fix: scrape once per hour

Reviewed-on: #24
Reviewed-by: fauno <fauno@sutty.coop.ar>

.env.sample

@@ -5,15 +5,33 @@ DOMAIN=monitoring-ng.example.com
 #TIMEOUT=120
 ENABLE_BACKUPS=true
 
-## Enable this secret for Promtail / Prometheus
+SECRET_BASIC_AUTH_VERSION=v1
-# SECRET_BASIC_AUTH_VERSION=v1
+# Enable Live Debugging
+LIVE_DEBUGGING=false
+# Enable this to send logs to a Loki server, adapt DOMAIN if server is
+# remote
+# LOKI_PUSH_URL=https://loki.$DOMAIN/loki/api/v1/push
+# Enable on systemd hosts to read logs from the journal
+# JOURNALD=1
 #
-# Promtail (Gathering Logs)
+# Enable on non-systemd hosts (Alpine, older Debian/Ubuntu) to tail
-# COMPOSE_FILE="$COMPOSE_FILE:compose.promtail.yml"
+# /var/log/*log files (syslog, auth.log, kern.log, etc.) that a local
-# LOKI_PUSH_URL=https://loki.monitoring.example.org/loki/api/v1/push
+# syslogd writes. No syslogd reconfiguration needed.
+# SYSLOG_FILES=1
+#
+# Enable to receive syslog messages over the network on port 514/tcp.
+# Use for remote devices that push syslog to this host, or for a 
+# local syslogd configured to forward over the network.
+# Not needed if you just want to read local log files — use SYSLOG_FILES instead.
+# SYSLOG=1
+# COMPOSE_FILE="$COMPOSE_FILE:compose.syslog.yml"
 
-## Expose node and cadvisor ports instead of traefik
+# Enable this to send metrics to a Prometheus server, adapt DOMAIN if
-# COMPOSE_FILE="$COMPOSE_FILE:compose.expose-ports.yml"
+# server is remote
+# PROMETHEUS_REMOTE_WRITE_URL=https://prometheus.$DOMAIN/api/v1/write
+
+# Monitor physical disks health
+# COMPOSE_FILE="$COMPOSE_FILE:compose.smartctl.yml"
 
 # Monitoring Server
 #
@@ -46,8 +64,6 @@ ENABLE_BACKUPS=true
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana.yml"
 # GF_SERVER_ROOT_URL=https://monitoring.example.com
 # SECRET_GF_ADMINPASSWD_VERSION=v1
-## Seperate domain for Grafana
-#GRAFANA_DOMAIN=grafana.example.com
 #
 ## Single-Sign-On with OIDC
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"

README.md

@@ -1,8 +1,8 @@
 # monitoring-ng
 
 Yet another monitoring stack ...
-This time its a all-in-one grafana/prometheus/loki/node_exporter/cadvisor/promtail stack.
+This time its a all-in-one grafana/prometheus/loki/alloy stack.
-It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-cloud/monitoring-lite) stack, but has everything in one recipe included now. So you can deploy monitoring instances to only gather metrics / logs (node_exporter/cadvisor/promtail) and also deploy instances with the full monitoring stack (grafana/prometheus/loki) with the same recipe and just different .env configuration.
+It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-cloud/monitoring-lite) stack, but has everything in one recipe included now. So you can deploy monitoring instances to only gather metrics / logs (alloy) and also deploy instances with the full monitoring stack (grafana/prometheus/loki) with the same recipe and just different .env configuration.
 
