Scale a HTTP Triggered app up and down in Kubernetes using KEDA and Prometheus

This blog post goes into how you can scale up and down your Http Triggered application in Kubernetes based on requests using KEDA and Prometheus.

The application here is an Azure Function app but it can be any app that exposes a Http interface. Where appropriate below I point out where you can use your app instead of an Azure Function app.

Among the major cloud providers, the FaaS implementation in Azure, Azure Functions, is unique that its runtime is open-source. The runtime and your code can therefore be deployed to a custom container or deployed on your own infrastructure including Kubernetes.

To enable scaling of a function app (or any other workload) in Kubernetes we at Azure (along with RedHat) built KEDA, Kubernetes Event Driven Autoscaling. With the combination of aforementioned runtime and KEDA you can run and scale your Azure Functions in your own Kubernetes cluster. Currently in KEDA we support more than twenty different message event sources including Kafka, RabbitMQ, NATS, Azure Queue, AWS SQS Queue, GCP Pub Sub etc. However, there is no support for Http request based scaling. This post outlines one approach on how you can scale a Http Trigerred function app in Kubernetes using the Prometheus KEDA scaled object and an Ingress Controller.

Overview

The basic idea is that we will deploy an Ingress Controller in this case the NGINX Ingress Controller and have all HTTP traffic to your function app go through it. We use Prometheus to track the incoming request metrics on the Ingress Controller. Finally, we use KEDA's Prometheus based scaler to scale up/down the function app deployment.

Walkthrough

Prerequisites

1. A Kubernetes cluster which has the ability to install a Service with a Load Balancer (usually any cloud provider). The steps below were tested using an AKS cluster.
2. kubectl pointing to your Kubernetes cluster
3. Helm to install the artifacts. All of the artifacts below use Helm3
4. Azure Functions core tools
5. docker installed locally and a Docker Hub account.

Steps

1. Create a namespace for your ingress resources
   

   kubectl create namespace ingress-nginx
   

2. Install the NGINX-Ingress ingress controller

   Use Helm to deploy an NGINX ingress controller and enable metrics and set the right annotations for Prometheus. The ingress controller is installed as service with LoadBalancer type. In addition, a backend Service and a metrics Service are also deployed.
   

   helm install ingress-controller stable/nginx-ingress \     
       --namespace ingress-nginx \
       --set controller.replicaCount=2 \
       --set controller.metrics.enabled=true \
       --set controller.podAnnotations."prometheus\.io/scrape"="true" \
       --set controller.podAnnotations."prometheus\.io/port"="10254"
   
   kubectl -n ingress-nginx get svc
   NAME                                                  TYPE           CLUSTER-IP     EXTERNAL-IP     PORT(S)                      AGE
   ingress-controller-nginx-ingress-controller           LoadBalancer   10.0.14.166    40.70.230.xxx   80:31036/TCP,443:32179/TCP   31s
   ingress-controller-nginx-ingress-controller-metrics   ClusterIP      10.0.240.199   <none>          9913/TCP                     31s
   ingress-controller-nginx-ingress-default-backend      ClusterIP      10.0.63.133    <none>          80/TCP                       31s
   

   The ingress controller is exposed via the EXTERNAL-IP 40.70.230.xxx above. Also have a look at the following page for instructions on how to install it for various configurations.
   
   Optionally - Create a DNS entry pointing to your ingress controller. For AKS, you can get a cloudapp.azure.com address using the procedure here. In the steps below the fqdn configured is "function-helloworld.eastus2.cloudapp.azure.com"

3. Deploy Prometheus to monitor the NGINX ingress Controller
   

   kubectl apply --kustomize github.com/kubernetes/ingress-nginx/deploy/prometheus/    
   
   kubectl -n ingress-nginx get svc
   NAME                                                  TYPE           CLUSTER-IP     EXTERNAL-IP     PORT(S)                      AGE
   ...
   prometheus-server                                     NodePort       10.0.38.50     <none>          9090:30860/TCP               34s
   
   kubectl -n ingress-nginx get pods
   NAME                                                              READY   STATUS    RESTARTS   AGE
   ..
   prometheus-server-86cd54f9d5-9xxh7                                1/1     Running   0          95s
   

   Note: If you happen to use any other namespace other than "ingress-nginx" then you need to go and change the namespace in the yaml files from here and then deploy.

