bakery-ia/infrastructure/helm/signoz-values-dev.yaml

# SigNoz Helm Chart Values - Development Environment
# Optimized for local development with minimal resource usage
#
# Official Chart: https://github.com/SigNoz/charts
# Install Command: helm install signoz signoz/signoz -n signoz --create-namespace -f signoz-values-dev.yaml

global:
  storageClass: "standard"
  domain: "monitoring.bakery-ia.local"
  # Docker Hub credentials for pulling images
  imagePullSecrets:
    - name: dockerhub-creds

# Frontend Configuration
frontend:
  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

  resources:
    requests:
      cpu: 50m  # Reduced for local dev
      memory: 128Mi  # Reduced for local dev
    limits:
      cpu: 500m
      memory: 512Mi

  env:
    - name: DEPLOYMENT_TYPE
      value: "kubernetes-helm"
    - name: SIGNOZ_LOCAL_DB_PATH
      value: "/var/lib/signoz"

  persistence:
    enabled: true
    size: 5Gi
    storageClass: "standard"

# AlertManager Configuration
alertmanager:
  replicaCount: 1
  image:
    repository: signoz/alertmanager
    tag: 0.23.5
    pullPolicy: IfNotPresent

  service:
    type: ClusterIP
    port: 9093

  resources:
    requests:
      cpu: 25m  # Reduced for local dev
      memory: 64Mi  # Reduced for local dev
    limits:
      cpu: 200m
      memory: 256Mi

  persistence:
    enabled: true
    size: 2Gi
    storageClass: "standard"

  config:
    global:
      resolve_timeout: 5m
    route:
      group_by: ['alertname', 'cluster', 'service']
      group_wait: 10s
      group_interval: 10s
      repeat_interval: 12h
      receiver: 'default'
    receivers:
      - name: 'default'
        # Add email, slack, webhook configs here

# ClickHouse Configuration - Time Series Database
# Minimal resources for local development on constrained Kind cluster
clickhouse:
  enabled: true
  installCustomStorageClass: false

  # Reduce ClickHouse resource requests for local dev
  clickhouse:
    resources:
      requests:
        cpu: 200m  # Reduced from default 500m
        memory: 512Mi
      limits:
        cpu: 1000m
        memory: 1Gi

# OpenTelemetry Collector - Data ingestion endpoint for all telemetry
otelCollector:
  enabled: true
  replicaCount: 1

  # Service configuration - expose both gRPC and HTTP endpoints
  service:
    type: ClusterIP
    ports:
      # gRPC receivers
      - name: otlp-grpc
        port: 4317
        targetPort: 4317
        protocol: TCP
      # HTTP receivers
      - name: otlp-http
        port: 4318
        targetPort: 4318
        protocol: TCP
      # Prometheus remote write
      - name: prometheus
        port: 8889
        targetPort: 8889
        protocol: TCP

  resources:
    requests:
      cpu: 50m   # Reduced from 100m
      memory: 128Mi  # Reduced from 256Mi
    limits:
      cpu: 500m
      memory: 512Mi

  # OpenTelemetry Collector configuration
  config:
    receivers:
      # OTLP receivers for traces, metrics, and logs from applications
      # All application telemetry is pushed via OTLP protocol
      otlp:
        protocols:
          grpc:
            endpoint: 0.0.0.0:4317
          http:
            endpoint: 0.0.0.0:4318
            cors:
              allowed_origins:
                - "*"

      # PostgreSQL receivers for database metrics
      # Collects metrics directly from PostgreSQL databases
      postgresql/auth:
        endpoint: auth-db-service.bakery-ia:5432
        username: ${POSTGRES_MONITOR_USER}
        password: ${POSTGRES_MONITOR_PASSWORD}
        databases:
          - auth_db
        collection_interval: 60s
        tls:
          insecure: false

      postgresql/inventory:
        endpoint: inventory-db-service.bakery-ia:5432
        username: ${POSTGRES_MONITOR_USER}
        password: ${POSTGRES_MONITOR_PASSWORD}
        databases:
          - inventory_db
        collection_interval: 60s
        tls:
          insecure: false

      postgresql/orders:
        endpoint: orders-db-service.bakery-ia:5432
        username: ${POSTGRES_MONITOR_USER}
        password: ${POSTGRES_MONITOR_PASSWORD}
        databases:
          - orders_db
        collection_interval: 60s
        tls:
          insecure: false

      # Add more PostgreSQL databases as needed
      # postgresql/SERVICE:
      #   endpoint: SERVICE-db-service.bakery-ia:5432
      #   ...

      # Redis receiver for cache metrics
      redis:
        endpoint: redis-service.bakery-ia:6379
        password: ${REDIS_PASSWORD}
        collection_interval: 60s
        tls:
          insecure: false
          cert_file: /etc/redis-tls/redis-cert.pem
          key_file: /etc/redis-tls/redis-key.pem
          ca_file: /etc/redis-tls/ca-cert.pem

      # RabbitMQ receiver via management API
      rabbitmq:
        endpoint: http://rabbitmq-service.bakery-ia:15672
        username: ${RABBITMQ_USER}
        password: ${RABBITMQ_PASSWORD}
        collection_interval: 60s

    processors:
      # Batch processor for better performance
      batch:
        timeout: 10s
        send_batch_size: 1024

      # Memory limiter to prevent OOM
      memory_limiter:
        check_interval: 1s
        limit_mib: 400
        spike_limit_mib: 100

      # Resource detection
      resourcedetection:
        detectors: [env, system]
        timeout: 5s

    exporters:
      # ClickHouse exporter for traces
      clickhousetraces:
        datasource: tcp://signoz-clickhouse:9000/?database=signoz_traces
        timeout: 10s

      # ClickHouse exporter for metrics
      clickhousemetricswrite:
        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics
        timeout: 10s

      # ClickHouse exporter for logs
      clickhouselogsexporter:
        dsn: tcp://signoz-clickhouse:9000/?database=signoz_logs
        timeout: 10s

      # Logging exporter for debugging (optional)
      logging:
        loglevel: info

    service:
      pipelines:
        # Traces pipeline
        traces:
          receivers: [otlp]
          processors: [memory_limiter, batch, resourcedetection]
          exporters: [clickhousetraces]

        # Metrics pipeline
        metrics:
          receivers: [otlp, postgresql/auth, postgresql/inventory, postgresql/orders, redis, rabbitmq]
          processors: [memory_limiter, batch, resourcedetection]
          exporters: [clickhousemetricswrite]

        # Logs pipeline
        logs:
          receivers: [otlp]
          processors: [memory_limiter, batch, resourcedetection]
          exporters: [clickhouselogsexporter]

# Additional Configuration
serviceAccount:
  create: true
  annotations: {}
  name: ""

# Security Context
securityContext:
  runAsNonRoot: true
  runAsUser: 1000
  fsGroup: 1000

# Network Policies (disabled for dev)
networkPolicy:
  enabled: false

# Monitoring SigNoz itself
selfMonitoring:
  enabled: true
  serviceMonitor:
    enabled: false