Propagate image building and model deployment errors

[ariefrahmansyah]

Description

Returns more information when failures happen on image building and model deployment process by propagating related kubernetes resources.

For image building, returns:

1. Kubernetes job conditions
2. Related pod's container status (in this case pyfunc-image-builder container)
3. Related pod's last termination message

For model deployment, returns:

1. Kserve inference service conditions
2. Related pod's container status
3. Related pod's last termination message

Screenshots

• When image building is OOMKilled:

• When docker image for custom model not exist:

• When deployment timeout because no node available:

Modifications

1. Add ParsePodContainerStatuses utility functions
2. Add related parsing function to parse inference service and kubernetes job.

Tests

Checklist

• Added PR label
• Added unit test, integration, and/or e2e tests
• Tested locally
• Updated documentation
• Update Swagger spec if the PR introduce API changes
• Regenerated Golang and Python client if the PR introduces API changes

Release Notes

[ghost]

👇 Click on the image for a new way to code review

Legend

[leonlnj]

Thanks, LGTM! Left some minor comments, but overall lgtm