Scaling Out SageMaker Endpoints to Reduce Tail Latency
This MLS-C01 practice question tests your understanding of machine learning implementation and operations. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. 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 SageMaker endpoint has a CloudWatch alarm configured as shown in the exhibit. The alarm fires when the p99 latency exceeds 500 ms for two consecutive minutes. Which action should the data scientist take to reduce latency?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Increase the number of instances behind the endpoint
Increasing the number of instances behind the endpoint adds more compute capacity to handle the inference requests, which directly reduces the queuing and processing time for each request. Since the alarm triggers when p99 latency exceeds 500 ms for two consecutive minutes, scaling out horizontally distributes the load and lowers tail latency.
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.
✓
Increase the number of instances behind the endpoint
Why this is correct
More instances distribute load, reducing latency.
Related concept
Read the scenario before looking for a memorised answer.
✗
Increase the batch size in the inference request
Why it's wrong here
Larger batch size may increase latency.
✗
Use SageMaker asynchronous inference instead of real-time
Why it's wrong here
Async inference is not for low latency.
✗
Switch to GPU instances even if the model does not require GPU
Why it's wrong here
GPU may not reduce latency if not utilized.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates may confuse latency reduction with throughput improvements, and incorrectly choose batch size increase or GPU switching, not realizing that scaling out is the direct remedy for high tail latency under sustained load.
Detailed technical explanation
How to think about this question
SageMaker real-time endpoints use an auto-scaling policy based on metrics like InvocationsPerInstance or custom CloudWatch alarms. When p99 latency exceeds a threshold, scaling out adds instances to reduce the request queue depth per instance, which directly lowers tail latency. In practice, a common cause of high p99 latency is a single instance being overwhelmed by concurrent requests, leading to queuing delays that are mitigated by horizontal scaling.
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.
Machine Learning Implementation and Operations — This question tests Machine Learning Implementation and Operations — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Increase the number of instances behind the endpoint — Increasing the number of instances behind the endpoint adds more compute capacity to handle the inference requests, which directly reduces the queuing and processing time for each request. Since the alarm triggers when p99 latency exceeds 500 ms for two consecutive minutes, scaling out horizontally distributes the load and lowers tail latency.
What should I do if I get this MLS-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 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.
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.