DEV Community

Carlo Columna
Carlo Columna

Posted on • Edited on

KEDA in Amazon EKS Part 2: Scale Based On AWS SQS Queue

#kubernetes #aws #keda #autoscaling

Kia ora everyone!

Welcome to the second part of a series of articles discussing the use of KEDA (Kubernetes Event-driven Autoscaling) for the autoscaling of Amazon EKS workloads. If you haven't, check out the first part below to learn why and how to install KEDA in Amazon EKS.

KEDA in Amazon EKS Part 1: Why and How to Install KEDA

This part two of this blog series focuses on scaling based on AWS SQS Queue.

Meme when the queue jumps and there's only one pod

The structure of this blog would be as follows:

  1. Prerequisites
  2. Create a demo application
  3. Scale based on two identity owner models: Here we'll go deeper in explaining the two models which are not extensively covered in the KEDA documentation.
  4. Common errors

Prerequisites

Before we can proceed, let's lay out the prerequisites:

  • AWS account
  • Access to an Amazon EKS cluster
  • IAM roles for service accounts (IRSA) setup for the EKS cluster. See here for more details.
  • KEDA installed in the EKS cluster, see part 1
  • Terminal with kubectl

Create a demo application

We'll use a demo application and set it up across different accounts to best illustrate the steps we'll go through. We will be using Terraform and Helm to deploy it.

Our demo application has the following requirements:

  • It is a simple NGINX application deployed in an EKS cluster in Account A in Oregon.
  • It has an IAM Role created in Account C in Canada Central. KEDA is deployed and running on the same EKS cluster using an IAM Role created in Account B in N. Virginia.
  • It scales based on a queue in Account C in Canada Central.

To better understand the scenario, the following is the architecture diagram for KEDA and our demo application.

KEDA and Demo Application Architecture
KEDA and Demo Application Architecture

Before we can install our demo application, we'll start by creating an IAM Role for it using Terraform, like so,



resource "aws_iam_role" "demo-app" {
  provider           = aws.account_c
  name               = "demo-app"
  assume_role_policy = module.demo-app-trust-policy.json
}
Enter fullscreen mode Exit fullscreen mode

For now, we are creating a role with no permissions. Later on, we'll update the role by granting it permission to access AWS resources.

We also set up the role's trust policy so our demo application can assume the role.



resource "aws_iam_role" "demo-app" { ... }

data "aws_iam_policy_document" "demo-app-trust-policy" {
  statement {
    actions = [
      "sts:AssumeRoleWithWebIdentity"
    ]
    principals {
      type = "Federated"
      identifiers = ["arn:aws:iam::111122223333:oidc-provider/oidc.eks.region-code.amazonaws.com/id/EXAMPLED539D4633E53DE1B71EXAMPLE"]
    }
    condition {
      test     = "StringEquals"
      variable = "oidc.eks.region-code.amazonaws.com/id/EXAMPLED539D4633E53DE1B71EXAMPLE:sub"
      values   = ["system:serviceaccount:demo-ns:demo-app"]
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

Now, let's create the Helm manifest of our basic deployment using the NGINX image.



---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: demo-app
  name: demo-app
  namespace: demo-ns
spec:
  replicas: 1
  selector:
    matchLabels:
      app: demo-app
  template:
    metadata:
      labels:
        app: demo-app
    spec:
      serviceAccountName: demo-app-sa
      containers:
      - image: nginx
        name: nginx
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: demo-app-sa
  namespace: demo-ns
  annotations:
    eks.amazonaws.com/role-arn: arn:aws:iam::111122223333:role/demo-app # demo-app IAM role ARN created from the previous step
Enter fullscreen mode Exit fullscreen mode

This creates a deployment with a ServiceAccount. If you noticed, we have added the IAM role we created above as an annotation so our application can access AWS resources. Let's save this file as demo-app.yaml.

To deploy, ideally, you package this manifest into a Helm chart or use kustomize. But to keep things short and simple in this blog, let's simply run a kubectl apply -f demo-app.yaml.

Scaling with KEDA

We've come to the more exciting part of this blog, setting up and testing the scaling using AWS SQS Queue. Before we can start, there is one important security consideration we have to make.

There are two ways that KEDA can get permission to access the SQS Queue and scale a workload. This is determined by setting the identityOwner to either pod which is the default, or operator.

  • pod: This sets the keda-operator to temporarily assume the role of the demo application. This means that the demo application role should have the necessary permissions to access the SQS Queue. We'll call this the Pod Identity Owner model.
  • operator : Grant the keda-operator direct access to the AWS SQS queue. We'll call this the Operator Identity Owner model.

Note that in this blog, when talking about permissions and IAM, the KEDAs role is the same as the keda-operators IAM role.

What model should you use?

