사고 대응 훈련 및 개선이 수행되고 있는가?

# 1. AWS FIS 카오스 훈련 템플릿
resource "aws_fis_experiment_template" "ec2_failure" {
  description = "EC2 instance failure simulation"
  role_arn    = aws_iam_role.fis.arn

  stop_condition {
    source = "aws:cloudwatch:alarm"
    value  = aws_cloudwatch_metric_alarm.high_cpu.arn
  }

  action {
    name      = "stop-instances"
    action_id = "aws:ec2:stop-instances"
    target    { key = "Instances"; value = "target-instances" }
  }

  target {
    name           = "target-instances"
    resource_type  = "aws:ec2:instance"
    selection_mode = "COUNT(1)"
    resource_tag   { key = "Environment"; value = "staging" }
  }

  tags = { ISMS-P = "2.11.4" }
}

# 2. 분기별 훈련 스케줄
resource "aws_cloudwatch_event_rule" "quarterly_training" {
  name                = "quarterly-incident-training"
  schedule_expression = "cron(0 9 1 1,4,7,10 ? *)"  # 매 분기 첫째 날
}

# 3. 월별 복구 테스트
resource "aws_backup_restore_testing_plan" "monthly" {
  name = "monthly-restore-testing"

  schedule_expression = "cron(0 3 15 * ? *)"  # 매월 15일

  recovery_point_selection {
    algorithm              = "LATEST_WITHIN_WINDOW"
    recovery_point_types   = ["CONTINUOUS"]
    include_vaults         = ["arn:aws:backup:*:*:backup-vault:*"]
  }
}

# 4. 훈련 결과 Dashboard
resource "aws_cloudwatch_dashboard" "training" {
  dashboard_name = "incident-response-training"
  dashboard_body = jsonencode({
    widgets = [
      { type = "metric", properties = { title = "FIS 훈련 실행", metrics = [["AWS/FIS", "ExperimentStarted"]] } },
      { type = "metric", properties = { title = "복구 테스트 결과", metrics = [["Custom/Backup", "RestoreTestSuccess"]] } }
    ]
  })
}

💡 핵심: FIS로 장애 시뮬레이션을 수행하고, Restore Testing으로 복구를 검증하고, EventBridge로 정기 훈련을 스케줄링하고, Dashboard로 결과를 분석합니다.

📚 참고 자료