fix: Ensure modelmesh container comes last in list #202
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Motivation Kubernetes starts containers sequentially in order, which can mean the start of later containers is held up if their images have to be pulled. For large model server images this can cause a problem because model-mesh waits for a limited amount of time at startup for the runtime to become ready before returning ready from its own probe. Making the `mm` container last in the list ensures that no image pulling time will be included in this startup polling time and avoids unnecessary timeouts / extended readiness probe failures. Modifications Add ensureMMContainerIsLast function to runtime deployment reconciliation logic which runs after other modifications to the pod spec. Result More stable deployments in cases where the model server image takes a long time to pull. Signed-off-by: Nick Hill <[email protected]>
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: chinhuang007, njhill The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
/lgtm |
ckadner
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
Kubernetes starts containers sequentially in order, which can mean the start of later containers is held up if their images have to be pulled. For large model server images this can cause a problem because model-mesh waits for a limited amount of time at startup for the runtime to become ready before returning ready from its own probe.
Making the
mmcontainer last in the list ensures that no image pulling time will be included in this startup polling time and avoids unnecessary timeouts / extended readiness probe failures.Modifications
ensureMMContainerIsLastfunction to runtime deployment reconciliation logic which runs after other modifications to the pod spec.Result
More stable deployments in cases where the model server image takes a long time to pull.
Signed-off-by: Nick Hill [email protected]