← PDE·Google Cloud

Question 344 of 499

Operationalizing machine learning models →hardMultiple ChoiceObjective-mapped

Quick Answer

The answer is to optimize the prediction container to handle requests faster by reducing image pre-processing and using async I/O. This is correct because the observed metrics—low CPU and GPU utilization with replicas stuck at the minimum of two—indicate the container itself is the bottleneck, not a lack of compute resources; each request takes too long, causing timeouts before the autoscaler can react. On the Google Professional Data Engineer exam, this scenario tests your understanding that Vertex AI prediction latency optimization often requires container-level tuning rather than infrastructure changes, and a common trap is to immediately adjust scaling or timeout settings when the real issue is inefficient request processing. Remember the “low utilization, high latency” paradox: if resources aren’t saturated but requests still time out, the container code is the culprit. A useful memory tip is “Optimize the container, not the cluster.”

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.

A healthcare company uses Vertex AI to deploy a medical image classification model. The model is deployed on a private endpoint with automatic scaling (minReplicaCount=2, maxReplicaCount=10). The model uses a custom container with a GPU for inference. Recently, during peak business hours (9 AM - 5 PM), users report that prediction requests frequently time out after 60 seconds, and the error rate increases. The team checks Cloud Monitoring and observes that CPU utilization averages 40%, GPU utilization averages 30%, and the number of replicas stays at 2. There are no errors in the container logs. The model serves a few hundred requests per second during peak. The team suspects the issue is not resource saturation but something else. What should they do to resolve the problem?

Question 1hardmultiple choice

Full question →

A
Switch from online prediction to batch prediction using Vertex AI Batch Prediction.
Why wrong: Batch prediction is not suitable for real-time user requests; it's designed for large-scale offline processing.
B
Increase the minReplicaCount to 5 to ensure more replicas are always available.
Why wrong: CPU and GPU utilization are low, so adding more replicas will not reduce latency; requests are already slow on each replica.
C
Increase the request timeout setting on the load balancer to 120 seconds.
Why wrong: This only masks the issue; requests will still be slow and may lead to poor user experience.
D
Optimize the prediction container to handle requests faster by reducing image pre-processing and using async I/O.
Improving request handling efficiency directly addresses the timeout. Likely the container is blocking on I/O or serialization.

Full breakdown with real-world context →

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

✓

Optimize the prediction container to handle requests faster by reducing image pre-processing and using async I/O.

Option D is correct because the symptoms—low CPU/GPU utilization, replicas stuck at 2, and timeouts—indicate that the container is taking too long to process each request, not that resources are saturated. Optimizing the container (e.g., reducing image pre-processing, using async I/O) reduces per-request latency, allowing the model to handle the same request rate within the 60-second timeout. This directly addresses the root cause without changing scaling or timeout settings.

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.

✗
Switch from online prediction to batch prediction using Vertex AI Batch Prediction.
Why it's wrong here
Batch prediction is not suitable for real-time user requests; it's designed for large-scale offline processing.
✗
Increase the minReplicaCount to 5 to ensure more replicas are always available.
Why it's wrong here
CPU and GPU utilization are low, so adding more replicas will not reduce latency; requests are already slow on each replica.
✗
Increase the request timeout setting on the load balancer to 120 seconds.
Why it's wrong here
This only masks the issue; requests will still be slow and may lead to poor user experience.
✓
Optimize the prediction container to handle requests faster by reducing image pre-processing and using async I/O.
Why this is correct
Improving request handling efficiency directly addresses the timeout. Likely the container is blocking on I/O or serialization.
Related concept
Read the scenario before looking for a memorised answer.

Common exam traps

Common exam trap: answer the scenario, not the keyword

The trap here is that candidates assume low resource utilization means the system is under-provisioned (leading them to increase replicas or timeout), when in fact the bottleneck is per-request latency within the container, which autoscaling cannot fix.

Detailed technical explanation

How to think about this question

Under the hood, Vertex AI online prediction uses a load balancer with a default 60-second timeout for HTTP responses. If the container’s inference logic (e.g., image pre-processing, model inference, post-processing) exceeds this duration, the load balancer terminates the connection and returns a 504 error. Even with autoscaling, if each replica can only handle a few requests per second due to slow code, the total throughput remains low, and replicas won't scale up because CPU/GPU utilization stays below the autoscaling target (typically 60-70%). In real-world scenarios, unoptimized Python loops or synchronous I/O in pre-processing are common culprits.

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

A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.

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.

Related PDE practice-question pages

Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.

Designing data processing systems practice questions

Practise PDE questions linked to Designing data processing systems.

Building and operationalizing data processing systems practice questions

Practise PDE questions linked to Building and operationalizing data processing systems.

Operationalizing machine learning models practice questions

Practise PDE questions linked to Operationalizing machine learning models.

Ensuring solution quality practice questions

Practise PDE questions linked to Ensuring solution quality.

PDE fundamentals practice questions

Practise PDE questions linked to PDE fundamentals.

PDE scenario practice questions

Practise PDE questions linked to PDE scenario.

PDE troubleshooting practice questions

Practise PDE questions linked to PDE troubleshooting.

Practice this exam

Start a free PDE practice session

Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.

10 questions 20 questions 30 questions 50 questions Timed 30

PDE practice-test guide →Study guide →Browse all practice tests

FAQ

Questions learners often ask

What does this PDE question test?

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: Optimize the prediction container to handle requests faster by reducing image pre-processing and using async I/O. — Option D is correct because the symptoms—low CPU/GPU utilization, replicas stuck at 2, and timeouts—indicate that the container is taking too long to process each request, not that resources are saturated. Optimizing the container (e.g., reducing image pre-processing, using async I/O) reduces per-request latency, allowing the model to handle the same request rate within the 60-second timeout. This directly addresses the root cause without changing scaling or timeout settings.

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.

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 →

How Courseiva writes practice questions · Editorial policy

Keep practising

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.

Loading comments…

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.