Quick Answer
The correct answer is MemoryUtilization, along with ModelLatency and Invocations, as these three metrics form the core triad for detecting SageMaker endpoint performance issues. MemoryUtilization reveals whether the instance is running out of RAM, which directly causes swapping and degraded inference speed, while ModelLatency measures the time per request to catch bottlenecks or underprovisioning, and Invocations tracks request volume to correlate load with latency spikes. On the AWS Certified Machine Learning Engineer Associate MLA-C01 exam, this question tests your ability to distinguish between infrastructure-level metrics (like CPUUtilization) and performance-specific signals—a common trap is selecting CPUUtilization instead of MemoryUtilization, but memory pressure is often the first indicator of a model’s footprint exceeding capacity. To remember the trio, think “LIM”: Latency, Invocations, Memory—the three pillars that tell you if your endpoint is healthy or hurting.
This MLA-C01 practice question tests your understanding of ml solution monitoring, maintenance and security. 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.
An ML engineer is setting up monitoring for a SageMaker endpoint. Which THREE metrics should be monitored to detect performance issues? (Select THREE.)
Model latency
High latency indicates performance degradation.
Invocations per second
Why wrong: This is a throughput metric, not a performance health indicator.
CPUUtilization
High CPU may indicate insufficient capacity.
MemoryUtilization
High memory can cause swapping and latency issues.
DiskWriteBytes
Why wrong: Disk I/O is not typically a bottleneck for SageMaker inference.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Model latency
Model latency is a critical metric for detecting performance issues in a SageMaker endpoint because it directly measures the time taken to process inference requests. High latency can indicate resource bottlenecks, model inefficiency, or scaling problems, and it is essential for meeting service-level agreements (SLAs). Monitoring latency helps identify when the endpoint is underprovisioned or when the model itself has degraded in performance.
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.
Model latency
Why this is correct
High latency indicates performance degradation.
Related concept
Read the scenario before looking for a memorised answer.
Invocations per second
Why it's wrong here
This is a throughput metric, not a performance health indicator.
CPUUtilization
Why this is correct
High CPU may indicate insufficient capacity.
Related concept
Read the scenario before looking for a memorised answer.
MemoryUtilization
Why this is correct
High memory can cause swapping and latency issues.
Related concept
Read the scenario before looking for a memorised answer.
DiskWriteBytes
Why it's wrong here
Disk I/O is not typically a bottleneck for SageMaker inference.
Common exam traps
The trap here is that candidates often confuse throughput metrics (like invocations per second) with performance health indicators, but the question specifically asks for metrics that detect performance issues, not just operational statistics.
Detailed technical explanation
Under the hood, SageMaker endpoints use auto-scaling policies based on metrics like invocation count and latency, but CPUUtilization and MemoryUtilization are key for detecting resource contention. For example, if CPUUtilization consistently exceeds 80%, the instance may be CPU-bound, leading to increased latency and potential throttling. In a real-world scenario, a memory leak in the model serving code could cause MemoryUtilization to grow over time, eventually triggering out-of-memory errors and failed invocations, which would not be caught by invocation count alone.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
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
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
ML Solution Monitoring, Maintenance and Security — study guide chapter
Learn the concepts, then practise the questions
ML Solution Monitoring, Maintenance and Security practice questions
Targeted practice on this topic area only
All MLA-C01 questions
507 questions across all exam domains
AWS Certified Machine Learning Engineer Associate MLA-C01 study guide
Full concept coverage aligned to exam objectives
MLA-C01 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 MLA-C01 questions linked to Data Preparation for Machine Learning.
Practise MLA-C01 questions linked to ML Model Development.
Practise MLA-C01 questions linked to Deployment and Orchestration of ML Workflows.
Practise MLA-C01 questions linked to ML Solution Monitoring, Maintenance and Security.
Practise MLA-C01 questions linked to MLA-C01 fundamentals.
Practise MLA-C01 questions linked to MLA-C01 scenario.
Practise MLA-C01 questions linked to MLA-C01 troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
ML Solution Monitoring, Maintenance and Security — This question tests ML Solution Monitoring, Maintenance and Security — Read the scenario before looking for a memorised answer..
The correct answer is: Model latency — Model latency is a critical metric for detecting performance issues in a SageMaker endpoint because it directly measures the time taken to process inference requests. High latency can indicate resource bottlenecks, model inefficiency, or scaling problems, and it is essential for meeting service-level agreements (SLAs). Monitoring latency helps identify when the endpoint is underprovisioned or when the model itself has degraded in performance.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
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 →
Last reviewed: Jun 24, 2026
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 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.