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: "localhost"

# 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: /$2
      nginx.ingress.kubernetes.io/use-regex: "true"
    hosts:
      - host: localhost
        paths:
          - path: /signoz(/|$)(.*)
            pathType: ImplementationSpecific
    tls: []

  resources:
    requests:
      cpu: 50m
      memory: 128Mi
    limits:
      cpu: 200m
      memory: 256Mi

  env:
    - name: FRONTEND_REFRESH_INTERVAL
      value: "30000"

# 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: 100m
      memory: 256Mi
    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: 50m
      memory: 128Mi
    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
clickhouse:
  replicaCount: 1
  image:
    repository: clickhouse/clickhouse-server
    tag: 24.1.2-alpine
    pullPolicy: IfNotPresent

  service:
    type: ClusterIP
    httpPort: 8123
    tcpPort: 9000

  resources:
    requests:
      cpu: 500m
      memory: 512Mi
    limits:
      cpu: 1000m
      memory: 1Gi

  persistence:
    enabled: true
    size: 10Gi
    storageClass: "standard"

  # ClickHouse configuration
  config:
    logger:
      level: information
    max_connections: 1024
    max_concurrent_queries: 100
    # Data retention (7 days for dev)
    merge_tree:
      parts_to_delay_insert: 150
      parts_to_throw_insert: 300

# OpenTelemetry Collector - Integrated with SigNoz
otelCollector:
  enabled: true
  replicaCount: 1
  image:
    repository: signoz/signoz-otel-collector
    tag: 0.102.8
    pullPolicy: IfNotPresent

  service:
    type: ClusterIP
    ports:
      otlpGrpc: 4317
      otlpHttp: 4318
      metrics: 8888
      healthCheck: 13133

  resources:
    requests:
      cpu: 100m
      memory: 256Mi
    limits:
      cpu: 500m
      memory: 512Mi

  # Full OTEL Collector Configuration
  config:
    extensions:
      health_check:
        endpoint: 0.0.0.0:13133
      zpages:
        endpoint: 0.0.0.0:55679

    receivers:
      otlp:
        protocols:
          grpc:
            endpoint: 0.0.0.0:4317
          http:
            endpoint: 0.0.0.0:4318
            cors:
              allowed_origins:
                - "http://localhost"
                - "https://localhost"

      # Prometheus receiver for scraping metrics
      prometheus:
        config:
          scrape_configs:
            - job_name: 'otel-collector'
              scrape_interval: 30s
              static_configs:
                - targets: ['localhost:8888']

    processors:
      batch:
        timeout: 10s
        send_batch_size: 1024

      memory_limiter:
        check_interval: 1s
        limit_mib: 400
        spike_limit_mib: 100

      # Resource detection for K8s
      resourcedetection:
        detectors: [env, system, docker]
        timeout: 5s

      # Add resource attributes
      resource:
        attributes:
          - key: deployment.environment
            value: development
            action: upsert

    exporters:
      # Export to SigNoz ClickHouse
      clickhousetraces:
        datasource: tcp://clickhouse:9000/?database=signoz_traces
        timeout: 10s

      clickhousemetricswrite:
        endpoint: tcp://clickhouse:9000/?database=signoz_metrics
        timeout: 10s

      clickhouselogsexporter:
        dsn: tcp://clickhouse:9000/?database=signoz_logs
        timeout: 10s

      # Debug logging
      logging:
        loglevel: info
        sampling_initial: 5
        sampling_thereafter: 200

    service:
      extensions: [health_check, zpages]
      pipelines:
        traces:
          receivers: [otlp]
          processors: [memory_limiter, batch, resourcedetection, resource]
          exporters: [clickhousetraces, logging]

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

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

# OpenTelemetry Collector Deployment Mode
otelCollectorDeployment:
  enabled: true
  mode: deployment

# Node Exporter for infrastructure metrics (optional)
nodeExporter:
  enabled: true
  service:
    type: ClusterIP
    port: 9100

  resources:
    requests:
      cpu: 50m
      memory: 64Mi
    limits:
      cpu: 100m
      memory: 128Mi

# Schemamanager - Manages ClickHouse schema
schemamanager:
  enabled: true
  image:
    repository: signoz/signoz-schema-migrator
    tag: 0.52.3
    pullPolicy: IfNotPresent

# 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