bakery-ia/infrastructure/monitoring/signoz/signoz-values-prod.yaml

# SigNoz Helm Chart Values - Production Environment
# High-availability configuration with resource optimization
# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by SigNoz Helm chart
#
# Official Chart: https://github.com/SigNoz/charts
# Install Command: helm install signoz signoz/signoz -n bakery-ia -f signoz-values-prod.yaml

global:
  storageClass: "microk8s-hostpath"  # For MicroK8s, use "microk8s-hostpath" or custom storage class
  clusterName: "bakery-ia-prod"
  domain: "monitoring.bakewise.ai"
  # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)

# Ingress configuration for SigNoz Frontend
# Configured to use HTTPS with TLS termination at ingress controller
# NOTE: SigNoz Helm chart expects ingress under "signoz.ingress", not "frontend.ingress"
# Reference: https://github.com/SigNoz/charts/blob/main/charts/signoz/values.yaml
signoz:
  ingress:
    enabled: true
    className: nginx
    annotations:
      nginx.ingress.kubernetes.io/ssl-redirect: "true"
      nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
      nginx.ingress.kubernetes.io/proxy-body-size: "100m"
      nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
      nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
      cert-manager.io/cluster-issuer: "letsencrypt-production"
      nginx.ingress.kubernetes.io/limit-rps: "50"
      nginx.ingress.kubernetes.io/limit-connections: "25"
    hosts:
      - host: monitoring.bakewise.ai
        paths:
          - path: /
            pathType: ImplementationSpecific
            port: 8080
    tls:
      - hosts:
          - monitoring.bakewise.ai
        secretName: bakery-ia-prod-tls-cert

# Resource configuration for production
# Optimized for 8 CPU core VPS deployment
clickhouse:
  persistence:
    size: 20Gi
  resources:
    requests:
      memory: "2Gi"
      cpu: "500m"
    limits:
      memory: "4Gi"
      cpu: "1000m"

otelCollector:
  resources:
    requests:
      memory: "1Gi"
      cpu: "500m"
    limits:
      memory: "2Gi"
      cpu: "1000m"
  # Additional config for Kubernetes infrastructure metrics scraping
  config:
    receivers:
      prometheus:
        config:
          scrape_configs:
            # Kube-state-metrics - Kubernetes object metrics
            - job_name: 'kube-state-metrics'
              static_configs:
                - targets: ['kube-state-metrics.bakery-ia.svc.cluster.local:8080']
              scrape_interval: 30s
              metric_relabel_configs:
                - source_labels: [__name__]
                  regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset|replicaset|job|cronjob|persistentvolume|persistentvolumeclaim|resourcequota|service|configmap|secret).*'
                  action: keep
            # Node-exporter - Host-level metrics
            - job_name: 'node-exporter'
              static_configs:
                - targets: ['node-exporter-prometheus-node-exporter.bakery-ia.svc.cluster.local:9100']
              scrape_interval: 30s
              metric_relabel_configs:
                - source_labels: [__name__]
                  regex: 'node_(cpu|memory|disk|filesystem|network|load).*'
                  action: keep
    service:
      pipelines:
        metrics:
          receivers: [otlp, prometheus]

queryService:
  resources:
    requests:
      memory: "1Gi"
      cpu: "500m"
    limits:
      memory: "2Gi"
      cpu: "1000m"

alertmanager:
  resources:
    requests:
      memory: "512Mi"
      cpu: "250m"
    limits:
      memory: "1Gi"
      cpu: "500m"