scripts: add relay metrics exporter

docs/CHAT-RELAY.md

@@ -190,6 +190,8 @@ docker compose run --rm --entrypoint sh relay -c \
   'simplex-chat-relay -d "$DB_CONN" -e "/set profile image file /avatar.png"'
 ```
 
+The stack also runs [sql_exporter](https://github.com/burningalchemist/sql_exporter), which publishes relay metrics read from the database (channels by relay status, members, queued deliveries and the age of the oldest one, messages in the last 24 hours) on `127.0.0.1:9399/metrics`. Edit `sql_exporter.yml` to change the queries, and remove the `metrics` service if they are not needed.
+
 The compose file already runs the relay with the web-preview options, writing previews and the CORS file to `/var/www/relay-web-channels`. To serve them, follow [Serve the previews with Caddy](#serve-the-previews-with-caddy) and [Reload CORS automatically](#reload-cors-automatically) below, but skip the `usermod -aG relay caddy` step: with Docker the files are world-readable and there is no `relay` user.
 
 ## Channel web previews

scripts/relay/docker-compose.yaml

@@ -26,6 +26,22 @@ services:
       - ./out:/out
     restart: unless-stopped
 
+  metrics:
+    image: burningalchemist/sql_exporter:latest
+    container_name: chat-relay-metrics
+    depends_on:
+      db:
+        condition: service_healthy
+    environment:
+      # Percent-encode the password if it contains URL-reserved characters.
+      SQLEXPORTER_TARGET_DSN: postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@db:5432/${POSTGRES_DB}?sslmode=disable
+    volumes:
+      - ./sql_exporter.yml:/etc/sql_exporter/sql_exporter.yml:ro
+    command: ["-config.file=/etc/sql_exporter/sql_exporter.yml"]
+    ports:
+      - "127.0.0.1:9399:9399"
+    restart: unless-stopped
+
   db:
     image: postgres:18
     container_name: chat-relay-db

scripts/relay/sql_exporter.yml

@@ -0,0 +1,71 @@
+global:
+  min_interval: 0s
+  max_connections: 3
+  max_idle_connections: 3
+
+target:
+  name: chat_relay
+  # Replaced by SQLEXPORTER_TARGET_DSN. A non-empty value is required here
+  # because the DSN is validated before environment variables are applied.
+  data_source_name: "postgresql://replaced-by-env"
+  collectors: [chat_relay]
+
+collectors:
+  - collector_name: chat_relay
+    metrics:
+      - metric_name: chat_relay_channels
+        type: gauge
+        help: "Channels by relay status."
+        key_labels: [status]
+        values: [channels]
+        query: |
+          SELECT relay_own_status AS status, count(*) AS channels
+          FROM simplex_v1_chat_schema.groups
+          WHERE relay_own_status IS NOT NULL
+          GROUP BY relay_own_status
+
+      - metric_name: chat_relay_published_channels
+        type: gauge
+        help: "Served channels that have a public address."
+        values: [channels]
+        query: |
+          SELECT count(*) AS channels
+          FROM simplex_v1_chat_schema.groups g
+          JOIN simplex_v1_chat_schema.group_profiles gp
+            ON gp.group_profile_id = g.group_profile_id
+          WHERE gp.public_group_id IS NOT NULL
+            AND g.relay_own_status IN ('active', 'accepted')
+
+      - metric_name: chat_relay_members
+        type: gauge
+        help: "Members across all channels."
+        values: [members]
+        query: |
+          SELECT count(*) AS members FROM simplex_v1_chat_schema.group_members
+
+      - metric_name: chat_relay_pending_deliveries
+        type: gauge
+        help: "Messages queued for delivery."
+        values: [deliveries]
+        query: |
+          SELECT count(*) AS deliveries
+          FROM simplex_v1_chat_schema.msg_deliveries
+          WHERE delivery_status = 'snd_pending'
+
+      - metric_name: chat_relay_oldest_pending_delivery_seconds
+        type: gauge
+        help: "Age of the oldest message queued for delivery."
+        values: [age]
+        query: |
+          SELECT COALESCE(EXTRACT(EPOCH FROM (now() - min(created_at))), 0) AS age
+          FROM simplex_v1_chat_schema.msg_deliveries
+          WHERE delivery_status = 'snd_pending'
+
+      - metric_name: chat_relay_messages_24h
+        type: gauge
+        help: "Chat items created in the last 24 hours."
+        values: [messages]
+        query: |
+          SELECT count(*) AS messages
+          FROM simplex_v1_chat_schema.chat_items
+          WHERE created_at > now() - interval '24 hours'