feat: Prometheus Metrics Exporter (Bounty #765)

grafana/alerts-rustchain.yml

@@ -0,0 +1,83 @@
+groups:
+  - name: rustchain_alerts
+    interval: 30s
+    rules:
+      # Alert: Node is down
+      - alert: NodeDown
+        expr: rustchain_node_up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "RustChain node is down"
+          description: "RustChain node has been down for more than 1 minute"
+
+      # Alert: Epoch stuck (no progress for 15 minutes = 1.5 epochs)
+      - alert: EpochStuck
+        expr: (time() - rustchain_epoch_current) > 900
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Epoch progress stuck"
+          description: "Epoch has not progressed in 5 minutes"
+
+      # Alert: Database growing too fast
+      - alert: DatabaseGrowth
+        expr: rate(rustchain_db_size_bytes[1h]) > 1073741824  # > 1GB/hour
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Database growing too fast"
+          description: "Database is growing faster than 1GB/hour"
+
+      # Alert: No active miners
+      - alert: NoActiveMiners
+        expr: rustchain_miners_active == 0
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "No active miners"
+          description: "No miners have attested in the last 2 epochs"
+
+      # Alert: Low enrolled miners
+      - alert: LowEnrolledMiners
+        expr: rustchain_epoch_enrolled_miners < 5
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low miner enrollment"
+          description: "Less than 5 miners enrolled in current epoch"
+
+      # Alert: High API latency
+      - alert: HighAPILatency
+        expr: histogram_quantile(0.95, rate(rustchain_api_request_duration_seconds_bucket[5m])) > 5
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High API latency"
+          description: "API p95 latency is above 5 seconds"
+
+      # Alert: Backup too old
+      - alert: BackupTooOld
+        expr: rustchain_backup_age_hours > 24
+        for: 1h
+        labels:
+          severity: warning
+        annotations:
+          summary: "Backup is too old"
+          description: "Last backup is more than 24 hours old"
+
+      # Alert: Node restarted recently
+      - alert: NodeRestarted
+        expr: rustchain_node_uptime_seconds < 300
+        for: 1m
+        labels:
+          severity: info
+        annotations:
+          summary: "Node recently restarted"
+          description: "Node has been up for less than 5 minutes"

grafana/dashboard-rustchain.json

@@ -0,0 +1,191 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "thresholds"},
+          "mappings": [{"options": {"0": {"color": "red", "index": 0, "text": "DOWN"}, "1": {"color": "green", "index": 1, "text": "UP"}}, "type": "value"}],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]}
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 0, "y": 0},
+      "id": 1,
+      "options": {"orientation": "auto", "reduceOptions": {"values": false, "calcs": ["lastNotNull"], "fields": ""}, "showThresholdLabels": false, "showThresholdMarkers": true},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_node_up", "refId": "A"}],
+      "title": "Node Status",
+      "type": "gauge"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "palette-classic"},
+          "custom": {"axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": true},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 8, "w": 12, "x": 6, "y": 0},
+      "id": 2,
+      "options": {"legend": {"calcs": [], "displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_node_uptime_seconds", "legendFormat": "Uptime", "refId": "A"}],
+      "title": "Node Uptime",
+      "type": "timeseries"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "thresholds"},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 100}, {"color": "red", "value": 500}]},
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 18, "y": 0},
+      "id": 3,
+      "options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"values": false, "calcs": ["lastNotNull"], "fields": ""}, "text": {}, "textMode": "auto"},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_epoch_current", "refId": "A"}],
+      "title": "Current Epoch",
+      "type": "stat"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "thresholds"},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 10}, {"color": "red", "value": 5}]},
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 18, "y": 4},
+      "id": 4,
+      "options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"values": false, "calcs": ["lastNotNull"], "fields": ""}, "text": {}, "textMode": "auto"},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_epoch_enrolled_miners", "refId": "A"}],
+      "title": "Enrolled Miners",
+      "type": "stat"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "palette-classic"},
+          "custom": {"axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": true},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 8},
+      "id": 5,
+      "options": {"legend": {"calcs": [], "displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "pluginVersion": "8.0.0",
+      "targets": [
+        {"expr": "rustchain_miners_active", "legendFormat": "Active Miners", "refId": "A"},
+        {"expr": "rustchain_miners_total", "legendFormat": "Total Miners", "refId": "B"}
+      ],
+      "title": "Miners Overview",
+      "type": "timeseries"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "palette-classic"},
+          "custom": {"axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": true},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 8},
+      "id": 6,
+      "options": {"legend": {"calcs": [], "displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_db_size_bytes", "legendFormat": "DB Size", "refId": "A"}],
+      "title": "Database Size",
+      "type": "timeseries"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "palette-classic"},
+          "custom": {"axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": true},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
+          "unit": "RTC"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 16},
+      "id": 7,
+      "options": {"legend": {"calcs": [], "displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "rustchain_total_supply_rtc", "legendFormat": "Total Supply", "refId": "A"}],
+      "title": "Total RTC Supply",
+      "type": "timeseries"
+    },
+    {
+      "datasource": "Prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "color": {"mode": "palette-classic"},
+          "custom": {"axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": true},
+          "mappings": [],
+          "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 16},
+      "id": 8,
+      "options": {"legend": {"calcs": [], "displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "pluginVersion": "8.0.0",
+      "targets": [{"expr": "histogram_quantile(0.95, rate(rustchain_api_request_duration_seconds_bucket[5m]))", "legendFormat": "p95", "refId": "A"}],
+      "title": "API Latency (p95)",
+      "type": "timeseries"
+    }
+  ],
+  "schemaVersion": 27,
+  "style": "dark",
+  "tags": ["rustchain", "blockchain"],
+  "templating": {"list": []},
+  "time": {"from": "now-6h", "to": "now"},
+  "timepicker": {},
+  "timezone": "",
+  "title": "RustChain Node Dashboard",
+  "uid": "rustchain-node",
+  "version": 1
+}

grafana/prometheus.yml

@@ -0,0 +1,18 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ['localhost:9093']
+
+rule_files:
+  - 'alerts-rustchain.yml'
+
+scrape_configs:
+  - job_name: 'rustchain-node'
+    static_configs:
+      - targets: ['localhost:5000']
+    metrics_path: /metrics
+    scrape_interval: 15s