Establish clean homelab infrastructure baseline

Reorganize the brownfield repository, remove retired and generated artifacts, harden ignore rules, and record the GitOps/IaC redesign.
2026-09-09 16:47:20 +00:00
commit 88a02ababa
418 changed files with 50579 additions and 0 deletions
@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# kube-state-metrics — metrics about k8s objects (deployments, pods, nodes, PVCs, ...).
+# Its chart ships a ServiceMonitor; the VM operator's Prometheus converter turns that
+# into a VMServiceScrape automatically, so no hand-written scrape CR is needed here.
+#
+# Prereq: the Prometheus-operator CRDs (ServiceMonitor, ...) must exist in the cluster
+# for `serviceMonitor.enabled` to apply. If they don't:
+#   kubectl apply --server-side -f \
+#     https://github.com/prometheus-operator/prometheus-operator/releases/latest/download/bundle.yaml \
+#     # (or just the monitoring.coreos.com CRDs)
+# Alternatively, disable the ServiceMonitor below and add a VMServiceScrape by hand.
+set -euo pipefail
+
+helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+helm repo update prometheus-community
+
+helm upgrade --install kube-state-metrics prometheus-community/kube-state-metrics \
+  --namespace monitoring \
+  --set prometheus.monitor.enabled=true \
+  --wait
@@ -0,0 +1,67 @@
+# Host metrics (CPU/mem/disk/net/filesystem) for every node. node-exporter has no
+# ServiceMonitor of its own here, so we scrape it directly with a VMNodeScrape:
+# vmagent discovers each Node and scrapes its InternalIP:9100.
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: node-exporter
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: node-exporter
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: node-exporter
+    spec:
+      hostNetwork: true          # bind 9100 on the node so VMNodeScrape can reach it
+      hostPID: true
+      tolerations:
+        - operator: Exists       # run on control-plane / tainted nodes too
+      containers:
+        - name: node-exporter
+          image: quay.io/prometheus/node-exporter:v1.9.1
+          args:
+            - --path.procfs=/host/proc
+            - --path.sysfs=/host/sys
+            - --path.rootfs=/host/root
+            - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
+          ports:
+            - name: metrics
+              containerPort: 9100
+              hostPort: 9100
+          resources:
+            requests:
+              cpu: 25m
+              memory: 32Mi
+            limits:
+              cpu: 200m
+              memory: 128Mi
+          volumeMounts:
+            - { name: proc, mountPath: /host/proc, readOnly: true }
+            - { name: sys, mountPath: /host/sys, readOnly: true }
+            - { name: root, mountPath: /host/root, readOnly: true, mountPropagation: HostToContainer }
+      volumes:
+        - { name: proc, hostPath: { path: /proc } }
+        - { name: sys, hostPath: { path: /sys } }
+        - { name: root, hostPath: { path: / } }
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMNodeScrape
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/part-of: victoria-metrics
+spec:
+  port: "9100"
+  scheme: http
+  interval: 30s
+  relabelConfigs:
+    - action: labelmap
+      regex: __meta_kubernetes_node_label_(.+)
+    - targetLabel: job
+      replacement: node-exporter