mgmt/infrastructure/monitor/monitoring-stack.nomad

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

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

    constraint {
      attribute = "${node.unique.name}"
      operator  = "="
      value     = "influxdb"
    }

    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 = "/usr/sbin/grafana-server"
        args = [
          "--config", "/etc/grafana/grafana.ini",
          "--homepath", "/usr/share/grafana",
          "cfg:default.paths.data=/opt/grafana/data",
          "cfg:default.paths.logs=/var/log/grafana",
          "cfg:default.paths.plugins=/var/lib/grafana/plugins",
          "cfg:default.paths.provisioning=/etc/grafana/provisioning"
        ]
      }

      resources {
        cpu    = 300
        memory = 512
      }

      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

    constraint {
      attribute = "${node.unique.name}"
      operator  = "="
      value     = "influxdb"
    }

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

      resources {
        cpu    = 300
        memory = 512
      }

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

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

  # Loki 服务组
  group "loki" {
    count = 1

    constraint {
      attribute = "${node.unique.name}"
      operator  = "="
      value     = "influxdb"
    }

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

    network {
      port "http" {
        static = 3100
        to     = 3100
      }
    }

    task "loki" {
      driver = "exec"

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

      template {
        data = <<EOF
auth_enabled: false

server:
  http_listen_port: 3100
  grpc_listen_port: 9096

common:
  path_prefix: /opt/loki/data
  storage:
    filesystem:
      chunks_directory: /opt/loki/data/chunks
      rules_directory: /opt/loki/data/rules
  replication_factor: 1
  ring:
    instance_addr: 127.0.0.1
    kvstore:
      store: inmemory

query_scheduler:
  max_outstanding_requests_per_tenant: 2048

schema_config:
  configs:
    - from: 2020-10-24
      store: boltdb-shipper
      object_store: filesystem
      schema: v12
      index:
        prefix: index_
        period: 24h

limits_config:
  allow_structured_metadata: false

ruler:
  alertmanager_url: http://localhost:9093

analytics:
  reporting_enabled: false
EOF
        destination = "local/config.yml"
      }

      config {
        command = "loki"
        args = [
          "-config.file=local/config.yml"
        ]
      }

      resources {
        cpu    = 300
        memory = 512
      }

      service {
        name = "loki"
        port = "http"
        
        tags = [
          "loki",
          "monitoring",
          "logs"
        ]

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