4. Deploy KEDA
   

   helm install keda kedacore/keda --namespace ingress-nginx     
   
   kubectl get pods -n ingress-nginx
   NAME                                                              READY   STATUS    RESTARTS   AGE
   ...
   keda-operator-697b98dcdd-8zdrk                                    2/2     Running   0          5d17h
   

5. Deploy a function app to the Kubernetes cluster
   Create a Python Http Trigerred function app, generate the required docker file and finally deploy the function app to the cluster.
   

   func init --worker-runtime python
   func new --template "HttpTrigger" --name helloworld
   func init --docker-only
   func kubernetes deploy --name function-helloworld --namespace ingress-nginx --service-type ClusterIP --registry anirudhgarg
   

   Note that the authentication mode has to be changed to anonymous for now while we are working to support function keys. Navigate to the function app folder and open the function.json file. Find the following line: "authLevel": "function" and change the authLevel to "anonymous"

   --name is the name of your Deployment. --registry points to your DockerHub registry and you have to be logged in to docker and connected to your account locally. See more here

   Note: Instead of using a function app you can deploy your own app that listens to Http requests. Just make sure you create a k8s Cluster IP Service pointing to your deployment.

6. Deploy an Ingress Resource pointing to the deployed function app Service.
   
   This is how the YAML looks like:
   

   apiVersion: extensions/v1beta1
   kind: Ingress
   metadata:
     name: function-helloworld
     namespace: ingress-nginx
     annotations:
       kubernetes.io/ingress.class: nginx
       nginx.ingress.kubernetes.io/rewrite-target: /$2    
   spec:  
     rules:  
       - host: <replace-with-host-name-pointing-to-ingress-controller>
         http:
           paths:                
           - backend:
               serviceName: function-helloworld-http
               servicePort: 80
             path: /helloworld(/|$)(.*)
   

   You can find an example here

   The serviceName attribute is the name of the Service for the function app. host should point to the fqdn configured pointing to the Ingress Controller. You can also choose a random name here but a host has to be configured otherwise Prometheus monitoring of the Ingress Resource will not work. A path has also been configured with prefix "helloworld".

7. Create an Ingress Resource with NGINX Ingress Controller annotations pointing to the Prometheus Service
   
   This is how the YAML looks like:
   

   apiVersion: extensions/v1beta1
   kind: Ingress
   metadata:
     name: prometheus-service
     namespace: ingress-nginx
     annotations:
       kubernetes.io/ingress.class: nginx    
   spec:
     rules:  
       - http:
           paths:
           - backend:
               serviceName: prometheus-server
               servicePort: 9090
             path: /
   

   The serviceName attribute is the name of the Service for the Promtheus Server.
   

   kubectl apply -f "https://raw.githubusercontent.com/anirudhgarg/azurefunction-k8s-http/master/prom-ingress.yml"    
   

8. Deploy the KEDA Prometheus Scaled object which inturn monitors the NGINX Ingress Controller
   

   kubectl apply -f "https://raw.githubusercontent.com/anirudhgarg/azurefunction-k8s-http/master/keda-prom.yml"    
   

