「成本估算与优化」

# 账单只能告诉你「花了多少」，不能告诉你「为什么」
aws ce get-cost-and-usage \
  --time-period Start=2026-09-01,End=2026-10-01 \
  --granularity MONTHLY \
  --metrics UnblendedCost

# 生成 plan 并交给 Infracost 分析，再只看变更增量
terraform plan -out=plan.tfplan
terraform show -json plan.tfplan > plan.json
infracost breakdown --path plan.json
infracost diff --path plan.json

# 典型输出：逐资源列出增量，最后给出月度总增量
# + aws_instance.web      +$146.00/mo
# + aws_db_instance.main  +$312.40/mo
# Monthly cost will increase by $458.40

# .github/workflows/cost.yml
name: cost-estimate

on:
  pull_request:
    paths: ["**.tf"]

jobs:
  infracost:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: infracost/actions/setup@v3
        with:
          api-key: ${{ secrets.INFRACOST_API_KEY }}
      - run: |
          terraform init
          terraform plan -out=plan.tfplan
          terraform show -json plan.tfplan > plan.json
      - run: infracost comment github --path plan.json \
          --repo $GITHUB_REPOSITORY \
          --pull-request ${{ github.event.pull_request.number }} \
          --github-token ${{ secrets.GITHUB_TOKEN }} \
          --behavior update

# infracost-policy.yml
version: 0.2

policies:
  - name: 单实例月成本上限
    resource_type: aws_instance
    checks:
      - type: monthly_cost
        max: 200

infracost breakdown --path plan.json --config-file infracost-policy.yml

# 用变量表达规格，便于统一调整与成本对比
variable "web_instance_type" {
  description = "Web 层实例规格"
  type        = string
  default     = "t3.medium"
}

resource "aws_instance" "web" {
  count         = var.web_instance_count
  instance_type = var.web_instance_type
  ami           = data.aws_ami.ubuntu.id
}

# 用 ARM 架构降本（同规格约便宜 20%）
variable "use_graviton" {
  type    = bool
  default = true
}

locals {
  instance_type = var.use_graviton ? "t4g.medium" : "t3.medium"
}

# gp3 比 gp2 便宜且性能可调，新项目默认选 gp3
resource "aws_ebs_volume" "data" {
  availability_zone = "us-east-1a"
  size              = 100
  type              = "gp3"    # 而非 gp2

  # 按实际需要配置 IOPS，避免为默认值付溢价
  iops       = 3000
  throughput = 125
}

# 冷数据用 infrequent access 或归档层
resource "aws_s3_bucket_lifecycle_configuration" "logs" {
  bucket = aws_s3_bucket.logs.id

  rule {
    id     = "archive-old-logs"
    status = "Enabled"

    transition {
      days          = 30
      storage_class = "STANDARD_IA"
    }

    transition {
      days          = 90
      storage_class = "GLACIER"
    }

    expiration {
      days = 365
    }
  }
}

# 未挂载的 EBS 卷
aws ec2 describe-volumes \
  --filters Name=status,Values=available \
  --query 'Volumes[].{ID:VolumeId,Size:Size,Created:CreateTime}' \
  --output table

# 未关联的弹性 IP（闲置也要计费）
aws ec2 describe-addresses \
  --query 'Addresses[?AssociationId==null].PublicIp'

# 停止超过 30 天的实例
aws ec2 describe-instances \
  --filters Name=instance-state-name,Values=stopped \
  --query 'Reservations[].Instances[].{ID:InstanceId,Launch:LaunchTime}'

# 用 data source 找出未使用的卷，纳入告警
data "aws_ebs_volumes" "all" {
  filter {
    name   = "status"
    values = ["available"]
  }
}

output "orphan_volumes" {
  value = [for v in data.aws_ebs_volumes.all.ids : v]
}

# 日志组设置保留天数，避免无限累积
resource "aws_cloudwatch_log_group" "app" {
  name              = "/app/service"
  retention_in_days = 30
}

# AWS Budgets 预算告警
resource "aws_budgets_budget" "monthly" {
  name         = "monthly-total"
  budget_type  = "COST"
  limit_amount = "5000"
  limit_unit   = "USD"
  time_unit    = "MONTHLY"

  notification {
    comparison_operator        = "GREATER_THAN"
    threshold                  = 80
    threshold_type             = "PERCENTAGE"
    notification_type          = "ACTUAL"
    subscriber_email_addresses = ["finops@example.com"]
  }

  notification {
    comparison_operator        = "GREATER_THAN"
    threshold                  = 100
    threshold_type             = "PERCENTAGE"
    notification_type          = "FORECASTED"
    subscriber_email_addresses = ["finops@example.com"]
  }
}

# 在代码层面限制规格：用 validation 拒绝超大实例
variable "instance_type" {
  type = string

  validation {
    condition = contains(
      ["t3.micro", "t3.small", "t3.medium", "t4g.medium"],
      var.instance_type
    )
    error_message = "仅允许使用审批过的实例规格。"
  }
}

locals {
  cost_tags = {
    CostCenter  = var.cost_center
    Environment = var.environment
    Owner       = var.team
    ManagedBy   = "terraform"
  }
}

# 激活成本分配标签后可按团队/环境查询
aws ce get-cost-and-usage \
  --time-period Start=2026-09-01,End=2026-10-01 \
  --granularity MONTHLY \
  --metrics UnblendedCost \
  --group-by Type=TAG,Key=CostCenter

# PR 模板中的成本检查项
# ## 成本影响
# - [ ] Infracost 评论已查看
# - [ ] 增量超过 $100/月 已获得审批
# - [ ] 已确认无替代的更省方案

# 对比优化前后的成本
infracost breakdown --path plan-before.json --format json > before.json
infracost breakdown --path plan-after.json  --format json > after.json
infracost diff --path after.json --compare-to before.json

# 用 Cost Explorer 找出 Top 成本项
aws ce get-cost-and-usage \
  --time-period Start=2026-09-01,End=2026-10-01 \
  --granularity MONTHLY \
  --metrics UnblendedCost \
  --group-by Type=DIMENSION,Key=SERVICE \
  --query 'ResultsByTime[0].Groups | sort_by(@, &Metrics.UnblendedCost.Amount) | reverse(@)[:10]'

# 利用率与成本对照：低利用率 + 高成本 = 优先优化对象
aws cloudwatch get-metric-statistics \
  --namespace AWS/EC2 \
  --metric-name CPUUtilization \
  --dimensions Name=InstanceId,Value=i-0abc123 \
  --start-time 2026-09-01T00:00:00Z \
  --end-time 2026-10-01T00:00:00Z \
  --period 86400 \
  --statistics Average