This PDE practice question tests your understanding of operationalizing machine learning models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. 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.
A team is debugging a sudden increase in prediction latency for a model deployed on Vertex AI Endpoints. Which TWO metrics in Cloud Monitoring should they examine first? (Choose two.)
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "first"
Why it matters: Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
CPU utilization
High CPU utilization can cause processing delays.
Memory utilization
Memory pressure can lead to swapping and increased latency.
gRPC port errors
Why wrong: These indicate connection issues, not latency causes.
Number of predictions
Why wrong: Prediction count helps correlate but is not a direct cause of latency.
Prediction request latency
Why wrong: This metric shows latency but not the root cause.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
CPU utilization
CPU utilization (A) is correct because a sudden increase in prediction latency often stems from the model consuming excessive CPU cycles during inference, especially for compute-intensive models like deep neural networks. Monitoring CPU utilization helps identify whether the endpoint's compute resources are saturated, causing requests to queue and latency to spike. Memory utilization (B) is correct because insufficient memory can lead to swapping or garbage collection pauses, directly increasing latency. Vertex AI Endpoints autoscales based on these metrics, so examining them first pinpoints resource bottlenecks.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
CPU utilization
Why this is correct
High CPU utilization can cause processing delays.
Clue confirmation
The clue word "first" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Memory utilization
Why this is correct
Memory pressure can lead to swapping and increased latency.
Clue confirmation
The clue word "first" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
gRPC port errors
Why it's wrong here
These indicate connection issues, not latency causes.
Number of predictions
Why it's wrong here
Prediction count helps correlate but is not a direct cause of latency.
Prediction request latency
Why it's wrong here
This metric shows latency but not the root cause.
Common exam traps
Google Cloud often tests the distinction between symptom metrics (like prediction request latency) and root-cause metrics (like CPU/memory utilization), trapping candidates who select the symptom as a diagnostic metric instead of the underlying resource indicators.
Trap categories for this question
Command / output trap
This metric shows latency but not the root cause.
Detailed technical explanation
Under the hood, Vertex AI Endpoints use containerized model servers (e.g., TensorFlow Serving or NVIDIA Triton) that expose CPU and memory utilization via the `container.googleapis.com/container/cpu/utilization` and `container.googleapis.com/container/memory/usage` metrics. A real-world scenario: a model with a large embedding table can cause memory pressure, leading to disk swapping and latency spikes; CPU utilization might remain low while memory utilization hits 95%, pinpointing the bottleneck. Subtle behavior: Vertex AI's autoscaler uses these metrics to trigger scale-out, but if the scaling threshold is set too high, latency can degrade before new nodes are added.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
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
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Operationalizing machine learning models — study guide chapter
Learn the concepts, then practise the questions
Operationalizing machine learning models practice questions
Targeted practice on this topic area only
All PDE questions
499 questions across all exam domains
Google Professional Data Engineer study guide
Full concept coverage aligned to exam objectives
PDE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PDE questions linked to Designing data processing systems.
Practise PDE questions linked to Building and operationalizing data processing systems.
Practise PDE questions linked to Operationalizing machine learning models.
Practise PDE questions linked to Ensuring solution quality.
Practise PDE questions linked to PDE fundamentals.
Practise PDE questions linked to PDE scenario.
Practise PDE questions linked to PDE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
The correct answer is: CPU utilization — CPU utilization (A) is correct because a sudden increase in prediction latency often stems from the model consuming excessive CPU cycles during inference, especially for compute-intensive models like deep neural networks. Monitoring CPU utilization helps identify whether the endpoint's compute resources are saturated, causing requests to queue and latency to spike. Memory utilization (B) is correct because insufficient memory can lead to swapping or garbage collection pauses, directly increasing latency. Vertex AI Endpoints autoscales based on these metrics, so examining them first pinpoints resource bottlenecks.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Yes — watch for: "first". Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
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 →
Keep practising
Last reviewed: Jun 30, 2026
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.