Canary Promotion

Launch a serverless SKLearn model and update via canary

In this demo you will:

  • Deploy a sklearn KfServing Iris Classifer
  • Run a load test to show knative autoscaling
  • Create a canary XGBoost model
  • Promote the Canary
  • Delete the model

From the Deploy UI create a server:

iris-create

Use the model url:

gs://kfserving-samples/models/sklearn/iris

Run a Load Test

When the deployment is ready click on it and “Start a Load Test”.

iris-load

Set the duration to 60 secs and the number of connections to 10.

Use the request.json file in this folder:

{
  "instances": [
    [6.8,  2.8,  4.8,  1.4],
    [6.0,  3.4,  4.5,  1.6]
  ]
}

You should see pod counts scale up and then down, something like:

iris-load2

Adding a Canary

Now follow the “Add Canary” wizard and add an XGBoost canary:

canary

Use the XGBoost Iris model whose saved Booster is stored at:

gs://kfserving-samples/models/xgboost/iris

One the canary is running you can rerun the load test and see traffic split between both.

canary-load

To promote canary press the “Promote Canary” button

promote

Delete the Deployment

Finally, you can delete the model.

delete

Last modified September 5, 2020: Update Demos section (91a072d)