PDE Practice Test 27 — 15 Questions

Question 1

A data science team has deployed a custom TensorFlow model on Vertex AI Prediction. They notice increasing prediction latency and a growing number of 503 errors during peak traffic hours. The model is served using a single regional endpoint with min replica count of 2 and max replica count of 10. Which TWO actions should the team take to address these issues?

Accepted Answer

Enable autoscaling with a higher max replica count and configure a CPU utilization target of 60%.

Answer

Use a larger machine type (e.g., n1-highmem-8) instead of the current n1-standard-4 to improve per-replica throughput.

Answer

Reduce the min replica count to 0 to allow the service to scale down to zero when not in use.

Answer

Deploy the model as a batch prediction job and move all online predictions to batch.

Question 2

Your team manages a multi-model ensemble deployed on Vertex AI Endpoint. The ensemble consists of three models: a neural network (NN), a gradient boosted tree (GBT), and a logistic regression (LR). They are deployed as separate endpoints and traffic is split using a traffic split configuration. Recently, the overall accuracy dropped from 92% to 85%. Monitoring shows that the NN model's latency has increased significantly, causing it to miss timeouts and fall back to default predictions. The other two models are performing normally. The NN model is the most complex and handles the majority of the traffic. You need to restore accuracy quickly. What should you do first?

Accepted Answer

Temporarily reduce the traffic percentage to the NN model to 0% and redistribute to GBT and LR until the NN issue is resolved.

Answer

Increase the timeout for predictions on the NN endpoint to avoid fallback.

Answer

Enable fallback logic to use the GBT model when NN times out, ensuring no prediction is missed.

Answer

Relaunch the NN model with a larger machine type and more replicas to reduce latency.

Question 3

A company is designing a CI/CD pipeline for their ML models using Cloud Build and Vertex AI. Which TWO practices should they adopt to ensure reliable and reproducible deployments?

Accepted Answer

Use immutable container images with version tags for each model deployment. Options B and D are correct. B (unit tests for preprocessing) ensures data consistency. D (immutable versioned images) ensures reproducibility. Option A (manual approval for all changes) slows down CI/CD. Option C (staging endpoint) is good but not required for reproducibility. Option E (single source of truth) is important but not a specific CI/CD practice.

Answer

Require manual approval for every model change before deployment

Answer

Store all model artifacts in a single Cloud Storage bucket without versioning

Answer

Deploy every model version directly to production for immediate use

Question 4

Your organization deploys multiple versions of the same model to Vertex AI Endpoint for A/B testing. You have a production model (v1) serving 90% of traffic and a candidate model (v2) serving 10%. After one week, you observe that v2 has a slightly lower AUC but significantly higher business metrics like click-through rate. The product team wants to gradually increase v2's traffic. However, you need to ensure that the overall prediction latency remains under 200 ms. Currently, the endpoint has 10 replicas for v1 and 2 replicas for v2. What is the best approach to roll out v2 while maintaining latency SLO?

Accepted Answer

Increase v2's traffic split by 10% each day while also adding replicas for v2 based on CPU utilization.

Answer

Merge v2's model into v1 by retraining v1 with v2's architecture and deploy as a single model.

Answer

Immediately set v2 to serve 100% traffic and monitor latency; if it exceeds 200 ms, roll back.

Answer

Use a separate endpoint for v2 and route traffic at the load balancer level.

Question 5

A data pipeline processes streaming data with Dataflow. The team notices occasional data duplication in BigQuery. What is the best approach to ensure exactly-once processing?

Accepted Answer

Configure Dataflow with exactly-once sinks using file staging and deduplication.. Option B is correct because Dataflow's exactly-once sink mechanism, which uses file staging and deduplication, ensures no duplicates. Option A (at-least-once delivery) can cause duplicates unless dedup is applied, but that's not automatic. Option C adds unnecessary complexity. Option D is incorrect because BigQuery does not natively support idempotent writes.

Answer

Use Pub/Sub with at-least-once delivery and deduplicate in BigQuery using a unique identifier.

Answer

Use Cloud Functions to deduplicate messages before they enter the pipeline.

Answer

Enable idempotent writes in BigQuery.

Question 6

A company is deploying a large-scale streaming application on Google Kubernetes Engine. They need to ensure the application can handle sudden traffic spikes without dropping data. Which architectural pattern is most appropriate?

Accepted Answer

Use a Pub/Sub topic as a buffer and autoscale consumer pods based on Pub/Sub subscription backlog.. Option A is correct because using a Pub/Sub buffer decouples producers from consumers, allowing autoscaling of consumers to handle spikes. Option B is wasteful and not dynamically scalable. Option C uses Cloud SQL, which is not designed for high-throughput buffering. Option D only addresses retries, not overall throughput capacity.

Answer

Implement custom retry logic with exponential backoff in the application.

Answer

Use Cloud SQL as a temporary buffer and process from there.

Answer

Pre-provision 3x the expected peak capacity to handle spikes.

Question 7

A data science team uses AI Platform Training with hyperparameter tuning. They observe that some trials fail due to transient errors. To improve solution quality and reduce costs, what should they do?

Accepted Answer

Set the maxFailedTrials parameter to a high value (e.g., 10).. Option D is correct because setting maxFailedTrials to a high value allows more trials to complete despite transient failures, improving the chance of finding a good model without wasting resources on re-running failed trials. Option A increases parallelism but still pays for failed trials. Option B (early stopping) prunes unpromising trials, but does not address transient errors. Option C increases cost per trial without solving the failure issue.