This depends on what works best in your setup. Let's summarise the pros and cons of each model.

Pod Identity Owner model

  • Good, because we don't have to know beforehand what privileges we need to give KEDA as long as our application has already access to the event source.
  • Good, in cases where KEDA cannot be given direct access to the event source
  • Bad, because KEDA gets all the permission of all workload that uses this permission model. This probably includes permissions that are not required for scaling purposes (such as write privilege) and thus breaking the principle of least privilege.
  • Bad, because it requires a bit more complicated setup

Operator Identity Owner model

  • Good, because KEDA only gets the permission it needs to trigger scaling so it follows the principle of least privilege
  • Good, because it's a simpler setup
  • Bad, because it requires more initial understanding what are the privileges that we need to grant KEDA to access an events source
  • Bad, in cases where the event source cannot be updated or set to be accessed by KEDA (e.g. if access policy cannot be set to the event source)

From a security and simplicity perspective, the Operator Identity Owner model is a better option. This is more so if you have an application that has access to sensitive information that you don't want keda-operator to get access to. However, there might be cases where you are restricted to using the Pod Identity Owner model. In these cases, you just have to be aware that the keda-operator gets all the permissions of the application role.

In this blog, we'll show how to scale each identity owner model starting with the default identityOwner: pod.

Pod Identity Owner Model

For this model to work it's important to understand the requirements:

  • We need to add an AssumeRole policy to the demo application roles trust policy to allow keda-operator to assume it
  • The demo application role has the permission to access the queue
  • We need to add an AssumeRole policy to the keda-operator role so it knows what role to assume

Going back to our demo applications architecture and incorporating the use of the Pod Identity Owner model, the architecture will look like below.

KEDA and Demo Application: Pod Identity Owner Model
KEDA and Demo Application: Pod Identity Owner Model

In this model, the demo application through its IAM role has access to the AWS SQS Queue. Meanwhile, KEDA can temporarily assume the demo applications role to get access to the same AWS SQS Queue to trigger scaling.

Here is the summary of the steps we'll go through.

  1. Create AWS SQS Queue
  2. Update the IAM Role of the demo application
  3. Update the IAM Role of KEDA
  4. Create scaler
  5. Test scaling

Steps

1. Create AWS SQS Queue

Using Terraform we can simply create a queue like so,



resource "aws_sqs_queue" "aws_sqs" {
  provider = aws.account_c
  name     = "demo-app-sqs"
}

output "demo_app_sqs_url" {
  value = aws_sqs_queue.aws_sqs.url
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

2. Update the IAM Role of the demo application

Now, let's update the role of our demo application by doing two things:

  • Grant our demo application permission to access the queue
  • Add a policy to allow KEDA to assume it

For the first one, let's add permission to access the queue created in the previous step like so,



resource "aws_iam_role" "demo-app" { ... }
data "aws_iam_policy_document" "demo-app-trust-policy" { ... }
data "aws_iam_policy_document" "sqs-policy-document" {
  statement {
    sid    = "SQS"
    effect = "Allow"
    actions = [
      "sqs:GetQueueAttributes", #Add IAM action to the demo-app role
    ]
    resources = [
      aws_sqs_queue.aws_sqs.arn,
    ]
  }
}
resource "aws_iam_role_policy" "sqs-policy" {
  depends_on = [
    aws_sqs_queue.aws_sqs
  ]
  provider = aws.account_c
  name     = "demo-app-sqs-policy"
  role     = aws_iam_role.demo-app.id
  policy   = data.aws_iam_policy_document.sqs-policy-document.json
}
Enter fullscreen mode Exit fullscreen mode

For the second one, let's add an sts:AssumeRole policy to our demo applications trust policy passing in the keda-operators role like so,



resource "aws_iam_role" "demo-app" { ... }

data "aws_iam_policy_document" "demo-app-trust-policy" {

  statement {
    sid    = "AssumeRoleKedaOperator"
    effect = "Allow"
    actions = [
      "sts:AssumeRole",
    ]
    principals {
      type        = "AWS"
      identifiers = var.keda_operator_role # "arn:aws:iam::111122223333:role/keda-operator"
    }
  }

  statement {
    actions = [
      "sts:AssumeRoleWithWebIdentity"
    ]
    principals {
      type = "Federated"
      identifiers = ["arn:aws:iam::111122223333:oidc-provider/oidc.eks.region-code.amazonaws.com/id/EXAMPLED539D4633E53DE1B71EXAMPLE"]
    }
    condition {
      test     = "StringEquals"
      variable = "oidc.eks.region-code.amazonaws.com/id/EXAMPLED539D4633E53DE1B71EXAMPLE:sub"
      values   = ["system:serviceaccount:demo-ns:demo-app"]
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

3. Update the IAM Role of KEDA

Let's update the role of keda-operator so it knows what role to assume by adding an sts:AssumeRole policy passing in our demo application's role.



resource "aws_iam_role" "keda-operator" { ... }

data "aws_iam_policy_document" "keda-operator-trust-policy" { ... }

data "aws_iam_policy_document" "assume-role-policy-document" {
  statement {
    sid    = "sts"
    effect = "Allow"
    actions = [
      "sts:AssumeRole",
    ]
    resources = var.application_roles_list # ["arn:aws:iam::111122223333:role/demo-app"]
  }
}

resource "aws_iam_role_policy" "assume-role-policy" {
  provider = aws.account_b
  count    = length(var.application_roles_list) == 0 ? 0 : 1 # This is needed otherwise Terraform will fail to create this resource when the role list is empty
  name     = "keda-operator-assume-role-policy"
  role     = aws_iam_role.keda-operator.id
  policy   = data.aws_iam_policy_document.assume-role-policy-document.json
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

4. Create scaler

Okay now, let's shift from AWS stuff to KEDA stuff. Let's start by creating the scaler.

KEDA scalers can both detect if a deployment should be activated or deactivated, and feed custom metrics for a specific event source.

To create a scaler, we have to define a ScaledObject custom resource.

The ScaledObject Custom Resource definition is used to define how KEDA should scale your application and what the triggers are.

The ScaledObject resource specifications are defined here. As part of the specification, we also have to define a trigger, which in our case is an AWS SQS Queue. The specification for AWS SQS Queue can be found here.

Following these specifications, our scaler configuration would be,



---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: demo-app-scaledobject
  namespace: demo-ns
spec:
  minReplicaCount: 0  # scale down to 0
  maxReplicaCount: 10 
  pollingInterval: 30 
  scaleTargetRef:
    name: demo-app    # name of our demo-app deployment
  triggers:
  - type: aws-sqs-queue
    authenticationRef:
      name: demo-app-trigger-auth-aws-credentials  # trigger auth object name
    metadata:
      queueURL: https://sqs.ca-central-1.amazonaws.com/111122223333/demo-app-sqs
      queueLength: "2" # 2 messages per pod 
      awsRegion: ca-central-1
      identityOwner: pod # defaults to pod if unset
---
apiVersion: keda.sh/v1alpha1
kind: TriggerAuthentication
metadata:
  name: demo-app-trigger-auth-aws-credentials
  namespace: demo-ns
spec:
  podIdentity:
    provider: aws-eks # or aws-kiam when using kiam
Enter fullscreen mode Exit fullscreen mode

Add this configuration to our manifest file, demo-app.yaml. We then deploy these resources on the same namespace as our demo application simply by running kubectl apply -f demo-app.yaml.

Describing our ScaledObject by running kubectl describe ScaledObject demo-app-scaledobject -n demo-ns shows it's active and happy.



Status:
  Conditions:
    Message:  ScaledObject is defined correctly and is ready for scaling
    Reason:   ScaledObjectReady
    Status:   True
    Type:     Ready
    Message:  Scaling is not performed because triggers are not active
    Reason:   ScalerNotActive
    Status:   False
    Type:     Active
    Message:  No fallbacks are active on this scaled object
    Reason:   NoFallbackFound
    Status:   False
    Type:     Fallback
  External Metric Names:
    s0-aws-sqs-demo-app
  Health:
    s0-aws-sqs-demo-app:
      Number Of Failures:  0
      Status:              Happy
  Hpa Name:                keda-hpa-demo-app
  Last Active Time:        2023-02-16T20:18:48Z
  Original Replica Count:  1
  Scale Target GVKR:
    Group:            apps
    Kind:             Deployment
    Resource:         deployments
    Version:          v1
  Scale Target Kind:  apps/v1.Deployment
Events:               <none>
Enter fullscreen mode Exit fullscreen mode

Let's check the logs of our KEDA deployments to see what they say,

keda-operator log:



INFO Reconciling ScaledObject {"controller": "scaledobject", "controllerGroup": "keda.sh", "controllerKind": "ScaledObject", "scaledObject": {"name":"demo-app-scaledobject","namespace":"demo-ns"}, "namespace": "demo-ns", "name": "demo-app", "reconcileID": "e40b3625-6794-4358-b285-a9a57194edee"}
Enter fullscreen mode Exit fullscreen mode

keda-operator-metrics-apiserver log:



1 trace.go:205] Trace[87882572]: "List" url:/apis/external.metrics.k8s.io/v1beta1/namespaces/demo-ns/s0-aws-sqs-demo-app,user-agent:kube-controller-manager/v1.22.16 (linux/amd64) kubernetes/52e500d/system:serviceaccount:kube-system:horizontal-pod-autoscaler,audit-id:1570ee53-ba50-4de8-81c7-727482dca392,client:172.16.113.69,accept:application/vnd.kubernetes.protobuf, */*,protocol:HTTP/2.0 (20-Feb-2023 05:04:01.958) (total time: 986ms):
Enter fullscreen mode Exit fullscreen mode

Both KEDA deployments acknowledge and reconciles with the new ScaledObject we created.

