AI-200 Containerized AI Workloads Practice Question
You deploy an AI inferencing service to an Azure Kubernetes Service (AKS) cluster. The service uses an ONNX Runtime container. Users report intermittent 504 Gateway Timeouts during peak batch request loads. You notice that the application pods are being terminated due to Out-Of-Memory (OOM) errors during heavy inference loads. How should you resolve this issue in your Kubernetes deployment manifest?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Increase the memory limit value in the container resource specifications.
When container workloads experience OOM kills during peak load, you must increase the memory limit in the container resource specifications and ensure requests are appropriately sized.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Decrease the readiness probe failureThreshold to remove faulty pods faster.
Why it's wrong here
Readiness probes control traffic routing, not the memory allocation ceiling that causes OOM terminations.
- ✓
Increase the memory limit value in the container resource specifications.
Why this is correct
Raising the memory limit prevents the Linux kernel OOM killer from terminating the container when memory usage spikes during large batch inferences.
- ✗
Enable the Kubernetes Horizontal Pod Autoscaler based on CPU utilization.
Why it's wrong here
CPU-based HPA will not trigger if the bottleneck is memory consumption rather than CPU utilization.
- ✗
Configure a liveness probe with an increased initialDelaySeconds value.
Why it's wrong here
Liveness probes restart unresponsive containers, but they do not solve physical memory exhaustion (OOM).
Visual reference
About these practice questions
One of 503 original AI-200 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed August 2026 · checked against the official Microsoft exam blueprint
This AI-200 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-200 exam.