easyMultiple ChoiceObjective-mapped
MLA-C01 Practice Question: Use SageMaker to serve real-time predictions with…
A company wants to use SageMaker to serve real-time predictions with a model that has a large memory footprint. They need to ensure the endpoint can handle traffic spikes. Which scaling policy should they use?
⚠ Common exam trap
Candidates often confuse step scaling with target tracking, assuming step scaling is more responsive for spikes, but target tracking is actually the recommended and simpler approach for handling unpredictable traffic in SageMaker real-time endpoints.
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
✓
Target tracking policy
Target tracking scaling policy is the correct choice because it automatically adjusts the number of instances in the SageMaker endpoint based on a target metric, such as InvocationsPerInstance or ModelLatency, to handle traffic spikes without manual intervention. This policy is ideal for real-time inference with large memory models because it dynamically scales resources up or down to maintain the target metric, ensuring consistent performance during unpredictable traffic bursts.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Simple scaling policy
Why it's wrong here
Simple scaling requires manual configuration of alarm thresholds.
- ✗
Scheduled scaling policy
Why it's wrong here
Scheduled scaling is for predictable traffic patterns, not spikes.
- ✓
Target tracking policy
Why this is correct
Target tracking automatically adjusts capacity to maintain a target metric value.
- ✗
Step scaling policy
Why it's wrong here
Step scaling adjusts capacity in fixed increments based on CloudWatch alarm thresholds, but for a model with a large memory footprint, the endpoint requires sufficient memory per instance to load the model before scaling out. Step scaling does not guarantee that new instances are provisioned with the correct instance type or memory allocation; it only adds more of the same instance type. This policy is tempting because it works well for stateless, CPU-bound workloads where adding any instance alleviates load, but here the bottleneck is per-instance memory capacity, not request count.
Go deeper
Related to this question
About these practice questions
Courseiva writes every MLA-C01 question from scratch — 835 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.