Microsoft Certified: Azure AI Engineer AssociatePlan and manage an Azure AI solutionMedium
A retail company is developing an Azure AI solution to provide personalized product recommendations to its customers. The solution will use Azure Machine Learning for model training and inference. To ensure the recommendations are highly relevant and updated frequently, the company plans to retrain the models daily. Which deployment strategy should be prioritized to minimize downtime during model updates?
- AIn-place deployment
- BRolling update deployment
- CCanary deployment
- DBlue/Green deployment
Show answer & explanationAnswer & explanation
Correct answer: D. Blue/Green deployment
Blue/Green deployment involves running two identical environments (Blue and Green). The new model is deployed to the inactive environment (Green), tested, and then traffic is switched, minimizing downtime and providing an easy rollback option.
Why the other options are wrong
- A. In-place deployment replaces the old version directly, leading to downtime during the update.
- B. Rolling updates update instances one by one, which can still cause performance degradation during the update, especially for stateful applications.
- C. Canary deployment routes a small percentage of traffic to the new version for testing, but a full cutover still needs a strategy like Blue/Green for minimal downtime.
Blue/Green Deployment
A deployment strategy where two identical production environments (Blue and Green) are maintained. One is active, serving traffic, while the other is idle. New versions are deployed to the idle environment, tested, and then traffic is switched.
- Minimizes downtime (near-zero downtime).
- Provides a quick and easy rollback mechanism.
- Requires double the infrastructure resources during deployment.
Memory trick: Blue/Green is like flipping a 'switch' between two identical tracks.