FEAT(otel): add OTel Collector for logs and traces

- Add OpenTelemetry Operator for CR management
- Deploy OTel Collector as DaemonSet via CR
- Enable filelog receiver for container log collection
- Replace Promtail with OTel filelog receiver
- Keep Prometheus for ServiceMonitor-based metrics scraping

kustomization.yaml

@@ -10,8 +10,9 @@ resources:
   - alertmanager/argocd.yaml
   - grafana/argocd.yaml
   - loki/argocd.yaml
-  - promtail/argocd.yaml
+  # promtail removed - OTel filelog receiver handles log collection
   - tempo/argocd.yaml
+  - opentelemetry-operator/argocd.yaml
   - opentelemetry-collector/argocd.yaml
   - node-exporter/argocd.yaml
   - kube-state-metrics/argocd.yaml

opentelemetry-collector/argocd.yaml

@@ -5,18 +5,14 @@ metadata:
   namespace: argocd
   finalizers:
   - resources-finalizer.argocd.argoproj.io
+  annotations:
+    argocd.argoproj.io/sync-wave: "1"
 spec:
   project: default
-  sources:
+  source:
-  - repoURL: https://open-telemetry.github.io/opentelemetry-helm-charts
+    repoURL: https://github.com/K3S-HOME/observability.git
-    chart: opentelemetry-collector
-    targetRevision: 0.108.0
-    helm:
-      valueFiles:
-      - $values/opentelemetry-collector/helm-values.yaml
-  - repoURL: https://github.com/K3S-HOME/observability.git
     targetRevision: main
-    ref: values
+    path: opentelemetry-collector/manifests
   destination:
     server: https://kubernetes.default.svc
     namespace: opentelemetry
@@ -29,6 +25,7 @@ spec:
     - CreateNamespace=true
     - PrunePropagationPolicy=foreground
     - PruneLast=true
+    - ServerSideApply=true
     retry:
       limit: 5
       backoff:

opentelemetry-collector/helm-values.yaml

@@ -4,6 +4,8 @@
 # Architecture:
 # - DaemonSet mode: one collector per node for efficient data collection
 # - OTLP receiver for traces, metrics, and logs
+# - Filelog receiver for container logs (replaces Promtail)
+# - Prometheus receiver for metrics scraping (replaces Prometheus scrape)
 # - Exports to: Tempo (traces), Prometheus (metrics), Loki (logs)
 #
 # Pipeline:
@@ -21,14 +23,14 @@ image:
 mode: daemonset
 
 # =============================================================================
-# Resource Limits (optimized for small cluster)
+# Resource Limits (increased for log + metrics collection)
 # =============================================================================
 resources:
   requests:
-    cpu: 25m
+    cpu: 50m
-    memory: 64Mi
+    memory: 256Mi
   limits:
-    memory: 64Mi
+    memory: 512Mi
 
 # =============================================================================
 # Tolerations (run on all nodes including master)
@@ -38,6 +40,25 @@ tolerations:
     operator: Exists
     effect: NoSchedule
 
+# =============================================================================
+# Extra Volumes for Log Collection
+# =============================================================================
+extraVolumes:
+  - name: varlogpods
+    hostPath:
+      path: /var/log/pods
+  - name: varlibdockercontainers
+    hostPath:
+      path: /var/lib/docker/containers
+
+extraVolumeMounts:
+  - name: varlogpods
+    mountPath: /var/log/pods
+    readOnly: true
+  - name: varlibdockercontainers
+    mountPath: /var/lib/docker/containers
+    readOnly: true
+
 # =============================================================================
 # Ports
 # =============================================================================
@@ -64,8 +85,11 @@ ports:
 # OpenTelemetry Collector Configuration
 # =============================================================================
 config:
+  # ---------------------------------------------------------------------------
   # Receivers - what data the collector accepts
+  # ---------------------------------------------------------------------------
   receivers:
+    # OTLP receiver for application telemetry
     otlp:
       protocols:
         grpc:
@@ -73,7 +97,84 @@ config:
         http:
           endpoint: 0.0.0.0:4318
 
