meal-order-manager/terraform/alarms.tf

# CloudWatch alarms for the Fargate API and orders table.

resource "aws_cloudwatch_metric_alarm" "alb_5xx" {
  count = local.is_prod ? 1 : 0

  alarm_name          = "${local.project}-alb-5xx"
  alarm_description   = "ALB 5xx from meal-order-manager"
  namespace           = "AWS/ApplicationELB"
  metric_name         = "HTTPCode_Target_5XX_Count"
  statistic           = "Sum"
  period              = 300
  evaluation_periods  = 1
  threshold           = 0
  comparison_operator = "GreaterThanThreshold"
  treat_missing_data  = "notBreaching"
  alarm_actions       = [data.aws_sns_topic.site_alerts[0].arn]

  dimensions = {
    LoadBalancer = aws_lb.api.arn_suffix
  }
}

resource "aws_cloudwatch_metric_alarm" "ecs_cpu" {
  count = local.is_prod ? 1 : 0

  alarm_name          = "${local.project}-ecs-cpu"
  alarm_description   = "meal-order-manager ECS CPU above 80 percent"
  namespace           = "AWS/ECS"
  metric_name         = "CPUUtilization"
  statistic           = "Average"
  period              = 300
  evaluation_periods  = 2
  threshold           = 80
  comparison_operator = "GreaterThanThreshold"
  treat_missing_data  = "notBreaching"
  alarm_actions       = [data.aws_sns_topic.site_alerts[0].arn]

  dimensions = {
    ClusterName = aws_ecs_cluster.api.name
    ServiceName = aws_ecs_service.api.name
  }
}

resource "aws_cloudwatch_metric_alarm" "jobs_dlq" {
  count = local.is_prod ? 1 : 0

  alarm_name          = "${local.project}-jobs-dlq"
  alarm_description   = "Jobs DLQ is not empty"
  namespace           = "AWS/SQS"
  metric_name         = "ApproximateNumberOfMessagesVisible"
  statistic           = "Maximum"
  period              = 300
  evaluation_periods  = 1
  threshold           = 0
  comparison_operator = "GreaterThanThreshold"
  treat_missing_data  = "notBreaching"
  alarm_actions       = [data.aws_sns_topic.site_alerts[0].arn]

  dimensions = {
    QueueName = aws_sqs_queue.jobs_dlq.name
  }
}

resource "aws_cloudwatch_metric_alarm" "dynamodb_read_throttles" {
  count = local.is_prod ? 1 : 0

  alarm_name          = "${local.project}-ddb-read-throttles"
  alarm_description   = "Orders table read throttles"
  namespace           = "AWS/DynamoDB"
  metric_name         = "ReadThrottleEvents"
  statistic           = "Sum"
  period              = 300
  evaluation_periods  = 1
  threshold           = 0
  comparison_operator = "GreaterThanThreshold"
  treat_missing_data  = "notBreaching"
  alarm_actions       = [data.aws_sns_topic.site_alerts[0].arn]

  dimensions = {
    TableName = aws_dynamodb_table.orders.name
  }
}

resource "aws_cloudwatch_metric_alarm" "dynamodb_write_throttles" {
  count = local.is_prod ? 1 : 0

  alarm_name          = "${local.project}-ddb-write-throttles"
  alarm_description   = "Orders table write throttles"
  namespace           = "AWS/DynamoDB"
  metric_name         = "WriteThrottleEvents"
  statistic           = "Sum"
  period              = 300
  evaluation_periods  = 1
  threshold           = 0
  comparison_operator = "GreaterThanThreshold"
  treat_missing_data  = "notBreaching"
  alarm_actions       = [data.aws_sns_topic.site_alerts[0].arn]

  dimensions = {
    TableName = aws_dynamodb_table.orders.name
  }
}