The correct choice is to use a custom metric such as memory utilization or request count for auto-scaling. This is because CPU utilization is a poor scaling metric for inference workloads that are I/O or memory-bound; during a flash sale, increased request concurrency causes queuing and latency spikes even when CPU remains low. A custom metric like request count per instance directly reflects the actual load on the endpoint, allowing Application Auto Scaling to scale out proactively before latency degrades. On the AWS Certified Machine Learning Engineer Associate MLA-C01 exam, this scenario tests your understanding that SageMaker auto-scaling with custom metrics is essential when CPU is low but latency is high—a common trap is assuming CPU always correlates with performance. Remember the mnemonic: “Low CPU, high latency? Scale on requests, not on capacity.”
MLA-C01 Deployment and Orchestration of ML Workflows Practice Question
This MLA-C01 practice question tests your understanding of deployment and orchestration of ml workflows. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. 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 company uses SageMaker endpoints with auto-scaling based on CPU utilization. During a flash sale, latency increases despite low CPU. What should be done?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use a custom metric such as memory utilization or request count for auto-scaling
Option A is correct because CPU utilization is a poor scaling metric for inference workloads that are I/O or memory-bound. During a flash sale, increased request concurrency can cause queuing and latency spikes even when CPU is low. Using a custom metric like request count per instance or memory utilization directly reflects the load on the inference endpoint, enabling the Application Auto Scaling target tracking policy to scale out proactively before latency degrades.
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.
✓
Use a custom metric such as memory utilization or request count for auto-scaling
Why this is correct
Custom metrics can better capture the actual load and scale appropriately.
Related concept
Read the scenario before looking for a memorised answer.
✗
Increase the instance size
Why it's wrong here
Larger instances may not address the root cause if CPU is not the bottleneck.
✗
Disable auto-scaling and use a larger instance
Why it's wrong here
This is a static solution; does not handle varying traffic efficiently.
✗
Switch to GPU instances
Why it's wrong here
GPU instances are for specialized workloads; not necessarily fixing scaling based on wrong metric.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates assume CPU utilization is always the best scaling metric for compute-bound workloads, but the MLA-C01 exam specifically tests the understanding that inference endpoints can be I/O-bound, making request count or memory utilization more appropriate for auto-scaling.
Detailed technical explanation
How to think about this question
Under the hood, SageMaker auto-scaling uses the AWS Application Auto Scaling service with target tracking policies that adjust the desired instance count based on a predefined or custom CloudWatch metric. When using CPU utilization, the policy assumes a linear relationship between CPU and load, but inference containers often spend time waiting on network I/O or model deserialization, causing CPU to remain idle while requests pile up. A custom metric such as 'InvocationsPerInstance' or 'RequestLatency' can be published via CloudWatch PutMetricData and then used in a target tracking policy to scale based on the actual throughput bottleneck.
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.
Deployment and Orchestration of ML Workflows — This question tests Deployment and Orchestration of ML Workflows — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Use a custom metric such as memory utilization or request count for auto-scaling — Option A is correct because CPU utilization is a poor scaling metric for inference workloads that are I/O or memory-bound. During a flash sale, increased request concurrency can cause queuing and latency spikes even when CPU is low. Using a custom metric like request count per instance or memory utilization directly reflects the load on the inference endpoint, enabling the Application Auto Scaling target tracking policy to scale out proactively before latency degrades.
What should I do if I get this MLA-C01 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 →
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 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.