PMLE Practice Question: Collaborating Within and Across Teams to Manage Data and Models
A company uses Vertex AI Feature Store with an online store for low-latency serving. They observe high latency during peak hours. The feature values are small (< 1 KB each) and the workload is read-heavy. Which change would most effectively reduce latency?
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
✓
Switch from Bigtable online store to Optimized online store
Switching from Bigtable online store to Optimized online store is recommended for read-heavy workloads with small feature values, offering lower latency at high QPS.
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 caching on the client side
Why it's wrong here
Client-side caching leaves the first request per key hitting the online store, so peak-hour latency persists and stale values risk training-serving skew. It suits repeated reads of identical feature keys within one process, not the shared, read-heavy serving path where Vertex AI's own online store caching targets latency.
- ✓
Switch from Bigtable online store to Optimized online store
Why this is correct
The optimized online store is purpose-built for low-latency, high-throughput serving of small feature values, so migrating from the Bigtable online store addresses the peak-hour latency directly. Increasing node count or reducing feature size does not change the underlying serving architecture.
- ✗
Use a larger machine type for Bigtable
Why it's wrong here
Bigtable node count, not machine type, governs throughput for a read-heavy small-value workload; a larger machine type adds per-node CPU and memory without adding serving capacity. It would help a CPU-bound single-node scan, not the distributed read fan-out causing peak-hour latency.
- ✗
Increase the number of Bigtable nodes
Why it's wrong here
Adding Bigtable nodes raises storage and scan throughput, but the online store's latency comes from per-key lookups, which node count does not accelerate. It is the right lever for large analytical scans or bulk feature backfills, not for sub-kilobyte read-heavy online serving.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PMLE practice question is part of Courseiva's free Google Cloud 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 PMLE exam.