loki + promtail new monitoring services

monitoring/loki.yaml

@@ -0,0 +1,153 @@
+# Loki — log aggregation (single-binary mode, local filesystem storage).
+#
+# Stores compressed, indexed pod logs shipped by Promtail. Queried by the
+# platform-engineer Hermes agent via the HTTP API (LogQL) and by Grafana.
+#
+# Storage: 20 GiB local PVC, 1-week retention enforced by the compactor.
+# Service: loki.monitoring:3100 (ClusterIP, no auth — homelab).
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: loki-config
+  namespace: monitoring
+data:
+  loki.yaml: |
+    auth_enabled: false
+
+    server:
+      http_listen_port: 3100
+      grpc_listen_port: 9096
+
+    common:
+      path_prefix: /loki
+      replication_factor: 1
+      ring:
+        instance_addr: 127.0.0.1
+        kvstore:
+          store: inmemory
+
+    schema_config:
+      configs:
+        - from: 2024-01-01
+          store: tsdb
+          object_store: filesystem
+          schema: v13
+          index:
+            prefix: index_
+            period: 24h
+
+    storage_config:
+      filesystem:
+        directory: /loki/chunks
+      tsdb_shipper:
+        active_index_directory: /loki/tsdb-index
+        cache_location: /loki/tsdb-cache
+
+    limits_config:
+      retention_period: 168h          # 1 week
+      max_query_series: 10000
+      reject_old_samples: true
+      reject_old_samples_max_age: 168h
+      allow_structured_metadata: false  # tsdb v13 compat
+
+    compactor:
+      working_directory: /loki/compactor
+      compaction_interval: 10m
+      retention_enabled: true
+      retention_delete_delay: 2h
+      retention_delete_worker_count: 50
+      delete_request_store: filesystem
+
+    analytics:
+      reporting_enabled: false
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: loki-data
+  namespace: monitoring
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 20Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: loki
+  namespace: monitoring
+  labels:
+    app: loki
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate          # single-writer storage
+  selector:
+    matchLabels:
+      app: loki
+  template:
+    metadata:
+      labels:
+        app: loki
+    spec:
+      nodeSelector:
+        kubernetes.io/arch: amd64   # Loki image; runs on the NUC
+      containers:
+      - name: loki
+        image: grafana/loki:3.4.4
+        args:
+          - -config.file=/etc/loki/loki.yaml
+        ports:
+        - name: http
+          containerPort: 3100
+        volumeMounts:
+        - name: config
+          mountPath: /etc/loki
+          readOnly: true
+        - name: data
+          mountPath: /loki
+        resources:
+          requests:
+            memory: "512Mi"
+            cpu: "250m"
+          limits:
+            memory: "1Gi"
+            cpu: "1000m"
+        readinessProbe:
+          httpGet:
+            path: /ready
+            port: 3100
+          initialDelaySeconds: 30
+          periodSeconds: 10
+          failureThreshold: 5
+        livenessProbe:
+          httpGet:
+            path: /ready
+            port: 3100
+          initialDelaySeconds: 60
+          periodSeconds: 30
+          failureThreshold: 5
+      volumes:
+      - name: config
+        configMap:
+          name: loki-config
+      - name: data
+        persistentVolumeClaim:
+          claimName: loki-data
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: loki
+  namespace: monitoring
+spec:
+  type: ClusterIP
+  selector:
+    app: loki
+  ports:
+    - name: http
+      port: 3100
+      targetPort: 3100