Merge pull request #428 from stakwork/setup/grafana-prometheus

chore: setup grafana and prometheus

prometheus/prometheus.yml

@@ -0,0 +1,24 @@
+global:
+  scrape_interval: 10s
+
+scrape_configs:
+  - job_name: 'swarms'
+    ec2_sd_configs:
+      - region: us-east-1
+        port: 9100
+    scheme: http  # Ensure Prometheus uses HTTP
+    relabel_configs:
+      # Keep only the EC2 instances with the tag Swarm set to superadmin
+      - source_labels: [__meta_ec2_tag_Swarm]
+        regex: superadmin
+        action: keep
+
+      # Extract the public IP from EC2 metadata and assign it to __address__
+      - source_labels: [__meta_ec2_public_ip]
+        regex: (.*)
+        target_label: __address__
+        replacement: "${1}:9100"
+
+      # Label the instances with their name and availability zone
+      - source_labels: [__meta_ec2_tag_Name, __meta_ec2_availability_zone]
+        target_label: instance

second-brain.yml

@@ -104,6 +104,16 @@ services:
       - AWS_S3_BUCKET_NAME=$AWS_S3_BUCKET_NAME
       - GITHUB_REQUEST_TOKEN=$GITHUB_REQUEST_TOKEN
       - SINGLE_AUDIO_OR_VIDEO_EPISODE_WORKFLOW_ID=$SINGLE_AUDIO_OR_VIDEO_EPISODE_WORKFLOW_ID
+  node_exporter:
+    image: quay.io/prometheus/node-exporter:latest
+    container_name: node_exporter
+    command:
+      - '--path.rootfs=/host'
+    network_mode: host
+    pid: host
+    restart: unless-stopped
+    volumes:
+      - '/:/host:ro,rslave'
 
 networks:
   sphinx-swarm:

superadmin.yml

@@ -95,7 +95,50 @@ services:
       - AWS_USER_ROLE=$AWS_USER_ROLE
       - GITHUB_REQUEST_TOKEN=$GITHUB_REQUEST_TOKEN
       - SINGLE_AUDIO_OR_VIDEO_EPISODE_WORKFLOW_ID=$SINGLE_AUDIO_OR_VIDEO_EPISODE_WORKFLOW_ID
+  prometheus:
+    image: prom/prometheus
+    container_name: prometheus
+    networks:
+      - sphinx-swarm
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+    ports:
+      - 9090:9090
+    restart: unless-stopped
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.prometheus.rule=Host(`prometheus.${HOST}`)"
+      - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
+      - "traefik.http.routers.prometheus.tls=true"
+      - "traefik.http.routers.prometheus.tls.certresolver=myresolver"
+      - "traefik.http.routers.prometheus.entrypoints=websecure"
+    volumes:
+      - ./prometheus:/etc/prometheus
+      - prom_data:/prometheus
+  grafana:
+    image: grafana/grafana
+    container_name: grafana
+    networks:
+      - sphinx-swarm
+    ports:
+      - 3000:3000
+    restart: unless-stopped
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.grafana.rule=Host(`grafana.${HOST}`)"
+      - "traefik.http.services.grafana.loadbalancer.server.port=3000"
+      - "traefik.http.routers.grafana.tls=true"
+      - "traefik.http.routers.grafana.tls.certresolver=myresolver"
+      - "traefik.http.routers.grafana.entrypoints=websecure"
+    environment:
+      - GF_SECURITY_ADMIN_USER=$GF_SECURITY_ADMIN_USER
+      - GF_SECURITY_ADMIN_PASSWORD=$GF_SECURITY_ADMIN_PASSWORD
+    volumes:
+      - ./grafana:/etc/grafana/provisioning/datasources
 
 networks:
   sphinx-swarm:
     external: true
+
+volumes:
+  prom_data: