add cadvisor

argocd/infra/cadvisor/cadvisor.yaml

@@ -0,0 +1,89 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  labels:
+    app: cadvisor
+  name: cadvisor
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    app: cadvisor
+  name: cadvisor
+  namespace: cadvisor
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  annotations:
+    seccomp.security.alpha.kubernetes.io/pod: docker/default
+  labels:
+    app: cadvisor
+  name: cadvisor
+  namespace: cadvisor
+spec:
+  selector:
+    matchLabels:
+      app: cadvisor
+      name: cadvisor
+  template:
+    metadata:
+      labels:
+        app: cadvisor
+        name: cadvisor
+    spec:
+      automountServiceAccountToken: false
+      containers:
+      - image: ghcr.io/google/cadvisor:0.60.6
+        name: cadvisor
+        ports:
+        - containerPort: 8080
+          name: http
+          protocol: TCP
+        resources:
+          limits:
+            cpu: 800m
+            memory: 2000Mi
+          requests:
+            cpu: 0
+            memory: 0
+        volumeMounts:
+        - mountPath: /rootfs
+          name: rootfs
+          readOnly: true
+        - mountPath: /var/run
+          name: var-run
+          readOnly: true
+        - mountPath: /sys
+          name: sys
+          readOnly: true
+        - mountPath: /var/lib/docker
+          name: docker
+          readOnly: true
+        - mountPath: /dev/disk
+          name: disk
+          readOnly: true
+      tolerations:
+        - key: storage-node
+          operator: Equal
+          value: "true"
+          effect: NoSchedule
+      serviceAccountName: cadvisor
+      terminationGracePeriodSeconds: 30
+      volumes:
+      - hostPath:
+          path: /
+        name: rootfs
+      - hostPath:
+          path: /var/run
+        name: var-run
+      - hostPath:
+          path: /sys
+        name: sys
+      - hostPath:
+          path: /var/lib/docker
+        name: docker
+      - hostPath:
+          path: /dev/disk
+        name: disk

argocd/infra/monitoring/prometheus/targets/cadvisor.yaml

@@ -0,0 +1,18 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PodMonitor
+metadata:
+  labels:
+    app: cadvisor
+    name: cadvisor
+  name: cadvisor
+  namespace: monitoring
+spec:
+  podMetricsEndpoints:
+  - port: http
+  namespaceSelector:
+    matchNames:
+    - cadvisor
+  selector:
+    matchLabels:
+      app: cadvisor
+

argocd/infra/monitoring/prometheus/targets/traefik-servicemonitor.yaml

@@ -1,17 +0,0 @@
-apiVersion: monitoring.coreos.com/v1
-kind: ServiceMonitor
-metadata:
-  labels:
-    app: traefik
-    name: traefik
-  name: traefik
-  namespace: monitoring
-spec:
-  endpoints:
-  - port: metrics
-  namespaceSelector:
-    matchNames:
-    - kube-system
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: traefik

argocd/rook/rook-ceph-operator-values.yaml

@@ -174,6 +174,7 @@ csi:
       value: "true"
       effect: NoSchedule
 
+  # TODO (Oct 2026) not seeing sidecar
   # -- Enable Ceph CSI Liveness sidecar deployment
   enableLiveness: true