feat(apps): export logs to open telemetry endpoint

README.md

@@ -126,11 +126,12 @@ These health checks are integrated with Azure Container Apps' health probe syste
 
 ## Observability with OpenTelemetry
 
-This project uses OpenTelemetry for distributed tracing and metrics collection. The setup includes:
+This project uses OpenTelemetry for distributed tracing, metrics collection, and logging. The setup includes:
 
 ### Core Features
 - Distributed tracing across services
 - Runtime and application metrics
+- Log aggregation and correlation
 - Integration with Azure Monitor/Application Insights
 - Support for both OTLP and Azure Monitor exporters
 - Automatic instrumentation for:
@@ -157,15 +158,72 @@ OpenTelemetry is configured through environment variables that are automatically
 ### Local Development
 
 For local development, the project includes a docker-compose setup with:
-- OpenTelemetry Collector
-- Grafana
-- Other supporting services
+- OpenTelemetry Collector (ports 4317/4318 for OTLP receivers)
+- Grafana (port 3000)
+- Jaeger (port 16686)
+- Loki (port 3100)
+- Prometheus (port 9090)
 
 To run the local observability stack:
 ```bash
 podman compose -f docker-compose-otel.yml up
 ```
 
+### Accessing Observability Tools
+
+Once the local stack is running, you can access the following tools:
+
+#### Distributed Tracing with Jaeger
+- URL: http://localhost:16686
+- Features:
+  - View distributed traces across services
+  - Search by service, operation, or trace ID
+  - Analyze timing and dependencies
+  - Debug request flows and errors
+
+#### Metrics with Prometheus
+- URL: http://localhost:9090
+- Features:
+  - Query raw metrics data
+  - View metric targets and service discovery
+  - Debug metric collection
+
+#### Log Aggregation with Loki
+- Direct URL: http://localhost:3100
+- Grafana Integration: http://localhost:3000 (preferred interface)
+- Features:
+  - Search and filter logs across all services
+  - Correlate logs with traces using trace IDs
+  - Create log-based alerts and dashboards
+  - Use LogQL to query logs:
+    ```logql
+    # Example: Find all error logs
+    {container="web-api"} |= "error"
+
+    # Example: Find logs with specific trace ID
+    {container=~"web-api|graphql"} |~ "trace_id=([a-f0-9]{32})"
+    ```
+
+#### Metrics and Dashboards in Grafana
+- URL: http://localhost:3000
+- Features:
+  - Pre-configured dashboards for:
+    - Application metrics
+    - Runtime metrics
+    - HTTP request metrics
+  - Data sources:
+    - Prometheus (metrics)
+    - Loki (logs)
+    - Jaeger (traces)
+  - Create custom dashboards
+  - Set up alerts
+
+#### OpenTelemetry Collector Endpoints
+- OTLP gRPC receiver: localhost:4317
+- OTLP HTTP receiver: localhost:4318
+- Prometheus metrics: localhost:8888
+- Prometheus exporter metrics: localhost:8889
+
 ### Request Filtering
 
 The telemetry setup includes smart filtering to:

docker-compose-otel.yml

@@ -22,6 +22,12 @@ services:
       - "14250:14250" # Model used by collector
     environment:
       - COLLECTOR_OTLP_ENABLED=true
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "localhost:16686"]
+      interval: 3s
+      timeout: 3s
+      retries: 10
+      start_period: 10s
 
   # Prometheus for metrics
   prometheus:
@@ -31,6 +37,21 @@ services:
     ports:
       - "9090:9090"
 
+  # Loki for log aggregation
+  loki:
+    image: grafana/loki:3.2.2
+    ports:
+      - "3100:3100"
+    volumes:
+      - ./local-otel-configuration/loki-config.yaml:/etc/loki/local-config.yaml
+    command: -config.file=/etc/loki/local-config.yaml
+    healthcheck:
+      test: ["CMD-SHELL", "wget -q --tries=1 -O- http://localhost:3100/ready"]
+      interval: 3s
+      timeout: 3s
+      retries: 10
+      start_period: 10s
+
   # Grafana for metrics visualization
   grafana:
     image: grafana/grafana:11.4.0
@@ -43,3 +64,5 @@ services:
       - ./local-otel-configuration/grafana-datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml
       - ./local-otel-configuration/grafana-dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml
       - ./local-otel-configuration/dashboards:/etc/grafana/provisioning/dashboards
+    depends_on:
+      - loki

