services:
  alloy:
    image: grafana/alloy:latest
    restart: unless-stopped
    hostname: ${ALLOY_HOSTNAME:?required}
    network_mode: host
    cap_drop: [ALL]
    cap_add: [DAC_OVERRIDE]
    security_opt:
      - no-new-privileges:true
    mem_limit: 2g
    pids_limit: 512
    depends_on:
      - dockerproxy
    environment:
      ALLOY_DEPLOY_MODE: docker
      REMOTECFG_URL: ${REMOTECFG_URL:?required}
      REMOTECFG_ID: ${REMOTECFG_ID:?required}
      REMOTECFG_USER: ${REMOTECFG_USER:?required}
      PROM_URL: ${PROM_URL:?required}
      PROM_USER: ${PROM_USER:?required}
      LOKI_URL: ${LOKI_URL:?required}
      LOKI_USER: ${LOKI_USER:?required}
      GRAFANA_TOKEN: ${GRAFANA_TOKEN:?required}
      GCLOUD_RW_API_KEY: ${GRAFANA_TOKEN:?required}
    volumes:
      - alloy-data:/var/lib/alloy/data
      - /proc:/rootproc:ro
      - /sys:/sys:ro
      - /:/rootfs:ro
      - /dev/disk/:/dev/disk:ro
      - /run/udev:/run/udev:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /var/log:/var/log:ro
      - /etc/machine-id:/etc/machine-id:ro
    configs:
      - { source: alloy_config, target: /etc/alloy/config.alloy }
    command: 'run --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy'

  dockerproxy:
    image: tecnativa/docker-socket-proxy:latest
    restart: unless-stopped
    security_opt:
      - no-new-privileges:true
    mem_limit: 64m
    pids_limit: 64
    environment:
      CONTAINERS: 1
      NETWORKS: 1
      IMAGES: 1
      INFO: 1
      VERSION: 1
      EVENTS: 1
    ports:
      - 127.0.0.1:2375:2375
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro

volumes:
  alloy-data:

configs:
  alloy_config:
    content: |
      remotecfg {
        url = sys.env("REMOTECFG_URL")
        id = sys.env("REMOTECFG_ID")
        poll_frequency = "60s"

        basic_auth {
          username = sys.env("REMOTECFG_USER")
          password = sys.env("GRAFANA_TOKEN")
        }
      }

      prometheus.remote_write "metrics_service" {
        endpoint {
          url = sys.env("PROM_URL")

          basic_auth {
            username = sys.env("PROM_USER")
            password = sys.env("GRAFANA_TOKEN")
          }
        }
      }

      loki.write "grafana_cloud_loki" {
        endpoint {
          url = sys.env("LOKI_URL")

          basic_auth {
            username = sys.env("LOKI_USER")
            password = sys.env("GRAFANA_TOKEN")
          }
        }
      }

      discovery.relabel "integrations_node_exporter" {
        targets = prometheus.exporter.unix.integrations_node_exporter.targets

        rule {
          target_label = "instance"
          replacement  = constants.hostname
        }

        rule {
          target_label = "job"
          replacement = "integrations/node_exporter"
        }
      }

      prometheus.exporter.unix "integrations_node_exporter" {
        disable_collectors = ["ipvs", "btrfs", "infiniband", "xfs", "zfs"]

        // Read host filesystems through the /rootfs and /rootproc bind mounts.
        rootfs_path = "/rootfs"
        procfs_path = "/rootproc"

        filesystem {
          fs_types_exclude     = "^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|tmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$"
          mount_points_exclude = "^/(dev|proc|run/credentials/.+|sys|var/lib/docker/.+)($|/)"
          mount_timeout        = "5s"
        }

        netclass {
          ignored_devices = "^(veth.*|cali.*|[a-f0-9]{15})$"
        }

        netdev {
          device_exclude = "^(veth.*|cali.*|[a-f0-9]{15})$"
        }
      }

      prometheus.scrape "integrations_node_exporter" {
        targets    = discovery.relabel.integrations_node_exporter.output
        forward_to = [prometheus.relabel.integrations_node_exporter.receiver]
      }

