Stack to create EC2 instances for ECS cluster.

aws-cluster-stack.yml

# Stack to create EC2 instances for ECS cluster. 
#
# aws cloudformation deploy \
#   --stack-name app-cluster-prod \
#   --template-file ./aws-cluster-stack.yaml \
#   --parameter-overrides \
#       KeyName=DEFAULT \
#       SecurityGroups=group1,group2 \
#       ImageId=ami-123456 \
#       InstanceType=c5.large \
#       Subnets=subnet-1234,subnet-5678 \
#       EcsClusterName=myapp-prod \
#  --capabilities CAPABILITY_IAM CAPABILITY_NAMED_IAM \
#  --no-execute-changeset

AWSTemplateFormatVersion: '2010-09-09'
Transform: 'AWS::Serverless-2016-10-31'

Description: EC2 instances for ECS cluster.

Parameters:
  KeyName:
    Description: The EC2 Key Pair to allow SSH access to the instance
    Type: AWS::EC2::KeyPair::KeyName
  SecurityGroups:
    Description: Security group ids to use for the instances.
    Type: CommaDelimitedList
  ImageId:
    Description: ECS-optimised AMI ID for your region. http://docs.aws.amazon.com/AmazonECS/latest/developerguide/ecs-optimized_AMI.html
    Type: String
  InstanceType:
    Description: EC2 instance type.
    Type: String
  Subnets:
    Description: Subnet ids for instance placement.
    Type: CommaDelimitedList
  EcsClusterName:
    Description: Name of the ECS cluster.
    Type: String

Resources:
  ## EC2
  InstanceRole:
    Type: AWS::IAM::Role
    Properties:
      Path: /
      ManagedPolicyArns:
        - arn:aws:iam::aws:policy/service-role/AmazonEC2ContainerServiceforEC2Role
        - arn:aws:iam::aws:policy/service-role/AmazonEC2RoleforSSM
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Action:
              - sts:AssumeRole
            Principal:
              Service: ec2.amazonaws.com
      Policies:
        - PolicyName: logs
          PolicyDocument:
            Version: '2012-10-17'
            Statement:
              - Effect: Allow
                Action:
                  - logs:*
                Resource:
                  - !Sub arn:aws:logs:${AWS::Region}:${AWS::AccountId}:log-group:*

  InstanceProfile:
    Type: AWS::IAM::InstanceProfile
    Properties:
      Path: /
      Roles:
        - !Ref InstanceRole

  AutoscalingLaunchConfig:
    Type: AWS::AutoScaling::LaunchConfiguration
    Properties:
      ImageId: !Ref ImageId
      InstanceType: !Ref InstanceType
      KeyName: !Ref KeyName
      SecurityGroups: !Ref SecurityGroups
      IamInstanceProfile: !Ref InstanceProfile
      UserData:
        !Base64:
          Fn::Sub: |
            - Content-Type: multipart/mixed; boundary="==BOUNDARY=="
              MIME-Version: 1.0

              --==BOUNDARY==
              MIME-Version: 1.0
              Content-Type: text/x-shellscript; charset="us-ascii"
              #!/bin/bash
              echo ECS_CLUSTER=${ClusterName} >> /etc/ecs/ecs.config
              STACK_NAME=${AWS::StackName}

              # Install awslogs and the jq JSON parser
              yum install -y awslogs jq https://s3-${AWS::Region}.amazonaws.com/amazon-ssm-${AWS::Region}/latest/linux_amd64/amazon-ssm-agent.rpm

              # Inject the CloudWatch Logs configuration file contents
              cat > /etc/awslogs/awslogs.conf <<- EOF
              [general]
              state_file = /var/lib/awslogs/agent-state

              [/var/log/dmesg]
              file = /var/log/dmesg
              log_group_name = /var/log/dmesg
              log_stream_name = {cluster}/{container_instance_id}

              [/var/log/messages]
              file = /var/log/messages
              log_group_name = /var/log/messages
              log_stream_name = {cluster}/{container_instance_id}
              datetime_format = %b %d %H:%M:%S

              [/var/log/docker]
              file = /var/log/docker
              log_group_name = /var/log/docker
              log_stream_name = {cluster}/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%S.%f

              [/var/log/ecs/ecs-init.log]
              file = /var/log/ecs/ecs-init.log.*
              log_group_name = /var/log/ecs/ecs-init.log
              log_stream_name = {cluster}/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%SZ

              [/var/log/ecs/ecs-agent.log]
              file = /var/log/ecs/ecs-agent.log.*
              log_group_name = /var/log/ecs/ecs-agent.log
              log_stream_name = {cluster}/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%SZ

              [/var/log/ecs/audit.log]
              file = /var/log/ecs/audit.log.*
              log_group_name = /var/log/ecs/audit.log
              log_stream_name = {cluster}/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%SZ

              [/var/log/amazon/ssm/amazon-ssm-agent.log]
              file = /var/log/amazon/ssm/amazon-ssm-agent.log
              log_group_name = amazon-ssm
              log_stream_name = agent-$STACK_NAME/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%SZ

              [/var/log/amazon/ssm/errors.log]
              file = /var/log/amazon/ssm/errors.log
              log_group_name = amazon-ssm
              log_stream_name = errors-$STACK_NAME/{container_instance_id}
              datetime_format = %Y-%m-%dT%H:%M:%SZ

              EOF

              --==BOUNDARY==
              MIME-Version: 1.0
              Content-Type: text/x-shellscript; charset="us-ascii"
              #!/bin/bash
              # Set the region to send CloudWatch Logs data to (the region where the container instance is located)
              region=$(curl 169.254.169.254/latest/meta-data/placement/availability-zone | sed s'/.$//')
              sed -i -e "s/region = us-east-1/region = $region/g" /etc/awslogs/awscli.conf

