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 upgrade --install signoz signoz/signoz -n bakery-ia -f signoz-values-prod.yaml
#
# IMPORTANT: This chart works together with k8s-infra chart for infrastructure monitoring
# Deploy k8s-infra after this: helm upgrade --install k8s-infra signoz/k8s-infra -n bakery-ia -f k8s-infra-values-prod.yaml
#
# MEMORY OPTIMIZATION NOTES:
# - ClickHouse memory increased to 8Gi to prevent OOM errors
# - Retention reduced to 3 days for traces, 7 days for metrics/logs

global:
  storageClass: "microk8s-hostpath"
  clusterName: "bakery-ia-prod"
  domain: "monitoring.bakewise.ai"

# Ingress configuration for SigNoz Frontend
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

# ============================================================================
# CLICKHOUSE CONFIGURATION
# Increased memory to 8Gi to prevent OOM errors (was 4Gi, causing code 241 errors)
# ============================================================================
clickhouse:
  persistence:
    size: 20Gi
  resources:
    requests:
      memory: "4Gi"
      cpu: "1000m"
    limits:
      memory: "8Gi"
      cpu: "2000m"

  # Server-level settings only (NOT user-level settings like max_threads)
  # User-level settings must go in profiles section
  settings:
    # Max server memory usage: 80% of container limit (6.4GB of 8GB)
    max_server_memory_usage: "6400000000"
    # Mark cache size (256MB)
    mark_cache_size: "268435456"
    # Uncompressed cache (256MB)
    uncompressed_cache_size: "268435456"
    # Max concurrent queries
    max_concurrent_queries: "100"

  # User-level settings go in profiles
  profiles:
    default:
      # Max memory per query: 2GB
      max_memory_usage: "2000000000"
      # Max threads per query
      max_threads: "4"
      # Background merges memory limit
      max_bytes_to_merge_at_max_space_in_pool: "1073741824"

  coldStorage:
    enabled: false

# ============================================================================
# DATA RETENTION CONFIGURATION
# Reduced retention to minimize storage and memory pressure
# ============================================================================
queryService:
  resources:
    requests:
      memory: "1Gi"
      cpu: "500m"
    limits:
      memory: "2Gi"
      cpu: "1000m"
  # Retention configuration via environment variables
  configVars:
    # Trace retention: 3 days (72 hours)
    SIGNOZ_TRACE_TTL_DURATION_HOURS: "72"
    # Logs retention: 7 days (168 hours)
    SIGNOZ_LOGS_TTL_DURATION_HOURS: "168"
    # Metrics retention: 7 days (168 hours)
    SIGNOZ_METRICS_TTL_DURATION_HOURS: "168"

# ============================================================================
# OTEL COLLECTOR CONFIGURATION
# This collector receives data from:
# - Application services (traces, logs, metrics via OTLP)
# - k8s-infra chart (infrastructure metrics)
# ============================================================================
otelCollector:
  resources:
    requests:
      memory: "1Gi"
      cpu: "500m"
    limits:
      memory: "2Gi"
      cpu: "1000m"

# ============================================================================
# ALERTMANAGER CONFIGURATION
# ============================================================================
alertmanager:
  resources:
    requests:
      memory: "512Mi"
      cpu: "250m"
    limits:
      memory: "1Gi"
      cpu: "500m"

# ============================================================================
# ZOOKEEPER CONFIGURATION
# ============================================================================
zookeeper:
  resources:
    requests:
      memory: "512Mi"
      cpu: "250m"
    limits:
      memory: "1Gi"
      cpu: "500m"
  persistence:
    size: 5Gi