deploy/docker-compose.yml

@@ -39,6 +39,13 @@ services:
       retries: 30
     volumes:
       - postgres-data:/var/lib/postgresql/data
+    # R7 starting limits: 512M leaves headroom over the default 128 MB shared_buffers +
+    # per-connection memory (R2 peaked at 28 backends / 69 MiB RSS); tighten after the run.
+    deploy:
+      resources:
+        limits:
+          cpus: "2.0"
+          memory: 512M
     networks: [internal]
 
   backend:
@@ -65,8 +72,19 @@ services:
       BACKEND_OTEL_METRICS_EXPORTER: otlp
       OTEL_EXPORTER_OTLP_ENDPOINT: http://otelcol:4317
       OTEL_EXPORTER_OTLP_INSECURE: "true"
+      # GOMAXPROCS matches the CPU limit below so the Go scheduler aligns with the
+      # cgroup quota (the runtime otherwise sees all of the host's cores).
+      GOMAXPROCS: "2"
     # No container healthcheck: the distroless image has no shell/wget. Readiness
     # is covered by the CI post-deploy probe (GET / through caddy).
+    # R7 starting limits (generous over the R2 ~1-core / <=100 MiB peak); tightened to
+    # the agreed prod values after the final stress run. deploy.resources.limits is
+    # honoured by `docker compose up` (Compose v2), not only by swarm.
+    deploy:
+      resources:
+        limits:
+          cpus: "2.0"
+          memory: 512M
     networks: [internal]
 
   gateway:
@@ -97,8 +115,17 @@ services:
       GATEWAY_OTEL_METRICS_EXPORTER: otlp
       OTEL_EXPORTER_OTLP_ENDPOINT: http://otelcol:4317
       OTEL_EXPORTER_OTLP_INSECURE: "true"
+      # GOMAXPROCS matches the CPU limit below (see backend).
+      GOMAXPROCS: "2"
       # GATEWAY_ADMIN_* intentionally unset: in the deployed contour the front
       # caddy owns the /_gm Basic-Auth and routes /_gm to the backend directly.
+    # R7 starting limits (generous over the R2 ~1-core / <=100 MiB peak); tighten after
+    # the final stress run.
+    deploy:
+      resources:
+        limits:
+          cpus: "2.0"
+          memory: 512M
     networks: [internal]
 
   # --- Landing (static) -------------------------------------------------------
@@ -121,6 +148,10 @@ services:
         VITE_GATEWAY_URL: ${VITE_GATEWAY_URL:-}
         VITE_APP_VERSION: ${APP_VERSION:-dev}
     restart: unless-stopped
+    deploy:
+      resources:
+        limits:
+          memory: 128M
     networks: [internal]
 
   # --- Telegram connector (egress via the VPN sidecar) -----------------------
@@ -167,6 +198,13 @@ services:
       TELEGRAM_OTEL_METRICS_EXPORTER: otlp
       OTEL_EXPORTER_OTLP_ENDPOINT: http://otelcol:4317
       OTEL_EXPORTER_OTLP_INSECURE: "true"
+      # The connector is light (the stress run does not drive Telegram); one P suffices.
+      GOMAXPROCS: "1"
+    deploy:
+      resources:
+        limits:
+          cpus: "1.0"
+          memory: 256M
 
   # --- Edge reverse proxy (single /_gm Basic-Auth; SPA + Connect -> gateway;
   #     the catch-all incl. the landing -> the static landing container) -------
@@ -183,6 +221,10 @@ services:
     volumes:
       - ${SCRABBLE_CONFIG_DIR:-.}/caddy/Caddyfile:/etc/caddy/Caddyfile:ro
       - caddy-data:/data
+    deploy:
+      resources:
+        limits:
+          memory: 128M
     networks:
       internal: {}
       edge:
@@ -194,8 +236,19 @@ services:
     image: otel/opentelemetry-collector-contrib:0.119.0
     restart: unless-stopped
     command: ["--config=/etc/otelcol/config.yaml"]
+    # The docker_stats receiver reads per-container metrics from the Docker API, so the
+    # collector (image UID 10001) joins the host's docker group to read the socket —
+    # DOCKER_GID defaults to the contour host's 989; set it for other hosts (prod). The
+    # socket is mounted read-only. This replaces cAdvisor, whose per-container metrics
+    # are empty on this host (separate-XFS /var/lib/docker).
+    group_add: ["${DOCKER_GID:-989}"]
     volumes:
       - ${SCRABBLE_CONFIG_DIR:-.}/otelcol/config.yaml:/etc/otelcol/config.yaml:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+    deploy:
+      resources:
+        limits:
+          memory: 512M
     networks: [internal]
 
