Imporve monitoring 2

infrastructure/helm/signoz-values-dev.yaml

@@ -1,11 +1,13 @@
 # SigNoz Helm Chart Values - Development Environment
 # Optimized for local development with minimal resource usage
+# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by bakery-ingress
 #
 # Official Chart: https://github.com/SigNoz/charts
-# Install Command: helm install signoz signoz/signoz -n signoz --create-namespace -f signoz-values-dev.yaml
+# Install Command: helm install signoz signoz/signoz -n bakery-ia -f signoz-values-dev.yaml
 
 global:
   storageClass: "standard"
+  clusterName: "bakery-ia-dev"
   domain: "monitoring.bakery-ia.local"
   # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)
   imagePullSecrets:
@@ -23,17 +25,10 @@ signoz:
     type: ClusterIP
     port: 8080
 
+  # DISABLE built-in ingress - using unified bakery-ingress instead
+  # Route configured in infrastructure/kubernetes/overlays/dev/dev-ingress.yaml
   ingress:
-    enabled: true
-    className: nginx
-    annotations: {}
-    hosts:
-      - host: monitoring.bakery-ia.local
-        paths:
-          - path: /
-            pathType: Prefix
-            port: 8080
-    tls: []
+    enabled: false
 
   resources:
     requests:
@@ -43,6 +38,17 @@ signoz:
       cpu: 1000m
       memory: 1Gi
 
+  # Environment variables (new format - replaces configVars)
+  env:
+    signoz_telemetrystore_provider: "clickhouse"
+    dot_metrics_enabled: "true"
+    signoz_emailing_enabled: "false"
+    signoz_alertmanager_provider: "signoz"
+    # Retention for dev (7 days)
+    signoz_traces_ttl_duration_hrs: "168"
+    signoz_metrics_ttl_duration_hrs: "168"
+    signoz_logs_ttl_duration_hrs: "168"
+
   persistence:
     enabled: true
     size: 5Gi
@@ -92,6 +98,11 @@ clickhouse:
   enabled: true
   installCustomStorageClass: false
 
+  image:
+    registry: docker.io
+    repository: clickhouse/clickhouse-server
+    tag: 25.5.6  # Official recommended version
+
   # Reduce ClickHouse resource requests for local dev
   clickhouse:
     resources:
@@ -102,15 +113,39 @@ clickhouse:
         cpu: 1000m
         memory: 1Gi
 
+  persistence:
+    enabled: true
+    size: 20Gi
+
 # Zookeeper Configuration (required by ClickHouse)
 zookeeper:
   enabled: true
+  replicaCount: 1  # Single replica for dev
+
+  image:
+    tag: 3.7.1  # Official recommended version
+
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
+
+  persistence:
+    enabled: true
+    size: 5Gi
 
 # OpenTelemetry Collector - Data ingestion endpoint for all telemetry
 otelCollector:
   enabled: true
   replicaCount: 1
 
+  image:
+    repository: signoz/signoz-otel-collector
+    tag: v0.129.12  # Latest recommended version
+
   # Service configuration - expose both gRPC and HTTP endpoints
   service:
     type: ClusterIP
@@ -130,6 +165,11 @@ otelCollector:
         port: 8889
         targetPort: 8889
         protocol: TCP
+      # Metrics
+      - name: metrics
+        port: 8888
+        targetPort: 8888
+        protocol: TCP
 
   resources:
     requests:
@@ -210,10 +250,11 @@ otelCollector:
         collection_interval: 60s
 
     processors:
-      # Batch processor for better performance
+      # Batch processor for better performance (optimized for high throughput)
       batch:
-        timeout: 10s
-        send_batch_size: 1024
+        timeout: 1s
+        send_batch_size: 10000  # Increased from 1024 for better performance
+        send_batch_max_size: 10000
 
       # Memory limiter to prevent OOM
       memory_limiter:
@@ -223,35 +264,57 @@ otelCollector:
 
       # Resource detection
       resourcedetection:
-        detectors: [env, system]
+        detectors: [env, system, docker]
         timeout: 5s
 
+      # Span metrics processor for automatic service metrics
+      spanmetrics:
+        metrics_exporter: signozclickhousemetrics
+        latency_histogram_buckets: [2ms, 4ms, 6ms, 8ms, 10ms, 50ms, 100ms, 200ms, 400ms, 800ms, 1s, 1400ms, 2s, 5s, 10s, 15s]
+        dimensions_cache_size: 10000
+
     exporters:
       # ClickHouse exporter for traces
       clickhousetraces:
         datasource: tcp://signoz-clickhouse:9000/?database=signoz_traces
         timeout: 10s
+        retry_on_failure:
+          enabled: true
+          initial_interval: 5s
+          max_interval: 30s
+          max_elapsed_time: 300s
 
       # ClickHouse exporter for metrics
       signozclickhousemetrics:
         dsn: "tcp://admin:27ff0399-0d3a-4bd8-919d-17c2181e6fb9@signoz-clickhouse:9000/signoz_metrics"
         timeout: 10s
+        retry_on_failure:
+          enabled: true
+          initial_interval: 5s
+          max_interval: 30s
+          max_elapsed_time: 300s
 
       # ClickHouse exporter for logs
       clickhouselogsexporter:
         dsn: tcp://signoz-clickhouse:9000/?database=signoz_logs
         timeout: 10s
+        retry_on_failure:
+          enabled: true
+          initial_interval: 5s
+          max_interval: 30s
 
       # Debug exporter for debugging (optional)
       debug:
         verbosity: detailed
+        sampling_initial: 5
+        sampling_thereafter: 200
 
     service:
       pipelines:
         # Traces pipeline
         traces:
           receivers: [otlp]
-          processors: [memory_limiter, batch, resourcedetection]
+          processors: [memory_limiter, batch, spanmetrics, resourcedetection]
           exporters: [clickhousetraces]
 
         # Metrics pipeline