Blue-green deployment for models in MLOps - Mini Project: Build & Apply

Blue-green deployment for models

📖 Scenario: You work in a team that manages machine learning models in production. To avoid downtime and risks when updating models, your team uses a blue-green deployment strategy. This means you have two identical environments: blue and green. One environment serves the live traffic, while the other is used to deploy and test the new model version. After testing, you switch traffic to the new environment.In this project, you will simulate a simple blue-green deployment system for ML models using Python dictionaries and variables.

🎯 Goal: You will build a small program that manages two model environments (blue and green) with their versions. You will set the active environment, deploy a new model version to the inactive environment, switch the active environment, and print the current active model version.

📋 What You'll Learn

Create a dictionary to hold model versions for blue and green environments

Create a variable to track the currently active environment

Write code to deploy a new model version to the inactive environment

Write code to switch the active environment to the inactive one

Print the active environment and its model version

💡 Why This Matters

🌍 Real World

Blue-green deployment is a common technique in MLOps to update machine learning models without downtime or risk. It allows teams to test new models in a safe environment before switching live traffic.

💼 Career

Understanding blue-green deployment helps you work with production ML systems, ensuring smooth updates and high availability, which is a key skill for MLOps engineers and DevOps professionals.

1

Create model version dictionary

Create a dictionary called model_versions with keys 'blue' and 'green'. Set the value for 'blue' to 'v1.0' and for 'green' to 'v0.9'.

MLOps

# Create the model_versions dictionary with blue and green versions
# Your code here

Hint

Use curly braces {} to create a dictionary with keys 'blue' and 'green' and their version strings as values.

2

Set active environment variable

Create a variable called active_env and set it to the string 'blue' to represent the currently active environment.

MLOps

model_versions = {'blue': 'v1.0', 'green': 'v0.9'}
# Set the active_env variable to 'blue'
# Your code here

Hint

Just assign the string 'blue' to the variable active_env.

3

Deploy new model version to inactive environment

Create a variable called inactive_env that is the opposite of active_env (if active_env is 'blue', inactive_env should be 'green', and vice versa). Then update the model_versions dictionary for the inactive_env key to the new version string 'v1.1'.

MLOps

model_versions = {'blue': 'v1.0', 'green': 'v0.9'}
active_env = 'blue'
# Determine inactive_env and update its model version to 'v1.1'
# Your code here

Hint

Use a conditional expression to set inactive_env. Then assign 'v1.1' to model_versions[inactive_env].

4

Switch active environment and print status

Switch the active_env to the inactive_env. Then print the string "Active environment: {active_env}, Model version: {version}" where {active_env} is the current active environment and {version} is the model version from model_versions for that environment.

MLOps

model_versions = {'blue': 'v1.0', 'green': 'v0.9'}
active_env = 'blue'
inactive_env = 'green' if active_env == 'blue' else 'blue'
model_versions[inactive_env] = 'v1.1'
# Switch active_env to inactive_env and print the active environment and model version
# Your code here

Hint

Assign active_env = inactive_env. Use an f-string in print to show the active environment and its model version.

Practice

1. What is the main purpose of blue-green deployment in model updates?

easy

A. To run two models at the same time and combine their outputs

B. To switch traffic to a new model only after it is fully tested and ready

C. To update the model directly in the production environment without backup

D. To deploy models only during off-peak hours

Solution

1. Step 1: Understand blue-green deployment concept

   Blue-green deployment uses two separate environments to avoid downtime and risk during updates.

2. Step 2: Identify the key purpose

   The main goal is to switch traffic to the new model only after it is fully tested and ready, ensuring safety.

3. Final Answer:

   To switch traffic to a new model only after it is fully tested and ready -> Option B

4. Quick Check:

   Safe model update = A [OK]

Hint: Blue-green means switch only after testing new model [OK]

Common Mistakes:

• Thinking both models run and combine outputs
• Updating production without backup
• Deploying only during off-peak hours

2. Which command correctly switches traffic from the blue environment to the green environment in a Kubernetes service?

easy

A. kubectl set image deployment/model-deploy model=green-model:latest

B. kubectl delete deployment model-deploy-blue

C. kubectl rollout restart deployment/model-deploy-green

D. kubectl patch service model-service -p '{"spec":{"selector":{"env":"green"}}}'

Solution

1. Step 1: Understand traffic switching in Kubernetes

   Traffic is routed by the service selector labels pointing to the correct deployment environment.

2. Step 2: Identify the command that changes service selector to green

   The patch command updates the service selector to point to pods labeled with "env=green".

3. Final Answer:

   kubectl patch service model-service -p '{"spec":{"selector":{"env":"green"}}}' -> Option D

4. Quick Check:

   Change service selector = B [OK]

Hint: Patch service selector to green environment label [OK]

Common Mistakes:

• Restarting deployment does not switch traffic
• Setting image changes deployment but not traffic
• Deleting blue deployment before switch causes downtime

3. Given this simplified deployment script snippet, what will be the output after running it?

current_env = "blue"
new_env = "green"
if current_env == "blue":
    print(f"Switching traffic to {new_env} environment")
else:
    print(f"Switching traffic to {current_env} environment")

medium

A. Switching traffic to green environment

B. Switching traffic to undefined environment

C. Switching traffic to blue environment

D. No output

Solution

1. Step 1: Analyze the condition in the script

   The variable current_env is "blue", so the if condition is true.

2. Step 2: Determine the printed output

   Since current_env is "blue", it prints "Switching traffic to green environment" using new_env.

3. Final Answer:

   Switching traffic to green environment -> Option A

4. Quick Check:

   current_env == "blue" triggers green switch = C [OK]

Hint: Check if current_env is blue, then print green [OK]

Common Mistakes:

• Confusing current_env and new_env variables
• Assuming else branch runs when condition is true
• Ignoring f-string formatting

4. You tried to switch traffic to the green model environment but users still hit the blue model. What is the most likely error?

medium

A. The service selector was not updated to point to the green environment

B. The green model deployment was deleted accidentally

C. The blue environment pods crashed and restarted

D. The model version in green environment is outdated

Solution

1. Step 1: Understand traffic routing in blue-green deployment

   Traffic is controlled by the service selector labels pointing to the active environment.

2. Step 2: Identify why traffic still hits blue

   If users still hit blue, the service selector likely was not updated to green, so traffic stays on blue.

3. Final Answer:

   The service selector was not updated to point to the green environment -> Option A

4. Quick Check:

   Traffic routing depends on service selector = D [OK]

Hint: Check if service selector changed to green environment [OK]

Common Mistakes:

• Assuming green deployment deletion causes traffic to blue
• Confusing pod crashes with traffic routing
• Thinking model version affects routing directly

5. You want to implement blue-green deployment for a machine learning model with minimal downtime. Which sequence of steps is correct?

hard

A. Deploy new model to green, switch traffic immediately, then test and monitor

B. Delete blue environment, deploy new model to green, switch traffic, monitor performance

C. Deploy new model to green environment, test it, switch service selector to green, monitor, then delete blue

D. Deploy new model to blue environment, test it, switch service selector to blue, monitor, then delete green

Solution

1. Step 1: Deploy and test new model in green environment

   Deploying and testing in green ensures the new model works without affecting users.

2. Step 2: Switch traffic to green, monitor, then clean up blue

   Switching traffic only after testing reduces risk. Monitoring ensures stability before deleting blue.

3. Final Answer:

   Deploy new model to green environment, test it, switch service selector to green, monitor, then delete blue -> Option C

4. Quick Check:

   Test before switch, monitor after = A [OK]

Hint: Test green first, then switch traffic, then delete blue [OK]

Common Mistakes:

• Deleting blue before green is ready
• Switching traffic before testing
• Deploying new model to blue environment instead of green