ShieldAI/infra/modules/cloudwatch/main.tf

variable "environment" {
  description = "Deployment environment"
  type        = string
}

variable "cluster_name" {
  description = "ECS cluster name"
  type        = string
}

variable "project_name" {
  description = "Project name"
  type        = string
}

variable "rds_identifier" {
  description = "RDS instance identifier"
  type        = string
}

variable "cache_endpoint" {
  description = "ElastiCache endpoint"
  type        = string
}

resource "aws_cloudwatch_dashboard" "main" {
  dashboard_name = "${var.project_name}-${var.environment}-dashboard"

  dashboard_body = jsonencode({
    widgets = [
      {
        type = "metric"
        properties = {
          title = "ECS CPU Utilization"
          metrics = [
            ["AWS/ECS", "CPUUtilization", "ClusterName", var.cluster_name]
          ]
          view     = "timeSeries"
          stacked  = false
          region   = "us-east-1"
          period  = 300
        }
      },
      {
        type = "metric"
        properties = {
          title = "ECS Memory Utilization"
          metrics = [
            ["AWS/ECS", "MemoryUtilization", "ClusterName", var.cluster_name]
          ]
          view     = "timeSeries"
          stacked  = false
          region   = "us-east-1"
          period  = 300
        }
      },
      {
        type = "metric"
        properties = {
          title = "RDS CPU Utilization"
          metrics = [
            ["AWS/RDS", "CPUUtilization", "DBInstanceIdentifier", var.rds_identifier]
          ]
          view     = "timeSeries"
          stacked  = false
          region   = "us-east-1"
          period  = 300
        }
      },
      {
        type = "metric"
        properties = {
          title = "ALB Request Count"
          metrics = [
            ["AWS/ApplicationELB", "RequestCount", "LoadBalancer", "${var.cluster_name}-alb"]
          ]
          view     = "timeSeries"
          stacked  = false
          region   = "us-east-1"
          period  = 60
        }
      },
      {
        type = "metric"
        properties = {
          title = "ALB 5xx Errors"
          metrics = [
            ["AWS/ApplicationELB", "HTTPCode_Elb_5XX_Count", "LoadBalancer", "${var.cluster_name}-alb"]
          ]
          view     = "timeSeries"
          stacked  = false
          region   = "us-east-1"
          period  = 60
        }
      }
    ]
  })
}

resource "aws_cloudwatch_metric_alarm" "ecs_cpu_high" {
  alarm_name          = "${var.project_name}-${var.environment}-ecs-cpu-high"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = 2
  metric_name         = "CPUUtilization"
  namespace           = "AWS/ECS"
  period              = 300
  statistic           = "Average"
  threshold           = 80
  alarm_description   = "ECS CPU utilization above 80%"

  dimensions = {
    ClusterName = var.cluster_name
  }
}

resource "aws_cloudwatch_metric_alarm" "ecs_memory_high" {
  alarm_name          = "${var.project_name}-${var.environment}-ecs-memory-high"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = 2
  metric_name         = "MemoryUtilization"
  namespace           = "AWS/ECS"
  period              = 300
  statistic           = "Average"
  threshold           = 85
  alarm_description   = "ECS memory utilization above 85%"

  dimensions = {
    ClusterName = var.cluster_name
  }
}

resource "aws_cloudwatch_metric_alarm" "alb_5xx" {
  alarm_name          = "${var.project_name}-${var.environment}-alb-5xx"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = 3
  metric_name         = "HTTPCode_Elb_5XX_Count"
  namespace           = "AWS/ApplicationELB"
  period              = 60
  statistic           = "Sum"
  threshold           = 10
  alarm_description   = "ALB 5xx errors above 10 per minute"

  dimensions = {
    LoadBalancer = "${var.cluster_name}-alb"
  }
}

resource "aws_cloudwatch_metric_alarm" "rds_cpu_high" {
  alarm_name          = "${var.project_name}-${var.environment}-rds-cpu-high"
  comparison_operator = "GreaterThanThreshold"
  evaluation_periods  = 2
  metric_name         = "CPUUtilization"
  namespace           = "AWS/RDS"
  period              = 300
  statistic           = "Average"
  threshold           = 75
  alarm_description   = "RDS CPU utilization above 75%"

  dimensions = {
    DBInstanceIdentifier = var.rds_identifier
  }
}

resource "aws_cloudwatch_metric_alarm" "rds_free_storage" {
  alarm_name          = "${var.project_name}-${var.environment}-rds-free-storage"
  comparison_operator = "LessThanThreshold"
  evaluation_periods  = 2
  metric_name         = "FreeStorageSpace"
  namespace           = "AWS/RDS"
  period              = 300
  statistic           = "Average"
  threshold           = 524288000
  alarm_description   = "RDS free storage below 500MB"

  dimensions = {
    DBInstanceIdentifier = var.rds_identifier
  }
}

output "dashboard_url" {
  description = "CloudWatch dashboard URL"
  value       = "https://us-east-1.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/${var.project_name}-${var.environment}-dashboard"
}