      // Keep only the Grafana Cloud Linux Node integration's metric list.
      prometheus.relabel "integrations_node_exporter" {
        forward_to = [prometheus.remote_write.metrics_service.receiver]

        rule {
          source_labels = ["__name__"]
          regex         = "node_arp_entries|node_boot_time_seconds|node_context_switches_total|node_cpu_seconds_total|node_disk_io_time_seconds_total|node_disk_io_time_weighted_seconds_total|node_disk_read_bytes_total|node_disk_read_time_seconds_total|node_disk_reads_completed_total|node_disk_write_time_seconds_total|node_disk_writes_completed_total|node_disk_written_bytes_total|node_filefd_allocated|node_filefd_maximum|node_filesystem_avail_bytes|node_filesystem_device_error|node_filesystem_files|node_filesystem_files_free|node_filesystem_readonly|node_filesystem_size_bytes|node_intr_total|node_load1|node_load15|node_load5|node_md_disks|node_md_disks_required|node_memory_Active_anon_bytes|node_memory_Active_bytes|node_memory_Active_file_bytes|node_memory_AnonHugePages_bytes|node_memory_AnonPages_bytes|node_memory_Bounce_bytes|node_memory_Buffers_bytes|node_memory_Cached_bytes|node_memory_CommitLimit_bytes|node_memory_Committed_AS_bytes|node_memory_DirectMap1G_bytes|node_memory_DirectMap2M_bytes|node_memory_DirectMap4k_bytes|node_memory_Dirty_bytes|node_memory_HugePages_Free|node_memory_HugePages_Rsvd|node_memory_HugePages_Surp|node_memory_HugePages_Total|node_memory_Hugepagesize_bytes|node_memory_Inactive_anon_bytes|node_memory_Inactive_bytes|node_memory_Inactive_file_bytes|node_memory_Mapped_bytes|node_memory_MemAvailable_bytes|node_memory_MemFree_bytes|node_memory_MemTotal_bytes|node_memory_SReclaimable_bytes|node_memory_SUnreclaim_bytes|node_memory_ShmemHugePages_bytes|node_memory_ShmemPmdMapped_bytes|node_memory_Shmem_bytes|node_memory_Slab_bytes|node_memory_SwapTotal_bytes|node_memory_VmallocChunk_bytes|node_memory_VmallocTotal_bytes|node_memory_VmallocUsed_bytes|node_memory_WritebackTmp_bytes|node_memory_Writeback_bytes|node_netstat_Icmp6_InErrors|node_netstat_Icmp6_InMsgs|node_netstat_Icmp6_OutMsgs|node_netstat_Icmp_InErrors|node_netstat_Icmp_InMsgs|node_netstat_Icmp_OutMsgs|node_netstat_IpExt_InOctets|node_netstat_IpExt_OutOctets|node_netstat_TcpExt_ListenDrops|node_netstat_TcpExt_ListenOverflows|node_netstat_TcpExt_TCPSynRetrans|node_netstat_Tcp_InErrs|node_netstat_Tcp_InSegs|node_netstat_Tcp_OutRsts|node_netstat_Tcp_OutSegs|node_netstat_Tcp_RetransSegs|node_netstat_Udp6_InDatagrams|node_netstat_Udp6_InErrors|node_netstat_Udp6_NoPorts|node_netstat_Udp6_OutDatagrams|node_netstat_Udp6_RcvbufErrors|node_netstat_Udp6_SndbufErrors|node_netstat_UdpLite_InErrors|node_netstat_Udp_InDatagrams|node_netstat_Udp_InErrors|node_netstat_Udp_NoPorts|node_netstat_Udp_OutDatagrams|node_netstat_Udp_RcvbufErrors|node_netstat_Udp_SndbufErrors|node_network_carrier|node_network_info|node_network_mtu_bytes|node_network_receive_bytes_total|node_network_receive_compressed_total|node_network_receive_drop_total|node_network_receive_errs_total|node_network_receive_fifo_total|node_network_receive_multicast_total|node_network_receive_packets_total|node_network_speed_bytes|node_network_transmit_bytes_total|node_network_transmit_compressed_total|node_network_transmit_drop_total|node_network_transmit_errs_total|node_network_transmit_fifo_total|node_network_transmit_multicast_total|node_network_transmit_packets_total|node_network_transmit_queue_length|node_network_up|node_nf_conntrack_entries|node_nf_conntrack_entries_limit|node_os_info|node_procs_running|node_sockstat_FRAG6_inuse|node_sockstat_FRAG_inuse|node_sockstat_RAW6_inuse|node_sockstat_RAW_inuse|node_sockstat_TCP6_inuse|node_sockstat_TCP_alloc|node_sockstat_TCP_inuse|node_sockstat_TCP_mem|node_sockstat_TCP_mem_bytes|node_sockstat_TCP_orphan|node_sockstat_TCP_tw|node_sockstat_UDP6_inuse|node_sockstat_UDPLITE6_inuse|node_sockstat_UDPLITE_inuse|node_sockstat_UDP_inuse|node_sockstat_UDP_mem|node_sockstat_UDP_mem_bytes|node_sockstat_sockets_used|node_softnet_dropped_total|node_softnet_processed_total|node_softnet_times_squeezed_total|node_systemd_service_restart_total|node_systemd_unit_state|node_textfile_scrape_error|node_time_zone_offset_seconds|node_timex_estimated_error_seconds|node_timex_maxerror_seconds|node_timex_offset_seconds|node_timex_sync_status|node_uname_info|node_vmstat_oom_kill|node_vmstat_pgfault|node_vmstat_pgmajfault|node_vmstat_pgpgin|node_vmstat_pgpgout|node_vmstat_pswpin|node_vmstat_pswpout|process_max_fds|process_open_fds|up"
          action        = "keep"
        }
      }

