Fix some issues

infrastructure/monitoring/signoz/k8s-infra-values-prod.yaml

@@ -0,0 +1,76 @@
+# SigNoz k8s-infra Helm Chart Values - Production Environment
+# Collects ALL Kubernetes infrastructure metrics and sends to SigNoz
+#
+# This chart REPLACES the need for:
+# - kube-state-metrics (delete after deploying this)
+# - node-exporter (delete after deploying this)
+#
+# Official Chart: https://github.com/SigNoz/charts/tree/main/charts/k8s-infra
+#
+# Install Command:
+#   helm upgrade --install k8s-infra signoz/k8s-infra -n bakery-ia -f k8s-infra-values-prod.yaml
+#
+# After install, remove redundant exporters:
+#   helm uninstall kube-state-metrics -n bakery-ia
+#   helm uninstall node-exporter-prometheus-node-exporter -n bakery-ia
+#   (or: helm uninstall prometheus -n bakery-ia if installed via prometheus stack)
+
+# ============================================================================
+# CONNECTION TO SIGNOZ
+# ============================================================================
+otelCollectorEndpoint: "signoz-otel-collector.bakery-ia.svc.cluster.local:4317"
+otelInsecure: true
+clusterName: "bakery-ia-prod"
+
+# ============================================================================
+# PRESETS - What metrics to collect
+# ============================================================================
+presets:
+  # Host metrics: CPU, memory, disk, filesystem, network, load
+  # Replaces node-exporter
+  hostMetrics:
+    enabled: true
+    collectionInterval: 30s
+
+  # Kubelet metrics: Pod/container CPU, memory usage
+  # Essential for seeing resource usage per pod in SigNoz
+  kubeletMetrics:
+    enabled: true
+    collectionInterval: 30s
+
+  # Kubernetes cluster metrics: deployments, pods, nodes status
+  # Replaces kube-state-metrics
+  clusterMetrics:
+    enabled: true
+    collectionInterval: 30s
+
+  # Enriches all telemetry with k8s metadata (pod name, namespace, etc.)
+  kubernetesAttributes:
+    enabled: true
+
+  # Kubernetes events (pod scheduled, failed, etc.)
+  kubernetesEvents:
+    enabled: true
+
+  # Container logs - disabled (apps send logs via OTLP directly)
+  logsCollection:
+    enabled: false
+
+# ============================================================================
+# OTEL AGENT (DaemonSet) - Runs on each node
+# ============================================================================
+otelAgent:
+  enabled: true
+  resources:
+    requests:
+      memory: "256Mi"
+      cpu: "100m"
+    limits:
+      memory: "512Mi"
+      cpu: "500m"
+
+# ============================================================================
+# OTEL DEPLOYMENT - Disabled (using DaemonSet only)
+# ============================================================================
+otelDeployment:
+  enabled: false