-
Notifications
You must be signed in to change notification settings - Fork 1.9k
OCPDOCS 17899 Document Kernel PSI Enablement in OpenShift 4.21 #104869
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
base: main
Are you sure you want to change the base?
Conversation
|
🤖 Thu Jan 15 22:49:30 - Prow CI generated the docs preview: |
| labels: | ||
| custom-kubelet: set-kubelet-config <1> | ||
| ---- | ||
| <1> If a label has been added it appears under `labels`. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🤖 [error] AsciiDocDITA.CalloutList: Callouts are not supported in DITA.
|
@mburke5678: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions 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. |
|
|
||
| [NOTE] | ||
| ==== | ||
| The performance impact of enabling PSI is negligible with the benefit of gaining critical resource pressure visibility for better scheduling and eviction decisions. This was tested on worker nodes (m5.2xl) on the AWS platform. For latency sensitive environments, we suggest testing it before enabling it on production. Enable it on 1 worker first, monitor for the performance impact, and gradually roll out to more workers. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The performance impact to of enabling PSI is negligible with the benefit of gaining critical resource pressure visibility for better scheduling and eviction decisions. This was tested on worker nodes (m5.2xl) on the AWS platform. For latency sensitive environments, we suggest testing it before enabling it on production. Enable it on 1 worker first, monitor for the performance impact, and gradually roll out to more workers. Enabling PSI introduces new metrics per container that can increase the RSS memory usage of prometheus-k8s pods. On a cluster with a big number of containers, monitor the memory usage of prometheus-k8s pods and adjust the resource if needed.
qiliRedHat
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I added 2 more sentences to the NOTE.
https://issues.redhat.com/browse/OSDOCS-17899
Link to docs preview:
QE review: