Otel grafana

context/otel-stack/grafana-datasources.yaml

@@ -0,0 +1,30 @@
+apiVersion: 1
+
+datasources:
+    - name: Prometheus
+      type: prometheus
+      uid: prometheus
+      access: proxy
+      orgId: 1
+      url: http://prometheus:9090
+      basicAuth: false
+      isDefault: false
+      version: 1
+      editable: false
+      jsonData:
+          httpMethod: GET
+    - name: Tempo
+      type: tempo
+      access: proxy
+      orgId: 1
+      url: http://tempo:3200
+      basicAuth: false
+      isDefault: true
+      version: 1
+      editable: false
+      apiVersion: 1
+      uid: tempo
+      jsonData:
+          httpMethod: GET
+          serviceMap:
+              datasourceUid: prometheus

context/otel-stack/otel-collector.yaml

@@ -0,0 +1,16 @@
+receivers:
+    otlp:
+        protocols:
+            grpc:
+            http:
+
+exporters:
+    otlp:
+        endpoint: tempo:4317
+        tls:
+            insecure: true
+service:
+    pipelines:
+        traces:
+            receivers: [otlp]
+            exporters: [otlp]

context/otel-stack/prometheus.yaml

@@ -0,0 +1,11 @@
+global:
+    scrape_interval: 15s
+    evaluation_interval: 15s
+
+scrape_configs:
+    - job_name: 'prometheus'
+      static_configs:
+          - targets: ['localhost:9090']
+    - job_name: 'tempo'
+      static_configs:
+          - targets: ['tempo:3200']

context/otel-stack/tempo.yaml

@@ -0,0 +1,65 @@
+stream_over_http_enabled: true
+server:
+    http_listen_port: 3200
+    log_level: info
+
+query_frontend:
+    search:
+        duration_slo: 5s
+        throughput_bytes_slo: 1.073741824e+09
+    trace_by_id:
+        duration_slo: 5s
+
+distributor:
+    receivers: # this configuration will listen on all ports and protocols that tempo is capable of.
+        jaeger: # the receives all come from the OpenTelemetry collector.  more configuration information can
+            protocols: # be found there: https://github.com/open-telemetry/opentelemetry-collector/tree/main/receiver
+                thrift_http: #
+                grpc: # for a production deployment you should only enable the receivers you need!
+                thrift_binary:
+                thrift_compact:
+        zipkin:
+        otlp:
+            protocols:
+                http:
+                grpc:
+        opencensus:
+
+ingester:
+    max_block_duration: 5m # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally
+
+compactor:
+    compaction:
+        block_retention: 1h # overall Tempo trace retention. set for demo purposes
+
+metrics_generator:
+    registry:
+        external_labels:
+            source: tempo
+            cluster: docker-compose
+    storage:
+        path: /var/tempo/generator/wal
+        remote_write:
+            - url: http://prometheus:9090/api/v1/write
+              send_exemplars: true
+    traces_storage:
+        path: /var/tempo/generator/traces
+
+storage:
+    trace:
+        backend: local # backend configuration to use
+        wal:
+            path: /var/tempo/wal # where to store the wal locally
+        local:
+            path: /var/tempo/blocks
+
+overrides:
+    defaults:
+        global:
+            max_bytes_per_trace: 100000000
+        ingestion:
+            max_traces_per_user: 10000
+        read:
+            max_bytes_per_tag_values_query: 100000000
+        metrics_generator:
+            processors: [service-graphs, span-metrics, local-blocks] # enables metrics generator

docs/06-configuring-services.md

@@ -16,6 +16,7 @@ This document describes configuration options of the services shipped with Spryk
 *     [WebDriver](#webdriver)
 *     [Dashboard](#dashboard)
 *     [Tideways](#tideways)
+*     [Local OpenTelemetry Stack](#grafana)
 
 
 ## Prerequisites
@@ -528,7 +529,7 @@ docker/sdk up
 
 By default, in the New Relic dashboard, the APM is displayed as `company-staging-newrelic-app`. To improve visibility, you may want to configure each application as a separate APM. For example, `YVES-DE (docker.dev)`.
 
