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>

k8s/tempo/deployment.yaml

@@ -0,0 +1,79 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: tempo
+  namespace: observability
+  labels:
+    app.kubernetes.io/name: tempo
+    app.kubernetes.io/component: traces
+    app.kubernetes.io/part-of: observability
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: tempo
+  template:
+    metadata:
+      labels:
+        app: tempo
+        app.kubernetes.io/name: tempo
+        app.kubernetes.io/component: traces
+        app.kubernetes.io/part-of: observability
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "3200"
+    spec:
+      securityContext:
+        runAsUser: 10001
+        runAsGroup: 10001
+        fsGroup: 10001
+      containers:
+        - name: tempo
+          image: grafana/tempo:3.0.3
+          args:
+            - -config.file=/etc/tempo/tempo.yaml
+            - -target=all
+          ports:
+            - name: http
+              containerPort: 3200
+            - name: grpc
+              containerPort: 9095
+            - name: otlp-grpc
+              containerPort: 4317
+            - name: otlp-http
+              containerPort: 4318
+            - name: zipkin
+              containerPort: 9411
+          resources:
+            requests:
+              cpu: 100m
+              memory: 512Mi
+            limits:
+              cpu: "2"
+              memory: 2Gi
+          readinessProbe:
+            httpGet:
+              path: /ready
+              port: http
+            initialDelaySeconds: 30
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /ready
+              port: http
+            initialDelaySeconds: 60
+            periodSeconds: 30
+          volumeMounts:
+            - name: config
+              mountPath: /etc/tempo
+            - name: data
+              mountPath: /var/tempo
+      volumes:
+        - name: config
+          configMap:
+            name: tempo-config
+        - name: data
+          persistentVolumeClaim:
+            claimName: tempo-data

k8s/tempo/kustomization.yaml

@@ -0,0 +1,18 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: observability
+
+resources:
+  - pvc.yaml
+  - deployment.yaml
+  - service.yaml
+
+configMapGenerator:
+  - name: tempo-config
+    files:
+      - tempo.yaml
+
+generatorOptions:
+  labels:
+    app.kubernetes.io/name: tempo
+    app.kubernetes.io/part-of: observability

k8s/tempo/pvc.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: tempo-data
+  namespace: observability
+  labels:
+    app.kubernetes.io/name: tempo
+    app.kubernetes.io/component: storage
+    app.kubernetes.io/part-of: observability
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 10Gi

k8s/tempo/service.yaml

@@ -0,0 +1,29 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: tempo
+  namespace: observability
+  labels:
+    app.kubernetes.io/name: tempo
+    app.kubernetes.io/component: traces
+    app.kubernetes.io/part-of: observability
+spec:
+  type: ClusterIP
+  selector:
+    app: tempo
+  ports:
+    - name: http
+      port: 3200
+      targetPort: http
+    - name: grpc
+      port: 9095
+      targetPort: grpc
+    - name: otlp-grpc
+      port: 4317
+      targetPort: otlp-grpc
+    - name: otlp-http
+      port: 4318
+      targetPort: otlp-http
+    - name: zipkin
+      port: 9411
+      targetPort: zipkin

k8s/tempo/tempo.yaml

@@ -0,0 +1,64 @@
+# Tempo 3.x in monolithic mode (-target=all), local storage on a PVC.
+stream_over_http_enabled: true
+multitenancy_enabled: false
+
+server:
+  http_listen_address: 0.0.0.0
+  http_listen_port: 3200
+  grpc_listen_address: 0.0.0.0
+  grpc_listen_port: 9095
+  log_level: info
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+    zipkin:
+      endpoint: 0.0.0.0:9411
+
+# Generates span metrics and service graphs, pushed to Prometheus through its
+# remote-write receiver (--web.enable-remote-write-receiver).
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+      cluster: orbstack
+  storage:
+    path: /var/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+        send_exemplars: true
+
+query_frontend:
+  search:
+    duration_slo: 5s
+    throughput_bytes_slo: 1073741824
+  trace_by_id:
+    duration_slo: 5s
+
+storage:
+  trace:
+    backend: local
+    wal:
+      path: /var/tempo/wal
+    local:
+      path: /var/tempo/blocks
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors:
+        - service-graphs
+        - span-metrics
+      generate_native_histograms: both
+    # Tempo 3.x: retention is no longer a top-level `compactor:` block; it is
+    # driven from here (backend_scheduler/backend_worker otherwise).
+    compaction:
+      block_retention: 168h
+
+usage_report:
+  reporting_enabled: false