run into trouble with your tests not passing.

If you are having difficulty getting your pull request seen, please follow the recommended escalation practices. Also, for tips and tricks in the contribution process you may want to read the Kubernetes contributor cheat sheet. We want to make sure your contribution gets all the attention it needs!

Thank you, and welcome to Kubernetes. 😃

[kubernetes-prow]

Hi @AI-Armless. Thanks for your PR.

I'm waiting for a kubernetes member to verify that this patch is reasonable to test. If it is, they should reply with /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work.

Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

I understand the commands that are listed here.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.