 
 <!-- metadata -->
@@ -47,13 +47,6 @@ Where gathering.org is the node you want to gather metrics from.
   - cadvisor.monitoring.gathering.org
   - node.monitoring.gathering.org
 
-### Expose node and cadvisor via ports instead of traefik
-
-In case you have no traefik running on the machine, you can expose the ports directly by uncommenting the following line:
-```
-# COMPOSE_FILE="$COMPOSE_FILE:compose.expose-ports.yml"
-```
-
 ## Setup Metrics Browser
 
 
@@ -165,4 +158,10 @@ It is possible to enable the following alerts, by setting the corresponding env
 - node disk space: `ALERT_NODE_DISK_SPACE_ENABLED`
 - node memory usage: `ALERT_NODE_MEMORY_USAGE_ENABLED`
 
+## smart monitoring
 
+To be able monitor hard drive health data, you need to configure
+`smartd` to run on the host system, and also the
+`collect-smartctl-json.sh` script provided here (via cronjob or as
+a `smartd` hook).  This is a limitation on Docker Swarm, which prevents
+the `smartctl_exporter` from running on privileged mode.

abra.sh

@@ -6,12 +6,12 @@ export GF_STACKS_DASH_VERSION=v2
 export GF_TRAEFIK_DASH_VERSION=v2
 export GF_BACKUP_DASH_VERSION=v1
 export GF_CUSTOM_INI_VERSION=v4
-export PROMTAIL_YML_VERSION=v3
 export LOKI_YML_VERSION=v3
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=e
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=a
 export GRAFANA_ALERTS_NODE_VERSION=v1c
+export CONFIG_ALLOY_VERSION=v10
 
 # creates a default prometheus scrape config for a given node
 add_node(){

collect-smartctl-json.service

@@ -0,0 +1,6 @@
+[Unit]
+Description=Collect SMART data
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/collect-smartctl-json.sh

collect-smartctl-json.sh

@@ -0,0 +1,69 @@
+#! /bin/bash
+# Adapted from https://github.com/prometheus-community/smartctl_exporter/blob/master/collect-smartctl-json.sh
+
+script_dir=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+# Data directory to dump smartctl output
+# This directory will be created if it doesn't exist
+data_dir="/var/lib/smartmontools/json"
+
+# The original script used --xall but that doesn't work
+# This matches the command in readSMARTctl()
+smartctl_args="--json --info --health --attributes --tolerance=verypermissive \
+--nocheck=standby --format=brief --log=error"
+
+# Ignore this devices
+smartctl_ignore_dev_regex="^(/dev/bus)"
+
+# Determine the json query tool to use
+if command -v jq >/dev/null; then
+	json_tool="jq"
+	json_args="--raw-output"
+elif command -v yq >/dev/null; then
+	json_tool="yq"
+	json_args="--unwrapScalar"
+else
+	echo -e "One of 'yq' or 'jq' is required. Please try again after \
+installing one of them"
+	exit 1
+fi
+
+if [[ ! "${UID}" -eq 0 ]] && ! command -v sudo >/dev/null; then
+	# Not root and sudo doesn't exist
+	echo "sudo does not exist. Please run this as root"
+	exit 1
+fi
+
+SUDO="sudo"
+if [[ "${UID}" -eq 0 ]]; then
+	# Don't use sudo if root
+	SUDO=""
+fi
+
+[[ ! -d "${data_dir}" ]] && mkdir --parents "${data_dir}"
+
+if [[ $# -ne 0 ]]; then
+	devices="${1}"
+else
+	devices="$(smartctl --scan --json | "${json_tool}" "${json_args}" \
+".devices[].name | select(test(\"${smartctl_ignore_dev_regex}\") | not)")"
+  mapfile -t devices <<< "${devices[@]}"
+fi
+
+for device in "${devices[@]}"
+  do
+	echo -n "Collecting data for '${device}'..."
+	# shellcheck disable=SC2086
+	data="$($SUDO smartctl ${smartctl_args} ${device})"
+	# Accommodate a smartmontools pre-7.3 bug
+	data=${data#"  Pending defect count:"}
+	type="$(echo "${data}" | "${json_tool}" "${json_args}" '.device.type')"
+	family="$(echo "${data}" | "${json_tool}" "${json_args}" \
+'select(.model_family != null) | .model_family | sub(" |/" ; "_" ; "g")
+ | sub("\"|\\(|\\)" ; "" ; "g")')"
+	model="$(echo "${data}" | "${json_tool}" "${json_args}" \
+'.model_name | sub(" |/" ; "_" ; "g") | sub("\"|\\(|\\)" ; "" ; "g")')"
+	device_name="$(basename "${device}")"
+	echo -e "\tSaving to ${device_name}.json"
+	echo "${data}" > "${data_dir}/${device_name}.json"
+done

