AWS Cloudformation Cloudwatch

Parameters:
  ErrorRateThreshold:
    Type: Number
    Default: 5
    Description: Error rate threshold for alarms (percentage)

  LatencyThreshold:
    Type: Number
    Default: 1000
    Description: Latency threshold in milliseconds

  CpuUtilizationThreshold:
    Type: Number
    Default: 80
    Description: CPU utilization threshold (percentage)

  LogRetentionDays:
    Type: Number
    Default: 30
    AllowedValues:
      - 1
      - 3
      - 7
      - 14
      - 30
      - 60
      - 90
      - 120
      - 365
    Description: Number of days to retain log events

Resources:
  HighCpuAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "${AWS::StackName}-high-cpu"
      AlarmDescription: Trigger when CPU utilization exceeds threshold
      MetricName: CPUUtilization
      Namespace: AWS/EC2
      Dimensions:
        - Name: InstanceId
          Value: !Ref InstanceId
      Statistic: Average
      Period: 60
      EvaluationPeriods: 3
      Threshold: !Ref CpuUtilizationThreshold
      ComparisonOperator: GreaterThanThreshold
      AlarmActions:
        - !Ref AlarmTopic

  ErrorRateAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "${AWS::StackName}-error-rate"
      MetricName: ErrorRate
      Namespace: !Ref CustomNamespace
      Dimensions:
        - Name: Service
          Value: !Ref ServiceName
      Statistic: Average
      Period: 60
      EvaluationPeriods: 5
      Threshold: !Ref ErrorRateThreshold
      ComparisonOperator: GreaterThanThreshold

Resources:
  AlarmNotificationTopic:
    Type: AWS::SNS::Topic
    Properties:
      DisplayName: !Sub "${AWS::StackName}-alarms"
      TopicName: !Sub "${AWS::StackName}-alarms"

  AlarmTopicPolicy:
    Type: AWS::SNS::TopicPolicy
    Properties:
      PolicyDocument:
        Statement:
          - Effect: Allow
            Principal:
              Service: cloudwatch.amazonaws.com
            Action: sns:Publish
            Resource: !Ref AlarmNotificationTopic
      Topics:
        - !Ref AlarmNotificationTopic

Resources:
  MonitoringDashboard:
    Type: AWS::CloudWatch::Dashboard
    Properties:
      DashboardName: !Sub "${AWS::StackName}-dashboard"
      DashboardBody: !Sub |
        {
          "widgets": [
            {
              "type": "metric",
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 6,
              "properties": {
                "title": "CPU Utilization",
                "metrics": [["AWS/EC2", "CPUUtilization", "InstanceId", "${InstanceId}"]],
                "period": 300,
                "stat": "Average",
                "region": "${AWS::Region}"
              }
            }
          ]
        }

Resources:
  ApplicationLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/applications/${Environment}/${ApplicationName}"
      RetentionInDays: !Ref LogRetentionDays
      KmsKeyId: !Ref LogEncryptionKey

Resources:
  ErrorMetricFilter:
    Type: AWS::Logs::MetricFilter
    Properties:
      LogGroupName: !Ref ApplicationLogGroup
      FilterPattern: '[level="ERROR", msg]'
      MetricTransformations:
        - MetricValue: "1"
          MetricNamespace: !Sub "${AWS::StackName}/Application"
          MetricName: ErrorCount

Resources:
  SystemHealthComposite:
    Type: AWS::CloudWatch::CompositeAlarm
    Properties:
      AlarmName: !Sub "${AWS::StackName}-system-health"
      AlarmRule: !Or
        - !Ref HighCpuAlarm
        - !Ref ErrorRateAlarm
      AlarmActions:
        - !Ref AlarmTopic

Resources:
  ErrorAnalysisQuery:
    Type: AWS::Logs::QueryDefinition
    Properties:
      Name: !Sub "${AWS::StackName}-errors"
      LogGroupNames:
        - !Ref ApplicationLogGroup
      QueryString: |
        fields @timestamp, @message
        | filter @message like /ERROR/
        | sort @timestamp desc
        | limit 100

aws cloudformation validate-template --template-body file://template.yaml

aws cloudformation validate-template \
  --template-body file://monitoring.yaml \
  --capabilities CAPABILITY_IAM

# Deploy stack
aws cloudformation create-stack \
  --stack-name my-monitoring-stack \
  --template-body file://monitoring.yaml \
  --parameters file://parameters.json \
  --capabilities CAPABILITY_IAM

# Wait for completion
aws cloudformation wait stack-create-complete \
  --stack-name my-monitoring-stack

# Verify alarms are in OK state
aws cloudwatch describe-alarms --stack-name my-monitoring-stack

# Check dashboard accessibility
aws cloudwatch get-dashboard --dashboard-name my-monitoring-stack-dashboard

# Set alarm to testing state
aws cloudwatch set-alarm-state \
  --alarm-name my-alarm \
  --state-value ALARM \
  --state-reason "Testing alarm action"

AWSTemplateFormatVersion: '2010-09-09'
Description: Complete CloudWatch monitoring setup

Parameters:
  Environment:
    Type: String
    Default: prod
    AllowedValues: [dev, staging, prod]

Resources:
  # SNS Topic for notifications
  AlarmTopic:
    Type: AWS::SNS::Topic
    Properties:
      DisplayName: !Sub "${Environment}-alarms"

  # Alarm for high CPU
  CpuAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "${AWS::StackName}-cpu-high"
      MetricName: CPUUtilization
      Namespace: AWS/EC2
      Statistic: Average
      Period: 300
      EvaluationPeriods: 2
      Threshold: 80
      ComparisonOperator: GreaterThanThreshold
      AlarmActions:
        - !Ref AlarmTopic

  # Dashboard
  Dashboard:
    Type: AWS::CloudWatch::Dashboard
    Properties:
      DashboardName: !Ref AWS::StackName
      DashboardBody: !Sub |
        {
          "widgets": [{
            "type": "metric",
            "properties": {
              "metrics": [["AWS/EC2", "CPUUtilization"]],
              "period": 300,
              "stat": "Average"
            }
          }]
        }

Resources:
  AppLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/app/${Environment}"
      RetentionInDays: 30

  ErrorMetricFilter:
    Type: AWS::Logs::MetricFilter
    Properties:
      LogGroupName: !Ref AppLogGroup
      FilterPattern: '"ERROR"'
      MetricTransformations:
        - MetricValue: "1"
          MetricNamespace: !Sub "${AWS::StackName}/App"
          MetricName: ErrorCount

  ErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "${AWS::StackName}-errors"
      MetricName: ErrorCount
      MetricNamespace: !Sub "${AWS::StackName}/App"
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold