The answer is that the custom container fails to expose the required CPU utilization metrics, preventing Vertex AI autoscaling from triggering. Vertex AI’s horizontal autoscaling relies on the custom container serving standard metrics—such as CPU usage via a Prometheus-format `/metrics` endpoint or through the Vertex AI custom metric adapter—to decide when to add replicas. Without these metrics, the autoscaler sees no utilization increase and keeps the replica count at the minimum of 2, even as CPU hits 100%, causing latency spikes and 503 errors under load. On the Google Professional Data Engineer exam, this scenario tests your understanding that autoscaling for custom containers is not automatic; you must instrument the container to emit the metrics Vertex AI can consume. A common trap is assuming the autoscaler reads CPU from the host machine, but it only scales based on metrics the container explicitly exposes. Memory tip: “No metrics, no scale—your container must tell the tale.”
PDE Operationalizing machine learning models Practice Question
This PDE practice question tests your understanding of operationalizing machine learning models. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
You are a machine learning engineer at a FinTech company. Your team has developed a credit risk model using XGBoost and deployed it on Vertex AI Prediction using a custom container. The model is used for real-time credit decisions, and the endpoint is configured with a single machine type (n1-standard-4) and min_replica_count = 2, max_replica_count = 10. Recently, the team observed that during a promotional campaign, the endpoint's prediction latency increased from 200ms to over 2 seconds, and some requests resulted in 503 errors. You check the Cloud Monitoring metrics and see that CPU utilization reached 100% on the existing replicas, but the number of replicas never scaled beyond the initial 2. The deployment uses a custom container that runs a TensorFlow Serving-like model server. The container image is stored in Artifact Registry. The Vertex AI endpoint is configured with a traffic split of 100% to this model version. What is the most likely cause of the scaling failure, and what step should you take to resolve it?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "most likely"
Why it matters: Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
Clue: "never"
Why it matters: Absolute qualifier. True only if the statement has zero exceptions — be cautious of options that seem obvious but break down in edge cases.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Ensure the custom container exposes the correct metrics for CPU utilization so that Vertex AI autoscaling can trigger.
Option C is correct because Vertex AI's autoscaling relies on the custom container exposing standard metrics (e.g., CPU utilization via the /metrics endpoint in a Prometheus format or through the Vertex AI custom metric adapter). If the container does not expose these metrics, the autoscaler cannot detect high CPU usage and will not trigger scaling beyond the initial replicas, leading to latency spikes and 503 errors under load.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Increase min_replica_count to 5 to handle the baseline load.
Why it's wrong here
This would increase cost but not fix the scaling failure; the system should scale dynamically.
✗
Change the endpoint configuration to use gRPC instead of HTTP to reduce latency.
Why it's wrong here
Latency is a symptom, not the root cause; scaling is the issue.
✓
Ensure the custom container exposes the correct metrics for CPU utilization so that Vertex AI autoscaling can trigger.
Why this is correct
Autoscaling relies on metrics; if the container doesn't expose them, scaling won't happen.
Clue confirmation
The clue words "most likely", "never" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
✗
Set the max_replica_count to a higher value like 20.
Why it's wrong here
The issue is that replicas didn't scale at all, not the max limit.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates assume autoscaling is automatic based on CPU utilization alone, but Vertex AI requires explicit metric exposure from custom containers; otherwise, the autoscaler remains inactive.
Detailed technical explanation
How to think about this question
Vertex AI Prediction uses the Horizontal Pod Autoscaler (HPA) under the hood, which requires custom containers to expose a /metrics endpoint with CPU/memory utilization data (or use the built-in Stackdriver adapter). Without these metrics, the HPA cannot compute the desired replica count, so it defaults to the minimum. In production, teams often use a sidecar container (e.g., Prometheus exporter) or ensure the model server (like TensorFlow Serving) exposes standard metrics to enable proper autoscaling.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Ensure the custom container exposes the correct metrics for CPU utilization so that Vertex AI autoscaling can trigger. — Option C is correct because Vertex AI's autoscaling relies on the custom container exposing standard metrics (e.g., CPU utilization via the /metrics endpoint in a Prometheus format or through the Vertex AI custom metric adapter). If the container does not expose these metrics, the autoscaler cannot detect high CPU usage and will not trigger scaling beyond the initial replicas, leading to latency spikes and 503 errors under load.
What should I do if I get this PDE question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "most likely", "never". Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This PDE practice question is part of Courseiva's free Google Cloud 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 PDE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.