job "monitoring-stack" {
  datacenters = ["dc1"]
  type        = "service"

  # Grafana 服务组
  group "grafana" {
    count = 1

    volume "grafana-data" {
      type      = "host"
      read_only = false
      source    = "grafana-data"
    }

    network {
      port "http" {
        static = 3000
        to     = 3000
      }
    }

    task "grafana" {
      driver = "exec"

      volume_mount {
        volume      = "grafana-data"
        destination = "/opt/grafana/data"
        read_only   = false
      }

      config {
        command = "/opt/grafana/bin/grafana-server"
        args = [
          "--config", "/opt/grafana/conf/grafana.ini",
          "--homepath", "/opt/grafana",
          "cfg:default.paths.data=/opt/grafana/data",
          "cfg:default.paths.logs=/opt/grafana/logs",
          "cfg:default.paths.plugins=/opt/grafana/plugins",
          "cfg:default.paths.provisioning=/opt/grafana/conf/provisioning"
        ]
      }

      resources {
        cpu    = 500
        memory = 1024
      }

      env {
        GF_SECURITY_ADMIN_PASSWORD = "admin123"
        GF_INSTALL_PLUGINS = "grafana-piechart-panel"
        GF_SERVER_DOMAIN = "grafana.tailnet-68f9.ts.net"
        GF_SERVER_ROOT_URL = "http://grafana.tailnet-68f9.ts.net:3000"
      }

      service {
        name = "grafana"
        port = "http"
        
        tags = [
          "grafana",
          "monitoring",
          "dashboard"
        ]

        check {
          type     = "http"
          path     = "/api/health"
          interval = "30s"
          timeout  = "5s"
        }
      }
    }
  }

  # Prometheus 服务组
  group "prometheus" {
    count = 1

    volume "prometheus-data" {
      type      = "host"
      read_only = false
      source    = "prometheus-data"
    }

    network {
      port "http" {
        static = 9090
        to     = 9090
      }
    }

    task "prometheus" {
      driver = "exec"

      volume_mount {
        volume      = "prometheus-data"
        destination = "/opt/prometheus/data"
        read_only   = false
      }

      config {
        command = "/opt/prometheus/prometheus"
        args = [
          "--config.file=/opt/prometheus/prometheus.yml",
          "--storage.tsdb.path=/opt/prometheus/data",
          "--web.console.libraries=/opt/prometheus/console_libraries",
          "--web.console.templates=/opt/prometheus/consoles",
          "--storage.tsdb.retention.time=15d",
          "--web.enable-lifecycle"
        ]
      }

      resources {
        cpu    = 500
        memory = 1024
      }

      service {
        name = "prometheus"
        port = "http"
        
        tags = [
          "prometheus",
          "monitoring",
          "metrics"
        ]

        check {
          type     = "http"
          path     = "/-/healthy"
          interval = "30s"
          timeout  = "5s"
        }
      }
    }
  }

  # Node Exporter 服务组
  group "node-exporter" {
    count = 1

    network {
      port "metrics" {
        static = 9100
        to     = 9100
      }
    }

    task "node-exporter" {
      driver = "exec"

      config {
        command = "/opt/node-exporter/node_exporter"
        args = [
          "--path.procfs=/proc",
          "--path.rootfs=/",
          "--path.sysfs=/sys",
          "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
        ]
      }

      resources {
        cpu    = 100
        memory = 256
      }

      service {
        name = "node-exporter"
        port = "metrics"
        
        tags = [
          "node-exporter",
          "monitoring",
          "metrics"
        ]

        check {
          type     = "http"
          path     = "/metrics"
          interval = "30s"
          timeout  = "5s"
        }
      }
    }
  }
}