Walk through a safe rolling update when the new model takes 90 seconds to load weights.
PICTURE THIS: HOW TO EXPLAIN IT
Simple meaning
Set a startup or readiness probe delay beyond 90 seconds, maxSurge so old Pods keep traffic, and maxUnavailable of 0 if capacity is tight.
WHY — Kubernetes instead of guessing?
Why interviewers care about Kubernetes:
who only read docs from people who shipped.
and tied to MLOps work.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1Set a startup or
readiness probe delay beyond 90 seconds, maxSurge so old Pods keep traffic, and maxUnavailable of 0 if capacity is tight.
- 2Pre-pull images with a
DaemonSet or larger surge on a staging node pool.
- 3Only after the new
Pods are Ready should kube-proxy shift Service endpoints.
- 4Give an example
One tiny concrete case you can say aloud.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
Set a startup or readiness probe delay beyond 90 seconds, maxSurge so old Pods keep traffic, and maxUnavailable of 0 if capacity is tight. Pre-pull images with a DaemonSet or larger surge on a staging node pool.