collect-smartctl-json.timer

@@ -0,0 +1,9 @@
+[Unit]
+Description=Collect SMART data
+
+[Timer]
+OnCalendar=hourly
+Persistent=true
+
+[Install]
+WantedBy=timers.target

compose.expose-ports.yml

@@ -1,13 +0,0 @@
----
-version: "3.8"
-
-services:
-  app:
-    ports:
-      - "9100:9100"
-    deploy:
-
-  cadvisor:
-    ports:
-      - "9101:8080"
-    deploy:

compose.grafana.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:12.4.0
+    image: grafana/grafana:12.4.3
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:
@@ -37,14 +37,14 @@ services:
     deploy:
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
-        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN:-$DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls=true"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls.certresolver=${LETS_ENCRYPT_ENV}"
     healthcheck:
-      test: "wget -q http://localhost:3000/ -O/dev/null"
+      test: "wget -q http://localhost:3000/healthz -O/dev/null"
       interval: 5s
       timeout: 10s
       retries: 3

compose.loki.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   loki:
-    image: grafana/loki:3.6.7
+    image: grafana/loki:3.7.2
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - proxy
@@ -27,7 +27,7 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-loki.loadbalancer.server.port=3100"
         - "traefik.http.routers.${STACK_NAME}-loki.rule=Host(`loki.${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-loki.entrypoints=web-secure"

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v3.10.0
+    image: prom/prometheus:v3.12.0
     secrets:
       - basic_auth
     volumes:
@@ -16,6 +16,8 @@ services:
       - "--web.console.libraries=/usr/share/prometheus/console_libraries"
       - "--web.console.templates=/usr/share/prometheus/consoles"
       - "--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_TIME}"
+      - "--enable-feature=remote-write-receiver"
+      - "--web.enable-remote-write-receiver"
     networks:
       - proxy
       - internal
@@ -24,12 +26,13 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-prometheus.loadbalancer.server.port=9090"
         - "traefik.http.routers.${STACK_NAME}-prometheus.rule=Host(`prometheus.${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.middlewares=basicauth@file"
 
 configs:
   prometheus_yml:

compose.promtail.yml

@@ -1,30 +0,0 @@
-version: "3.8"
-
-services:
-  promtail:
-    image: grafana/promtail:3.6.7
-    volumes:
-      - /var/log:/var/log:ro
-      - /var/run/docker.sock:/var/run/docker.sock
-    command: -config.file=/etc/promtail/config.yml
-    configs:
-      - source: promtail_yml
-        target: /etc/promtail/config.yml
-    networks:
-      - internal
-    secrets:
-      - basic_auth
-    environment:
-      - DOMAIN
-      - LOKI_PUSH_URL
-
-configs:
-  promtail_yml:
-    name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
-    file: promtail.yml.tmpl
-    template_driver: golang
-
-secrets:
-  basic_auth:
-    external: true
-    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

compose.pushgateway.yml

@@ -17,7 +17,7 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-pushgateway.loadbalancer.server.port=9191"
         - "traefik.http.routers.${STACK_NAME}-pushgateway.rule=Host(`pushgateway.${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-pushgateway.entrypoints=web-secure"