   prometheus:
@@ -208,6 +261,10 @@ services:
     volumes:
       - ${SCRABBLE_CONFIG_DIR:-.}/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
       - prometheus-data:/prometheus
+    deploy:
+      resources:
+        limits:
+          memory: 512M
     networks: [internal]
 
   tempo:
@@ -218,6 +275,11 @@ services:
     volumes:
       - ${SCRABBLE_CONFIG_DIR:-.}/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro
       - tempo-data:/var/tempo
+    # tempo peaked at ~446 MiB in R2; 1G leaves headroom for the final run.
+    deploy:
+      resources:
+        limits:
+          memory: 1G
     networks: [internal]
 
   grafana:
@@ -247,26 +309,10 @@ services:
       # provider logs "no such file or directory").
       - ${SCRABBLE_CONFIG_DIR:-.}/grafana/dashboards:/etc/grafana/dashboards:ro
       - grafana-data:/var/lib/grafana
-    networks: [internal]
+    deploy:
-
+      resources:
-  # cAdvisor exports per-container resource metrics (CPU / memory / network / disk)
+        limits:
-  # for the R2/R7 stress runs' resource baseline. Prometheus scrapes it at :8080
+          memory: 512M
-  # over the internal network. It needs read access to the host's cgroup and
-  # container state; --docker_only trims non-container cgroup series.
-  cadvisor:
-    container_name: scrabble-cadvisor
-    image: gcr.io/cadvisor/cadvisor:v0.49.1
-    restart: unless-stopped
-    privileged: true
-    command: ["--docker_only=true", "--housekeeping_interval=15s"]
-    devices:
-      - /dev/kmsg
-    volumes:
-      - /:/rootfs:ro
-      - /var/run:/var/run:ro
-      - /sys:/sys:ro
-      - /var/lib/docker/:/var/lib/docker:ro
-      - /dev/disk/:/dev/disk:ro
     networks: [internal]
 
   # postgres_exporter exports Postgres server metrics (connections, cache hit ratio,
@@ -279,6 +325,10 @@ services:
     depends_on: [postgres]
     environment:
       DATA_SOURCE_NAME: postgresql://${POSTGRES_USER:-scrabble}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-scrabble}?sslmode=disable
+    deploy:
+      resources:
+        limits:
+          memory: 128M
     networks: [internal]
 
 networks:

deploy/grafana/dashboards/resources.json

@@ -4,7 +4,7 @@
   "tags": ["scrabble"],
   "timezone": "",
   "schemaVersion": 39,
-  "version": 1,
+  "version": 2,
   "refresh": "30s",
   "time": { "from": "now-1h", "to": "now" },
   "panels": [
@@ -43,30 +43,30 @@
     {
       "type": "timeseries",
       "title": "Container CPU (cores) by container",
-      "description": "cAdvisor container_cpu_usage_seconds_total rate, per scrabble-* container (the load harness appears when run as --name scrabble-loadtest). Verify the metric name against live Prometheus if empty.",
+      "description": "docker_stats container.cpu.utilization (a gauge where 100 == one core) / 100, per scrabble-* container; the load harness appears when run as --name scrabble-loadtest. Verify the scaling against live Prometheus.",
       "gridPos": { "h": 8, "w": 12, "x": 0, "y": 5 },
       "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "refId": "A", "expr": "sum(rate(container_cpu_usage_seconds_total{name=~\"scrabble-.+\"}[5m])) by (name)", "legendFormat": "{{name}}" }]
+      "targets": [{ "refId": "A", "expr": "max(container_cpu_utilization{container_name=~\"scrabble-.+\"}) by (container_name) / 100", "legendFormat": "{{container_name}}" }]
     },
     {
       "type": "timeseries",
-      "title": "Container memory (working set) by container",
+      "title": "Container memory (usage) by container",
-      "description": "cAdvisor container_memory_working_set_bytes, per scrabble-* container.",
+      "description": "docker_stats container.memory.usage.total bytes, per scrabble-* container.",
       "gridPos": { "h": 8, "w": 12, "x": 12, "y": 5 },
       "fieldConfig": { "defaults": { "unit": "bytes" }, "overrides": [] },
       "datasource": { "type": "prometheus", "uid": "prometheus" },
-      "targets": [{ "refId": "A", "expr": "max(container_memory_working_set_bytes{name=~\"scrabble-.+\"}) by (name)", "legendFormat": "{{name}}" }]
+      "targets": [{ "refId": "A", "expr": "max(container_memory_usage_total{container_name=~\"scrabble-.+\"}) by (container_name)", "legendFormat": "{{container_name}}" }]
     },
     {
       "type": "timeseries",
       "title": "Container network I/O by container",
-      "description": "cAdvisor receive (+) and transmit (-) byte rates per scrabble-* container.",
+      "description": "docker_stats receive (+) and transmit (-) byte rates per scrabble-* container (summed across interfaces).",
       "gridPos": { "h": 8, "w": 12, "x": 0, "y": 13 },
       "fieldConfig": { "defaults": { "unit": "Bps" }, "overrides": [] },
       "datasource": { "type": "prometheus", "uid": "prometheus" },
       "targets": [
-        { "refId": "A", "expr": "sum(rate(container_network_receive_bytes_total{name=~\"scrabble-.+\"}[5m])) by (name)", "legendFormat": "rx {{name}}" },
+        { "refId": "A", "expr": "sum(rate(container_network_io_usage_rx_bytes{container_name=~\"scrabble-.+\"}[5m])) by (container_name)", "legendFormat": "rx {{container_name}}" },
-        { "refId": "B", "expr": "-sum(rate(container_network_transmit_bytes_total{name=~\"scrabble-.+\"}[5m])) by (name)", "legendFormat": "tx {{name}}" }
+        { "refId": "B", "expr": "-sum(rate(container_network_io_usage_tx_bytes{container_name=~\"scrabble-.+\"}[5m])) by (container_name)", "legendFormat": "tx {{container_name}}" }
       ]
     },
     {

deploy/otelcol/config.yaml

@@ -6,6 +6,18 @@ receivers:
     protocols:
       grpc:
         endpoint: 0.0.0.0:4317
+  # Per-container resource metrics (CPU / memory / network) read straight from the
+  # Docker API. This replaces cAdvisor, which on the contour host resolves only the
+  # root cgroup (its /var/lib/docker is a separate XFS mount), and works the same in
+  # prod. The collector reaches the socket via group_add in docker-compose.yml.
+  # collection_interval matches Prometheus' 30s scrape. container.cpu.utilization is a
+  # gauge where 100 == one core (it mirrors `docker stats` CPU%).
+  docker_stats:
+    endpoint: unix:///var/run/docker.sock
+    collection_interval: 30s
+    metrics:
+      container.cpu.utilization:
+        enabled: true
 
 processors:
   batch: {}
@@ -33,6 +45,6 @@ service:
       processors: [batch]
       exporters: [otlp/tempo]
     metrics:
-      receivers: [otlp]
+      receivers: [otlp, docker_stats]
       processors: [batch]
       exporters: [prometheus]

deploy/prometheus/prometheus.yml

@@ -6,17 +6,14 @@ global:
   evaluation_interval: 30s
 
 scrape_configs:
+  # otelcol exposes both the services' OTLP metrics and the docker_stats receiver's
+  # per-container resource metrics (CPU/memory/network) on one endpoint.
   - job_name: otelcol
     static_configs:
       - targets: ["otelcol:9464"]
   - job_name: prometheus
     static_configs:
       - targets: ["localhost:9090"]
-  # Container resource metrics (CPU/memory/network/disk) for every contour
-  # container, for the R2/R7 stress runs' resource baseline.
-  - job_name: cadvisor
-    static_configs:
-      - targets: ["cadvisor:8080"]
   # Postgres server metrics (connections, cache hit ratio, transactions, db size).
   - job_name: postgres_exporter
     static_configs: