Canary releases for model updates in MLOps - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a canary release in the context of model updates?

A canary release is a method where a new model version is gradually rolled out to a small subset of users or traffic before full deployment. This helps detect issues early without affecting all users.

beginner

Why use canary releases for updating machine learning models?

Canary releases reduce risk by testing new models on limited traffic, allowing teams to monitor performance and catch errors before full rollout.

intermediate

Name two key metrics to monitor during a canary release of a model.

Accuracy and latency are important metrics to monitor. Accuracy ensures the model predictions are correct, and latency checks if the model responds quickly enough.

intermediate

How does traffic routing work in a canary release?

Traffic routing directs a small percentage of user requests to the new model version while the rest go to the stable version. This split can be controlled by load balancers or service mesh tools.

beginner

What should you do if the canary model shows poor performance?

If the canary model performs poorly, you should stop the rollout, roll back to the stable model, and investigate the issues before trying again.

What is the main goal of a canary release for model updates?

A Train the model faster

B Deploy new model to all users immediately

C Remove old model without testing

D Test new model on a small user group before full deployment

Canary releases aim to test new models on a small subset of users to catch issues early.

Which tool can help route traffic during a canary release?

A Text editor

B Load balancer

C Database

D Version control system

Load balancers can split traffic between model versions during canary releases.

If the canary model has higher latency, what should you do?

A Stop rollout and investigate

B Increase traffic to canary model

C Ignore latency metrics

D Continue rollout without changes

Higher latency can hurt user experience, so stop rollout and fix issues first.

Which metric is NOT typically monitored during a canary release?

A User interface color

B Model accuracy

C Response latency

D Error rate

User interface color is unrelated to model performance monitoring.

What happens if a canary release is successful?

A Old model is kept without changes

B New model is deleted

C New model is rolled out to all users

D Traffic is stopped

A successful canary release leads to full deployment of the new model.

Explain the process and benefits of using canary releases for machine learning model updates.

Think about how you would safely test a new model version with real users.

Describe how traffic routing is managed during a canary release and why it is important.

Consider how you send some users to the new model while others use the old one.

Practice

1. What is the main purpose of a canary release when updating machine learning models?

easy

A. To train the model faster using more data

B. To immediately replace the old model with the new one for all users

C. To test the new model on a small group of users before full deployment

D. To reduce the size of the model for faster inference

Solution

1. Step 1: Understand canary release concept

   Canary releases deploy a new model to a small subset of users first to test its performance safely.

2. Step 2: Compare options

   Only To test the new model on a small group of users before full deployment describes testing on a small group before full rollout, which is the main purpose.

3. Final Answer:

   To test the new model on a small group of users before full deployment -> Option C

4. Quick Check:

   Canary release = small group test [OK]

Hint: Canary means small test group before full rollout [OK]

Common Mistakes:

• Thinking canary releases replace models immediately
• Confusing canary with model training speed
• Assuming canary reduces model size

2. Which of the following is the correct way to specify 10% traffic to a new model version in a deployment configuration?

easy

A. "traffic_split": {"new_model": 10, "old_model": 90}

B. "traffic_split": {"new_model": 0.1, "old_model": 0.9}

C. "traffic_split": {"new_model": "10%", "old_model": "90%"}

D. "traffic_split": {"new_model": 1, "old_model": 9}

Solution

1. Step 1: Understand traffic split format

   Traffic splits are usually specified as fractions summing to 1.0, representing percentages as decimals.

2. Step 2: Evaluate options

   "traffic_split": {"new_model": 0.1, "old_model": 0.9} uses decimal fractions (0.1 and 0.9) correctly. "traffic_split": {"new_model": 10, "old_model": 90} uses integers but not fractions. "traffic_split": {"new_model": "10%", "old_model": "90%"} uses strings with percent signs, which is invalid syntax. "traffic_split": {"new_model": 1, "old_model": 9} sums to 10, not 1.

3. Final Answer:

   "traffic_split": {"new_model": 0.1, "old_model": 0.9} -> Option B

4. Quick Check:

   Traffic split decimals sum to 1 [OK]

Hint: Use decimals summing to 1 for traffic percentages [OK]

Common Mistakes:

• Using integers instead of decimals for traffic split
• Including percent signs in values
• Traffic splits not summing to 1

3. Given this simplified code snippet for routing traffic in a canary release:

def route_request(user_id):
    if user_id % 10 == 0:
        return "new_model"
    else:
        return "old_model"

print(route_request(20))
print(route_request(23))

What will be the output?

medium

A. new_model\nold_model

B. old_model\nnew_model

C. new_model\nnew_model

D. old_model\nold_model

Solution

1. Step 1: Analyze routing logic

   The function sends users with user_id divisible by 10 to the new model, others to old model.

2. Step 2: Evaluate given user_ids

   For user_id 20: 20 % 10 == 0, so returns "new_model". For user_id 23: 23 % 10 == 3, so returns "old_model".

3. Final Answer:

   new_model old_model -> Option A

4. Quick Check:

   Divisible by 10 = new_model [OK]

Hint: Check modulo condition for routing [OK]

Common Mistakes:

• Misunderstanding modulo operator
• Swapping outputs for user IDs
• Assuming all users get new model

4. You deployed a canary release but noticed the new model is receiving 100% of traffic instead of 10%. Which fix will correct this issue?

medium

A. Change traffic split from {"new_model": 1, "old_model": 0} to {"new_model": 0.1, "old_model": 0.9}

B. Increase the new model traffic to 50% to balance load

C. Restart the deployment without changing traffic split

D. Remove the old model from deployment

Solution

1. Step 1: Identify traffic split error

   Current split {"new_model": 1, "old_model": 0} sends all traffic to new model, causing 100% traffic.

2. Step 2: Correct traffic split values

   Setting split to {"new_model": 0.1, "old_model": 0.9} correctly routes 10% traffic to new model and 90% to old model.

3. Final Answer:

   Change traffic split from {"new_model": 1, "old_model": 0} to {"new_model": 0.1, "old_model": 0.9} -> Option A

4. Quick Check:

   Traffic split controls user percentage [OK]

Hint: Check traffic split decimals sum to 1 [OK]

Common Mistakes:

• Restarting without fixing traffic split
• Increasing new model traffic without reason
• Removing old model prematurely

5. You want to safely update a model with a canary release. The new model shows better accuracy but higher latency. What is the best approach to decide whether to proceed with full rollout?

hard

A. Deploy new model only to internal users without monitoring

B. Ignore latency since accuracy is more important; rollout immediately

C. Increase traffic to new model to 100% to gather more data quickly

D. Monitor both accuracy and latency metrics during canary; rollback if latency impact is unacceptable

Solution

1. Step 1: Understand trade-offs in canary release

   Canary releases test new model performance including accuracy and latency to ensure overall user experience.

2. Step 2: Choose monitoring and rollback strategy

   Monitoring both metrics allows informed decision; rollback if latency harms user experience despite accuracy gains.

3. Final Answer:

   Monitor both accuracy and latency metrics during canary; rollback if latency impact is unacceptable -> Option D

4. Quick Check:

   Balance metrics and rollback if needed [OK]

Hint: Watch all key metrics before full rollout [OK]

Common Mistakes:

• Ignoring latency impact
• Rushing full rollout without monitoring
• Skipping rollback plans