Add VictoriaMetrics observability stack + sync catalog for monitoring test

- VM stack 10 charts: victoria-metrics-cluster/auth, victoria-logs-cluster, victoria-metrics-agent/alert, opentelemetry-collector, kube-state-metrics, prometheus-node-exporter, alertmanager, perses (JWT/OIDC, Infisical-ready) - ArgoCD ApplicationSet (syncWave) + per-chart dip-values overlays - doc/victoria-metrics-architecture.md, define-chart-resources updates - includes pending working-tree changes (mlflow, kubeflow, apisix, CLAUDE.md) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 11:10:51 +09:00
parent a55427730e
commit 6290322f1b
514 changed files with 68103 additions and 40 deletions
@@ -0,0 +1,9 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+useGOMEMLIMIT: true
@@ -0,0 +1,27 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+clusterRole:
+  create: true
+  name: "testing-clusterrole"
+  rules:
+    - apiGroups:
+      - ''
+      resources:
+      - 'pods'
+      - 'nodes'
+      verbs:
+      - 'get'
+      - 'list'
+      - 'watch'
+  clusterRoleBinding:
+    name: "testing-clusterrolebinding"
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,26 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+config:
+  receivers:
+    jaeger: null
+    otlp: null
+    zipkin: null
+    hostmetrics:
+      scrapers:
+        cpu:
+        disk:
+        filesystem:
+  service:
+    pipelines:
+      metrics:
+        receivers:
+          - prometheus
+          - hostmetrics
+      traces: null
+      logs: null
@@ -0,0 +1,12 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,33 @@
+global:
+  test: templated-value
+
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+# Tests `tpl` function reference used in pod labels and
+# ingress.hosts[*]
+podLabels:
+  testLabel: "{{ .Values.global.test }}"
+
+additionalLabels:
+  testLabel: "{{ .Values.global.test }}"
+  someLabel: "someValue"
+
+ingress:
+  enabled: true
+  hosts:
+    - host: "{{ .Values.global.test }}"
+      paths:
+        - path: /
+          pathType: Prefix
+          port: 4318
@@ -0,0 +1,21 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+ports:
+  jaeger-compact:
+    enabled: false
+  jaeger-thrift:
+    enabled: false
+  jaeger-grpc:
+    enabled: false
+  zipkin:
+    enabled: false
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,15 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 10
+  behavior: {}
+  targetCPUUtilizationPercentage: 80
+  targetMemoryUtilizationPercentage: 80
@@ -0,0 +1,15 @@
+mode: statefulset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 10
+  behavior: {}
+  targetCPUUtilizationPercentage: 80
+  targetMemoryUtilizationPercentage: 80
@@ -0,0 +1,21 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+internalTelemetryViaOTLP:
+  endpoint: "http://localhost:4318"
+  headers:
+    - name: "x-opentelemetry-customer"
+      value: "a value"
+  traces:
+    enabled: true
+  metrics:
+    enabled: true
+  logs:
+    enabled: true
@@ -0,0 +1,49 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+ingress:
+  enabled: true
+
+  ingressClassName: nginx
+  annotations:
+    test.io/collector: default
+  hosts:
+    - host: defaultcollector.example.com
+      paths:
+        - path: /
+          pathType: Prefix
+          port: 4318
+
+  additionalIngresses:
+    - name: additional-basic
+      hosts:
+        - host: additional-basic.example.com
+          paths:
+            - path: /
+              pathType: Prefix
+              port: 4318
+
+    - name: additional-advanced
+      ingressClassName: nginx
+      annotations:
+        test.io/ingress: additional-advanced
+      hosts:
+        - host: additional-advanced.example.com
+          paths:
+            - path: /
+              pathType: Exact
+              port: 4318
+      tls:
+        - secretName: somesecret
+          hosts:
+            - additional-advanced.example.com
@@ -0,0 +1,37 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+networkPolicy:
+  enabled: true
+
+  allowIngressFrom:
+    - namespaceSelector: {}
+    - ipBlock:
+        cidr: 127.0.0.1/32
+
+  extraIngressRules:
+    - ports:
+      - port: metrics
+        protocol: TCP
+      from:
+        - ipBlock:
+            cidr: 127.0.0.1/32
+
+  egressRules:
+    - to:
+        - podSelector:
+            matchLabels:
+              app: jaeger
+      ports:
+        - port: 4317
+          protocol: TCP
@@ -0,0 +1,15 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+networkPolicy:
+  enabled: true
@@ -0,0 +1,15 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+config:
+  service:
+    telemetry:
+      metrics:
+        address: ${env:MY_POD_IP}:8888
@@ -0,0 +1,17 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
+
+config:
+  service:
+    telemetry:
+      metrics:
+        address: 0.0.0.0:8888
+      resource:
+        "k8s.namespace.name": "default"
@@ -0,0 +1,17 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  annotationDiscovery:
+    logs:
+      enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  clusterMetrics:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  clusterMetrics:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  hostMetrics:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  kubernetesEvents:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  kubeletMetrics:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  kubernetesAttributes:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  kubernetesObjects:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,16 @@
+mode: deployment
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  kubernetesObjects:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,17 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  logsCollection:
+    enabled: true
+    includeCollectorLogs: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,19 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-ebpf-profiler"
+
+command:
+  name: "otelcol-ebpf-profiler"
+  extraArgs: ["--feature-gates=+service.profilesSupport"]
+
+presets:
+  profiling:
+    enabled: true
+  kubernetesAttributes:
+    enabled: true
+
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M
@@ -0,0 +1,11 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+presets:
+  resourceDetection:
+    enabled: true
@@ -0,0 +1,37 @@
+mode: daemonset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+livenessProbe:
+  initialDelaySeconds: 10
+  periodSeconds: 5
+  timeoutSeconds: 3
+  failureThreshold: 2
+  terminationGracePeriodSeconds: 40
+  httpGet:
+    port: 8989
+    path: /healthz
+
+readinessProbe:
+  initialDelaySeconds: 10
+  periodSeconds: 5
+  timeoutSeconds: 3
+  successThreshold: 2
+  failureThreshold: 2
+  httpGet:
+    port: 8989
+    path: /healthz
+
+startupProbe:
+  initialDelaySeconds: 10
+  periodSeconds: 5
+  timeoutSeconds: 3
+  failureThreshold: 10
+  terminationGracePeriodSeconds: 40
+  httpGet:
+    port: 8989
+    path: /healthz
@@ -0,0 +1,13 @@
+mode: statefulset
+
+image:
+  repository: "ghcr.io/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-k8s"
+
+command:
+  name: "otelcol-k8s"
+
+replicaCount: 2
+resources:
+  limits:
+    cpu: 100m
+    memory: 200M