local-otel-configuration/dashboards/runtime-metrics.json

@@ -85,13 +85,19 @@
             "type": "timeseries",
             "targets": [
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
                     "expr": "dialogporten_process_runtime_dotnet_gc_heap_size_bytes",
                     "legendFormat": "Heap Size",
                     "refId": "A"
+                },
+                {
+                    "expr": "dialogporten_process_runtime_dotnet_gc_committed_memory_size_bytes",
+                    "legendFormat": "Committed Memory",
+                    "refId": "B"
+                },
+                {
+                    "expr": "dialogporten_dotnet_process_memory_working_set_bytes",
+                    "legendFormat": "Working Set",
+                    "refId": "C"
                 }
             ]
         },
@@ -171,13 +177,14 @@
             "type": "timeseries",
             "targets": [
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
                     "expr": "rate(dialogporten_process_runtime_dotnet_gc_collections_count_total[5m])",
-                    "legendFormat": "Gen {{generation}}",
+                    "legendFormat": "Collections/sec",
                     "refId": "A"
+                },
+                {
+                    "expr": "rate(dialogporten_process_runtime_dotnet_gc_duration_nanoseconds_total[5m])",
+                    "legendFormat": "GC Duration/sec",
+                    "refId": "B"
                 }
             ]
         },
@@ -257,22 +264,19 @@
             "type": "timeseries",
             "targets": [
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
                     "expr": "dialogporten_process_runtime_dotnet_thread_pool_queue_length",
                     "legendFormat": "Queue Length",
                     "refId": "A"
                 },
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
                     "expr": "dialogporten_process_runtime_dotnet_thread_pool_threads_count",
                     "legendFormat": "Thread Count",
                     "refId": "B"
+                },
+                {
+                    "expr": "rate(dialogporten_process_runtime_dotnet_thread_pool_completed_items_count_total[5m])",
+                    "legendFormat": "Completed Items/sec",
+                    "refId": "C"
                 }
             ]
         },
@@ -352,20 +356,12 @@
             "type": "timeseries",
             "targets": [
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
-                    "expr": "rate(dialogporten_process_runtime_dotnet_exceptions_count_total[$__rate_interval])",
+                    "expr": "rate(dialogporten_process_runtime_dotnet_exceptions_count_total[5m])",
                     "legendFormat": "Exceptions/sec",
                     "refId": "A"
                 },
                 {
-                    "datasource": {
-                        "type": "prometheus",
-                        "uid": "Prometheus"
-                    },
-                    "expr": "rate(dialogporten_process_runtime_dotnet_monitor_lock_contention_count_total[$__rate_interval])",
+                    "expr": "rate(dialogporten_process_runtime_dotnet_monitor_lock_contention_count_total[5m])",
                     "legendFormat": "Lock Contentions/sec",
                     "refId": "B"
                 }

local-otel-configuration/grafana-datasources.yml

@@ -5,4 +5,11 @@ datasources:
     type: prometheus
     access: proxy
     url: http://prometheus:9090
-    isDefault: true 
+    isDefault: true
+
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    jsonData:
+      maxLines: 1000

local-otel-configuration/loki-config.yaml

@@ -0,0 +1,45 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  path_prefix: /tmp/loki
+
+compactor:
+  working_directory: /tmp/loki/compactor
+  compaction_interval: 10m
+
+ingester:
+  lifecycler:
+    address: 127.0.0.1
+    ring:
+      kvstore:
+        store: inmemory
+      replication_factor: 1
+    final_sleep: 0s
+  chunk_idle_period: 5m
+  chunk_retain_period: 30s
+
+schema_config:
+  configs:
+    - from: 2020-10-24
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+storage_config:
+  tsdb_shipper:
+    active_index_directory: /tmp/loki/tsdb-index
+    cache_location: /tmp/loki/tsdb-cache
+    cache_ttl: 24h
+  filesystem:
+    directory: /tmp/loki/chunks
+
+limits_config:
+  reject_old_samples: true
+  reject_old_samples_max_age: 168h
+  allow_structured_metadata: true

local-otel-configuration/otel-collector-config.yaml

@@ -25,6 +25,8 @@ exporters:
     verbosity: detailed
     sampling_initial: 5
     sampling_thereafter: 200
+  otlphttp:
+    endpoint: "http://loki:3100/otlp"
 
 extensions:
   health_check:
@@ -49,4 +51,4 @@ service:
     logs:
       receivers: [otlp]
       processors: [batch]
-      exporters: [debug]
+      exporters: [otlphttp, debug]