Merge pull request 'feat(monitoring): add VictoriaMetrics trial stack' (#95) from feat/victoria-metrics-migration into main

Reviewed-on: https://gitea.forust.xyz/forust/homelab/pulls/95

.gitea/workflows/ci.yaml

@@ -294,6 +294,11 @@ jobs:
           echo "server-side dry-run: ${#manifests[@]} manifests, ${#kustomize_apps[@]} kustomize apps"
           failed=0
           for m in ${manifests[@]+"${manifests[@]}"}; do
+            if [[ "$m" == "prometheus-stack/k8s/vmagent.yaml" ]] \
+              && ! kubectl get crd vmagents.operator.victoriametrics.com >/dev/null 2>&1; then
+              echo "skip server-side dry-run until the VictoriaMetrics Operator CRD is installed: $m"
+              continue
+            fi
             if ! out="$(kubectl apply --dry-run=server -f "$m" 2>&1)"; then
               failed=1
               echo "::error file=${m}::$(printf '%s' "$out" | head -1)"

.gitea/workflows/deploy-lib.sh

@@ -546,6 +546,7 @@ rollback_workloads() {
 # have to be declared as custom.regex managers in renovate/renovate.json.
 HELM_RELEASES=(
   "prometheus-stack|prometheus-community/kube-prometheus-stack|prometheus|86.2.3|prometheus-stack/k8s/grafana-values.yaml|prometheus-stack/k8s/active"
+  "victoria-operator|victoriametrics/victoria-metrics-operator|prometheus|0.68.1|prometheus-stack/k8s/victoria-operator-values.yaml|prometheus-stack/k8s/active"
   "loki|grafana/loki|prometheus|7.3.0|loki/k8s/loki-values.yaml|loki/k8s/active"
   "alloy|grafana/alloy|prometheus|1.12.1|loki/k8s/alloy-values.yaml|loki/k8s/active"
   "reloader|stakater/reloader|reloader|2.2.17|reloader/k8s/reloader-values.yaml|reloader/k8s/active"
@@ -557,6 +558,7 @@ helm_repo_for() {
     prometheus-community/*) echo "prometheus-community https://prometheus-community.github.io/helm-charts" ;;
     grafana/*) echo "grafana https://grafana.github.io/helm-charts" ;;
     stakater/*) echo "stakater https://stakater.github.io/stakater-charts" ;;
+    victoriametrics/*) echo "victoriametrics https://victoriametrics.github.io/helm-charts" ;;
   esac
 }
 

prometheus-stack/k8s/README.md

@@ -0,0 +1,17 @@
+# VictoriaMetrics
+
+The `victoria-operator` Helm release converts Prometheus Operator
+`ServiceMonitor` resources into owned `VMServiceScrape` resources. The
+`VMAgent` selects converted scrapes labeled `release: prometheus-stack` in all
+namespaces and writes them to the existing single-node VictoriaMetrics
+instance. Changes to selected `ServiceMonitor` resources are reconciled
+automatically; there is no copied Prometheus scrape-config blob to regenerate.
+
+The agent drops targets for the Prometheus server service to avoid duplicating
+its self-scrape. `scraper: victoria` identifies the samples ingested by this
+VMAgent.
+
+The VictoriaMetrics Operator chart and its CRDs are installed before the
+Kubernetes manifests by the normal deploy workflow. On a cluster where the
+operator CRDs are not installed yet, CI skips the server-side dry-run of the
+`VMAgent` resource; the deploy installs the chart before applying that resource.

prometheus-stack/k8s/grafana-values.yaml

@@ -38,6 +38,8 @@ grafana:
 
   # One block covers both the dashboards and datasources sidecars (p95 91M / 80M).
   sidecar:
+    datasources:
+      defaultDatasourceEnabled: false
     resources:
       requests:
         memory: "96Mi"
@@ -50,6 +52,11 @@ grafana:
       type: loki
       url: http://loki-gateway.prometheus.svc.cluster.local
       access: proxy
+    - name: VictoriaMetrics
+      type: prometheus
+      url: http://victoria-metrics.prometheus.svc.cluster.local:8428
+      access: proxy
+      isDefault: true
 
 prometheus:
   prometheusSpec:

prometheus-stack/k8s/ingress.yaml

@@ -31,3 +31,105 @@ spec:
           port: 80
   tls:
     secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: prometheus-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`prom.workstation.internal`) || Host(`prom.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: prometheus-stack-kube-prom-prometheus
+          port: 9090
+  tls:
+    secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: alertmanager-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`am.workstation.internal`) || Host(`am.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: prometheus-stack-kube-prom-alertmanager
+          port: 9093
+  tls:
+    secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: loki-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`loki.workstation.internal`) || Host(`loki.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: loki-gateway
+          port: 80
+  tls:
+    secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: alloy-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`alloy.workstation.internal`) || Host(`alloy.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: alloy
+          port: 12345
+  tls:
+    secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: victoria-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`victoria.workstation.internal`) || Host(`victoria.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: victoria-metrics
+          port: 8428
+  tls:
+    secretName: internal-wildcard-tls
+---
+apiVersion: traefik.io/v1alpha1
+kind: IngressRoute
+metadata:
+  name: vmalert-local
+  namespace: prometheus
+spec:
+  entryPoints:
+    - websecure
+  routes:
+    - match: Host(`vmalert.workstation.internal`) || Host(`vmalert.gigaforust.internal`)
+      kind: Rule
+      services:
+        - name: vmalert
+          port: 8880
+  tls:
+    secretName: internal-wildcard-tls

prometheus-stack/k8s/victoria-operator-values.yaml

@@ -0,0 +1,12 @@
+nameOverride: victoria-operator
+
+operator:
+  enable_converter_ownership: true
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 96Mi
+  limits:
+    cpu: 200m
+    memory: 256Mi

prometheus-stack/k8s/victoria.yaml

@@ -0,0 +1,79 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: victoria-metrics
+  namespace: prometheus
+spec:
+  selector:
+    app: victoria-metrics
+  ports:
+    - port: 8428
+      targetPort: 8428
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: victoria-pvc
+  namespace: prometheus
+spec:
+  resources:
+    requests:
+      storage: 10Gi
+  volumeMode: Filesystem
+  accessModes:
+    - ReadWriteOnce
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: victoria-deployment
+  namespace: prometheus
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: victoria-metrics
+  strategy:
+    type: Recreate
+  template:
+    metadata:
+      labels:
+        app: victoria-metrics
+    spec:
+      containers:
+        - name: victoria
+          image: victoriametrics/victoria-metrics:v1.153.0-scratch
+          args:
+            - -storageDataPath=/vmdata
+            - -retentionPeriod=30d
+            - -httpListenAddr=:8428
+          ports:
+            - containerPort: 8428
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: 8428
+            initialDelaySeconds: 15
+            periodSeconds: 10
+            failureThreshold: 6
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: 8428
+            initialDelaySeconds: 60
+            periodSeconds: 30
+            failureThreshold: 3
+          volumeMounts:
+            - name: vmdata
+              mountPath: /vmdata
+          resources:
+            requests:
+              cpu: "100m"
+              memory: "256Mi"
+            limits:
+              cpu: "1000m"
+              memory: "1Gi"
+      volumes:
+        - name: vmdata
+          persistentVolumeClaim:
+            claimName: victoria-pvc

prometheus-stack/k8s/vmagent.yaml

@@ -0,0 +1,29 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMAgent
+metadata:
+  name: vmagent
+  namespace: prometheus
+spec:
+  image:
+    tag: v1.153.0
+  scrapeInterval: 30s
+  externalLabels:
+    scraper: victoria
+  serviceScrapeNamespaceSelector: {}
+  serviceScrapeSelector:
+    matchLabels:
+      release: prometheus-stack
+  globalScrapeRelabelConfigs:
+    - action: drop
+      source_labels:
+        - __meta_kubernetes_service_name
+      regex: prometheus-stack-kube-prom-prometheus
+  remoteWrite:
+    - url: http://victoria-metrics.prometheus.svc.cluster.local:8428/api/v1/write
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: "1000m"
+      memory: 1Gi

prometheus-stack/k8s/vmalert.yaml

@@ -0,0 +1,70 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: vmalert
+  namespace: prometheus
+spec:
+  selector:
+    app: vmalert
+  ports:
+    - port: 8880
+      targetPort: 8880
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vmalert-deployment
+  namespace: prometheus
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vmalert
+  strategy:
+    type: Recreate
+  template:
+    metadata:
+      labels:
+        app: vmalert
+    spec:
+      containers:
+        - name: vmalert
+          image: victoriametrics/vmalert:v1.153.0
+          args:
+            - -datasource.url=http://victoria-metrics.prometheus.svc.cluster.local:8428
+            - -remoteWrite.url=http://victoria-metrics.prometheus.svc.cluster.local:8428
+            - -notifier.url=http://prometheus-stack-kube-prom-alertmanager.prometheus.svc.cluster.local:9093
+            - -rule=/etc/vm/rules/*.yaml
+            - -evaluationInterval=60s
+            - -httpListenAddr=:8880
+          ports:
+            - containerPort: 8880
+          readinessProbe:
+            httpGet:
+              path: /metrics
+              port: 8880
+            initialDelaySeconds: 15
+            periodSeconds: 10
+            failureThreshold: 6
+          livenessProbe:
+            httpGet:
+              path: /metrics
+              port: 8880
+            initialDelaySeconds: 60
+            periodSeconds: 30
+            failureThreshold: 3
+          volumeMounts:
+            - name: rules
+              mountPath: /etc/vm/rules
+              readOnly: true
+          resources:
+            requests:
+              cpu: "50m"
+              memory: "64Mi"
+            limits:
+              cpu: "200m"
+              memory: "256Mi"
+      volumes:
+        - name: rules
+          configMap:
+            name: prometheus-prometheus-stack-kube-prom-prometheus-rulefiles-0

renovate/renovate.json

@@ -52,6 +52,15 @@
       "depNameTemplate": "kube-prometheus-stack",
       "registryUrlTemplate": "https://prometheus-community.github.io/helm-charts"
     },
+    {
+      "customType": "regex",
+      "description": "VictoriaMetrics Operator chart version pinned in the deploy workflow",
+      "managerFilePatterns": [".gitea/workflows/deploy-lib.sh"],
+      "matchStrings": ["\\|victoriametrics/victoria-metrics-operator\\|prometheus\\|(?<currentValue>[0-9.]+)\\|"],
+      "datasourceTemplate": "helm",
+      "depNameTemplate": "victoria-metrics-operator",
+      "registryUrlTemplate": "https://victoriametrics.github.io/helm-charts"
+    },
     {
       "customType": "regex",
       "description": "grafana/loki chart version pinned in the deploy workflow",