使用Terraform自动化配置GCP Stackdriver告警与通知的问题求助

你已经搞定了通知渠道和正常运行时间检查的基础配置，接下来只需要添加告警策略资源就能把两者关联起来，实现当uptime检查失败时自动触发通知。下面是直接结合你现有代码的完整配置方案：

完整配置代码 #

# 你已有的通知渠道配置
resource "google_monitoring_notification_channel" "basic" {
 display_name = "Test Notification Channel"
 type = "email"
 labels = {
 email_address = "fakeid007@gmail.com"
 }
 project = "department1"
}

# 你已有的uptime检查配置
resource "google_monitoring_uptime_check_config" "http" {
 display_name = "01 - Website uptime check [global]"
 timeout = "10s"
 period = "60s"
 project = "department1"
 http_check {
 path = "/"
 port = "80"
 mask_headers = null
 use_ssl = null
 validate_ssl = null
 request_method = "GET"
 }
 monitored_resource {
 type = "uptime_url"
 labels = {
 host = "35.184.98.16"
 }
 }
}

# 新增告警策略：关联uptime检查与通知渠道
resource "google_monitoring_alert_policy" "uptime_failure_alert" {
 display_name = "Uptime Check Failure Alert"
 project      = "department1"

 # 定义告警触发条件：当uptime检查失败时
 conditions {
 display_name = "Uptime Check Failed"
 condition_threshold {
   # 精准匹配你创建的uptime检查，用Terraform插值避免手动输入错误
   filter = "metric.type=\"monitoring.googleapis.com/uptime_check/check_failed\" AND resource.type=\"uptime_url\" AND resource.label.\"host\"=\"${google_monitoring_uptime_check_config.http.monitored_resource.0.labels.host}\""
   comparison = "COMPARISON_GT"
   threshold_value = 0
   duration = "0s" # 检查失败立即触发告警

   # 配置触发次数：这里设置1次失败就告警，可按需调整
   trigger {
     count = 1
   }
 }
 }

 # 绑定你之前创建的邮件通知渠道
 notification_channels = [google_monitoring_notification_channel.basic.id]

 # 告警严重级别，可选值：CRITICAL、ERROR、WARNING、INFO、DEBUG
 severity = "CRITICAL"
}

关键细节说明 #

• 条件过滤：通过filter规则精准关联你创建的特定uptime检查，用Terraform插值语法直接引用现有资源的host参数，避免手动输入错误。
• 触发逻辑：check_failed指标在检查正常时为0，失败时为1，所以设置threshold_value = 0+COMPARISON_GT就能在失败时立即触发告警。
• 通知绑定：notification_channels直接引用你已创建的通知渠道ID，确保告警触发时自动发送邮件。

验证步骤 #

运行terraform apply完成部署后，你可以在Stackdriver控制台确认：

1. 「告警」>「告警策略」列表中会出现你配置的Uptime Check Failure Alert
2. 手动模拟站点故障（比如关闭目标服务），测试是否能收到告警邮件通知

内容的提问来源于stack exchange，提问作者d.s