The keda-operator has also created an HPA for our demo application.



$ kubectl get hpa -n demo-ns
NAME                REFERENCE             TARGETS             MINPODS   MAXPODS   REPLICAS   AGE
keda-hpa-demo-app   Deployment/demo-app   <unknown>/1 (avg)   1         10        0          5s
Enter fullscreen mode Exit fullscreen mode

From now on, this HPA will be managed keda-operator to set the number of replicas based on the metrics provided by the keda-operator-metrics-apiserver.

5. Test scaling

To trigger scaling, let's send some messages to our queue using AWS Console. Let's send 4 messages to target 2 replicas.

Sending messages to the queue

Going back to the cluster, let's check the events from our ScaledObject and HPA.

keda-hpa-demo-app events:



Conditions:
  Type            Status  Reason              Message
  ----            ------  ------              -------
  AbleToScale     True    SucceededRescale    the HPA controller was able to update the target scale to 2
  ScalingActive   True    ValidMetricFound    the HPA was able to successfully calculate a replica count from external metric s0-aws-sqs-demo-app(&LabelSelector{MatchLabels:map[string]string{scaledobject.keda.sh/name: demo-app,},MatchExpressions:[]LabelSelectorRequirement{},})
  ScalingLimited  False   DesiredWithinRange  the desired count is within the acceptable range
Events:
  Type    Reason             Age               From                       Message
  ----    ------             ----              ----                       -------
  Normal  SuccessfulRescale  10s (x2 over 4d)  horizontal-pod-autoscaler  New size: 2; reason: external metric s0-aws-sqs-demo-app(&LabelSelector{MatchLabels:map[string]string{scaledobject.keda.sh/name: demo-app,},MatchExpressions:[]LabelSelectorRequirement{},}) above target
Enter fullscreen mode Exit fullscreen mode

demo-app-scaledobject events:



Events:
  Type    Reason                    Age               From           Message
  ----    ------                    ----              ----           -------
  Normal  KEDAScaleTargetActivated  10s (x3 over 4d)  keda-operator  Scaled apps/v1.Deployment demo-ns/demo-app from 0 to 2
Enter fullscreen mode Exit fullscreen mode

Putting a watch on the demo-ns shows the new pods that get created as a result of the scaling,



$ kubectl get pods -n demo-ns -w
NAME                           READY   STATUS              RESTARTS   AGE
demo-app-674d8c455c-n7svp      0/1     Pending             0          0s
demo-app-674d8c455c-n7svp      0/1     Pending             0          0s
demo-app-674d8c455c-n7svp      0/1     ContainerCreating   0          0s
demo-app-674d8c455c-n7svp      1/1     Running             0          3s
demo-app-674d8c455c-64jvw      0/1     Pending             0          0s
demo-app-674d8c455c-64jvw      0/1     Pending             0          0s
demo-app-674d8c455c-64jvw      0/1     ContainerCreating   0          0s
demo-app-674d8c455c-64jvw      1/1     Running             0          2s
Enter fullscreen mode Exit fullscreen mode

Let's trigger descaling by deleting the messages in the queue. Poll for messages, select all and delete them.

Deleting the messages in the queue pod model

Getting the events from the demo-ns shows:



$ kubectl get events -n demo-ns
LAST SEEN   TYPE     REASON                       OBJECT                                             MESSAGE
4m2s        Normal   Killing                      pod/demo-app-674d8c455c-64jvw    Stopping container demo-app
4m2s        Normal   Killing                      pod/demo-app-674d8c455c-n7svp    Stopping container demo-app
4m2s        Normal   SuccessfulDelete             replicaset/demo-app-674d8c455c   Deleted pod: demo-app-674d8c455c-n7svp
4m2s        Normal   SuccessfulDelete             replicaset/demo-app-674d8c455c   Deleted pod: demo-app-674d8c455c-64jvw
4m3s        Normal   ScalingReplicaSet            deployment/demo-app              Scaled down replica set demo-app-674d8c455c to 0
4m3s        Normal   KEDAScaleTargetDeactivated   scaledobject/demo-app            Deactivated apps/v1.Deployment demo-ns/demo-app from 2 to 0
Enter fullscreen mode Exit fullscreen mode

Getting the pods shows they are now in terminating state,



$ kubectl get pods -n demo-ns -w
NAME                           READY   STATUS        RESTARTS   AGE
demo-app-674d8c455c-n7svp      1/1     Terminating   0          90m
demo-app-674d8c455c-64jvw      1/1     Terminating   0          90m
demo-app-674d8c455c-n7svp      0/1     Terminating   0          90m
demo-app-674d8c455c-n7svp      0/1     Terminating   0          90m
demo-app-674d8c455c-n7svp      0/1     Terminating   0          90m
demo-app-674d8c455c-64jvw      0/1     Terminating   0          90m
demo-app-674d8c455c-64jvw      0/1     Terminating   0          90m
demo-app-674d8c455c-64jvw      0/1     Terminating   0          90m
Enter fullscreen mode Exit fullscreen mode

Awesome! Great work! You made it this far.

