Databricks-ML-Assoc Model Deployment Practice Question
A team's Model Serving endpoint occasionally returns errors when the upstream feature store is slow. They want the endpoint to retry transient failures and reduce cold-start latency for bursty traffic. Which combination of endpoint settings best addresses both concerns?
⚠ Common exam trap
The trap here is assuming the serving endpoint automatically retries upstream dependency failures, when that resilience must be implemented by the caller or model code.
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 a non-zero min_instances for warm capacity and implement client-side retry with backoff for transient upstream errors.
Warm capacity via a non-zero minimum instance count prevents the provisioning delay that causes cold-start latency during bursts. Because the endpoint itself does not automatically retry upstream feature store calls, retry with backoff belongs in the client or model logic. Combining warm replicas with retry logic addresses latency and transient failures without sacrificing scalability or observability.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable inference tables and route all traffic through a single replica to simplify retry logic.
Why it's wrong here
Inference tables provide logging, not retry behavior, and pinning traffic to a single replica removes horizontal scaling that bursty workloads need. That would create a bottleneck and increase latency under load. This option confuses observability with reliability engineering and would degrade the endpoint's ability to absorb traffic spikes, leaving transient-error handling unsolved.
- ✗
Increase the endpoint's workload size to Large and disable request timeouts on the client.
Why it's wrong here
A larger workload size adds compute per replica but does not eliminate cold starts for bursty traffic if replicas are not kept warm, and it does not retry failed calls. Disabling client timeouts can cause requests to hang indefinitely when the feature store is slow, worsening the user experience. This option neither reliably reduces latency nor improves resilience to transient errors.
- ✓
Configure a non-zero min_instances for warm capacity and implement client-side retry with backoff for transient upstream errors.
Why this is correct
Keeping at least one instance warm avoids provisioning delay during bursts, directly reducing cold-start latency. Retrying transient failures with exponential backoff in the calling application or model code handles the intermittent feature store slowness. Together these settings address both the latency and reliability concerns described, making this the balanced operational choice.
- ✗
Set min_instances to zero and enable scale-to-zero to lower cost during idle periods.
Why it's wrong here
Scale-to-zero reduces cost by shutting down replicas when idle, but it increases cold-start latency because a new replica must be provisioned before serving bursty traffic. It also does nothing to retry transient upstream failures. This configuration works against the stated latency goal and leaves the error-handling requirement unaddressed, so it is the opposite of what the team needs.
About these practice questions
Courseiva writes every Databricks-ML-Assoc question from scratch — 319 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 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.