feat: add observability stack to gitops (kube-prom-stack, loki, helm-dashboard, blackbox-exporter)

2026-04-29 13:33:35 +02:00
parent befea76e7e
commit 86feb58574
7 changed files with 209 additions and 0 deletions
@@ -0,0 +1,72 @@
+grafana:
+  additionalDataSources:
+  - name: loki
+    type: loki
+    url: http://loki.observability.svc.cluster.local:3100
+  ingress:
+    enabled: true
+    ingressClassName: public
+    hosts:
+    - grafana.alexandre-vazquez.cloud
+    annotations:
+      external-dns.alpha.kubernetes.io/hostname: grafana.alexandre-vazquez.internal
+  additionalIngresses:
+  - name: grafana-ingress-internal
+    ingressClassName: public
+    hosts:
+    - grafana.alexandre-vazquez.internal
+    annotations:
+      external-dns.alpha.kubernetes.io/hostname: grafana.alexandre-vazquez.internal
+
+kubeApiServer:
+  serviceMonitor:
+    metricRelabelings:
+    - action: drop
+      sourceLabels: [__name__]
+      regex: apiserver_request_duration_seconds_bucket|apiserver_request_sli_duration_seconds_bucket|apiserver_request_body_size_bytes_bucket|apiserver_response_sizes_bucket|apiserver_watch_list_duration_seconds_bucket|apiserver_watch_cache_read_wait_seconds_bucket|apiserver_watch_events_sizes_bucket|apiserver_admission_controller_admission_duration_seconds_bucket|apiserver_admission_webhook_admission_duration_seconds_bucket|apiserver_flowcontrol_request_execution_seconds_bucket|apiserver_flowcontrol_request_wait_duration_seconds_bucket
+
+kubeControllerManager:
+  endpoints:
+  - 192.168.1.40
+  serviceMonitor:
+    metricRelabelings:
+    - action: drop
+      sourceLabels: [__name__]
+      regex: workqueue_queue_duration_seconds_bucket|workqueue_work_duration_seconds_bucket|storage_operation_duration_seconds_bucket|rest_client_request_duration_seconds_bucket
+
+kubeEtcd:
+  serviceMonitor:
+    metricRelabelings:
+    - action: drop
+      sourceLabels: [__name__]
+      regex: etcd_request_duration_seconds_bucket|etcd_disk_backend_commit_duration_seconds_bucket|etcd_disk_wal_fsync_duration_seconds_bucket|etcd_network_peer_round_trip_time_seconds_bucket
+
+kubeScheduler:
+  endpoints:
+  - 192.168.1.40
+  serviceMonitor:
+    metricRelabelings:
+    - action: drop
+      sourceLabels: [__name__]
+      regex: scheduler_plugin_execution_duration_seconds_bucket|scheduler_scheduling_algorithm_duration_seconds_bucket|scheduler_pod_scheduling_duration_seconds_bucket|scheduler_framework_extension_point_duration_seconds_bucket
+
+kubelet:
+  serviceMonitor:
+    metricRelabelings:
+    - action: drop
+      sourceLabels: [__name__]
+      regex: storage_operation_duration_seconds_bucket|rest_client_request_duration_seconds_bucket|kubelet_runtime_operations_duration_seconds_bucket|kubelet_cgroup_manager_duration_seconds_bucket|kubelet_pod_start_duration_seconds_bucket|kubelet_pod_worker_duration_seconds_bucket
+
+prometheus:
+  prometheusSpec:
+    evaluationInterval: 60s
+    scrapeInterval: 60s
+    storageSpec:
+      volumeClaimTemplate:
+        spec:
+          accessModes:
+          - ReadWriteOnce
+          storageClassName: ceph-rbd
+          resources:
+            requests:
+              storage: 20Gi