Add main docker services

- Grafana
- Prometheus
- NGINX
- Grafana Agent
- OTEL Collector

datasources.yaml

@@ -0,0 +1,65 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: true
+    version: 1
+    editable: true
+    jsonData:
+      httpMethod: POST
+      exemplarTraceIdDestinations:
+        - datasourceUid: Azure
+          name: traceID
+          urlDisplayLabel: View Trace in Azure
+  - name: Azure
+    type: grafana-azure-monitor-datasource
+    uid: azure
+    access: proxy
+    orgId: 1
+    version: 1
+    editable: true
+    jsonData:
+      tenantId: $TENANT_ID # Directory (tenant) ID
+      clientId: $CLIENT_ID # Application (tenant) ID
+      cloudName: azuremonitor
+
+    secureJsonData:
+      clientSecret: $CLIENT_SECRET
+  - name: Tempo
+    type: tempo
+    access: proxy
+    orgId: 1
+    url: http://tempo:3200
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: true
+    apiVersion: 1
+    uid: tempo
+    jsonData:
+      httpMethod: GET
+      serviceMap:
+        datasourceUid: prometheus
+      tracesToLogs:
+        datasourceUid: "Loki"
+        mapTagNamesEnabled: true
+        tags: ["traceId"]
+        mappedTags: [{ key: "traceId", value: "tid" }]
+        spanStartTimeShift: "1h"
+        spanEndTimeShift: "1h"
+        filterByTraceID: true
+        filterBySpanID: false
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://gateway:3100
+    jsonData:
+      httpHeaderName1: "X-Scope-OrgID"
+    secureJsonData:
+      httpHeaderValue1: "tenant1"

docker-compose.main.yml

@@ -0,0 +1,152 @@
+---
+networks:
+  grafana:
+
+services:
+  grafana:
+    image: grafana/grafana:latest
+    container_name: grafana
+    environment:
+      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+      - GF_AUTH_DISABLE_LOGIN_FORM=true
+      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor,azureMonitorPrometheusExemplars
+      - TENANT_ID=${TENANT_ID}
+      - CLIENT_ID=${CLIENT_ID}
+      - CLIENT_SECRET=${CLIENT_SECRET}
+    depends_on:
+      - gateway
+    ports:
+      - "3002:3000"
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1",
+        ]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    volumes:
+      - ./datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
+    networks:
+      grafana:
+
+  gateway:
+    image: nginx:latest
+    container_name: grafana-gateway
+    depends_on:
+      - loki-read
+      - loki-write
+    entrypoint:
+      - sh
+      - -euc
+      - |
+        cat <<EOF > /etc/nginx/nginx.conf
+        user  nginx;
+        worker_processes  5;  ## Default: 1
+
+        events {
+          worker_connections   1000;
+        }
+
+        http {
+          resolver 127.0.0.11;
+
+          server {
+            listen             3100;
+
+            location = / {
+              return 200 'OK';
+              auth_basic off;
+            }
+
+            location = /api/prom/push {
+              proxy_pass       http://loki-write:3100\$$request_uri;
+            }
+
+            location = /api/prom/tail {
+              proxy_pass       http://loki-read:3100\$$request_uri;
+              proxy_set_header Upgrade \$$http_upgrade;
+              proxy_set_header Connection "upgrade";
+            }
+
+            location ~ /api/prom/.* {
+              proxy_pass       http://loki-read:3100\$$request_uri;
+            }
+
+            location = /loki/api/v1/push {
+              proxy_pass       http://loki-write:3100\$$request_uri;
+            }
+
+            location = /loki/api/v1/tail {
+              proxy_pass       http://loki-read:3100\$$request_uri;
+              proxy_set_header Upgrade \$$http_upgrade;
+              proxy_set_header Connection "upgrade";
+            }
+
+            location ~ /loki/api/.* {
+              proxy_pass       http://loki-read:3100\$$request_uri;
+            }
+          }
+        }
+        EOF
+        /docker-entrypoint.sh nginx -g "daemon off;"
+    ports:
+      - "3100:3100"
+    healthcheck:
+      test: ["CMD", "service", "nginx", "status"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      grafana:
+      loki:
+
+  agent:
+    image: grafana/agent:v0.27.1
+    container_name: grafana-agent
+    volumes:
+      - ./grafana-agent.yaml:/etc/agent.yaml
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+    entrypoint:
+      - /bin/agent
+      - -config.file=/etc/agent.yaml
+    networks:
+      grafana:
+      tempo:
+
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    command:
+      - --config.file=/etc/prometheus.yaml
+      - --web.enable-remote-write-receiver
+      - --enable-feature=exemplar-storage
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus.yaml
+    ports:
+      - "9090:9090"
+    networks:
+      grafana:
+
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib
+    command: [--config=/etc/otel-collector-config.yaml]
+    container_name: otel-collector
+    volumes:
+      - ./otel-config.yaml:/etc/otel-collector-config.yaml
+    environment:
+      - APPLICATIONINSIGHTS_CONNECTION_STRING=${APPLICATIONINSIGHTS_CONNECTION_STRING}
+    ports:
+      - 1888 # pprof extension
+      - 8888 # Prometheus metrics exposed by the collector
+      - 8889 # Prometheus exporter metrics
+      - 13133 # health_check extension
+      - 4317 # OTLP gRPC receiver
+      - 4318 # OTLP http receiver
+      - 55679 # zpages extension
+    networks:
+      tempo:
+      grafana:

grafana-agent.yaml

@@ -0,0 +1,38 @@
+server:
+  log_level: debug
+
+traces:
+  configs:
+    - name: default
+      receivers:
+        otlp:
+          protocols:
+            grpc:
+      remote_write:
+        - endpoint: tempo:4317
+          insecure: true
+      batch:
+        timeout: 5s
+        send_batch_size: 100
+      automatic_logging:
+        backend: logs_instance
+        logs_instance_name: default
+        roots: true
+
+logs:
+  configs:
+    - name: default
+      positions:
+        filename: /tmp/positions.yaml
+      clients:
+        - url: http://grafana-gateway:3100/loki/api/v1/push
+          tenant_id: tenant1
+      scrape_configs:
+        - job_name: docker_scrape
+          docker_sd_configs:
+            - host: unix:///var/run/docker.sock
+              refresh_interval: 5s
+          relabel_configs:
+            - source_labels: ["__meta_docker_container_name"]
+              regex: "/(.*)"
+              target_label: "container"

otel-config.yaml

@@ -0,0 +1,22 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+exporters:
+  logging:
+  otlp:
+    endpoint: "http://agent:4317"
+    tls:
+      insecure: true
+  azuremonitor:
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      exporters: [otlp, azuremonitor]
+  telemetry:
+    logs:
+      level: "debug"

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: "exemplars"
+    static_configs:
+      - targets: ["exemplars:8081"]

start.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+docker compose \
+    -f docker-compose.main.yml \
+    -f ./docker-compose.tempo.yml \
+    -f ./docker-compose.loki.yml \
+    -f ./docker-compose.exemplars.yml up -d

stop.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+docker-compose \
+    -f docker-compose.main.yml \
+    -f ./docker-compose.tempo.yml \
+    -f ./docker-compose.loki.yml \
+    -f ./docker-compose.exemplars.yml down