Добавлен сбор телеметрии на ВМ2

VM2_services/codebase/services/observability/otel-collector.yaml

@@ -11,6 +11,43 @@ receivers:
         endpoint: 0.0.0.0:4317
       http:
         endpoint: 0.0.0.0:4318
+  prometheus:
+    config:
+      scrape_configs:
+        - job_name: otel-collector
+          scrape_interval: 30s
+          static_configs:
+            - targets: ["127.0.0.1:8888"]
+              labels:
+                service_name: otel-collector
+        - job_name: redis-safety
+          scrape_interval: 30s
+          static_configs:
+            - targets: ["redis-exporter:9121"]
+              labels:
+                service_name: redis
+        - job_name: nginx
+          scrape_interval: 30s
+          static_configs:
+            - targets: ["nginx-exporter:9113"]
+              labels:
+                service_name: nginx
+  hostmetrics:
+    root_path: /hostfs
+    collection_interval: 30s
+    scrapers:
+      cpu:
+      disk:
+      filesystem:
+        exclude_mount_points:
+          mount_points:
+            - /hostfs/(dev|proc|sys|run)($|/)
+          match_type: regexp
+      load:
+      memory:
+      network:
+      paging:
+      processes:
 
 processors:
   memory_limiter:
@@ -19,7 +56,7 @@ processors:
     spike_limit_mib: 96
   resource/vm2:
     attributes:
-      - {key: service.namespace, value: han-processing, action: upsert}
+      - {key: service.namespace, value: han-chat, action: upsert}
       - {key: deployment.environment, value: "${env:APP_ENV}", action: upsert}
       - {key: service.version, value: "${env:RELEASE_VERSION}", action: upsert}
   attributes/redact:
@@ -39,6 +76,32 @@ processors:
       - {key: messaging.message.body, action: delete}
       - {key: aws.s3.key, action: delete}
       - {key: s3.object.key, action: delete}
+  filter/noise:
+    error_mode: ignore
+    traces:
+      span:
+        - 'attributes["http.route"] == "/health/live"'
+        - 'attributes["http.route"] == "/nginx-health/live"'
+    logs:
+      log_record:
+        - 'severity_number < SEVERITY_NUMBER_INFO'
+  tail_sampling:
+    decision_wait: 10s
+    num_traces: 10000
+    expected_new_traces_per_sec: 50
+    policies:
+      - name: errors
+        type: status_code
+        status_code:
+          status_codes: [ERROR]
+      - name: slow
+        type: latency
+        latency:
+          threshold_ms: 1000
+      - name: baseline
+        type: probabilistic
+        probabilistic:
+          sampling_percentage: 10
   batch:
     timeout: 5s
     send_batch_size: 1024
@@ -64,13 +127,16 @@ service:
   pipelines:
     traces:
       receivers: [otlp]
-      processors: [memory_limiter, resource/vm2, attributes/redact, batch]
+      processors: [memory_limiter, resource/vm2, attributes/redact, filter/noise, tail_sampling, batch]
       exporters: [otlp/remote]
     metrics:
-      receivers: [otlp]
+      receivers: [otlp, prometheus, hostmetrics]
       processors: [memory_limiter, resource/vm2, attributes/redact, batch]
       exporters: [otlp/remote]
     logs:
       receivers: [otlp]
-      processors: [memory_limiter, resource/vm2, attributes/redact, batch]
+      processors: [memory_limiter, resource/vm2, attributes/redact, filter/noise, batch]
       exporters: [otlp/remote]
+  telemetry:
+    metrics:
+      address: 0.0.0.0:8888