open-webui/iac/monitoring.tf

# Auto Scaling Target
resource "aws_appautoscaling_target" "ecs_target" {
  max_capacity       = 10
  min_capacity       = 2
  resource_id        = "service/${var.cluster_name}/${var.service_name}"
  scalable_dimension = "ecs:service:DesiredCount"
  service_namespace  = "ecs"

  depends_on = [aws_ecs_service.webui_scaled]
}

# Auto Scaling Policy - Scale Up
resource "aws_appautoscaling_policy" "scale_up" {
  name               = "openwebui-scale-up"
  policy_type        = "TargetTrackingScaling"
  resource_id        = aws_appautoscaling_target.ecs_target.resource_id
  scalable_dimension = aws_appautoscaling_target.ecs_target.scalable_dimension
  service_namespace  = aws_appautoscaling_target.ecs_target.service_namespace

  target_tracking_scaling_policy_configuration {
    target_value = 70.0

    predefined_metric_specification {
      predefined_metric_type = "ECSServiceAverageCPUUtilization"
    }

    scale_out_cooldown = 300
    scale_in_cooldown  = 300
  }
}

# CloudWatch Dashboard
resource "aws_cloudwatch_dashboard" "webui_dashboard" {
  dashboard_name = "OpenWebUI-HorizontalScaling"

  dashboard_body = jsonencode({
    widgets = [
      {
        type   = "metric"
        x      = 0
        y      = 0
        width  = 12
        height = 6

        properties = {
          metrics = [
            ["AWS/ECS", "CPUUtilization", "ServiceName", var.service_name, "ClusterName", var.cluster_name],
            [".", "MemoryUtilization", ".", ".", ".", "."]
          ]
          period = 300
          stat   = "Average"
          region = var.aws_region
          title  = "ECS Service Metrics"
        }
      },
      {
        type   = "metric"
        x      = 0
        y      = 6
        width  = 12
        height = 6

        properties = {
          metrics = [
            ["AWS/ApplicationELB", "TargetResponseTime", "LoadBalancer", aws_lb.webui_alb.arn_suffix],
            [".", "RequestCount", ".", "."],
            [".", "HTTPCode_Target_2XX_Count", ".", "."],
            [".", "HTTPCode_Target_4XX_Count", ".", "."],
            [".", "HTTPCode_Target_5XX_Count", ".", "."]
          ]
          period = 300
          stat   = "Sum"
          region = var.aws_region
          title  = "ALB Metrics"
        }
      },
      {
        type   = "metric"
        x      = 0
        y      = 12
        width  = 12
        height = 6

        properties = {
          metrics = [
            ["AWS/ElastiCache", "CPUUtilization", "CacheClusterId", aws_elasticache_replication_group.redis.id],
            [".", "DatabaseMemoryUsagePercentage", ".", "."],
            [".", "NetworkBytesIn", ".", "."],
            [".", "NetworkBytesOut", ".", "."]
          ]
          period = 300
          stat   = "Average"
          region = var.aws_region
          title  = "Redis Metrics"
        }
      }
    ]
  })
}

# CloudWatch Alarms
resource "aws_cloudwatch_metric_alarm" "high_cpu" {
  alarm_name          = "openwebui-high-cpu"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = "2"
  metric_name         = "CPUUtilization"
  namespace           = "AWS/ECS"
  period              = "300"
  statistic           = "Average"
  threshold           = "85"
  alarm_description   = "This metric monitors ECS CPU utilization"
  alarm_actions       = [aws_sns_topic.alerts.arn]

  dimensions = {
    ServiceName = var.service_name
    ClusterName = var.cluster_name
  }
}

resource "aws_cloudwatch_metric_alarm" "high_memory" {
  alarm_name          = "openwebui-high-memory"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = "2"
  metric_name         = "MemoryUtilization"
  namespace           = "AWS/ECS"
  period              = "300"
  statistic           = "Average"
  threshold           = "90"
  alarm_description   = "This metric monitors ECS memory utilization"
  alarm_actions       = [aws_sns_topic.alerts.arn]

  dimensions = {
    ServiceName = var.service_name
    ClusterName = var.cluster_name
  }
}

resource "aws_cloudwatch_metric_alarm" "alb_high_response_time" {
  alarm_name          = "openwebui-alb-high-response-time"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = "2"
  metric_name         = "TargetResponseTime"
  namespace           = "AWS/ApplicationELB"
  period              = "300"
  statistic           = "Average"
  threshold           = "2"
  alarm_description   = "This metric monitors ALB response time"
  alarm_actions       = [aws_sns_topic.alerts.arn]

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

resource "aws_cloudwatch_metric_alarm" "redis_high_cpu" {
  alarm_name          = "openwebui-redis-high-cpu"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = "2"
  metric_name         = "CPUUtilization"
  namespace           = "AWS/ElastiCache"
  period              = "300"
  statistic           = "Average"
  threshold           = "75"
  alarm_description   = "This metric monitors Redis CPU utilization"
  alarm_actions       = [aws_sns_topic.alerts.arn]

  dimensions = {
    CacheClusterId = aws_elasticache_replication_group.redis.id
  }
}

# SNS Topic for alerts
resource "aws_sns_topic" "alerts" {
  name = "openwebui-scaling-alerts"

  tags = {
    Name = "OpenWebUI Scaling Alerts"
  }
}

# SNS Topic subscription (replace with actual email)
resource "aws_sns_topic_subscription" "email_alerts" {
  topic_arn = aws_sns_topic.alerts.arn
  protocol  = "email"
  endpoint  = "loi.tra@gravityglobal.com"  # Replace with actual email
}