compose.smartctl.yml

@@ -0,0 +1,18 @@
+---
+version: "3.8"
+services:
+  smartctl:
+    image: "prometheuscommunity/smartctl-exporter:v0.14.0"
+    volumes:
+    - "/dev:/dev"
+    - "/var/lib/smartmontools/json:/debug"
+    command:
+    - "--smartctl.fake-data"
+    - "--smartctl.interval=1h"
+    networks:
+    - "proxy"
+    deploy:
+      labels:
+        - "prometheus.io/scrape=true"
+        - "prometheus.io/port=9633"
+        - "prometheus.io/path=/metrics"

compose.syslog.yml

@@ -0,0 +1,6 @@
+---
+version: "3.8"
+services:
+  app:
+    ports:
+    - "514:514"

compose.yml

@@ -3,89 +3,53 @@ version: "3.8"
 
 services:
   app:
-    image: prom/node-exporter:v1.10.2
+    image: grafana/alloy:v1.16.1
-    user: root
+    hostname: "${DOMAIN}"
-    environment:
-      - NODE_ID={{.Node.ID}}
-    volumes:
-      - /proc:/host/proc:ro
-      - /sys:/host/sys:ro
-      - /:/rootfs:ro
-      - /etc/hostname:/etc/nodename:ro
-    command:
-      - "--path.sysfs=/host/sys"
-      - "--path.procfs=/host/proc"
-      - "--path.rootfs=/rootfs"
-      - "--collector.textfile.directory=/etc/node-exporter/"
-      - "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)"
-      - "--no-collector.ipvs"
     configs:
-      - source: entrypoint
+      - source: config_alloy
-        target: /entrypoint.sh
+        target: /etc/alloy/config.alloy
+    volumes:
+      - /:/rootfs:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - /sys:/sys:ro
+      - /var/lib/docker:/var/lib/docker:ro
+      - alloy-data:/var/lib/alloy/data
+    command:
+      - "run"
+      - "--storage.path=/var/lib/alloy/data"
+      - "--server.http.listen-addr=0.0.0.0:12345"
+      - "/etc/alloy/config.alloy"
     networks:
-      - internal
       - proxy
-    entrypoint: [ "/bin/sh", "-e", "/entrypoint.sh" ]
+      - internal
+    secrets:
+      - basic_auth
     deploy:
       restart_policy:
         condition: on-failure
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
-        - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
-        - "traefik.http.services.${STACK_NAME}-node.loadbalancer.server.port=9100"
-        - "traefik.http.routers.${STACK_NAME}-node.rule=Host(`node.${DOMAIN}`)"
-        - "traefik.http.routers.${STACK_NAME}-node.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}-node.tls=true"
-        - "traefik.http.routers.${STACK_NAME}-node.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - "traefik.http.routers.${STACK_NAME}-node.middlewares=basicauth@file"
         - "coop-cloud.${STACK_NAME}.version=1.6.0+v1.8.1"
-        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT}"
-
-  cadvisor:
-    image: gcr.io/cadvisor/cadvisor:v0.55.1
-    command:
-      - "-logtostderr"
-      - "--enable_metrics=cpu,cpuLoad,disk,diskIO,process,memory,network"
-      # all possible metrics: advtcp,app,cpu,cpuLoad,cpu_topology,cpuset,disk,diskIO,hugetlb,memory,memory_numa,network,oom_event,percpu,perf_event,process,referenced_memory,resctrl,sched,tcp,udp.
-      - "--housekeeping_interval=120s"
-      - "--docker_only=true"
-    volumes:
-      - /var/lib/docker/:/var/lib/docker:ro
-      - /dev/disk/:/dev/disk:ro
-      - /sys:/sys:ro
-      - /var/run:/var/run:ro
-      - /:/rootfs:ro
-    networks:
-      - internal
-      - proxy
-    deploy:
-      restart_policy:
-        condition: on-failure
-      labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
-        - "traefik.http.services.${STACK_NAME}-cadvisor.loadbalancer.server.port=8080"
+        - "traefik.http.services.${STACK_NAME}-alloy.loadbalancer.server.port=12345"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.rule=Host(`cadvisor.${DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-alloy.rule=Host(`alloy.${DOMAIN}`)"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.entrypoints=web-secure"
+        - "traefik.http.routers.${STACK_NAME}-alloy.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.tls=true"
+        - "traefik.http.routers.${STACK_NAME}-alloy.tls=true"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.routers.${STACK_NAME}-alloy.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.middlewares=basicauth@file"
+        - "traefik.http.routers.${STACK_NAME}-alloy.middlewares=basicauth@file"
-    healthcheck:
-      test: wget --quiet --tries=1 --spider http://localhost:8080/healthz || exit 1
-      interval: 15s
-      timeout: 15s
-      retries: 5
-      start_period: 30s
-
 configs:
-  entrypoint:
+  config_alloy:
-    name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
+    template_driver: golang
-    file: node-exporter-entrypoint.sh
+    name: ${STACK_NAME}_config_alloy_${CONFIG_ALLOY_VERSION}
-
+    file: config.alloy.tmpl
-
-
 networks:
   proxy:
     external: true
   internal:
+volumes:
+  alloy-data:
+secrets:
+  basic_auth:
+    external: true
+    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

config.alloy.tmpl

@@ -0,0 +1,266 @@
+logging {
+  level = "info"
+  format = "logfmt"
+}
+
+livedebugging {
+  enabled = {{ env "LIVE_DEBUGGING" }}
+}
+
+discovery.docker "linux" {
+  host = "unix:///var/run/docker.sock"
+}
+
+{{ if ne (env "PROMETHEUS_REMOTE_WRITE_URL") "" }}
+prometheus.exporter.cadvisor "docker" {
+  docker_only = true
+  enabled_metrics = ["cpu", "cpuLoad", "disk", "diskIO", "memory", "network", "process"]
+}
+
+prometheus.exporter.unix "default" {
+  include_exporter_metrics = true
+  rootfs_path = "/rootfs"
+  procfs_path = "/rootfs/proc"
+  sysfs_path = "/rootfs/sys"
+
+  disable_collectors = ["ipvs"]
+
+  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)$"
+    mount_points_exclude = "^/(sys|proc|dev|host|etc)($|/)"
+    mount_timeout        = "5s"
+  }
+
+  netclass { ignored_devices = "^(veth.*)$" }
+  netdev   { device_exclude  = "^(veth.*)$" }
+}
+
+prometheus.exporter.self "alloy" {}
+
+prometheus.scrape "default" {
+  scrape_interval = "120s"
+
+  targets = array.concat(
+    prometheus.exporter.self.alloy.targets,
+    prometheus.exporter.unix.default.targets,
+    prometheus.exporter.cadvisor.docker.targets,
+    discovery.docker.containers.targets,
+  )
+
+  forward_to = [prometheus.remote_write.prometheus.receiver]
+}
+
+prometheus.remote_write "prometheus" {
+  endpoint {
+    url = "{{ env "PROMETHEUS_REMOTE_WRITE_URL" }}"
+
+    basic_auth {
+      username = "admin"
+      password = "{{ secret "basic_auth" }}"
+    }
+  }
+}
+
+discovery.docker "containers" {
+  host                = "unix:///var/run/docker.sock"
+  match_first_network = false
+}
+
+// Scrape Prometheus metrics from other containers on this host.
+// Containers opt in via Docker labels:
+//   prometheus.io/scrape=true        required: enable scraping
+//   prometheus.io/port=9090          optional: port exposing /metrics (defaults to first exposed port)
+//   prometheus.io/path=/metrics      optional: path to metrics endpoint (default: /metrics)
+//   prometheus.io/auth=basic         optional: use basic auth with the shared basic_auth secret
+discovery.dockerswarm "swarm" {
+  host = "unix:///var/run/docker.sock"
+  role = "services"
+}
+
+discovery.relabel "metrics" {
+  targets = discovery.dockerswarm.swarm.targets
+
+  rule {
+    source_labels = ["__meta_dockerswarm_network_name"]
+    regex         = "proxy"
+    action        = "keep"
+  }
+
+  rule {
+    source_labels = ["__meta_dockerswarm_service_label_prometheus_io_scrape"]
+    regex         = "true"
+    action        = "keep"
+  }
+
+  rule {
+    source_labels = ["__address__", "__meta_dockerswarm_service_label_prometheus_io_port"]
+    regex         = `(.+):\d+;(\d+)`
+    target_label  = "__address__"
+    replacement   = "$1:$2"
+  }
+
+  rule {
+    source_labels = ["__meta_dockerswarm_service_label_prometheus_io_path"]
+    regex         = `(.+)`
+    target_label  = "__metrics_path__"
+  }
+
+  rule {
+    source_labels = ["__meta_dockerswarm_service_name"]
+    target_label  = "job"
+  }
+}
+
+discovery.relabel "metrics_noauth" {
+  targets = discovery.relabel.metrics.output
+  rule {
+    source_labels = ["__meta_dockerswarm_service_label_prometheus_io_auth"]
+    regex         = "^$"
+    action        = "keep"
+  }
+}
+
+discovery.relabel "metrics_basicauth" {
+  targets = discovery.relabel.metrics.output
+  rule {
+    source_labels = ["__meta_dockerswarm_service_label_prometheus_io_auth"]
+    regex         = "basic"
+    action        = "keep"
+  }
+}
+
+discovery.relabel "metrics_bearerauth" {
+  targets = discovery.relabel.metrics.output
+  rule {
+    source_labels = ["__meta_dockerswarm_service_label_prometheus_io_auth"]
+    regex         = "bearer"
+    action        = "keep"
+  }
+}
+
+prometheus.scrape "containers" {
+  scrape_interval = "120s"
+  targets         = discovery.relabel.metrics_noauth.output
+  forward_to      = [prometheus.remote_write.prometheus.receiver]
+}
+
+prometheus.scrape "containers_basicauth" {
+  scrape_interval = "120s"
+  targets         = discovery.relabel.metrics_basicauth.output
+  forward_to      = [prometheus.remote_write.prometheus.receiver]
+  basic_auth {
+    username = "admin"
+    password = "{{ secret "basic_auth" }}"
+  }
+}
+
+prometheus.scrape "containers_bearerauth" {
+  scrape_interval = "120s"
+  targets         = discovery.relabel.metrics_bearerauth.output
+  forward_to      = [prometheus.remote_write.prometheus.receiver]
+  bearer_token    = "{{ secret "basic_auth" }}"
+}
+{{ end }}
+
+{{ if ne (env "LOKI_PUSH_URL") "" }}
+discovery.relabel "docker" {
+  targets = discovery.docker.linux.targets
+
+  rule {
+    source_labels = ["__meta_docker_container_name"]
+    target_label  = "container_name"
+  }
+  rule {
+    source_labels = ["__meta_docker_container_id"]
+    target_label  = "container_id"
+  }
+  rule {
+    source_labels = ["__meta_docker_container_label_com_docker_stack_namespace"]
+    target_label  = "stack_namespace"
+  }
+  rule {
+    source_labels = ["__meta_docker_container_label_com_docker_swarm_service_name"]
+    target_label  = "service_name"
+  }
+  rule {
+    source_labels = ["__meta_docker_container_log_stream"]
+    target_label  = "stream"
+  }
+}
+
+loki.source.docker "docker" {
+  host       = "unix:///var/run/docker.sock"
+  targets    = discovery.relabel.docker.output
+  labels     = {"app" = "docker"}
+  forward_to = [loki.write.loki.receiver]
+}
+
+// JOURNALD: reads the systemd journal binary log directly.
+// Use on systemd hosts (most modern Linux distros). Requires no syslogd.
+{{ if eq (env "JOURNALD") "1" }}
+loki.source.journal "journal" {
+  path = "/rootfs/var/log/journal"
+  labels = { job = "{{ env "DOMAIN" }}" }
+  forward_to = [loki.write.loki.receiver]
+}
+{{ end }}
+
+// SYSLOG_FILES: tails all /var/log/*log files (syslog, auth.log, kern.log, etc.).
+// Use on non-systemd hosts where a syslogd writes to /var/log.
+{{ if eq (env "SYSLOG_FILES") "1" }}
+local.file_match "syslog_files" {
+  path_targets = [{ __path__ = "/rootfs/var/log/*log" }]
+}
+
+loki.source.file "syslog_files" {
+  targets    = local.file_match.syslog_files.targets
+  forward_to = [loki.process.syslog_files.receiver]
+}
+
+loki.process "syslog_files" {
+  stage.static_labels {
+    values = { job = "syslog" }
+  }
+  forward_to = [loki.write.loki.receiver]
+}
+{{ end }}
+
+// SYSLOG: opens a network syslog listener on port 514.
+// Use when a remote device or a local syslogd configured to 
+// forward over the network sends logs to this host.
+// Requires compose.syslog.yml to publish port 514 to the host.
+// This is NOT needed for reading local log files — use SYSLOG_FILES instead.
+{{ if eq (env "SYSLOG") "1" }}
+loki.relabel "syslog" {
+  rule {
+    action = "labelmap"
+    regex = "__syslog_(.+)"
+  }
+
+  forward_to = []
+}
+
+loki.source.syslog "syslog" {
+  listener {
+    address = "[::]:514"
+    label_structured_data = true
+    labels = { component = "loki.source.syslog" }
+  }
+
+  relabel_rules = loki.relabel.syslog.rules
+  forward_to = [loki.write.loki.receiver]
+}
+{{ end }}
+
+loki.write "loki" {
+  endpoint {
+    url = "{{ env "LOKI_PUSH_URL" }}"
+
+    basic_auth {
+      username = "admin"
+      password = "{{ secret "basic_auth" }}"
+    }
+  }
+  external_labels = { hostname = "{{ env "DOMAIN" }}" }
+}
+{{ end }}

node-exporter-entrypoint.sh

@@ -1,11 +0,0 @@
-#!/bin/sh -e
-
-NODE_NAME=$(cat /etc/nodename)
-
-mkdir -p /etc/node-exporter
-
-echo "node_meta{node_id=\"$NODE_ID\", container_label_com_docker_swarm_node_id=\"$NODE_ID\", node_name=\"$NODE_NAME\"} 1" > /etc/node-exporter/node-meta.prom
-
-set -- /bin/node_exporter "$@"
-
-exec "$@"

promtail.yml.tmpl

@@ -1,37 +0,0 @@
-server:
-  http_listen_port: 9080
-  grpc_listen_port: 0
-
-positions:
-  filename: /tmp/positions.yaml
-
-clients:
-  - url: {{ env "LOKI_PUSH_URL" }}
-    basic_auth:
-      username: admin
-      password: {{ secret "basic_auth" }}
-    external_labels:
-      hostname: {{ env "DOMAIN" }}
-
-scrape_configs:
-- job_name: system
-  static_configs:
-  - targets:
-      - localhost
-    labels:
-      job: varlogs
-      __path__: /var/log/*log
-
-- job_name: "docker"
-  docker_sd_configs:
-    - host: "unix:///var/run/docker.sock"
-      refresh_interval: "10s"
-  relabel_configs:
-    - source_labels: ['__meta_docker_container_name']
-      target_label: "container_name"
-    - source_labels: ['__meta_docker_container_id']
-      target_label: "container_id"
-    - source_labels: ['__meta_docker_container_label_com_docker_stack_namespace']
-      target_label: "stack_namespace"
-    - source_labels: ['__meta_docker_container_label_com_docker_swarm_service_name']
-      target_label: "service_name"