+    # Filelog receiver for container logs (replaces Promtail)
+    filelog:
+      include:
+        - /var/log/pods/*/*/*.log
+      exclude:
+        # Exclude collector's own logs to prevent feedback loop
+        - /var/log/pods/opentelemetry_opentelemetry-collector*/*/*.log
+      start_at: end
+      include_file_path: true
+      include_file_name: false
+      operators:
+        # Route based on log format
+        - type: router
+          id: get-format
+          routes:
+            - output: parser-docker
+              expr: 'body matches "^\\{"'
+            - output: parser-containerd
+              expr: 'body matches "^[^ Z]+Z"'
+          default: parser-containerd
+
+        # Docker JSON format parser
+        - type: json_parser
+          id: parser-docker
+          output: extract-metadata-from-filepath
+          timestamp:
+            parse_from: attributes.time
+            layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+
+        # Containerd/CRI format parser
+        - type: regex_parser
+          id: parser-containerd
+          regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
+          output: extract-metadata-from-filepath
+          timestamp:
+            parse_from: attributes.time
+            layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+
+        # Extract metadata from file path
+        - type: regex_parser
+          id: extract-metadata-from-filepath
+          regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9-]+)\/(?P<container_name>[^\/]+)\/.*$'
+          parse_from: attributes["log.file.path"]
+
+        # Move attributes to resource
+        - type: move
+          from: attributes.namespace
+          to: resource["k8s.namespace.name"]
+        - type: move
+          from: attributes.pod_name
+          to: resource["k8s.pod.name"]
+        - type: move
+          from: attributes.container_name
+          to: resource["k8s.container.name"]
+        - type: move
+          from: attributes.uid
+          to: resource["k8s.pod.uid"]
+        - type: move
+          from: attributes.stream
+          to: attributes["log.iostream"]
+        - type: move
+          from: attributes.log
+          to: body
+
+    # Prometheus receiver - self metrics only
+    # Infrastructure metrics (node-exporter, kube-state-metrics) handled by Prometheus
+    prometheus:
+      config:
+        scrape_configs:
+          # OTel Collector self metrics only
+          - job_name: 'otel-collector'
+            scrape_interval: 30s
+            static_configs:
+              - targets: ['${env:MY_POD_IP}:8888']
+
+  # ---------------------------------------------------------------------------
   # Processors - how data is transformed
+  # ---------------------------------------------------------------------------
   processors:
     # Batch processor for efficient exports
     batch:
@@ -84,8 +185,8 @@ config:
     # Memory limiter to prevent OOM
     memory_limiter:
       check_interval: 5s
-      limit_mib: 200
+      limit_mib: 400
-      spike_limit_mib: 50
+      spike_limit_mib: 100
 
     # Add Kubernetes metadata
     k8sattributes:
@@ -112,7 +213,9 @@ config:
       timeout: 5s
       override: false
 
+  # ---------------------------------------------------------------------------
   # Exporters - where data goes
+  # ---------------------------------------------------------------------------
   exporters:
     # Tempo for traces
     otlp/tempo:
@@ -137,12 +240,16 @@ config:
     debug:
       verbosity: basic
 
+  # ---------------------------------------------------------------------------
   # Extensions
+  # ---------------------------------------------------------------------------
   extensions:
     health_check:
       endpoint: 0.0.0.0:13133
 
+  # ---------------------------------------------------------------------------
   # Service pipelines
+  # ---------------------------------------------------------------------------
   service:
     extensions: [health_check]
     pipelines:
@@ -152,15 +259,15 @@ config:
         processors: [memory_limiter, k8sattributes, resourcedetection, batch]
         exporters: [otlp/tempo]
 
-      # Metrics pipeline
+      # Metrics pipeline (OTLP + Prometheus scraping)
       metrics:
-        receivers: [otlp]
+        receivers: [otlp, prometheus]
         processors: [memory_limiter, k8sattributes, resourcedetection, batch]
         exporters: [prometheusremotewrite]
 
-      # Logs pipeline
+      # Logs pipeline (OTLP + Filelog)
       logs:
-        receivers: [otlp]
+        receivers: [otlp, filelog]
         processors: [memory_limiter, k8sattributes, resourcedetection, batch]
         exporters: [loki]
 
@@ -171,20 +278,23 @@ serviceAccount:
   create: true
 
 # =============================================================================
-# RBAC for k8sattributes processor
+# RBAC for k8sattributes processor and prometheus receiver
 # =============================================================================
 clusterRole:
   create: true
   rules:
     - apiGroups: [""]
-      resources: ["pods", "namespaces", "nodes"]
+      resources: ["pods", "namespaces", "nodes", "endpoints", "services"]
       verbs: ["get", "watch", "list"]
     - apiGroups: ["apps"]
       resources: ["replicasets", "deployments"]
       verbs: ["get", "watch", "list"]
+    - apiGroups: ["discovery.k8s.io"]
+      resources: ["endpointslices"]
+      verbs: ["get", "watch", "list"]
 
 # =============================================================================
-# ServiceMonitor for Prometheus
+# ServiceMonitor for Prometheus (keep for backward compatibility)
 # =============================================================================
 serviceMonitor:
   enabled: true

opentelemetry-collector/manifests/collector.yaml

@@ -0,0 +1,231 @@
+# OpenTelemetry Collector with Target Allocator
+# Managed by OpenTelemetry Operator
+#
+# Architecture:
+# - DaemonSet mode: one collector per node for log collection
+# - Target Allocator: distributes scrape targets across collectors
+# - Filelog receiver for container logs
+# - Prometheus receiver with Target Allocator for metrics
+# - Exports to: Tempo (traces), Prometheus (metrics), Loki (logs)
+apiVersion: opentelemetry.io/v1beta1
+kind: OpenTelemetryCollector
+metadata:
+  name: otel-collector
+  namespace: opentelemetry
+spec:
+  mode: daemonset
+  image: otel/opentelemetry-collector-contrib:0.113.0
+  serviceAccount: otel-collector
+
+  # Target Allocator disabled - metrics collected by Prometheus directly
+  # OTel handles logs (filelog) and traces (otlp) only
+
+  resources:
+    requests:
+      cpu: 50m
+      memory: 256Mi
+    limits:
+      memory: 512Mi
+
+  tolerations:
+    - key: node-role.kubernetes.io/control-plane
+      operator: Exists
+      effect: NoSchedule
+
+  volumeMounts:
+    - name: varlogpods
+      mountPath: /var/log/pods
+      readOnly: true
+    - name: varlibdockercontainers
+      mountPath: /var/lib/docker/containers
+      readOnly: true
+
+  volumes:
+    - name: varlogpods
+      hostPath:
+        path: /var/log/pods
+    - name: varlibdockercontainers
+      hostPath:
+        path: /var/lib/docker/containers
+
+  ports:
+    - name: otlp-grpc
+      port: 4317
+      protocol: TCP
+      targetPort: 4317
+    - name: otlp-http
+      port: 4318
+      protocol: TCP
+      targetPort: 4318
+    - name: metrics
+      port: 8888
+      protocol: TCP
+      targetPort: 8888
+
+  env:
+    - name: K8S_NODE_NAME
+      valueFrom:
+        fieldRef:
+          fieldPath: spec.nodeName
+    - name: K8S_POD_NAME
+      valueFrom:
+        fieldRef:
+          fieldPath: metadata.name
+    - name: K8S_POD_IP
+      valueFrom:
+        fieldRef:
+          fieldPath: status.podIP
+
+  config:
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
+
+      # Filelog receiver for container logs
+      filelog:
+        include:
+          - /var/log/pods/*/*/*.log
+        exclude:
+          - /var/log/pods/opentelemetry_otel-collector*/*/*.log
+        start_at: end
+        include_file_path: true
+        include_file_name: false
+        operators:
+          - type: router
+            id: get-format
+            routes:
+              - output: parser-docker
+                expr: 'body matches "^\\{"'
+              - output: parser-containerd
+                expr: 'body matches "^[^ Z]+Z"'
+            default: parser-containerd
+
+          - type: json_parser
+            id: parser-docker
+            output: extract-metadata-from-filepath
+            timestamp:
+              parse_from: attributes.time
+              layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+
+          - type: regex_parser
+            id: parser-containerd
+            regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
+            output: extract-metadata-from-filepath
+            timestamp:
+              parse_from: attributes.time
+              layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+
+          - type: regex_parser
+            id: extract-metadata-from-filepath
+            regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9-]+)\/(?P<container_name>[^\/]+)\/.*$'
+            parse_from: attributes["log.file.path"]
+
+          - type: move
+            from: attributes.namespace
+            to: resource["k8s.namespace.name"]
+          - type: move
+            from: attributes.pod_name
+            to: resource["k8s.pod.name"]
+          - type: move
+            from: attributes.container_name
+            to: resource["k8s.container.name"]
+          - type: move
+            from: attributes.uid
+            to: resource["k8s.pod.uid"]
+          - type: move
+            from: attributes.stream
+            to: attributes["log.iostream"]
+          - type: move
+            from: attributes.log
+            to: body
+
+      # Prometheus receiver - self metrics only
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: otel-collector
+              scrape_interval: 60s
+              static_configs:
+                - targets: ['${env:K8S_POD_IP}:8888']
+
+    processors:
+      batch:
+        timeout: 10s
+        send_batch_size: 1024
+        send_batch_max_size: 2048
+
+      memory_limiter:
+        check_interval: 5s
+        limit_mib: 400
+        spike_limit_mib: 100
+
+      k8sattributes:
+        extract:
+          metadata:
+            - k8s.namespace.name
+            - k8s.deployment.name
+            - k8s.pod.name
+            - k8s.node.name
+        passthrough: false
+        pod_association:
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.ip
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.uid
+          - sources:
+              - from: connection
+
+      resourcedetection:
+        detectors: [env, system]
+        timeout: 5s
+        override: false
+
+    exporters:
+      otlp/tempo:
+        endpoint: tempo.tempo.svc.cluster.local:4317
+        tls:
+          insecure: true
+
+      prometheusremotewrite:
+        endpoint: http://prometheus-kube-prometheus-prometheus.prometheus.svc:9090/api/v1/write
+        tls:
+          insecure: true
+        external_labels:
+          otel_collector: ${env:K8S_POD_NAME}
+
+      loki:
+        endpoint: http://loki.loki.svc.cluster.local:3100/loki/api/v1/push
+        default_labels_enabled:
+          exporter: true
+          level: true
+
+      debug:
+        verbosity: basic
+
+    extensions:
+      health_check:
+        endpoint: 0.0.0.0:13133
+
+    service:
+      extensions: [health_check]
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
+          exporters: [otlp/tempo]
+
+        metrics:
+          receivers: [otlp, prometheus]
+          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
+          exporters: [prometheusremotewrite]
+
+        logs:
+          receivers: [otlp, filelog]
+          processors: [memory_limiter, k8sattributes, resourcedetection, batch]
+          exporters: [loki]

opentelemetry-collector/manifests/kustomization.yaml

@@ -0,0 +1,6 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - rbac.yaml
+  - collector.yaml

