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 +1,142 @@
+# =============================================================================
+# vmagent — PaaSup 커스텀 오버라이드 (Kubernetes 메트릭 수집)
+# 차트: victoria-metrics/victoria-metrics-agent
+# 역할: kubelet / cadvisor / kube-state-metrics / node-exporter / 파드 annotation scrape
+# 전송 대상: VictoriaMetrics Cluster vminsert:8480 (쓰기 경로는 vmauth 미경유)
+#
+# accountID 매핑(예시): 0=플랫폼 공통(fallback) / 1=demo01 / 2=demo02 / 9000=platform
+#   네임스페이스별 분기는 urlRelabelConfig(ConfigMap: vmagent-relabel-configs) 마운트로 처리.
+#   해당 ConfigMap은 온보딩 시 별도 생성한다(CUSTOM-README 참조).
+# =============================================================================
+
+# remoteWrite — 최소 1개 필요. accountID별 엔드포인트 + urlRelabelConfig 파일 분기
+remoteWrite:
+  - url: "http://vmcluster-victoria-metrics-cluster-vminsert.monitoring.svc.cluster.local:8480/insert/1/prometheus/api/v1/write"
+    urlRelabelConfig: /relabel/demo01.yaml
+  - url: "http://vmcluster-victoria-metrics-cluster-vminsert.monitoring.svc.cluster.local:8480/insert/2/prometheus/api/v1/write"
+    urlRelabelConfig: /relabel/demo02.yaml
+  - url: "http://vmcluster-victoria-metrics-cluster-vminsert.monitoring.svc.cluster.local:8480/insert/9000/prometheus/api/v1/write"
+    urlRelabelConfig: /relabel/platform.yaml
+  - url: "http://vmcluster-victoria-metrics-cluster-vminsert.monitoring.svc.cluster.local:8480/insert/0/prometheus/api/v1/write"
+
+extraVolumes:
+  - name: relabel-configs
+    configMap:
+      name: vmagent-relabel-configs
+extraVolumeMounts:
+  - name: relabel-configs
+    mountPath: /relabel
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+# 스크레이프 설정 — kubelet/cadvisor/exporters/파드 annotation
+config:
+  global:
+    scrape_interval: 30s
+    external_labels:
+      cluster: local
+
+  scrape_configs:
+    - job_name: kubelet
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        insecure_skip_verify: true
+      authorization:
+        credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+        - role: node
+      relabel_configs:
+        - target_label: __address__
+          replacement: kubernetes.default.svc:443
+        - source_labels: [__meta_kubernetes_node_name]
+          regex: (.+)
+          target_label: __metrics_path__
+          replacement: /api/v1/nodes/$1/proxy/metrics
+        - source_labels: [__meta_kubernetes_node_name]
+          target_label: node
+
+    - job_name: cadvisor
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        insecure_skip_verify: true
+      authorization:
+        credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      kubernetes_sd_configs:
+        - role: node
+      relabel_configs:
+        - target_label: __address__
+          replacement: kubernetes.default.svc:443
+        - source_labels: [__meta_kubernetes_node_name]
+          regex: (.+)
+          target_label: __metrics_path__
+          replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
+        - source_labels: [__meta_kubernetes_node_name]
+          target_label: node
+
+    - job_name: kube-state-metrics
+      honor_labels: true
+      kubernetes_sd_configs:
+        - role: endpoints
+          namespaces:
+            names: [monitoring]
+      relabel_configs:
+        - source_labels: [__meta_kubernetes_service_label_app_kubernetes_io_name]
+          regex: kube-state-metrics
+          action: keep
+        - source_labels: [__meta_kubernetes_endpoint_port_name]
+          regex: http
+          action: keep
+
+    - job_name: node-exporter
+      kubernetes_sd_configs:
+        - role: endpoints
+          namespaces:
+            names: [monitoring]
+      relabel_configs:
+        - source_labels: [__meta_kubernetes_service_label_app_kubernetes_io_name]
+          regex: prometheus-node-exporter
+          action: keep
+        - source_labels: [__meta_kubernetes_endpoint_port_name]
+          regex: metrics
+          action: keep
+        - source_labels: [__meta_kubernetes_pod_node_name]
+          target_label: node
+
+    - job_name: kubernetes-pods
+      kubernetes_sd_configs:
+        - role: pod
+      relabel_configs:
+        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+          regex: "true"
+          action: keep
+        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+          regex: (.+)
+          target_label: __metrics_path__
+        - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+          regex: ([^:]+)(?::\d+)?;(\d+)
+          replacement: $1:$2
+          target_label: __address__
+        - source_labels: [__meta_kubernetes_namespace]
+          target_label: namespace
+        - source_labels: [__meta_kubernetes_pod_name]
+          target_label: pod
+        - source_labels: [__meta_kubernetes_pod_label_app]
+          target_label: app
+
+# RBAC — kubelet/cadvisor/엔드포인트 접근 권한
+rbac:
+  create: true
+  extraRules:
+    - apiGroups: [""]
+      resources: [nodes, nodes/proxy, nodes/metrics, pods, services, endpoints, namespaces]
+      verbs: [get, list, watch]
+    - nonResourceURLs: [/metrics, /metrics/cadvisor]
+      verbs: [get]