Databricks-ML-Assoc Model Deployment Practice Question
A team wants to route production traffic to a new model version while keeping risk low. They configure a Databricks Model Serving endpoint with two served entities: `champion` (entity_version 5) and `challenger` (entity_version 6). They want 95% of requests to hit `champion` and 5% to hit `challenger`. Which configuration accomplishes this?
⚠ Common exam trap
It's easy for candidates to confuse resource-allocation settings such as workload size or scale-to-zero with traffic-routing settings, which are configured separately in `traffic_config`.
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
✓
Set `traffic_config` with routes assigning `traffic_percentage` 95 to `champion` and 5 to `challenger`.
Databricks Model Serving uses `traffic_config` with a `routes` list, where each route references a served entity by name and assigns an integer `traffic_percentage`. Summing route percentages to 100 achieves the desired 95/5 split. Other configuration fields like workload size and scale-to-zero govern resources and scaling behavior, not request distribution.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Set `traffic_config` with routes assigning `traffic_percentage` 95 to `champion` and 5 to `challenger`.
Why this is correct
Databricks Model Serving supports `traffic_config` with a `routes` array, where each entry names a served entity and specifies an integer `traffic_percentage`. Summing to 100 across routes enables canary or A/B routing. Setting 95 for champion and 5 for challenger delivers the desired split. This is the supported mechanism for gradual rollout without redeploying the endpoint.
- ✗
Deploy two separate endpoints and use a client-side load balancer to send 95% of calls to the champion endpoint.
Why it's wrong here
While client-side load balancing can technically distribute calls, it shifts routing logic out of Databricks Model Serving and requires custom code, monitoring, and failover handling. The scenario asks for a configuration within a single endpoint using served entities, and Databricks provides native `traffic_config` for exactly this purpose. Splitting into two endpoints also doubles operational overhead.
- ✗
Set `scale_to_zero_enabled` to true only on `challenger` so it receives proportionally fewer requests.
Why it's wrong here
`scale_to_zero_enabled` controls whether a served entity can scale down to zero replicas when idle; it does not distribute traffic proportionally. When traffic arrives, the entity scales up and serves whatever requests the router sends. Using it to influence traffic share is a misuse; the router ignores scaling settings when choosing which entity handles a given request.
- ✗
Set `workload_size` to `Small` on `champion` and `Large` on `challenger` to bias traffic toward the larger entity.
Why it's wrong here
`workload_size` determines the compute resources allocated per served entity replica, not the fraction of requests routed to it. A `Large` workload size gives more memory and CPU for heavier models but does not attract more traffic. Traffic distribution is governed exclusively by `traffic_config` routes, so this approach would not produce a 95/5 split.
About these practice questions
This Databricks-ML-Assoc question is part of Courseiva's 319-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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.