Databricks-ML-Assoc Model Deployment Practice Question
A team observes that their Databricks Model Serving endpoint occasionally returns HTTP 429 responses during bursty traffic, even though the endpoint shows low average CPU utilization. They want to reduce these throttling errors without over-provisioning capacity. Which action is most appropriate?
⚠ Common exam trap
The trap here is equating low average CPU with sufficient capacity, when 429s during bursts are caused by concurrency queue saturation rather than sustained compute pressure.
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
✓
Increase the endpoint's `max_instances` and tune the autoscaling concurrency target so replicas scale out faster during bursts.
Throttling at low average CPU points to concurrency saturation during short bursts. Allowing the endpoint to scale to more replicas and configuring autoscaling to react to concurrency sooner lets the endpoint absorb spikes before requests are rejected. This addresses the root cause without permanently over-provisioning capacity during steady-state periods.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Switch the endpoint to a smaller workload size so individual replicas handle requests faster.
Why it's wrong here
Workload size determines the compute resources per replica. Choosing a smaller size reduces per-replica capacity, which would make concurrency saturation worse, not better. The scenario already shows low average CPU, so the bottleneck is queueing and scaling responsiveness, not per-replica compute. Downgrading would increase 429 frequency rather than alleviate it.
- ✗
Enable scale-to-zero and rely on autoscaling to handle bursts.
Why it's wrong here
Scale-to-zero reduces cost during idle periods but worsens burst behavior because replicas must cold-start before serving traffic. During the cold-start window, requests queue and can be rejected with 429s. This directly contradicts the goal of reducing throttling errors under bursty load, so it is the opposite of what the team should configure.
- ✓
Increase the endpoint's `max_instances` and tune the autoscaling concurrency target so replicas scale out faster during bursts.
Why this is correct
HTTP 429 responses from Model Serving typically indicate that the per-replica request queue is saturated even though average CPU is low, because bursts arrive faster than replicas can accept them. Raising `max_instances` allows more replicas to spin up, and tuning the concurrency target makes the autoscaler react sooner, absorbing bursts before requests are rejected.
- ✗
Increase the endpoint's `min_instances` so that more replicas are always warm.
Why it's wrong here
Raising `min_instances` keeps more replicas running, which helps with cold starts but does not address burst-driven concurrency limits. If the endpoint is already scaled out, additional always-on replicas increase cost without changing the per-replica request queue behavior. The 429s stem from momentary concurrency saturation, not from insufficient baseline capacity, so this action is misaligned with the observed symptom.
About these practice questions
One of 319 original Databricks-ML-Assoc 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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-ML-Assoc practice question is part of Courseiva's free Databricks 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 Databricks-ML-Assoc exam.