That's how easy to scale based on a queue using KEDA. Next, we'll look at using the operator identity model which I personally recommend.

Operator Identity Owner Model

When identityOwner set to operator - the only requirement is that the KEDA operator has the correct IAM permissions on the SQS queue. Additional Authentication Parameters are not required.

Going back to our demo applications architecture and incorporating the use of the Operator Identity Owner model, the architecture will look like below.

KEDA and Demo Application: Operator Identity Owner Model
KEDA and Demo Application: Operator Identity Owner Model

Let's create a new set of resources to differentiate from the resources we created in the previous section. Here is the summary of the steps we'll go through.

  1. Create AWS SQS Queue with access policy
  2. Grant KEDA permissions to the AWS SQS Queue
  3. Create second demo application
  4. Create scaler
  5. Test scaling

Steps

1. Create AWS SQS Queue with access policy

The first step we have to do is create a queue. Using Terraform we can create it like so,



resource "aws_sqs_queue" "aws_sqs_operator" {
  provider = aws.account_c
  name     = "demo-app-sqs-operator"
}
Enter fullscreen mode Exit fullscreen mode

An access policy is needed to explicitly allow KEDA to access certain SQS API actions. This is needed when doing cross-account access. To create the access policy we need the IAM permission to read a queue, in this case, it's SQS:GetQueueAttributes, it's the only permission we need. We also need to pass the KEDA IAM role created in Part 1: Why and How to Install KEDA.



data "aws_iam_policy_document" "sqs_access_policy_data_operator" {
  statement {
    actions   = ["SQS:GetQueueAttributes"]
    resources = [ aws_sqs_queue.aws_sqs_operator.arn ]
    effect    = "Allow"
    principals {
      type        = "AWS"
      identifiers = var.keda_operator_role # "arn:aws:iam::111122223333:role/keda-operator"
    }
  }
}
resource "aws_sqs_queue_policy" "sqs_access_policy_operator" {
  provider = aws.account_c
  depends_on = [
    aws_sqs_queue.aws_sqs_operator
  ]
  queue_url = aws_sqs_queue.aws_sqs_operator.url
  policy    = data.aws_iam_policy_document.sqs_access_policy_data_operator.json
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

2. Grant KEDA access to the AWS SQS Queue

For this step, we'll have to update our KEDA installation. We need to grant KEDA or in particular the keda-operator direct permission to the queue we created. We do this by adding the same policy we added on the queue access policy to the keda-operator role.



resource "aws_iam_role" "keda-operator" { ... }
data "aws_iam_policy_document" "keda-operator-trust-policy" { ... }
output "keda_operator_role_arn" { ... }
resource "aws_iam_role_policy" "sqs-policy" {
  name     = "sqs-queue-policy"
  role     = aws_iam_role.keda-operator.id
  policy   = data.aws_iam_policy_document.sqs-policy-document.json
}
data "aws_iam_policy_document" "sqs-policy-document" {
  statement {
    sid    = "SQS"
    effect = "Allow"
    actions = [
      "sqs:GetQueueAttributes",
    ]
    resources = [ "arn:aws:sqs:region-code:111122223333:demo-app-sqs-operator" ] # queue arn
  }
}
Enter fullscreen mode Exit fullscreen mode

Run terraform apply.

3. Create second demo application

Let's deploy a second demo application so we can keep the first one and we can test both as much as we like. We would have to also create an IAM role for it. Scroll to the top to see the Terraform on how to create one.

Our second demo application will now look as follows:



---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: demo-app-operator
  name: demo-app-operator
  namespace: demo-ns
spec:
  replicas: 1
  selector:
    matchLabels:
      app: demo-app-operator
  template:
    metadata:
      labels:
        app: demo-app-operator
    spec:
      serviceAccountName: demo-app-operator-sa
      containers:
      - image: nginx
        name: nginx
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: demo-app-operator-sa
  namespace: demo-ns
  annotations:
    eks.amazonaws.com/role-arn: arn:aws:iam::111122223333:role/demo-app-operator
Enter fullscreen mode Exit fullscreen mode

Let's save this file as demo-app-operator.yaml. Let's deploy our second demo application to the same namespace using kubectl.

4. Create scaler

Let's now create our scaler specifications. This time it will be simpler because we don't need the TriggerAuthentication resource anymore.



apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: demo-app-scaledobject-operator
  namespace: demo-ns
spec:
  minReplicaCount: 0  # scale down to 0
  maxReplicaCount: 10 
  pollingInterval: 30 
  scaleTargetRef:
    name: demo-app-operator    # name of our demo-app deployment
  triggers:
  - type: aws-sqs-queue
    metadata:
      queueURL: https://sqs.ca-central-1.amazonaws.com/111122223333/demo-app-sqs-operator
      queueLength: "2" # 2 messages per pod 
      awsRegion: ca-central-1
      identityOwner: operator # defaults to pod if unset
Enter fullscreen mode Exit fullscreen mode

Add this configuration to our manifest file, demo-app-operator.yaml. Let's deploy our ScaledObject and check if it's happy.



Status:
  Conditions:
    Message:  ScaledObject is defined correctly and is ready for scaling
    Reason:   ScaledObjectReady
    Status:   True
    Type:     Ready
    Message:  Scaling is not performed because triggers are not active
    Reason:   ScalerNotActive
    Status:   False
    Type:     Active
    Message:  No fallbacks are active on this scaled object
    Reason:   NoFallbackFound
    Status:   False
    Type:     Fallback
  External Metric Names:
    s0-aws-sqs-demo-app-operator
  Health:
    s0-aws-sqs-demo-app-operator:
      Number Of Failures:  0
      Status:              Happy
  Hpa Name:                keda-hpa-demo-app-operator
  Last Active Time:        2023-02-16T21:44:24Z
  Original Replica Count:  1
  Scale Target GVKR:
    Group:            apps
    Kind:             Deployment
    Resource:         deployments
    Version:          v1
  Scale Target Kind:  apps/v1.Deployment
Events:               <none>
Enter fullscreen mode Exit fullscreen mode

Check also the logs of both KEDA deployments if they have reconciled with the new ScaledObject we created.
The keda-operator has also created an HPA for our second demo application.



$ kubectl get hpa -n demo-ns
NAME                         REFERENCE                                    TARGETS             MINPODS   MAXPODS   REPLICAS   AGE
keda-hpa-demo-app-operator   Deployment/demo-app-operator   <unknown>/1 (avg)   1         10        0          4d16h
keda-hpa-demo-app            Deployment/demo-app        <unknown>/2 (avg)   1         10        0          4d16h
Enter fullscreen mode Exit fullscreen mode

Awesome! It's time to trigger scaling!

5. Test scaling

Let's send messages to our queue.

send messages to our queue

In the cluster, let's get the latest events from our demo-ns.



$ kubectl get events -n demo-ns
LAST SEEN   TYPE     REASON                     OBJECT                                                             MESSAGE
5m31s       Normal   SuccessfulRescale          horizontalpodautoscaler/keda-hpa-demo-app-operator   New size: 3; reason: external metric s0-aws-sqs-demo-app-operator(&LabelSelector{MatchLabels:map[string]string{scaledobject.keda.sh/name: demo-app-operator,},MatchExpressions:[]LabelSelectorRequirement{},}) above target
5m31s       Normal   Scheduled                  pod/demo-app-operator-7cff88c99b-5ddjv               Successfully assigned demo-ns/demo-app-operator-7cff88c99b-5ddjv to ip-11-111-111-111.us-west-2.compute.internal
5m29s       Normal   Pulled                     pod/demo-app-operator-7cff88c99b-5ddjv               Container image "nginx:latest" already present on machine
5m29s       Normal   Created                    pod/demo-app-operator-7cff88c99b-5ddjv               Created container demo-app-operator
5m29s       Normal   Started                    pod/demo-app-operator-7cff88c99b-5ddjv               Started container demo-app-operator
5m36s       Normal   Scheduled                  pod/demo-app-operator-7cff88c99b-gwz46               Successfully assigned demo-ns/demo-app-operator-7cff88c99b-gwz46 to ip-11-111-111-111.us-west-2.compute.internal
5m34s       Normal   Pulled                     pod/demo-app-operator-7cff88c99b-gwz46               Container image "nginx:latest" already present on machine
5m34s       Normal   Created                    pod/demo-app-operator-7cff88c99b-gwz46               Created container demo-app-operator
5m34s       Normal   Started                    pod/demo-app-operator-7cff88c99b-gwz46               Started container demo-app-operator
5m31s       Normal   Scheduled                  pod/demo-app-operator-7cff88c99b-xn7c8               Successfully assigned demo-ns/demo-app-operator-7cff88c99b-xn7c8 to ip-11-111-111-111.us-west-2.compute.internal
5m29s       Normal   Pulled                     pod/demo-app-operator-7cff88c99b-xn7c8               Container image "nginx:latest" already present on machine
5m29s       Normal   Created                    pod/demo-app-operator-7cff88c99b-xn7c8               Created container demo-app-operator
5m29s       Normal   Started                    pod/demo-app-operator-7cff88c99b-xn7c8               Started container demo-app-operator
5m36s       Normal   SuccessfulCreate           replicaset/demo-app-operator-7cff88c99b              Created pod: demo-app-operator-7cff88c99b-gwz46
5m31s       Normal   SuccessfulCreate           replicaset/demo-app-operator-7cff88c99b              Created pod: demo-app-operator-7cff88c99b-xn7c8
5m31s       Normal   SuccessfulCreate           replicaset/demo-app-operator-7cff88c99b              Created pod: demo-app-operator-7cff88c99b-5ddjv
5m36s       Normal   ScalingReplicaSet          deployment/demo-app-operator                         Scaled up replica set demo-app-operator-7cff88c99b to 1
5m36s       Normal   KEDAScaleTargetActivated   scaledobject/demo-app-operator                       Scaled apps/v1.Deployment demo-ns/demo-app-operator from 0 to 1
5m31s       Normal   ScalingReplicaSet          deployment/demo-app-operator                         Scaled up replica set demo-app-operator-7cff88c99b to 3
Enter fullscreen mode Exit fullscreen mode

Putting a watch on the demo-ns shows the new pods that get created as a result of the scaling,



$ kubectl get pods -n demo-ns -w
NAME                                 READY   STATUS              RESTARTS   AGE
demo-app-operator-7cff88c99b-gwz46   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-gwz46   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-gwz46   0/1     ContainerCreating   0          0s
demo-app-operator-7cff88c99b-gwz46   1/1     Running             0          3s
demo-app-operator-7cff88c99b-xn7c8   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-xn7c8   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-5ddjv   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-5ddjv   0/1     Pending             0          0s
demo-app-operator-7cff88c99b-xn7c8   0/1     ContainerCreating   0          0s
demo-app-operator-7cff88c99b-5ddjv   0/1     ContainerCreating   0          1s
demo-app-operator-7cff88c99b-5ddjv   1/1     Running             0          2s
demo-app-operator-7cff88c99b-xn7c8   1/1     Running             0          3s
Enter fullscreen mode Exit fullscreen mode

Let's trigger descaling by deleting the messages in the queue.

Deleting the messages in the queue

Getting the events from the demo-ns shows:



$ kubectl get events -n demo-ns
LAST SEEN   TYPE     REASON                       OBJECT                                             MESSAGE
4m2s        Normal   Killing                      pod/demo-app-674d8c455c-64jvw    Stopping container demo-app
4m2s        Normal   Killing                      pod/demo-app-674d8c455c-n7svp    Stopping container demo-app
4m2s        Normal   SuccessfulDelete             replicaset/demo-app-674d8c455c   Deleted pod: demo-app-674d8c455c-n7svp
4m2s        Normal   SuccessfulDelete             replicaset/demo-app-674d8c455c   Deleted pod: demo-app-674d8c455c-64jvw
4m3s        Normal   ScalingReplicaSet            deployment/demo-app              Scaled down replica set demo-app-674d8c455c to 0
4m3s        Normal   KEDAScaleTargetDeactivated   scaledobject/demo-app            Deactivated apps/v1.Deployment demo-ns/demo-app from 2 to 0
Enter fullscreen mode Exit fullscreen mode

Getting the pods shows,



$ kubectl get pods -n demo-ns -w
NAME                                 READY   STATUS              RESTARTS   AGE
demo-app-operator-7cff88c99b-gwz46   1/1     Terminating         0          14m
demo-app-operator-7cff88c99b-xn7c8   1/1     Terminating         0          13m
demo-app-operator-7cff88c99b-5ddjv   1/1     Terminating         0          13m
demo-app-operator-7cff88c99b-5ddjv   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-xn7c8   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-xn7c8   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-xn7c8   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-5ddjv   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-5ddjv   0/1     Terminating         0          13m
demo-app-operator-7cff88c99b-gwz46   0/1     Terminating         0          14m
demo-app-operator-7cff88c99b-gwz46   0/1     Terminating         0          14m
demo-app-operator-7cff88c99b-gwz46   0/1     Terminating         0          14m
Enter fullscreen mode Exit fullscreen mode

Yaaay! Awesome work in following through with this guide. We have scaled our demo application based on a queue using two different identity models.

If you have run through some errors, check out below for a list of errors that I encountered and how to fix them.

Watch out for the next part of KEDA in Amazon EKS mini-series. On the next one, we'll use KEDA to scale a workload based on http traffic! This ability is a game-changer for our scaling capabilities.

Common Errors

Here are some possible errors that you may encounter following this blog and how to solve them. These errors can be seen by describing the ScaledObject in your namespace.

WebIdentityErr 



Warning  KEDAScalerFailed  18s  keda-operator  WebIdentityErr: failed to retrieve credentials caused by: AccessDenied: Not authorized to perform sts:AssumeRoleWithWebIdentity status code: 403, request id: 24f2181f-8a1b-4a4d-8de3-f85d501787a7
Enter fullscreen mode Exit fullscreen mode

This is often caused by an issue with the role's trust policy. Double check the values.

TriggerAuthentication 



2023-02-16T03:46:46Z ERROR scalehandler Error getting triggerAuth {"type": "ScaledObject", "namespace": "demo-ns", "name": "demo-app", "triggerAuthRef.Name": "demo-app-trigger-auth-aws-credentials", "error": "TriggerAuthentication.keda.sh \"demo-app-trigger-auth-aws-credentials\" not found"}
Enter fullscreen mode Exit fullscreen mode

Check that the TriggerAuthentication object gets created.

NonExistentQueue: wsdl 



Warning  KEDAScalerFailed  78s  keda-operator  AWS.SimpleQueueService.NonExistentQueue: The specified queue does not exist for this wsdl version status code: 400, request id: b01e1553-fa5d-5bde-8190-493cc508300f
Enter fullscreen mode Exit fullscreen mode

You might have set the incorrect region on the values.yaml file. Double-check that you are setting the region where the queue is.

AccessDenied 



  Warning  KEDAScalerFailed  3m40s  keda-operator  AccessDenied: User: arn:aws:sts::620528608035:assumed-role/keda-operator/1677015712377894955 is not authorized to perform: sts:AssumeRole on resource: arn:aws:iam::046921848075:role/demo-app status code: 403, request id: 6001b079-4cc9-4309-b364-5958316ce52b
Enter fullscreen mode Exit fullscreen mode

This can be caused by a missing sts:AssumeRole policy on the keda-operator role or on your workload's role.



    Warning  KEDAScalerFailed  0s  keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied. status code: 403, request id: c9b51391-2132-551e-b998-4ffe48b8de74
Enter fullscreen mode Exit fullscreen mode

This can be caused by missing permissions to access the queue. When using the Operator Identity Model, check that:

  1. access policy has been added to the queue
  2. permissions have been added to the KEDA role


Events:
  Type     Reason              Age   From           Message
  ----     ------              ----  ----           -------
  Normal   KEDAScalersStarted  109s  keda-operator  Started scalers watch
  Warning  KEDAScalerFailed    106s  keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied.
           status code: 403, request id: dabe543b-d61f-57a4-9c6b-089fdde8daa9
  Warning  KEDAScalerFailed  92s  keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied.
           status code: 403, request id: 84ae713a-5e5b-5c73-98d9-2d9e525f953d
  Warning  KEDAScalerFailed  77s  keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied.
           status code: 403, request id: 3955aad9-0221-5a6f-a7c4-f67d0e32145f
  Normal   ScaledObjectReady  69s (x2 over 109s)  keda-operator  ScaledObject is ready for scaling
  Warning  KEDAScalerFailed   62s                 keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied.
           status code: 403, request id: eddee0ca-6e76-520b-b4ac-bc6e62543864
  Warning  KEDAScalerFailed  47s  keda-operator  AccessDenied: Access to the resource https://sqs.ca-central-1.amazonaws.com/ is denied.
           status code: 403, request id: 7f1a95e9-3e9c-550b-82d0-c94d32adf964
  Normal   KEDAScaleTargetDeactivated  33s  keda-operator  Deactivated apps/v1.Deployment demo-ns/demo-app-operator from 1 to 0
Enter fullscreen mode Exit fullscreen mode

From the example above, sometimes it may also take a minute before KEDA can access the queue.

Reach out for a yarn

If you have some questions, feedback or just want to reach out for a good ol' yarn, please connect and flick me a message at https://www.linkedin.com/in/carlo-columna/.

References:

Top comments (1)

Collapse
 
awsfanboy profile image
Arshad Zackeriya 🇳🇿 ☁️ •

Well explained @carlocolumna

Read next

sarvar_04 profile image

🚀 Amazon Nova: AWS's New Foundation Model for GenAI🤖

Sarvar Nadaf -

franckpachot profile image

Aurora Limitless - Resharding

Franck Pachot -

pawelpiwosz profile image

AWS Re:Invent announcement: Lambda SnapStart for .Net - let's try it!

Paweł Piwosz -

mohit0303 profile image

Your ML/AI Success Begins Here: Data Ingestion & Storage on AWS

mohit mishra -