      loki.relabel "integrations_node_exporter" {
        forward_to = [loki.write.grafana_cloud_loki.receiver]
        rule {
          target_label = "job"
          replacement  = "integrations/node_exporter"
        }
        rule {
          target_label = "instance"
          replacement  = constants.hostname
        }
      }

      journal_module "integrations_node_exporter" {
        forward_to = [loki.relabel.integrations_node_exporter.receiver]
      }

      // File logs from the Linux Node integration: syslog, messages, *.log.
      local.file_match "integrations_node_exporter_files" {
        path_targets = [{
          __address__ = "localhost",
          __path__    = "/var/log/{syslog,messages,*.log}",
        }]
      }
      loki.source.file "integrations_node_exporter_files" {
        targets    = local.file_match.integrations_node_exporter_files.targets
        forward_to = [loki.relabel.integrations_node_exporter.receiver]
      }

      // Journal logs.
      declare "journal_module" {
        argument "forward_to" {
            optional = false
        }

        loki.source.journal "default"  {
            max_age       = "12h0m0s"
            forward_to    = [loki.process.default.receiver]
            relabel_rules = loki.relabel.default.rules
        }

        loki.relabel "default" {
            rule {
                source_labels = ["__journal__systemd_unit"]
                target_label  = "unit"
            }
            rule {
                source_labels = ["__journal__boot_id"]
                target_label  = "boot_id"
            }
            rule {
                source_labels = ["__journal__transport"]
                target_label  = "transport"
            }
            rule {
                source_labels = ["__journal_priority_keyword"]
                target_label  = "level"
            }
            forward_to    = []
        }
        loki.process "default" {
            forward_to    = argument.forward_to.value
        }
      }

      prometheus.exporter.cadvisor "integrations_cadvisor" {
          docker_only            = true
          store_container_labels = false
          docker_host            = "tcp://127.0.0.1:2375"
      }
      discovery.relabel "integrations_cadvisor" {
          targets = prometheus.exporter.cadvisor.integrations_cadvisor.targets

          rule {
              target_label = "job"
              replacement  = "integrations/docker"
          }

          rule {
              target_label = "instance"
              replacement  = constants.hostname
          }
      }

      prometheus.relabel "integrations_cadvisor" {
          forward_to = [prometheus.remote_write.metrics_service.receiver]

          rule {
              source_labels = ["__name__"]
              regex         = "container_cpu_usage_seconds_total|container_fs_reads_total|container_fs_usage_bytes|container_fs_writes_total|container_last_seen|container_memory_cache|container_memory_rss|container_memory_usage_bytes|container_memory_working_set_bytes|container_network_receive_bytes_total|container_network_receive_errors_total|container_network_receive_packets_dropped_total|container_network_transmit_bytes_total|container_network_transmit_errors_total|container_network_transmit_packets_dropped_total|container_spec_memory_limit_bytes|container_spec_memory_reservation_limit_bytes|machine_memory_bytes|machine_scrape_error|up"
              action        = "keep"
          }
      }

      prometheus.scrape "integrations_cadvisor" {
          targets    = discovery.relabel.integrations_cadvisor.output
          forward_to = [prometheus.relabel.integrations_cadvisor.receiver]
      }

      discovery.docker "logs_integrations_docker" {
          host             = "tcp://127.0.0.1:2375"
          refresh_interval = "5s"
      }
      discovery.relabel "logs_integrations_docker" {
          targets = []

          rule {
              target_label = "job"
              replacement  = "integrations/docker"
          }

          rule {
              target_label = "instance"
              replacement  = constants.hostname
          }

          rule {
              source_labels = ["__meta_docker_container_name"]
              regex         = "/(.*)"
              target_label  = "container"
          }

          rule {
              source_labels = ["__meta_docker_container_log_stream"]
              target_label  = "stream"
          }
      }
      loki.source.docker "logs_integrations_docker" {
          host             = "tcp://127.0.0.1:2375"
          targets          = discovery.docker.logs_integrations_docker.targets
          forward_to       = [loki.process.logs_integrations_docker.receiver]
          relabel_rules    = discovery.relabel.logs_integrations_docker.rules
          refresh_interval = "5s"
      }

      // Drop container log lines older than Grafana Cloud Loki accepts.
      loki.process "logs_integrations_docker" {
          forward_to = [loki.write.grafana_cloud_loki.receiver]

          stage.drop {
              older_than          = "168h"
              drop_counter_reason = "too_old"
          }
      }