Imporve monitoring

2026-01-09 06:57:18 +01:00
parent e8fda39e50
commit 4af860c010
16 changed files with 333 additions and 635 deletions
--- a/infrastructure/helm/deploy-signoz.sh
+++ b/infrastructure/helm/deploy-signoz.sh
@@ -37,6 +37,14 @@ show_help() {
    $0 prod                   # Deploy to production
    $0 --upgrade prod         # Upgrade production deployment
    $0 --remove dev           # Remove development deployment"
+    echo ""
+    echo "Docker Hub Authentication:"
+    echo "  This script automatically creates a Docker Hub secret for image pulls."
+    echo "  Provide credentials via environment variables (recommended):"
+    echo "    export DOCKERHUB_USERNAME='your-username'"
+    echo "    export DOCKERHUB_PASSWORD='your-personal-access-token'"
+    echo "  Or ensure you're logged in with Docker CLI:"
+    echo "    docker login"
 }

 # Parse command line arguments
@@ -124,6 +132,82 @@ ensure_namespace() {
    fi
 }

+# Function to create Docker Hub secret for image pulls
+create_dockerhub_secret() {
+    echo "${BLUE}Setting up Docker Hub image pull secret...${NC}"
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would create Docker Hub secret in namespace $NAMESPACE"
+        return
+    fi
+
+    # Check if secret already exists
+    if kubectl get secret dockerhub-creds -n "$NAMESPACE" &> /dev/null; then
+        echo "${GREEN}Docker Hub secret already exists in namespace $NAMESPACE.${NC}"
+        return
+    fi
+
+    # Check if Docker Hub credentials are available
+    if [[ -n "$DOCKERHUB_USERNAME" ]] && [[ -n "$DOCKERHUB_PASSWORD" ]]; then
+        echo "${BLUE}Found DOCKERHUB_USERNAME and DOCKERHUB_PASSWORD environment variables${NC}"
+
+        kubectl create secret docker-registry dockerhub-creds \
+            --docker-server=https://index.docker.io/v1/ \
+            --docker-username="$DOCKERHUB_USERNAME" \
+            --docker-password="$DOCKERHUB_PASSWORD" \
+            --docker-email="${DOCKERHUB_EMAIL:-noreply@bakery-ia.local}" \
+            -n "$NAMESPACE"
+
+        echo "${GREEN}Docker Hub secret created successfully.${NC}"
+
+    elif [[ -f "$HOME/.docker/config.json" ]]; then
+        echo "${BLUE}Attempting to use Docker CLI credentials...${NC}"
+
+        # Try to extract credentials from Docker config
+        if grep -q "credsStore" "$HOME/.docker/config.json"; then
+            echo "${YELLOW}Docker is using a credential store. Please set environment variables:${NC}"
+            echo "  export DOCKERHUB_USERNAME='your-username'"
+            echo "  export DOCKERHUB_PASSWORD='your-password-or-token'"
+            echo "${YELLOW}Continuing without Docker Hub authentication...${NC}"
+            return
+        fi
+
+        # Try to extract from base64 encoded auth
+        AUTH=$(cat "$HOME/.docker/config.json" | jq -r '.auths["https://index.docker.io/v1/"].auth // empty' 2>/dev/null)
+        if [[ -n "$AUTH" ]]; then
+            echo "${GREEN}Found Docker Hub credentials in Docker config${NC}"
+            local DOCKER_USERNAME=$(echo "$AUTH" | base64 -d | cut -d: -f1)
+            local DOCKER_PASSWORD=$(echo "$AUTH" | base64 -d | cut -d: -f2-)
+
+            kubectl create secret docker-registry dockerhub-creds \
+                --docker-server=https://index.docker.io/v1/ \
+                --docker-username="$DOCKER_USERNAME" \
+                --docker-password="$DOCKER_PASSWORD" \
+                --docker-email="${DOCKERHUB_EMAIL:-noreply@bakery-ia.local}" \
+                -n "$NAMESPACE"
+
+            echo "${GREEN}Docker Hub secret created successfully.${NC}"
+        else
+            echo "${YELLOW}Could not find Docker Hub credentials${NC}"
+            echo "${YELLOW}To enable automatic Docker Hub authentication:${NC}"
+            echo "  1. Run 'docker login', OR"
+            echo "  2. Set environment variables:"
+            echo "     export DOCKERHUB_USERNAME='your-username'"
+            echo "     export DOCKERHUB_PASSWORD='your-password-or-token'"
+            echo "${YELLOW}Continuing without Docker Hub authentication...${NC}"
+        fi
+    else
+        echo "${YELLOW}Docker Hub credentials not found${NC}"
+        echo "${YELLOW}To enable automatic Docker Hub authentication:${NC}"
+        echo "  1. Run 'docker login', OR"
+        echo "  2. Set environment variables:"
+        echo "     export DOCKERHUB_USERNAME='your-username'"
+        echo "     export DOCKERHUB_PASSWORD='your-password-or-token'"
+        echo "${YELLOW}Continuing without Docker Hub authentication...${NC}"
+    fi
+    echo ""
+}
+
 # Function to deploy SigNoz
 deploy_signoz() {
    local values_file="infrastructure/helm/signoz-values-$ENVIRONMENT.yaml"
@@ -278,12 +362,15 @@ main() {
    
    # Ensure namespace
    ensure_namespace
-    
+
    if [[ "$REMOVE" == true ]]; then
        remove_signoz
        exit 0
    fi
-    
+
+    # Create Docker Hub secret for image pulls
+    create_dockerhub_secret
+
    # Deploy SigNoz
    deploy_signoz
    
--- a/infrastructure/helm/signoz-values-dev.yaml
+++ b/infrastructure/helm/signoz-values-dev.yaml
@@ -7,74 +7,41 @@
 global:
  storageClass: "standard"
  domain: "monitoring.bakery-ia.local"
-  # Docker Hub credentials for pulling images
+  # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)
  imagePullSecrets:
-    - name: dockerhub-creds
+    - dockerhub-creds

-# Frontend Configuration
-frontend:
+# Docker Hub credentials for pulling images (root level for SigNoz components)
+imagePullSecrets:
+  - dockerhub-creds
+
+# SignOz Main Component (includes frontend and query service)
+signoz:
  replicaCount: 1
-  image:
-    repository: signoz/frontend
-    tag: 0.52.3
-    pullPolicy: IfNotPresent
-
-  service:
-    type: ClusterIP
-    port: 3301
-
-  ingress:
-    enabled: true
-    className: nginx
-    annotations:
-      nginx.ingress.kubernetes.io/rewrite-target: /$2
-      nginx.ingress.kubernetes.io/use-regex: "true"
-    hosts:
-      - host: monitoring.bakery-ia.local
-        paths:
-          - path: /signoz(/|$)(.*)
-            pathType: ImplementationSpecific
-    tls: []
-
-  resources:
-    requests:
-      cpu: 25m  # Reduced for local dev
-      memory: 64Mi  # Reduced for local dev
-    limits:
-      cpu: 200m
-      memory: 256Mi
-
-  env:
-    - name: FRONTEND_REFRESH_INTERVAL
-      value: "30000"
-    - name: BASE_URL
-      value: "https://monitoring.bakery-ia.local/signoz"
-
-# Query Service Configuration
-queryService:
-  replicaCount: 1
-  image:
-    repository: signoz/query-service
-    tag: 0.52.3
-    pullPolicy: IfNotPresent

  service:
    type: ClusterIP
    port: 8080

+  ingress:
+    enabled: true
+    className: nginx
+    annotations: {}
+    hosts:
+      - host: monitoring.bakery-ia.local
+        paths:
+          - path: /
+            pathType: Prefix
+            port: 8080
+    tls: []
+
  resources:
    requests:
-      cpu: 50m  # Reduced for local dev
-      memory: 128Mi  # Reduced for local dev
+      cpu: 100m  # Combined frontend + query service
+      memory: 256Mi
    limits:
-      cpu: 500m
-      memory: 512Mi
-
-  env:
-    - name: DEPLOYMENT_TYPE
-      value: "kubernetes-helm"
-    - name: SIGNOZ_LOCAL_DB_PATH
-      value: "/var/lib/signoz"
+      cpu: 1000m
+      memory: 1Gi

  persistence:
    enabled: true
@@ -135,6 +102,10 @@ clickhouse:
        cpu: 1000m
        memory: 1Gi

+# Zookeeper Configuration (required by ClickHouse)
+zookeeper:
+  enabled: true
+
 # OpenTelemetry Collector - Data ingestion endpoint for all telemetry
 otelCollector:
  enabled: true
@@ -262,8 +233,8 @@ otelCollector:
        timeout: 10s

      # ClickHouse exporter for metrics
-      clickhousemetricswrite:
-        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics
+      signozclickhousemetrics:
+        dsn: "tcp://admin:27ff0399-0d3a-4bd8-919d-17c2181e6fb9@signoz-clickhouse:9000/signoz_metrics"
        timeout: 10s

      # ClickHouse exporter for logs
@@ -271,9 +242,9 @@ otelCollector:
        dsn: tcp://signoz-clickhouse:9000/?database=signoz_logs
        timeout: 10s

-      # Logging exporter for debugging (optional)
-      logging:
-        loglevel: info
+      # Debug exporter for debugging (optional)
+      debug:
+        verbosity: detailed

    service:
      pipelines:
@@ -287,7 +258,7 @@ otelCollector:
        metrics:
          receivers: [otlp, postgresql/auth, postgresql/inventory, postgresql/orders, redis, rabbitmq]
          processors: [memory_limiter, batch, resourcedetection]
-          exporters: [clickhousemetricswrite]
+          exporters: [signozclickhousemetrics]

        # Logs pipeline
        logs:
--- a/infrastructure/helm/signoz-values-prod.yaml
+++ b/infrastructure/helm/signoz-values-prod.yaml
@@ -7,6 +7,13 @@
 global:
  storageClass: "standard"
  domain: "monitoring.bakewise.ai"
+  # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)
+  imagePullSecrets:
+    - dockerhub-creds
+
+# Docker Hub credentials for pulling images (root level for SigNoz components)
+imagePullSecrets:
+  - dockerhub-creds

 # Frontend Configuration
 frontend:
@@ -351,8 +358,8 @@ otelCollector:
          max_interval: 30s
          max_elapsed_time: 300s

-      clickhousemetricswrite:
-        endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+      signozclickhousemetrics:
+        endpoint: "tcp://clickhouse:9000/?database=signoz_metrics"
        timeout: 10s
        retry_on_failure:
          enabled: true
@@ -369,9 +376,9 @@ otelCollector:
          max_interval: 30s
          max_elapsed_time: 300s

-      # Minimal logging for prod
-      logging:
-        loglevel: warn
+      # Debug exporter for debugging (replaces deprecated logging exporter)
+      debug:
+        verbosity: detailed
        sampling_initial: 2
        sampling_thereafter: 500

@@ -381,17 +388,17 @@ otelCollector:
        traces:
          receivers: [otlp]
          processors: [memory_limiter, batch, resourcedetection, resource]
-          exporters: [clickhousetraces, logging]
+          exporters: [clickhousetraces, debug]

        metrics:
          receivers: [otlp, prometheus]
          processors: [memory_limiter, batch, resourcedetection, resource]
-          exporters: [clickhousemetricswrite]
+          exporters: [signozclickhousemetrics]

        logs:
          receivers: [otlp]
          processors: [memory_limiter, batch, resourcedetection, resource]
-          exporters: [clickhouselogsexporter, logging]
+          exporters: [clickhouselogsexporter, debug]

 # OpenTelemetry Collector Deployment Mode
 otelCollectorDeployment: