Courseiva
ModelingmediumMultiple ChoiceObjective-mapped

MLS-C01 Modeling Practice Question

Network Topology
$ aws sagemaker describe-endpoint-configendpoint-config-name my-configRefer to the exhibit.```"EndpointConfigName": "my-config","ProductionVariants": ["VariantName": "variant-1","ModelName": "my-model","InitialInstanceCount": 1,"InstanceType": "ml.m5.large","InitialVariantWeight": 1.0

A team deployed a SageMaker endpoint with the configuration shown in the exhibit. During a traffic spike, the endpoint becomes unresponsive. Which change to the endpoint configuration would best improve availability?

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

Configure auto-scaling for the endpoint

Configuring auto-scaling for the SageMaker endpoint allows it to automatically add or remove instances based on traffic load, improving availability during spikes. Option A is incorrect because setting initial instance count to 0 would cause requests to fail until an instance is provisioned, and on-demand invocation does not improve availability. Option B is incorrect because adding a second production variant with the same model does not change the total number of instances; the endpoint would still have only one instance if both variants share the same instance count. Option D is incorrect because changing the instance type to ml.m5.xlarge might provide more resources per instance but does not increase the number of instances; a single instance can still become overwhelmed.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Reduce the initial instance count to 0 and use on-demand invocation

    Why it's wrong here

    Reducing instance count would cause unavailability during spikes.

  • Add a second production variant with the same model

    Why it's wrong here

    Multiple variants are for A/B testing, not for scaling load.

  • Configure auto-scaling for the endpoint

    Why this is correct

    Auto-scaling dynamically adds instances during traffic spikes, improving availability.

  • Change the instance type to ml.m5.xlarge

    Why it's wrong here

    A larger instance may handle more load but still a single point of failure; auto-scaling is better.

About these practice questions

One of 1,672 original MLS-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This MLS-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 MLS-C01 exam.