From 7c52a9dc34d60a6ec60a5d2e8b384dd285a1123e Mon Sep 17 00:00:00 2001
From: Marcus Noble <github@marcusnoble.co.uk>
Date: Sat, 20 Sep 2025 08:43:59 +0100
Subject: [PATCH] Added cadvisor

Signed-off-by: Marcus Noble <github@marcusnoble.co.uk>
---
 manifests/monitoring/cadvisor.yaml | 87 ++++++++++++++++++++++++++++++
 manifests/monitoring/vmagent.yaml  | 33 ++++++++++++
 2 files changed, 120 insertions(+)
 create mode 100644 manifests/monitoring/cadvisor.yaml

diff --git a/manifests/monitoring/cadvisor.yaml b/manifests/monitoring/cadvisor.yaml
new file mode 100644
index 0000000..1e77bf3
--- /dev/null
+++ b/manifests/monitoring/cadvisor.yaml
@@ -0,0 +1,87 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    app: cadvisor
+    app.kubernetes.io/name: cadvisor
+  name: cadvisor
+  namespace: monitoring
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  annotations:
+    seccomp.security.alpha.kubernetes.io/pod: docker/default
+  labels:
+    app: cadvisor
+    app.kubernetes.io/name: cadvisor
+  name: cadvisor
+  namespace: monitoring
+spec:
+  selector:
+    matchLabels:
+      app: cadvisor
+      app.kubernetes.io/name: cadvisor
+      name: cadvisor
+  template:
+    metadata:
+      labels:
+        app: cadvisor
+        app.kubernetes.io/name: cadvisor
+        name: cadvisor
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      priorityClassName: system-node-critical
+      tolerations:
+        - key: "CriticalAddonsOnly"
+          operator: "Exists"
+      automountServiceAccountToken: false
+      containers:
+      - image: ghcr.io/google/cadvisor:v0.53.0
+        name: cadvisor
+        ports:
+        - containerPort: 8080
+          name: http
+          protocol: TCP
+        resources:
+          limits:
+            cpu: 800m
+            memory: 2000Mi
+          requests:
+            cpu: 400m
+            memory: 400Mi
+        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
+      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
diff --git a/manifests/monitoring/vmagent.yaml b/manifests/monitoring/vmagent.yaml
index e04360e..fc0c186 100644
--- a/manifests/monitoring/vmagent.yaml
+++ b/manifests/monitoring/vmagent.yaml
@@ -17,6 +17,7 @@ data:
     - job_name: 'vmagent'
       static_configs:
         - targets: ['localhost:8429']
+
     - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
       job_name: kubernetes-nodes
       kubernetes_sd_configs:
@@ -36,6 +37,38 @@ data:
         ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
         insecure_skip_verify: true
 
+    - job_name: cadvisor
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        insecure_skip_verify: true
+      kubernetes_sd_configs:
+      - role: node
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - replacement: kubernetes.default.svc:443
+        target_label: __address__
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
+      # Drop high cardinality labels
+      - action: labeldrop
+        regex: id
+      # Drop unneeded labels
+      - action: labeldrop
+        regex: beta_kubernetes_io_os
+      - action: labeldrop
+        regex: beta_kubernetes_io_arch
+      - action: labeldrop
+        regex: kubernetes_io_arch
+      - action: labeldrop
+        regex: kubernetes_io_os
+      - action: labeldrop
+        regex: topology_jiva_openebs_io_nodeName
+
     - job_name: kubernetes-service-endpoints
       kubernetes_sd_configs:
       - role: endpoints