-To do it, adjust the Monitoring service in `src/Pyz/Service/Monitoring/MonitoringDependencyProvider.php`:  
+To do it, adjust the Monitoring service in `src/Pyz/Service/Monitoring/MonitoringDependencyProvider.php`:
 
 ```php
 <?php declare(strict_types = 1);
@@ -655,3 +656,31 @@ tideways:
 docker/sdk boot deploy.*.yml &&\
 docker/sdk up
 ```
+
+## Local OpenTelemetry Stack
+
+The Local OpenTelemetry Stack is a powerful tool designed for real-time monitoring of Application Performance Monitoring (APM) locally. It allows you to track APM traces across all containers or specific ones running PHP applications.
+
+This stack integrates the following containers into your local environment:
+* tempo-init
+* tempo
+* collector
+* prometheus
+* grafana
+
+### Configuration
+
+1. Adjust your `deploy.*.yml` as follows:
+
+```yaml
+    grafana:
+        engine: otel-stack
+        endpoints:
+            grafana:
+```
+
+2. Bootstrap the docker setup and rebuild the application:
+```bash
+docker/sdk boot deploy.*.yml &&\
+docker/sdk up
+```

generator/src/templates/nginx/http/gateway/otel-stack.server.conf.twig

@@ -0,0 +1,2 @@
+{% extends "nginx/http/gateway/server.conf.twig" %}
+{% block upstream %}{{ upstream }}:3000{% endblock upstream %}

generator/src/templates/service/otel-stack/default/otel-stack.yml.twig

@@ -0,0 +1 @@
+{% include "service/#{engine}/latest/#{engine}.yml.twig" with _context only %}

generator/src/templates/service/otel-stack/latest/otel-stack.yml.twig

@@ -0,0 +1,95 @@
+
+  # Tempo runs as user 10001, and docker compose creates the volume as root.
+  # As such, we need to chown the volume in order for Tempo to start correctly.
+  tempo-init:
+      image: &tempoImage grafana/tempo:main-1a21818
+      user: root
+      entrypoint:
+          - "chown"
+          - "10001:10001"
+          - "/var/tempo"
+      volumes:
+          - {{ serviceName }}-{{ serviceData['engine'] }}-data:/var/tempo:rw
+
+  tempo:
+      image: *tempoImage
+      command: [ "-config.file=/etc/tempo.yaml" ]
+      volumes:
+          - ./${DEPLOYMENT_PATH}/context/otel-stack/tempo.yaml:/etc/tempo.yaml
+          - {{ serviceName }}-{{ serviceData['engine'] }}-data:/var/tempo:rw
+      networks:
+          - private
+      ports:
+          - "14268"  # jaeger ingest
+          - "3200"   # tempo
+          - "4317"  # otlp grpc
+          - "4318"  # otlp http
+          - "9411"   # zipkin
+      depends_on:
+          - tempo-init
+      healthcheck:
+          test: [ "CMD", "curl", "-f", "http://localhost:3200/metrics" ]
+          interval: 30s
+          timeout: 10s
+          retries: 3
+          start_period: 10s
+
+  collector:
+      image: otel/opentelemetry-collector:0.86.0
+      command: [ "--config=/etc/otel-collector.yaml" ]
+      volumes:
+          - ./${DEPLOYMENT_PATH}/context/otel-stack/otel-collector.yaml:/etc/otel-collector.yaml
+      networks:
+          - private
+      healthcheck:
+          test: [ "CMD", "curl", "-f", "http://localhost:13133/health" ]
+          interval: 30s
+          timeout: 10s
+          retries: 3
+          start_period: 10s
+      ports:
+          - "4318:4318"
+          - "4317:4317"
+  prometheus:
+      image: prom/prometheus:latest
+      command:
+          - --config.file=/etc/prometheus.yaml
+          - --web.enable-remote-write-receiver
+          - --enable-feature=exemplar-storage
+      networks:
+          - private
+      volumes:
+          - ./${DEPLOYMENT_PATH}/context/otel-stack/prometheus.yaml:/etc/prometheus.yaml
+      ports:
+          - "9090:9090"
+      healthcheck:
+          test: [ "CMD", "curl", "-f", "http://localhost:9090/-/healthy" ]
+          interval: 30s
+          timeout: 10s
+          retries: 3
+          start_period: 10s
+
+  grafana:
+      image: grafana/grafana:11.0.0
+      volumes:
+          - ./${DEPLOYMENT_PATH}/context/otel-stack/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
+      networks:
+          - public
+          - private
+      environment:
+          - GF_AUTH_ANONYMOUS_ENABLED=true
+          - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+          - GF_AUTH_DISABLE_LOGIN_FORM=true
+          - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
+      labels:
+          'spryker.app.name': grafana
+          'spryker.app.type': hidden
+          'spryker.project': ${SPRYKER_DOCKER_PREFIX}:${SPRYKER_DOCKER_TAG}
+      ports:
+          - "3000:3000"
+      healthcheck:
+          test: [ "CMD", "curl", "-f", "http://localhost:3000/" ]
+          interval: 30s
+          timeout: 10s
+          retries: 3
+          start_period: 10s