Deploy a CloudWatch dashboard for an Amazon ECS service

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147

AWSTemplateFormatVersion: '2010-09-09'
Description: This template deploys an automatically generated CloudWatch
             dashboard for the referenced ECS service.
Transform:
  - AWS::LanguageExtensions

Parameters:
  ServiceArn:
    Type: String
    Description: The ARN of the service that we want to generate the dashboard from.

Resources:
  # A CloudWatch log group for persisting the deployment events
  ServiceEventLog:
    Type: AWS::Logs::LogGroup

  # Create the EventBridge rule that captures deployment events into the CloudWatch log group
  CaptureServiceDeploymentEvents:
    Type: AWS::Events::Rule
    Properties:
      Description:
        Fn::Sub:
          - 'Capture service deployment events from the ECS service ${ServiceName}'
          # Scary but working way to get service's human name from it's ARN
          - ServiceName: !Select [2, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
      EventPattern:
        source:
          - aws.ecs
        detail-type:
          - "ECS Deployment State Change"
          - "ECS Service Action"
        resources:
          - !Ref ServiceArn
      # Where to send the events
      Targets:
        - Arn: !Sub arn:aws:logs:${AWS::Region}:${AWS::AccountId}:log-group:${ServiceEventLog}
          Id: 'CloudWatchLogGroup'

  # Create a log group resource policy that allows EventBridge to put logs into
  # the log group
  LogGroupForEventsPolicy:
    Type: AWS::Logs::ResourcePolicy
    Properties:
      PolicyName: EventBridgeToCWLogsPolicy
      PolicyDocument: !Sub
      - >
        {
          "Version": "2012-10-17",
          "Statement": [
            {
              "Sid": "EventBridgetoCWLogsPolicy",
              "Effect": "Allow",
              "Principal": {
                "Service": [
                  "delivery.logs.amazonaws.com",
                  "events.amazonaws.com"
                ]
              },
              "Action": [
                "logs:CreateLogStream",
                "logs:PutLogEvents"
              ],
              "Resource": [
                "${LogArn}"
              ]
            }
          ]
        }
      - { LogArn: !GetAtt ServiceEventLog.Arn, RuleArn: !GetAtt CaptureServiceDeploymentEvents.Arn}

  # This resource creates the widgets that will live in the CloudWatch
  # dashboard, by pulling stats from Container Insights
  ServiceDashboard:
    Type: AWS::CloudWatch::Dashboard
    Properties:
      DashboardName:
        Fn::Sub:
          - "${ServiceName}-dashboard"
          - ServiceName: !Select [2, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
      DashboardBody:
        Fn::ToJsonString:
          widgets:
            # A table that shows recent deployment events
            - type: log
              x: 0
              y: 0
              width: 24
              height: 4
              properties:
                region: !Ref AWS::Region
                title: Service Deployments
                query: !Sub "SOURCE '${ServiceEventLog}' | fields @timestamp, detail.eventName, detail.deploymentId | sort @timestamp desc | limit 500"
                view: table

            # A graph showing the running task count over time
            - type: metric
              x: 0
              y: 13
              width: 24
              height: 6
              properties:
                metrics:
                - - "ECS/ContainerInsights"
                  - "RunningTaskCount"
                  - "ServiceName"
                  # Extract service name from service ARN
                  - !Select [2, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
                  - "ClusterName"
                  # Extract cluster name from service ARN
                  - !Select [1, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
                - [ ".", "DesiredTaskCount", ".", ".", ".", "." ]
                view: timeSeries
                stacked: false
                region: !Ref AWS::Region
                stat: Sum
                period: 60
                yAxis:
                  left:
                    min: 0
                title: "DesiredTaskCount, RunningTaskCount"

            # A graph showing CPU and Memory utilization over time
            - type: metric
              x: 0
              y: 13
              width: 24
              height: 6
              properties:
                metrics:
                - - "ECS/ContainerInsights"
                  - "CpuUtilized"
                  - "ServiceName"
                  # Extract service name from service ARN
                  - !Select [2, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
                  - "ClusterName"
                  # Extract cluster name from service ARN
                  - !Select [1, !Split ['/', !Select [5, !Split [':', !Ref ServiceArn]]]]
                - [ ".", "MemoryUtilized", ".", ".", ".", "." ]
                view: timeSeries
                stacked: false
                region: !Ref AWS::Region
                stat: Sum
                period: 60
                yAxis:
                  left:
                    min: 0
                title: "CPU Utilization, Memory Utilization"