              --==BOUNDARY==
              MIME-Version: 1.0
              Content-Type: text/upstart-job; charset="us-ascii"

              #upstart-job
              description "Configure and start CloudWatch Logs agent on Amazon ECS container instance"
              author "Amazon Web Services"
              start on started ecs

              script
                exec 2>>/var/log/ecs/cloudwatch-logs-start.log
                set -x

                until curl -s http://localhost:51678/v1/metadata
                do
                  sleep 1
                done

                # Grab the cluster and container instance ARN from instance metadata
                cluster=$(curl -s http://localhost:51678/v1/metadata | jq -r '. | .Cluster')
                container_instance_id=$(curl -s http://localhost:51678/v1/metadata | jq -r '. | .ContainerInstanceArn' | awk -F/ '{print $2}' )

                # Replace the cluster name and container instance ID placeholders with the actual values
                sed -i -e "s/{cluster}/$cluster/g" /etc/awslogs/awslogs.conf
                sed -i -e "s/{container_instance_id}/$container_instance_id/g" /etc/awslogs/awslogs.conf

                service awslogs start
                chkconfig awslogs on
              end script
              --==BOUNDARY==--
            - ClusterName: !Ref EcsClusterName

  AutoscalingGroup:
    Type: AWS::AutoScaling::AutoScalingGroup
    Properties:
      VPCZoneIdentifier: !Ref SubnetIds
      LaunchConfigurationName: !Ref AutoscalingLaunchConfig
      MinSize: 0
      MaxSize: 0
      HealthCheckType: EC2
      Tags:
        - Key: !Ref AWS::StackName
          Value: 'true'
          PropagateAtLaunch: true
        - Key: Name
          Value: !Ref AWS::StackName
          PropagateAtLaunch: true
        - Key: role
          Value: !Ref AWS::StackName
          PropagateAtLaunch: true

  LifecycleHookRole:
    Type: AWS::IAM::Role
    Properties:
      Path: /
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Action:
              - sts:AssumeRole
            Principal:
              Service: autoscaling.amazonaws.com
      Policies:
        - PolicyName: SNSAccess
          PolicyDocument:
            Version: '2012-10-17'
            Statement:
              - Effect: Allow
                Action:
                  - sns:Publish
                Resource: !ImportValue ops-lambdas-prod:EcsLifecycleHookTopicArn

  AutoscalingGroupInstanceTerminationHook:
    Type: AWS::AutoScaling::LifecycleHook
    Properties:
      AutoScalingGroupName: !Ref AutoscalingGroup
      HeartbeatTimeout: 600
      LifecycleTransition: autoscaling:EC2_INSTANCE_TERMINATING
      NotificationTargetARN: !ImportValue ops-lambdas-prod:EcsLifecycleHookTopicArn
      RoleARN: !GetAtt LifecycleHookRole.Arn

  InstanceScaleOutPolicy:
    Type: AWS::AutoScaling::ScalingPolicy
    Properties:
      AdjustmentType: PercentChangeInCapacity
      AutoScalingGroupName: !Ref AutoscalingGroup
      EstimatedInstanceWarmup: 420
      PolicyType: StepScaling
      StepAdjustments:
        - MetricIntervalLowerBound: 0
          MetricIntervalUpperBound: 10
          ScalingAdjustment: 10
        - MetricIntervalLowerBound: 10
          ScalingAdjustment: 30

  InstanceScaleInPolicy:
    Type: AWS::AutoScaling::ScalingPolicy
    Properties:
      AdjustmentType: PercentChangeInCapacity
      AutoScalingGroupName: !Ref AutoscalingGroup
      EstimatedInstanceWarmup: 420
      PolicyType: StepScaling
      StepAdjustments:
        - MetricIntervalUpperBound: 0
          MetricIntervalLowerBound: -10
          ScalingAdjustment: -10
        - MetricIntervalUpperBound: -10
          ScalingAdjustment: -30

  InstanceCpuAlarmHigh:
    Type: AWS::CloudWatch::Alarm
    Properties:
      EvaluationPeriods: 5
      Statistic: Average
      Threshold: 80
      AlarmDescription: Alarm if instance CPU high enough to trigger scale out policy.
      Period: 60
      AlarmActions:
        - !Ref InstanceScaleOutPolicy
      Namespace: AWS/EC2
      Dimensions:
        - Name: AutoScalingGroupName
          Value: !Ref AutoscalingGroup
      ComparisonOperator: GreaterThanOrEqualToThreshold
      MetricName: CPUUtilization

  InstanceCpuAlarmLow:
      Type: AWS::CloudWatch::Alarm
      Properties:
        EvaluationPeriods: 30
        Statistic: Average
        Threshold: 30
        AlarmDescription: Alarm if instance CPU low long enough to trigger scale in policy.
        Period: 60
        AlarmActions:
          - !Ref InstanceScaleInPolicy
        Namespace: AWS/EC2
        Dimensions:
          - Name: AutoScalingGroupName
            Value: !Ref AutoscalingGroup
        ComparisonOperator: LessThanOrEqualToThreshold
        MetricName: CPUUtilization

Outputs:
  AutoscalingGroupName:
    Description: Name of ASG.
    Value: !Ref AutoscalingGroup

Thanks for it, that helped me a lot, this part of the code:

ops-lambdas-prod:EcsLifecycleHookTopicArn

Is it another stack that created this SNS to use here? Do you have some examples of that?

Thanks again.