@babylonjs-toolkit/server 0.0.0-stage → 9.35.0

package/templates/init/monitoring/grafana-dashboard.json

@@ -0,0 +1,539 @@
+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS",
+      "label": "Prometheus",
+      "description": "The Prometheus that scrapes the game servers",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    }
+  ],
+  "__requires": [
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    },
+    {
+      "type": "panel",
+      "id": "timeseries",
+      "name": "Time series",
+      "version": ""
+    }
+  ],
+  "title": "Babylon Game Server",
+  "uid": "babylon-game-server",
+  "description": "Players, sessions, traffic, process health and dedicated runner timing of a Babylon Game Server fleet.",
+  "tags": [
+    "babylon-game-server"
+  ],
+  "schemaVersion": 39,
+  "version": 1,
+  "editable": true,
+  "refresh": "30s",
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "templating": {
+    "list": []
+  },
+  "annotations": {
+    "list": []
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "timeseries",
+      "title": "Players",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum(babylon_game_server_players)",
+          "legendFormat": "players"
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Sessions",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum(babylon_game_server_sessions)",
+          "legendFormat": "sessions"
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Joins and refusals per second",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum(rate(babylon_game_server_joins_total{result=\"accepted\"}[5m]))",
+          "legendFormat": "joins"
+        },
+        {
+          "refId": "B",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum by (reason) (rate(babylon_game_server_refusals_total[5m]))",
+          "legendFormat": "refused: {{reason}}"
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "type": "timeseries",
+      "title": "Frame bytes per second",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum by (direction) (rate(babylon_game_server_bytes_total[5m]))",
+          "legendFormat": "{{direction}}"
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "type": "timeseries",
+      "title": "Room messages per second",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum by (direction) (rate(babylon_game_server_messages_total[5m]))",
+          "legendFormat": "{{direction}}"
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "type": "timeseries",
+      "title": "CPU",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "rate(babylon_game_server_process_cpu_seconds_total[5m]) * 100",
+          "legendFormat": "{{instance}}"
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "type": "timeseries",
+      "title": "Memory",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "babylon_game_server_process_resident_memory_bytes",
+          "legendFormat": "resident {{instance}}"
+        },
+        {
+          "refId": "B",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "babylon_game_server_nodejs_heap_size_used_bytes",
+          "legendFormat": "heap {{instance}}"
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "type": "timeseries",
+      "title": "Event-loop lag p99",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "babylon_game_server_nodejs_eventloop_lag_p99_seconds",
+          "legendFormat": "{{instance}}"
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "type": "timeseries",
+      "title": "Garbage collection time per second",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "rate(babylon_game_server_nodejs_gc_duration_seconds_sum[5m])",
+          "legendFormat": "{{instance}}"
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "type": "timeseries",
+      "title": "Dedicated frame time p95",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(babylon_game_server_dedicated_frame_seconds_bucket[5m])))",
+          "legendFormat": "p95"
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "type": "timeseries",
+      "title": "Dedicated tick overruns per second",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 40
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "expr": "sum(rate(babylon_game_server_dedicated_tick_overruns_total[5m]))",
+          "legendFormat": "overruns"
+        }
+      ]
+    }
+  ]
+}

package/templates/init/monitoring/prometheus-alerts.yml

@@ -0,0 +1,51 @@
+# Prometheus alert rules for the Babylon Game Server. They mirror the admin console's built-in alert rules where
+# Prometheus can see the same figures: instanceLost, refusalSpike, authFailureSpike, eventLoopLag, memoryHigh and
+# dedicatedOverruns, with the console's default thresholds. The console's other rules (instanceNotReady,
+# redisUnreachable, certificateExpiring, versionMismatch, nearLimits, newAdminAddress, accountLockout) read data the
+# metrics endpoint does not publish, so they run in the console only.
+# Load this file through rule_files in prometheus.yml. The job name matches prometheus-scrape.yml.
+groups:
+  - name: babylon-game-server
+    rules:
+      - alert: GameServerInstanceLost
+        expr: up{job="babylon-game-server"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Game server {{ $labels.instance }} is not answering metrics scrapes"
+      - alert: GameServerRefusalSpike
+        expr: sum(rate(babylon_game_server_refusals_total[5m])) * 60 > 60
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "The fleet refuses {{ $value | humanize }} joins per minute"
+      - alert: GameServerAuthFailureSpike
+        expr: sum(rate(babylon_game_server_auth_failures_total[5m])) * 60 > 30
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "The fleet sees {{ $value | humanize }} failed token checks per minute"
+      - alert: GameServerEventLoopLag
+        expr: babylon_game_server_nodejs_eventloop_lag_mean_seconds * 1000 > 200
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Game server {{ $labels.instance }} event loop lags {{ $value | humanize }} ms"
+      - alert: GameServerMemoryHigh
+        expr: babylon_game_server_process_resident_memory_bytes > 1536 * 1024 * 1024
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Game server {{ $labels.instance }} uses {{ $value | humanize1024 }}B of memory"
+      - alert: GameServerDedicatedOverruns
+        expr: sum(rate(babylon_game_server_dedicated_tick_overruns_total[5m])) * 60 > 30
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Dedicated runners overran {{ $value | humanize }} ticks per minute"

package/templates/init/monitoring/prometheus-scrape.yml

@@ -0,0 +1,17 @@
+# Prometheus scrape config for the Babylon Game Server (GET /metrics on the server's own port).
+# Merge this job into your prometheus.yml and list every instance as a target (or use your platform's service
+# discovery). The metric names all start with babylon_game_server_.
+scrape_configs:
+  - job_name: babylon-game-server
+    metrics_path: /metrics
+    scrape_interval: 15s
+    static_configs:
+      - targets:
+          - "game-server:2567"
+    # When the server protects its metrics (GAME_SERVER_METRICS_REQUIRE_ADMIN_TOKEN=true), Prometheus must send the
+    # admin token. Keep the token in a file that only Prometheus can read, and uncomment these lines:
+    # authorization:
+    #   type: Bearer
+    #   credentials_file: /etc/prometheus/game-server-admin-token
+    # Behind TLS, also set:
+    # scheme: https

package/templates/init/railway.json

@@ -0,0 +1,13 @@
+{
+  "$schema": "https://railway.com/railway.schema.json",
+  "build": {
+    "builder": "DOCKERFILE",
+    "dockerfilePath": "Dockerfile"
+  },
+  "deploy": {
+    "healthcheckPath": "/game-server/ready",
+    "healthcheckTimeout": 60,
+    "restartPolicyType": "ON_FAILURE",
+    "numReplicas": 1
+  }
+}

package/templates/init/render.yaml

@@ -0,0 +1,19 @@
+# TLS: edge (Render terminates TLS for <service>.onrender.com and your custom domains)
+# UDP: not supported on this host (Render routes inbound HTTP and WebSocket only: https://render.com/docs/websocket)
+# Auth: set GAME_SERVER_AUTH_* to enable (add them under envVars, secrets with sync: false)
+#
+# Babylon Game Server {{version}} on Render, WebSocket only. Commit this folder to a repository, then create a
+# Blueprint from it (Render dashboard > New > Blueprint). Render sets PORT, which the server honours.
+# Players use wss://<service>.onrender.com.
+services:
+  - type: web
+    name: babylon-game-server
+    runtime: docker
+    dockerfilePath: ./Dockerfile
+    plan: starter
+    numInstances: 1
+    healthCheckPath: /game-server/ready
+    envVars:
+      # Render's proxy sends the player's address in x-forwarded-for.
+      - key: GAME_SERVER_TRUST_PROXY
+        value: "true"