opentelemetry-collector/manifests/rbac.yaml

@@ -0,0 +1,85 @@
+# RBAC for OpenTelemetry Collector and Target Allocator
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: otel-collector
+  namespace: opentelemetry
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: otel-collector
+rules:
+  # For k8sattributes processor
+  - apiGroups: [""]
+    resources: ["pods", "namespaces", "nodes", "endpoints", "services"]
+    verbs: ["get", "watch", "list"]
+  - apiGroups: ["apps"]
+    resources: ["replicasets", "deployments", "statefulsets", "daemonsets"]
+    verbs: ["get", "watch", "list"]
+  - apiGroups: ["discovery.k8s.io"]
+    resources: ["endpointslices"]
+    verbs: ["get", "watch", "list"]
+  # For Target Allocator - ServiceMonitor/PodMonitor discovery
+  - apiGroups: ["monitoring.coreos.com"]
+    resources: ["servicemonitors", "podmonitors"]
+    verbs: ["get", "watch", "list"]
+  # For node metrics
+  - apiGroups: [""]
+    resources: ["nodes/metrics", "nodes/stats", "nodes/proxy"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: otel-collector
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: otel-collector
+subjects:
+  - kind: ServiceAccount
+    name: otel-collector
+    namespace: opentelemetry
+---
+# Target Allocator ServiceAccount and RBAC
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: otel-collector-targetallocator
+  namespace: opentelemetry
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: otel-targetallocator
+rules:
+  # Core resources for service discovery
+  - apiGroups: [""]
+    resources: ["pods", "nodes", "services", "endpoints", "namespaces"]
+    verbs: ["get", "watch", "list"]
+  - apiGroups: ["discovery.k8s.io"]
+    resources: ["endpointslices"]
+    verbs: ["get", "watch", "list"]
+  # Prometheus CRs
+  - apiGroups: ["monitoring.coreos.com"]
+    resources: ["servicemonitors", "podmonitors", "probes", "scrapeconfigs"]
+    verbs: ["get", "watch", "list"]
+  # For allocator coordination
+  - apiGroups: ["opentelemetry.io"]
+    resources: ["opentelemetrycollectors"]
+    verbs: ["get", "watch", "list"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: otel-targetallocator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: otel-targetallocator
+subjects:
+  - kind: ServiceAccount
+    name: otel-collector-targetallocator
+    namespace: opentelemetry

opentelemetry-operator/argocd.yaml

@@ -0,0 +1,44 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: opentelemetry-operator
+  namespace: argocd
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+  annotations:
+    argocd.argoproj.io/sync-wave: "0"
+spec:
+  project: default
+  sources:
+  - repoURL: https://open-telemetry.github.io/opentelemetry-helm-charts
+    chart: opentelemetry-operator
+    targetRevision: 0.74.0
+    helm:
+      valueFiles:
+      - $values/opentelemetry-operator/helm-values.yaml
+  - repoURL: https://github.com/K3S-HOME/observability.git
+    targetRevision: main
+    ref: values
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: opentelemetry-operator
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+      allowEmpty: false
+    syncOptions:
+    - CreateNamespace=true
+    - PrunePropagationPolicy=foreground
+    - PruneLast=true
+    - ServerSideApply=true
+    retry:
+      limit: 5
+      backoff:
+        duration: 5s
+        factor: 2
+        maxDuration: 3m
+    managedNamespaceMetadata:
+      labels:
+        goldilocks.fairwinds.com/enabled: 'true'
+  revisionHistoryLimit: 10

opentelemetry-operator/helm-values.yaml

@@ -0,0 +1,41 @@
+# OpenTelemetry Operator Helm Values
+# Chart: https://github.com/open-telemetry/opentelemetry-helm-charts/tree/main/charts/opentelemetry-operator
+
+# Manager (Operator) configuration
+manager:
+  collectorImage:
+    repository: otel/opentelemetry-collector-contrib
+  targetAllocatorImage:
+    repository: ghcr.io/open-telemetry/opentelemetry-operator/target-allocator
+  autoInstrumentationImage:
+    java:
+      repository: ghcr.io/open-telemetry/opentelemetry-operator/autoinstrumentation-java
+    nodejs:
+      repository: ghcr.io/open-telemetry/opentelemetry-operator/autoinstrumentation-nodejs
+    python:
+      repository: ghcr.io/open-telemetry/opentelemetry-operator/autoinstrumentation-python
+    dotnet:
+      repository: ghcr.io/open-telemetry/opentelemetry-operator/autoinstrumentation-dotnet
+    go:
+      repository: ghcr.io/open-telemetry/opentelemetry-operator/autoinstrumentation-go
+  resources:
+    limits:
+      memory: 256Mi
+    requests:
+      cpu: 10m
+      memory: 64Mi
+
+# Admission webhooks (uses cert-manager self-signed CA)
+admissionWebhooks:
+  certManager:
+    enabled: true
+
+# Kube RBAC Proxy
+kubeRBACProxy:
+  enabled: true
+  resources:
+    limits:
+      memory: 64Mi
+    requests:
+      cpu: 5m
+      memory: 32Mi

opentelemetry-operator/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - argocd.yaml

prometheus/helm-values.yaml

@@ -45,6 +45,9 @@ prometheus:
     enabled: true
 
   prometheusSpec:
+    # Enable remote write receiver for OTel Collector
+    enableRemoteWriteReceiver: true
+
     # HA: 2 replicas on different worker nodes
     replicas: 2
     replicaExternalLabelName: prometheus_replica
@@ -81,7 +84,7 @@ prometheus:
       limits:
         memory: 768Mi
     
-    # ServiceMonitor 자동 발견 - 모든 ServiceMonitor 선택
+    # ServiceMonitor selector - scrape all ServiceMonitors
     serviceMonitorSelectorNilUsesHelmValues: false
     serviceMonitorSelector: {}
     podMonitorSelectorNilUsesHelmValues: false
@@ -100,69 +103,9 @@ prometheus:
     externalLabels:
       cluster: "mayne-cluster"
 
-    additionalScrapeConfigs:
+    # additionalScrapeConfigs removed - OTel handles scraping now
-      # ArgoCD metrics
+    # Targets moved to OTel prometheus receiver kubernetes-pods job
-      - job_name: 'argocd-metrics'
+    additionalScrapeConfigs: []
-        static_configs:
-          - targets:
-            - 'argocd-application-controller-metrics.argocd.svc.cluster.local:8082'
-            labels:
-              service: argocd-controller
-          - targets:
-            - 'argocd-server-metrics.argocd.svc.cluster.local:8083'
-            labels:
-              service: argocd-server
-          - targets:
-            - 'argocd-repo-server-metrics.argocd.svc.cluster.local:8084'
-            labels:
-              service: argocd-repo
-
-      # Cert-Manager
-      - job_name: 'cert-manager'
-        static_configs:
-          - targets:
-            - 'cert-manager.cert-manager.svc.cluster.local:9402'
-
-      # MinIO
-      - job_name: 'minio-cluster'
-        static_configs:
-          - targets:
-            - 'minio.minio.svc.cluster.local:9000'
-        metrics_path: /minio/v2/metrics/cluster
-        scheme: http
-
-      - job_name: 'minio-node'
-        static_configs:
-          - targets:
-            - 'minio.minio.svc.cluster.local:9000'
-        metrics_path: /minio/v2/metrics/node
-        scheme: http
-
-      # Ingress NGINX
-      - job_name: 'ingress-nginx'
-        kubernetes_sd_configs:
-          - role: pod
-            namespaces:
-              names:
-                - ingress-nginx
-        relabel_configs:
-          - source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
-            action: keep
-            regex: ingress-nginx
-          - source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_component]
-            action: keep
-            regex: controller
-          - source_labels: [__address__]
-            action: replace
-            regex: ([^:]+)(?::\d+)?
-            replacement: $1:10254
-            target_label: __address__
-          - source_labels: [__meta_kubernetes_pod_name]
-            action: replace
-            target_label: pod
-          - source_labels: [__meta_kubernetes_namespace]
-            action: replace
-            target_label: namespace
 
 # API Server 메트릭 수집 비활성화 (메모리 절감: ~37k series)
 kubeApiServer: