easyMultiple Choice
PDE Practice Question: A team deployed a model to Vertex AI Endpoint and…
A team deployed a model to Vertex AI Endpoint and notices latency spikes during peak hours. What should they first investigate?
⚠ Common exam trap
Google Cloud often tests the misconception that latency spikes are always due to model complexity or feature engineering, when in fact the first diagnostic step should always be to verify the serving infrastructure's scaling configuration.
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
✓
Check if autoscaling is enabled and configured correctly
Latency spikes during peak hours typically indicate that the serving infrastructure is unable to handle the increased request volume. The first step is to check if autoscaling is enabled and configured correctly on the Vertex AI Endpoint, as this determines whether additional compute nodes are automatically provisioned to match demand. Without proper autoscaling, the endpoint will be overwhelmed, leading to queuing delays and latency spikes.
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 to batch prediction
Why it's wrong here
Batch prediction processes stored data asynchronously and returns results to a destination, so it cannot serve the online requests hitting the endpoint during peak hours. It is tempting because it removes per-request serving load, and would be correct if the workload were offline scoring rather than interactive low-latency inference.
- ✗
Reduce number of features
Why it's wrong here
Reducing features changes model inputs and accuracy, and does not address why the endpoint's latency rises only under peak concurrency. It is tempting because feature count affects inference cost, and would be correct if profiling showed feature retrieval or payload size dominating latency at all load levels.
- ✗
Increase machine type
Why it's wrong here
Increasing machine type raises per-replica capacity but does not explain spikes that occur only at peak; the cause may be insufficient replicas, autoscaling lag, or quota limits. It is tempting because vertical scaling is a familiar remedy, and would be correct if profiling showed CPU or memory saturation on each replica.
- ✓
Check if autoscaling is enabled and configured correctly
Why this is correct
Autoscaling governs how Vertex AI Endpoint provisions replicas against traffic, so misconfigured minimum or maximum replica counts, or an absent scaling metric, directly cause peak-hour latency spikes. Verifying this first addresses the stem's load-dependent symptom before investigating model-level or network causes.
Go deeper
Related to this question
About these practice questions
This PDE question is part of Courseiva's 747-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 PDE 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 PDE exam.