chat-service.yml

AWSTemplateFormatVersion: '2010-09-09'
Description: Socket.io chat service
Parameters:
  EnvironmentName:
    Type: String
    Default: production
    Description: A name for the environment that this cloudformation will be part of.
                 Used to locate other resources in the same environment.
  ServiceName:
    Type: String
    Default: chat
    Description: A name for the service
  ImageUrl:
    Type: String
    Default: nginx
    Description: The url of a docker image that contains the application process that
                 will handle the traffic for this service
  ContainerPort:
    Type: Number
    Default: 3000
    Description: What port number the application inside the docker container is binding to
  ContainerCpu:
    Type: Number
    Default: 256
    Description: How much CPU to give the container. 1024 is 1 CPU
  ContainerMemory:
    Type: Number
    Default: 1024
    Description: How much memory in megabytes to give the container
  Path:
    Type: String
    Default: "*"
    Description: A path on the public load balancer that this service
                 should be connected to. Use * to send all load balancer
                 traffic to this service.
  Priority:
    Type: Number
    Default: 10
    Description: The priority for the routing rule added to the load balancer.
                 This only applies if your have multiple services which have been
                 assigned to different paths on the load balancer.
  DesiredCount:
    Type: Number
    Default: 2
    Description: How many copies of the service task to run

Resources:
  # A log group for storing the container logs for this service
  LogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Join ['-', [!Ref 'EnvironmentName', 'service', !Ref 'ServiceName']]

  # The task definition. This is a simple metadata description of what
  # container to run, and what resource requirements it has.
  TaskDefinition:
    Type: AWS::ECS::TaskDefinition
    Properties:
      Family: !Ref 'ServiceName'
      Cpu: !Ref 'ContainerCpu'
      Memory: !Ref 'ContainerMemory'
      NetworkMode: awsvpc
      RequiresCompatibilities:
        - FARGATE
      ExecutionRoleArn:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'ECSTaskExecutionRole']]
      TaskRoleArn:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'ChatServiceRole']]
      ContainerDefinitions:
        - Name: !Ref 'ServiceName'
          Cpu: !Ref 'ContainerCpu'
          Memory: !Ref 'ContainerMemory'
          Image: !Ref 'ImageUrl'
          Environment:
            - Name: REGION
              Value: !Ref 'AWS::Region'
            - Name: NODE_ENV
              Value: production
            - Name: REDIS_ENDPOINT
              Value:
                Fn::ImportValue:
                  !Join [':', [!Ref 'EnvironmentName', 'RedisEndpoint']]
            - Name: DYNAMODB_ENDPOINT
              Value: !Join ['.', ['https://dynamodb', !Ref 'AWS::Region', 'amazonaws.com']]
            - Name: ENV_NAME
              Value: !Ref 'EnvironmentName'
          PortMappings:
            - ContainerPort: !Ref 'ContainerPort'
          LogConfiguration:
            LogDriver: 'awslogs'
            Options:
              awslogs-group: !Join ['-', [!Ref 'EnvironmentName', 'service', !Ref 'ServiceName']]
              awslogs-region: !Ref 'AWS::Region'
              awslogs-stream-prefix: !Ref 'ServiceName'

  # The service. The service is a resource which allows you to run multiple
  # copies of a type of task, and gather up their logs and metrics, as well
  # as monitor the number of running tasks and replace any that have crashed
  Service:
    Type: AWS::ECS::Service
    DependsOn:
      - HTTPRule
      - HTTPSRule
    Properties:
      ServiceName: !Ref 'ServiceName'
      Cluster:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
      LaunchType: FARGATE
      DeploymentConfiguration:
        MaximumPercent: 200
        MinimumHealthyPercent: 75
      DesiredCount: !Ref 'DesiredCount'
      NetworkConfiguration:
        AwsvpcConfiguration:
          AssignPublicIp: DISABLED #Since our services are going to be in private subnets
          SecurityGroups:
            - Fn::ImportValue:
                !Join [':', [!Ref 'EnvironmentName', 'FargateContainerSecurityGroup']]
          Subnets:
            - !ImportValue SubnetAZ1Private
            - !ImportValue SubnetAZ2Private
      TaskDefinition: !Ref 'TaskDefinition'
      LoadBalancers:
        - ContainerName: !Ref 'ServiceName'
          ContainerPort: !Ref 'ContainerPort'
          TargetGroupArn: !Ref 'TargetGroup'

  # A target group. This is used for keeping track of all the tasks, and
  # what IP addresses / port numbers they have. You can query it yourself,
  # to use the addresses yourself, but most often this target group is just
  # connected to an application load balancer, or network load balancer, so
  # it can automatically distribute traffic across all the targets.
  TargetGroup:
    Type: AWS::ElasticLoadBalancingV2::TargetGroup
    Properties:
      HealthCheckIntervalSeconds: 6
      HealthCheckPath: /
      Matcher:
        HttpCode: 301
      HealthCheckProtocol: HTTP
      HealthCheckTimeoutSeconds: 5
      HealthyThresholdCount: 2
      TargetType: ip
      Name: !Join ['-', [!Ref 'EnvironmentName', !Ref 'ServiceName']]
      Port: 80
      Protocol: HTTP
      UnhealthyThresholdCount: 2
      TargetGroupAttributes:
        - Key: stickiness.enabled
          Value: true
        - Key: deregistration_delay.timeout_seconds
          Value: 30
      VpcId: !ImportValue VPC

  # Create rules to forward both HTTP and HTTPS traffic to the service's
  # target group. The service itself will handle redirecting HTTP traffic
  # to HTTPS
  HTTPRule:
    Type: AWS::ElasticLoadBalancingV2::ListenerRule
    Properties:
      Actions:
        - TargetGroupArn: !Ref 'TargetGroup'
          Type: 'forward'
      Conditions:
        - Field: path-pattern
          Values: [!Ref 'Path']
      ListenerArn:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'PublicListenerHTTP']]
      Priority: !Ref 'Priority'
  HTTPSRule:
    Type: AWS::ElasticLoadBalancingV2::ListenerRule
    Properties:
      Actions:
        - TargetGroupArn: !Ref 'TargetGroup'
          Type: 'forward'
      Conditions:
        - Field: path-pattern
          Values: [!Ref 'Path']
      ListenerArn:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'PublicListenerHTTPS']]
      Priority: !Ref 'Priority'

  # Enable autoscaling for this service
  ScalableTarget:
    Type: AWS::ApplicationAutoScaling::ScalableTarget
    DependsOn: Service
    Properties:
      ServiceNamespace: 'ecs'
      ScalableDimension: 'ecs:service:DesiredCount'
      ResourceId:
        Fn::Join:
          - '/'
          - - service
            - Fn::ImportValue: !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
            - !Ref 'ServiceName'
      MinCapacity: 2
      MaxCapacity: 10
      RoleARN:
        Fn::ImportValue:
          !Join [':', [!Ref 'EnvironmentName', 'AutoscalingRole']]

  # Create scaling policies for the service
  ScaleDownPolicy:
    Type: AWS::ApplicationAutoScaling::ScalingPolicy
    DependsOn: ScalableTarget
    Properties:
      PolicyName:
        Fn::Join:
          - '/'
          - - scale
            - !Ref 'EnvironmentName'
            - !Ref 'ServiceName'
            - down
      PolicyType: StepScaling
      ResourceId:
        Fn::Join:
          - '/'
          - - service
            - Fn::ImportValue: !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
            - !Ref 'ServiceName'
      ScalableDimension: 'ecs:service:DesiredCount'
      ServiceNamespace: 'ecs'
      StepScalingPolicyConfiguration:
        AdjustmentType: 'ChangeInCapacity'
        StepAdjustments:
          - MetricIntervalUpperBound: 0
            ScalingAdjustment: -1
        MetricAggregationType: 'Average'
        Cooldown: 60

  ScaleUpPolicy:
    Type: AWS::ApplicationAutoScaling::ScalingPolicy
    DependsOn: ScalableTarget
    Properties:
      PolicyName:
        Fn::Join:
          - '/'
          - - scale
            - !Ref 'EnvironmentName'
            - !Ref 'ServiceName'
            - up
      PolicyType: StepScaling
      ResourceId:
        Fn::Join:
          - '/'
          - - service
            - Fn::ImportValue: !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
            - !Ref 'ServiceName'
      ScalableDimension: 'ecs:service:DesiredCount'
      ServiceNamespace: 'ecs'
      StepScalingPolicyConfiguration:
        AdjustmentType: 'ChangeInCapacity'
        StepAdjustments:
          - MetricIntervalLowerBound: 0
            MetricIntervalUpperBound: 15
            ScalingAdjustment: 1
          - MetricIntervalLowerBound: 15
            MetricIntervalUpperBound: 25
            ScalingAdjustment: 2
          - MetricIntervalLowerBound: 25
            ScalingAdjustment: 3
        MetricAggregationType: 'Average'
        Cooldown: 60

  # Create alarms to trigger these policies
  LowCpuUsageAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName:
        Fn::Join:
          - '-'
          - - low-cpu
            - !Ref 'EnvironmentName'
            - !Ref 'ServiceName'
      AlarmDescription:
        Fn::Join:
          - ' '
          - - "Low CPU utilization for service"
            - !Ref 'ServiceName'
            - "in stack"
            - !Ref 'EnvironmentName'
      MetricName: CPUUtilization
      Namespace: AWS/ECS
      Dimensions:
        - Name: ServiceName
          Value: !Ref 'ServiceName'
        - Name: ClusterName
          Value:
            Fn::ImportValue: !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
      Statistic: Average
      Period: 60
      EvaluationPeriods: 1
      Threshold: 20
      ComparisonOperator: LessThanOrEqualToThreshold
      AlarmActions:
        - !Ref ScaleDownPolicy

  HighCpuUsageAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName:
        Fn::Join:
          - '-'
          - - high-cpu
            - !Ref 'EnvironmentName'
            - !Ref 'ServiceName'
      AlarmDescription:
        Fn::Join:
          - ' '
          - - "High CPU utilization for service"
            - !Ref 'ServiceName'
            - "in stack"
            - !Ref 'EnvironmentName'
      MetricName: CPUUtilization
      Namespace: AWS/ECS
      Dimensions:
        - Name: ServiceName
          Value: !Ref 'ServiceName'
        - Name: ClusterName
          Value:
            Fn::ImportValue: !Join [':', [!Ref 'EnvironmentName', 'ClusterName']]
      Statistic: Average
      Period: 60
      EvaluationPeriods: 1
      Threshold: 70
      ComparisonOperator: GreaterThanOrEqualToThreshold
      AlarmActions:
        - !Ref ScaleUpPolicy