Answer

Enable early stopping using a Bayesian optimization algorithm.

Answer

Use larger machine types for each trial.

Answer

Increase the number of parallel trials.

Question 8

A company runs batch jobs on Dataproc. They need to ensure that if a job fails, it automatically retries with exponential backoff. What is the recommended approach?

Accepted Answer

Use Dataproc Workflow Templates with the maxAttempts parameter set to 3.. Option C is correct because Dataproc Workflow Templates support configuring maxAttempts and retry policy in the template, enabling automatic retries with exponential backoff. Option A (Composer) is overkill for simple retry. Option B (cron job) would need custom logic. Option D (Cloud Functions) also requires custom implementation.

Answer

Schedule a cron job to check job status and restart manually.

Answer

Use a Cloud Function triggered by Stackdriver alerts to restart the job.

Answer

Create a Cloud Composer DAG that monitors job status and retries on failure.

Question 9

A team developed a microservice that writes logs to stdout. They want to centralize logs for analysis. Which GCP service should they use to automatically collect and store logs?

Accepted Answer

Use the Cloud Logging client library (google-cloud-logging) for the microservice's language.. Option D is correct because Cloud Logging with the client library automatically captures stdout logs and sends them to Cloud Logging. Option A (Cloud Logging agent) is for VMs, not containers. Option B (Cloud Storage) is for object storage. Option C (Pub/Sub) is for messaging, not log collection.

Answer

Install the Cloud Logging agent on the VM running the microservice.

Answer

Publish logs to a Pub/Sub topic and later store them.

Answer

Write logs directly to Cloud Storage.

Question 10

A data platform uses Cloud Spanner for transactional data. They are experiencing high latency during write-heavy periods. To maintain solution quality, what configuration change is most effective?

Accepted Answer

Use interleaved tables to reduce the number of split operations.. Option A is correct because interleaved tables improve data locality, reducing the number of splits and distributed commits, thus reducing write latency. Option B (increasing nodes) can increase throughput but may increase latency due to more distributed transactions. Option C (online schema changes) does not directly affect write performance. Option D (manual splitting) is not recommended and may worsen performance.

Answer

Enable online schema changes.

Answer

Increase the number of nodes in the Cloud Spanner instance.

Answer

Manually split the table using ALTER TABLE statements.

Question 11

A company uses Cloud Functions to process events from Cloud Storage. They notice that occasionally functions are not triggered. What should they check first to ensure solution quality?

Accepted Answer

Verify that the Cloud Storage bucket has notifications configured for the correct event type.. Option C is correct because the first step is to verify the Cloud Storage bucket notification configuration, as a misconfigured trigger will cause missed events. Option A (function timeout) does not cause missing triggers. Option B (memory) is unrelated. Option D (logs) are helpful but after verifying trigger configuration.

Answer

Check the logs for function execution.

Answer

Increase the function memory allocation.

Answer

Increase the function timeout.

Question 12

A financial services company uses Dataflow pipelines with late data handling. They need to ensure that all late-arriving data is processed correctly but also want to control costs. What is the best configuration?

Accepted Answer

Use fixed windows with allowed lateness set to the maximum expected delay (e.g., 2 days) and a trivial watermark.. Option D is correct because using fixed windows with allowed lateness set to the maximum expected delay and a trivial watermark balances completeness and cost. Option A (global window with long allowed lateness) can cause high state cost. Option B (session windows) may merge late data incorrectly. Option C (sliding windows with short allowed lateness and side input) is complex and may miss data.

Answer

Use a global window with a very long allowed lateness (e.g., 7 days).

Answer

Use session windows with a gap duration of 1 hour and allowed lateness of 2 days.

Answer

Use sliding windows with a short allowed lateness (e.g., 10 minutes) and a side input containing historical data.

Question 13

A team is deploying a model on AI Platform Prediction. They want to monitor for data drift to maintain model quality. Which service should they use?

Accepted Answer

AI Platform Continuous Evaluation. Option B is correct because AI Platform Continuous Evaluation is designed to monitor model performance and detect data drift. Option A (Cloud Monitoring) is for infrastructure metrics. Option C (Cloud Audit Logs) is for API activity. Option D (Cloud DLP) is for data loss prevention.

Answer

Cloud DLP

Answer

Cloud Monitoring

Answer

Cloud Audit Logs

Question 14

A data engineer needs to monitor the performance of BigQuery queries to identify opportunities for optimization. Which TWO metrics should they focus on? (Choose two.)

Accepted Answer

Slot usage. Options A and E are correct: Slot usage indicates resource consumption, and data scanned per query directly correlates with cost and performance. Option B (number of tables joined) is not a direct metric. Option C (execution time) is important but can be affected by many factors. Option D (number of users) is irrelevant.

Answer

Query execution time

Answer

Number of tables joined

Answer

Number of users

Question 15

A company uses Cloud Build to deploy containerized applications. They want to ensure build and deployment quality. Which THREE steps should they include in their CI/CD pipeline? (Choose three.)

Accepted Answer

Scan container images for vulnerabilities using Container Analysis.. Options B, D, and E are correct: Container scanning catches vulnerabilities, canary deployments reduce risk, and pinning base image digests ensures reproducibility. Option A (unit tests after deployment) is too late. Option C (direct deployment to production) bypasses safety checks.

Answer

Run unit tests after deployment.

Answer

Deploy directly to production on every commit.