Declarative Grafana / Prometheus / Loki / Tempo observability stack

Deploys the whole stack into the observability namespace of the local cluster with Kustomize alone — no helm install, no dashboard created by hand in the UI. The Makefile carries every command: deploy, dashboards, diagnostics, PVC flush, teardown. Dashboards are files, never UI objects. Each carries a stable uid, which is what keeps URLs, cross-links and alerts alive across redeployments, and references datasources by stable uid rather than by name. The dashboard ConfigMap is generated without a name-suffix hash so applying it updates it in place and Grafana reloads without a restart, while the provisioning ConfigMaps keep their hash precisely so that a change there does force one. Prometheus scrapes the kubelet /metrics/resource endpoint rather than /metrics/cadvisor: on this cluster cadvisor exposes machine_* series only and no container_* at all, which would leave every CPU and memory panel empty. Alloy ships every pod's logs to Loki through the Kubernetes API, so no /var/log mount is needed. Tempo's metrics_generator feeds span metrics and the service graph back into Prometheus, and the datasources are wired so a log line's trace_id opens the matching trace. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-25 07:27:38 +02:00
commit 3937b4f366
42 changed files with 7597 additions and 0 deletions
@@ -0,0 +1,85 @@
+# Loki 3.x in monolithic mode (-target=all), filesystem storage on a PVC.
+auth_enabled: false
+
+server:
+  http_listen_address: 0.0.0.0
+  http_listen_port: 3100
+  grpc_listen_address: 0.0.0.0
+  grpc_listen_port: 9096
+  log_level: info
+  grpc_server_max_concurrent_streams: 1000
+
+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
+
+schema_config:
+  configs:
+    - from: "2024-01-01"
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+storage_config:
+  tsdb_shipper:
+    active_index_directory: /loki/tsdb-index
+    cache_location: /loki/tsdb-cache
+  filesystem:
+    directory: /loki/chunks
+
+compactor:
+  working_directory: /loki/compactor
+  retention_enabled: true
+  delete_request_store: filesystem
+  compaction_interval: 10m
+  retention_delete_delay: 2h
+
+limits_config:
+  retention_period: 168h
+  max_query_series: 5000
+  ingestion_rate_mb: 16
+  ingestion_burst_size_mb: 32
+  reject_old_samples: true
+  reject_old_samples_max_age: 168h
+  volume_enabled: true
+  metric_aggregation_enabled: true
+  allow_structured_metadata: true
+
+pattern_ingester:
+  enabled: true
+  metric_aggregation:
+    loki_address: localhost:3100
+
+query_range:
+  align_queries_with_step: true
+  cache_results: true
+  results_cache:
+    cache:
+      embedded_cache:
+        enabled: true
+        max_size_mb: 100
+
+frontend:
+  encoding: protobuf
+
+ruler:
+  storage:
+    type: local
+    local:
+      directory: /loki/rules
+  rule_path: /loki/rules-tmp
+  enable_api: true
+
+analytics:
+  reporting_enabled: false