monitoring: Bestandsaufnahme des laufenden Stacks

Import des bisherigen Stands aus /opt/monitoring auf dem Operating-Host,
unveraendert. Images auf :latest, Grafana ohne Provisioning (Datasources und
Dashboards nur in der grafana.db), keine Dokumentation.

Dient als Ausgangspunkt fuer den Umbau auf einen vollstaendig
provisionierbaren Stack.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

.gitignore

@@ -0,0 +1 @@
+.env

monitoring/alloy/config.alloy

@@ -0,0 +1,26 @@
+discovery.docker "linux_containers" {
+  host = "unix:///var/run/docker.sock"
+}
+
+loki.source.docker "docker_logs" {
+  host       = "unix:///var/run/docker.sock" // Diesen Wert habe ich hinzugefügt
+  targets    = discovery.docker.linux_containers.targets
+  forward_to = [loki.write.local_loki.receiver]
+}
+
+loki.write "local_loki" {
+  endpoint {
+    url = "http://loki:3100/loki/api/v1/push"
+  }
+}
+
+prometheus.scrape "node_exporter" {
+  targets = [{"__address__" = "node-exporter:9100"}]
+  forward_to = [prometheus.remote_write.local_prometheus.receiver]
+}
+
+prometheus.remote_write "local_prometheus" {
+  endpoint {
+    url = "http://prometheus:9090/api/v1/write"
+  }
+}

monitoring/docker-compose.yml

@@ -0,0 +1,100 @@
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    restart: unless-stopped
+    volumes:
+      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=45d'
+      - '--storage.tsdb.retention.size=15GB'
+      - '--web.enable-remote-write-receiver'
+    ports:
+      - "9090:9090"
+    networks:
+      - traefik
+
+  loki:
+    image: grafana/loki:latest
+    container_name: loki
+    restart: unless-stopped
+    volumes:
+      - ./loki/loki-config.yaml:/etc/loki/local-config.yaml:ro
+      - loki_data:/loki
+    command: -config.file=/etc/loki/local-config.yaml
+    ports:
+      - "3100:3100"
+    networks:
+      - traefik
+
+  alloy:
+    image: grafana/alloy:latest
+    container_name: alloy
+    restart: unless-stopped
+    volumes:
+      - ./alloy/config.alloy:/etc/alloy/config.alloy:ro
+      - /var/log:/var/log:ro
+      - /var/lib/docker/containers:/var/lib/docker/containers:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+    command: run --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy
+    cap_add:
+      - DAC_READ_SEARCH
+      - NET_RAW
+    networks:
+      - traefik
+    depends_on:
+      - prometheus
+      - loki
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: grafana
+    restart: unless-stopped
+    environment:
+      - GF_SECURITY_ADMIN_USER=${Grafana_ADMIN}
+      - GF_SECURITY_ADMIN_PASSWORD=${Grafana_ADMIN_PW}
+    volumes:
+      - grafana_data:/var/lib/grafana
+    labels:
+      - "traefik.enable=true"
+      - "traefik.docker.network=traefik"
+      - "traefik.http.routers.grafana.rule=Host(`selendis.axion1337.de`)"
+      - "traefik.http.routers.grafana.entrypoints=websecure"
+      - "traefik.http.routers.grafana.tls.certresolver=le"
+      - "traefik.http.services.grafana.loadbalancer.server.port=3000"
+    depends_on:
+      - prometheus
+      - loki
+    networks:
+      - traefik
+
+  node-exporter:
+    image: prom/node-exporter:latest
+    container_name: node-exporter
+    restart: unless-stopped
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - '--path.rootfs=/rootfs'
+      - '--web.listen-address=:9100'
+      - '--web.disable-exporter-metrics'
+    ports:
+      - "9100:9100"
+    networks:
+      - traefik
+
+volumes:
+  prometheus_data:
+  grafana_data:
+  loki_data:
+
+networks:
+  traefik:
+    external: true

monitoring/loki/loki-config.yaml

@@ -0,0 +1,37 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  instance_addr: 127.0.0.1
+  path_prefix: /loki
+  storage:
+    filesystem:
+      chunks_directory: /loki/chunks
+      rules_directory: /loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+limits_config:
+  retention_period: 2160h
+  # Hier war der Fehler:
+  allow_structured_metadata: true
+
+schema_config:
+  configs:
+    - from: 2024-01-01
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+# Der chunk_store_config Block wurde entfernt, da 'common' das jetzt übernimmt.
+
+table_manager:
+  retention_deletes_enabled: true
+  retention_period: 2160h

monitoring/prometheus/prometheus.yml

@@ -0,0 +1,42 @@
+global:
+  scrape_interval: 15s
+
+# local metrics
+scrape_configs:
+  ## operating server
+  - job_name: "operating_prometheus"
+    static_configs:
+      - targets: ["localhost:9090"]
+
+  - job_name: "operating_node-exporter"
+    static_configs:
+      - targets: ["node-exporter:9100"]
+
+  - job_name: "operating_cadvisor"
+    static_configs:
+      - targets: ["cadvisor:8080"]
+
+  - job_name: "operating_traefik"
+    metrics_path: "/metrics"
+    static_configs:
+      - targets: ["traefik:8080"]
+
+  - job_name: "k3s_host_node"
+    static_configs:
+      - targets: ["10.0.0.2:9100"]
+        labels:
+          instance: "k3s-host"
+
+  - job_name: "pterodactyl_host_node"
+    static_configs:
+      - targets: ["157.90.155.206:9100"]
+        labels:
+          instance: "pterodactyl"
+
+  - job_name: "gameserver_cadvisor"
+    static_configs:
+      - targets: ["157.90.155.206:8080"]
+  ## matrix server (auskommentiert, aber jetzt syntaktisch korrekt eingerückt)
+  # - job_name: "matrix_prometheus"
+  #   static_configs:
+  #     - targets: ["matrix-server-ip:9090"]