Ecs

# Create cluster
aws ecs create-cluster --cluster-name my-cluster

# With capacity providers
aws ecs create-cluster \
  --cluster-name my-cluster \
  --capacity-providers FARGATE FARGATE_SPOT \
  --default-capacity-provider-strategy \
    capacityProvider=FARGATE,weight=1 \
    capacityProvider=FARGATE_SPOT,weight=1

cat > task-definition.json << 'EOF'
{
  "family": "web-app",
  "networkMode": "awsvpc",
  "requiresCompatibilities": ["FARGATE"],
  "cpu": "256",
  "memory": "512",
  "executionRoleArn": "arn:aws:iam::123456789012:role/ecsTaskExecutionRole",
  "taskRoleArn": "arn:aws:iam::123456789012:role/ecsTaskRole",
  "containerDefinitions": [
    {
      "name": "web",
      "image": "123456789012.dkr.ecr.us-east-1.amazonaws.com/my-app:latest",
      "portMappings": [
        {
          "containerPort": 8080,
          "protocol": "tcp"
        }
      ],
      "environment": [
        {"name": "NODE_ENV", "value": "production"}
      ],
      "secrets": [
        {
          "name": "DB_PASSWORD",
          "valueFrom": "arn:aws:secretsmanager:us-east-1:123456789012:secret:db-password"
        }
      ],
      "logConfiguration": {
        "logDriver": "awslogs",
        "options": {
          "awslogs-group": "/ecs/web-app",
          "awslogs-region": "us-east-1",
          "awslogs-stream-prefix": "ecs",
          "mode": "non-blocking",
          "max-buffer-size": "25m"
        }
      },
      "healthCheck": {
        "command": ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"],
        "interval": 30,
        "timeout": 5,
        "retries": 3,
        "startPeriod": 60
      }
    }
  ]
}
EOF

aws ecs register-task-definition --cli-input-json file://task-definition.json

aws ecs create-service \
  --cluster my-cluster \
  --service-name web-service \
  --task-definition web-app:1 \
  --desired-count 2 \
  --launch-type FARGATE \
  --network-configuration "awsvpcConfiguration={
    subnets=[subnet-12345678,subnet-87654321],
    securityGroups=[sg-12345678],
    assignPublicIp=DISABLED
  }" \
  --load-balancers "targetGroupArn=arn:aws:elasticloadbalancing:us-east-1:123456789012:targetgroup/web-tg/1234567890123456,containerName=web,containerPort=8080" \
  --health-check-grace-period-seconds 60 \
  --deployment-configuration "deploymentCircuitBreaker={enable=true,rollback=true}"

aws ecs run-task \
  --cluster my-cluster \
  --task-definition my-batch-job:1 \
  --launch-type FARGATE \
  --network-configuration "awsvpcConfiguration={
    subnets=[subnet-12345678],
    securityGroups=[sg-12345678],
    assignPublicIp=ENABLED
  }"

# Register new task definition with updated image
aws ecs register-task-definition --cli-input-json file://task-definition.json

# Update service to use new version
aws ecs update-service \
  --cluster my-cluster \
  --service web-service \
  --task-definition web-app:2 \
  --force-new-deployment

# Create service with Spot + fallback
aws ecs create-service \
  --cluster batch-cluster \
  --service-name queue-processor \
  --task-definition my-processor:1 \
  --desired-count 0 \
  --capacity-provider-strategy \
    capacityProvider=FARGATE_SPOT,weight=4,base=0 \
    capacityProvider=FARGATE,weight=1,base=1 \
  --network-configuration "awsvpcConfiguration={
    subnets=[subnet-12345678],
    securityGroups=[sg-12345678],
    assignPublicIp=DISABLED
  }"

# Register scalable target (scale to zero when queue empty)
aws application-autoscaling register-scalable-target \
  --service-namespace ecs \
  --resource-id service/batch-cluster/queue-processor \
  --scalable-dimension ecs:service:DesiredCount \
  --min-capacity 0 \
  --max-capacity 20

# Scale-out alarm: messages > 100
aws cloudwatch put-metric-alarm \
  --alarm-name queue-scale-out \
  --metric-name ApproximateNumberOfMessagesVisible \
  --namespace AWS/SQS \
  --dimensions Name=QueueName,Value=my-queue \
  --statistic Average \
  --period 60 \
  --evaluation-periods 1 \
  --threshold 100 \
  --comparison-operator GreaterThanThreshold \
  --alarm-actions <scale-out-policy-arn>

# Scale-in alarm: queue empty for 3 periods (conservative to avoid flapping)
aws cloudwatch put-metric-alarm \
  --alarm-name queue-scale-in \
  --metric-name ApproximateNumberOfMessagesVisible \
  --namespace AWS/SQS \
  --dimensions Name=QueueName,Value=my-queue \
  --statistic Average \
  --period 60 \
  --evaluation-periods 3 \
  --threshold 0 \
  --comparison-operator LessThanOrEqualToThreshold \
  --alarm-actions <scale-in-policy-arn>

# TargetValue = acceptable latency / avg processing time per message (e.g. 10s / 0.1s = 100)
aws application-autoscaling put-scaling-policy \
  --service-namespace ecs \
  --resource-id service/batch-cluster/queue-processor \
  --scalable-dimension ecs:service:DesiredCount \
  --policy-name sqs-backlog-per-task \
  --policy-type TargetTrackingScaling \
  --target-tracking-scaling-policy-configuration '{
    "TargetValue": 100,
    "CustomizedMetricSpecification": {
      "Metrics": [
        {"Id": "m1", "ReturnData": false, "MetricStat": {"Stat": "Sum",
          "Metric": {"Namespace": "AWS/SQS", "MetricName": "ApproximateNumberOfMessagesVisible",
            "Dimensions": [{"Name": "QueueName", "Value": "my-queue"}]}}},
        {"Id": "m2", "ReturnData": false, "MetricStat": {"Stat": "Average",
          "Metric": {"Namespace": "ECS/ContainerInsights", "MetricName": "RunningTaskCount",
            "Dimensions": [{"Name": "ClusterName", "Value": "batch-cluster"},
                           {"Name": "ServiceName", "Value": "queue-processor"}]}}},
        {"Id": "e1", "Expression": "m1 / m2", "ReturnData": true}
      ]
    }
  }'

# Register scalable target
aws application-autoscaling register-scalable-target \
  --service-namespace ecs \
  --resource-id service/my-cluster/web-service \
  --scalable-dimension ecs:service:DesiredCount \
  --min-capacity 2 \
  --max-capacity 10

# Target tracking policy
aws application-autoscaling put-scaling-policy \
  --service-namespace ecs \
  --resource-id service/my-cluster/web-service \
  --scalable-dimension ecs:service:DesiredCount \
  --policy-name cpu-target-tracking \
  --policy-type TargetTrackingScaling \
  --target-tracking-scaling-policy-configuration '{
    "TargetValue": 70.0,
    "PredefinedMetricSpecification": {
      "PredefinedMetricType": "ECSServiceAverageCPUUtilization"
    },
    "ScaleOutCooldown": 60,
    "ScaleInCooldown": 120
  }'

aws ecs update-service \
  --cluster my-cluster \
  --service web-service \
  --monitoring "metricConfigurations=[{metricNames=[CPUUtilization,MemoryUtilization],resolutionSeconds=20}]"