   This is how the YAML looks like:
   

   apiVersion: keda.k8s.io/v1alpha1
   kind: ScaledObject
   metadata:
   name: prometheus-scaledobject
   namespace: ingress-nginx
   labels:
       deploymentName: function-helloworld-http
   spec:
   scaleTargetRef:
       deploymentName: function-helloworld-http
   pollingInterval: 15
   cooldownPeriod:  30
   minReplicaCount: 1
   maxReplicaCount: 10
   triggers:
   - type: prometheus
     metadata:
       serverAddress: http://prometheus-server.ingress-nginx.svc.cluster.local:9090
       metricName: access_frequency
       threshold: '1'
       query: sum(rate(nginx_ingress_controller_requests[1m]))
   

   deploymentName is the name of the function app Deployment, the pollingInterval is how frequently in seconds does KEDA poll Prometheus, we have a minimum of 1 pod (minReplicaCount) and the maximum scale out is 10 pods (maxReplicaCount). query is pointing to the prometheus query which tracks the metrics to incoming requests to the ingress controller in the last minute. Since the threshold is '1' the function app will scale as long as the number of requests/minute > 60.

9. Test !
   The function app is now listening on:
   http://function-helloworld.eastus2.cloudapp.azure.com/helloworld/api/helloworld?name=anirudh

Note that if you did not create a domain name pointing to your Ingress Controller then you might need to use curl --resolve or its equivalent to invoke the function app

```
 curl -v function-helloworld.eastus2.cloudapp.azure.com/helloworld/api/helloworld?name=anirudh
* Trying 40.70.230.199...
* TCP_NODELAY set
* Connected to function-helloworld.eastus2.cloudapp.azure.com (40.70.230.199) port 80 (#0)
> GET /helloworld/api/helloworld?name=anirudh HTTP/1.1
> Host: function-helloworld.eastus2.cloudapp.azure.com
> User-Agent: curl/7.55.1
> Accept: */*
>
< HTTP/1.1 200 OK
< Server: openresty/1.15.8.2
< Date: Mon, 13 Jan 2020 01:47:30 GMT
< Content-Type: text/plain; charset=utf-8
< Content-Length: 14
< Connection: keep-alive
<
Hello anirudh!* Connection #0 to host function-helloworld.eastus2.cloudapp.azure.com left intact
```

Now you can use your favorite Http requests tool and send requests at a high enough rate to triger the scale out. (I used a tool called k6)

```
kubectl -n ingress-nginx get pods
NAME                                                              READY   STATUS              RESTARTS   AGE
function-helloworld-http-6ccd9c9bbf-6f6d7                         0/1     ContainerCreating   0          0s
function-helloworld-http-6ccd9c9bbf-98bzq                         1/1     Running             0          15s
function-helloworld-http-6ccd9c9bbf-dcdwc                         0/1     ContainerCreating   0          0s
function-helloworld-http-6ccd9c9bbf-fr7hq                         0/1     ContainerCreating   0          0s
function-helloworld-http-6ccd9c9bbf-k9lhn                         1/1     Running             0          6d20h
function-helloworld-http-6ccd9c9bbf-mfp4c                         1/1     Running             0          15s
function-helloworld-http-6ccd9c9bbf-v7g47                         0/1     ContainerCreating   0          0s
function-helloworld-http-6ccd9c9bbf-x9l2t                         1/1     Running             0          15s
ingress-controller-nginx-ingress-controller-6c9f7486d4-27vjq      1/1     Running             0          7d1h
ingress-controller-nginx-ingress-controller-6c9f7486d4-b8ddr      1/1     Running             0          7d1h
ingress-controller-nginx-ingress-default-backend-df57464f-lvqmj   1/1     Running             0          7d1h
keda-operator-697b98dcdd-8zdrk                                    2/2     Running             0          6d18h
prometheus-server-86cd54f9d5-9xxh7                                1/1     Running             0          7d1h
```

After a while if there are no further requests the function pods will scale back down to 1. Note that we are only scaling down to 1 here.

Hope you found this useful. Please try it out and let me know in the comments or send me a tweet if this approach worked for you or not. We are looking to streamline this process further as we go forward.

Acknowledgments for inspiration - Autoscaling Kubernetes apps with Prometheus and KEDA post by Abhishek Gupta, and to OpenFaaS which also uses Prometheus metrics for request based scaling.