Databricks-DE-Pro Cost and Performance Optimization Practice Question
A data engineering team runs a nightly batch job on a Databricks job cluster. The job reads a large Parquet dataset, performs transformations, and writes the result to a Delta table. The cluster is configured with autoscaling from 4 to 16 workers and uses the default Spark configuration. The team observes that the job runs for 2 hours, but the cluster's CPU utilization is only around 30% throughout the run. They want to reduce cost without increasing runtime. Which action is most likely to achieve this?
⚠ Common exam trap
The trap here is assuming that more workers always improve performance, when in fact low CPU utilization signals over-provisioning and reducing workers is the cost-effective fix.
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
✓
Reduce the number of workers in the cluster to match the observed CPU utilization.
The cluster is over-provisioned because CPU utilization is low, indicating the job is not CPU-bound. Reducing the number of workers aligns compute with actual demand and lowers cost without increasing runtime. Other options either add overhead or target the wrong bottleneck, such as shuffle partitioning or driver size, which are not indicated by uniformly low CPU usage.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Cache the Parquet dataset in memory before performing transformations.
Why it's wrong here
Caching can speed up iterative access, but this is a single-pass batch job that reads the dataset once. Caching would consume memory and add overhead without reducing the overall runtime, and it does not address the low CPU utilization. In fact, it could increase cost by using more memory and potentially causing spills, while the cluster remains underutilized.
- ✓
Reduce the number of workers in the cluster to match the observed CPU utilization.
Why this is correct
Since CPU utilization is low, the cluster is over-provisioned relative to the workload's actual parallelism. Reducing the maximum worker count lowers cost while likely maintaining similar runtime, because the job is not CPU-bound and additional workers are idle. This directly aligns compute resources with the workload's needs without changing the job logic or risking performance regression.
- ✗
Switch the job to use Photon and increase the driver node size.
Why it's wrong here
Photon can accelerate certain operations, but the job is not CPU-bound; it is likely I/O or shuffle-bound. Increasing driver size may help if the driver is a bottleneck, but low CPU utilization across the cluster suggests the driver is not the limiting factor. This action adds cost without addressing the root cause of underutilization, and may not reduce runtime.
- ✗
Enable auto-optimize shuffle and set spark.sql.shuffle.partitions to a higher value.
Why it's wrong here
Increasing shuffle partitions can reduce per-task data size but adds scheduling overhead and more small tasks. With low CPU utilization, the bottleneck is likely not partition size but rather insufficient parallelism or I/O wait. This change might even worsen performance by creating too many tiny tasks, and it does not directly address the underlying underutilization of the cluster.
About these practice questions
One of 267 original Databricks-DE-Pro 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-DE-Pro 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-DE-Pro exam.