Skip to content

TELCODOCS-2918 - Enable default-preemption for numaresources-operator scheduler - #118974

Open
slovern wants to merge 1 commit into
openshift:mainfrom
slovern:TELCODOCS-2918
Open

TELCODOCS-2918 - Enable default-preemption for numaresources-operator scheduler#118974
slovern wants to merge 1 commit into
openshift:mainfrom
slovern:TELCODOCS-2918

Conversation

@slovern

@slovern slovern commented Aug 27, 2026

Copy link
Copy Markdown
Contributor

TELCODOCS-2918 - Enable default-preemption for numaresources-operator scheduler

Version(s): 5.0

Issue: https://redhat.atlassian.net/browse/TELCODOCS-2918

Link to docs preview: Scheduling critical workloads with preemption

QE review:

  • QE has approved this change.

Additional information:

@openshift-ci openshift-ci Bot added the size/L Denotes a PR that changes 100-499 lines, ignoring generated files. label Aug 27, 2026
@ocpdocs-previewbot

ocpdocs-previewbot commented Aug 27, 2026

Copy link
Copy Markdown

@slovern slovern changed the title TELCODOCS-2918 - Enable default-preemption for numaresources-operato… TELCODOCS-2918 - Enable default-preemption for numaresources-operator scheduler Aug 27, 2026
@openshift-ci

openshift-ci Bot commented Aug 31, 2026

Copy link
Copy Markdown

@slovern: all tests passed!

Full PR test history. Your PR dashboard.

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. I understand the commands that are listed here.

@shajmakh shajmakh left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Thanks @slovern.
I made initial review, and I think there are more details to add. will have another round of review when technical enablement is completed.


* Critical workloads are guaranteed resources even on heavily utilized clusters
* Cluster resources are used more efficiently by allowing important pods to displace less important ones
* Service degradation is prevented by ensuring that infrastructure and high-priority application pods can always be scheduled

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

..can always be scheduled

no commit, a lot of factors are involved. I'd replace that with ".. are always prioritized"

= NUMA Resources Operator scheduler preemption configuration

[role="_abstract"]
You can configure preemption for the NUMA Resources Operator scheduler by using the `preemptionMode` field in the `NUMAResourcesScheduler` custom resource. This field controls whether the scheduler uses the `DefaultPreemption` plugin to preempt lower-priority pods.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

worth mentioning explicitly that it is disabled by default.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

okay I see that is mentioned below in the table.

= Enabling preemption for the NUMA-aware scheduler

[role="_abstract"]
To enable priority-based preemption for the NUMA Resources Operator scheduler, configure the `NUMAResourcesScheduler` custom resource. When enabled, the scheduler can preempt lower-priority pods to make room for higher-priority pods on constrained cluster nodes.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

worth mentioning here that the field is disabled by default.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size/L Denotes a PR that changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants