Merge pull request #251 from squat/wg-exporter

Add WireGuard monitor and docs

Makefile

@@ -242,7 +242,7 @@ website/docs/README.md: README.md
 	cat README.md >> $@
 	cp -r docs/graphs website/static/img/
 	sed -i 's/\.\/docs\///g' $@
-	find $(@D)  -type f -name '*.md' | xargs -I{} sed -i 's/\.\/\(.\+\.svg\)/\/img\/\1/g' {}
+	find $(@D)  -type f -name '*.md' | xargs -I{} sed -i 's/\.\/\(.\+\.\(svg\|png\)\)/\/img\/\1/g' {}
 	sed -i 's/graphs\//\/img\/graphs\//g' $@
 	# The next line is a workaround until mdx, docusaurus' markdown parser, can parse links with preceding brackets.
 	sed -i  's/\[\]\(\[.*\](.*)\)/\[\]\1/g' website/docs/api.md

docs/grafana/kilo.json

@@ -0,0 +1,962 @@
+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS",
+      "label": "prometheus",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    }
+  ],
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "7.5.4"
+    },
+    {
+      "type": "panel",
+      "id": "graph",
+      "name": "Graph",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    },
+    {
+      "type": "panel",
+      "id": "stat",
+      "name": "Stat",
+      "version": ""
+    }
+  ],
+  "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": [
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 12,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "sum by (pod) (rate(wireguard_received_bytes_total[1h])) + sum by (pod) (rate(wireguard_sent_bytes_total[1h]))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [
+        {
+          "$$hashKey": "object:64",
+          "colorMode": "background6",
+          "fill": true,
+          "fillColor": "rgba(234, 112, 112, 0.12)",
+          "line": false,
+          "lineColor": "rgba(237, 46, 24, 0.60)",
+          "op": "time"
+        }
+      ],
+      "timeShift": null,
+      "title": "Throughput",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:42",
+          "format": "Bps",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:43",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 10,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "(sum(rate(wireguard_sent_bytes_total[5m])) - sum(rate(wireguard_received_bytes_total[5m])))/(sum(rate(wireguard_sent_bytes_total[5m])) + sum(rate(wireguard_received_bytes_total[5m])))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Slip (send - received)",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:502",
+          "format": "percentunit",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:503",
+          "format": "Bps",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "hiddenSeries": false,
+      "id": 16,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "sum by (public_key) (time() - (wireguard_latest_handshake_seconds!=0))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "latest handshake",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:219",
+          "format": "s",
+          "label": null,
+          "logBase": 1,
+          "max": "1000",
+          "min": "0",
+          "show": true
+        },
+        {
+          "$$hashKey": "object:220",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "hiddenSeries": false,
+      "id": 18,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "sum by (instance) (rate(kilo_reconciles_total[30m]))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "kilo reconciles",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:539",
+          "decimals": null,
+          "format": "hertz",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:540",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 4,
+        "x": 0,
+        "y": 16
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "text": {},
+        "textMode": "auto"
+      },
+      "pluginVersion": "7.5.4",
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "avg(kilo_peers)",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "title": "Kilo Peers",
+      "type": "stat"
+    },
+    {
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 4,
+        "x": 4,
+        "y": 16
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "text": {},
+        "textMode": "auto"
+      },
+      "pluginVersion": "7.5.4",
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "avg(kilo_nodes)",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Kilo Nodes",
+      "type": "stat"
+    },
+    {
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 4,
+        "x": 8,
+        "y": 16
+      },
+      "id": 8,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "text": {},
+        "textMode": "auto"
+      },
+      "pluginVersion": "7.5.4",
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "sum(kilo_leader)",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "title": "segments",
+      "type": "stat"
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "hiddenSeries": false,
+      "id": 6,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "sum by (instance) (rate(kilo_errors_total[10m]))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Kilo Errors",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:446",
+          "format": "hertz",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:447",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "hiddenSeries": false,
+      "id": 20,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "sum by (instance) (rate(process_cpu_seconds_total{pod=~\"kilo-.*\"}[1m]))",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "CPU usage",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:162",
+          "format": "percentunit",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:163",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "hiddenSeries": false,
+      "id": 22,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.4",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": false,
+          "expr": "sum by (instance) (process_resident_memory_bytes{pod=~\"kilo-.*\"})",
+          "interval": "",
+          "legendFormat": "",
+          "queryType": "randomWalk",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Memory Allocation",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:231",
+          "format": "decbytes",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:232",
+          "format": "decmbytes",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "collapsed": false,
+      "datasource": null,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 32
+      },
+      "id": 14,
+      "panels": [],
+      "title": "Row title",
+      "type": "row"
+    }
+  ],
+  "refresh": false,
+  "schemaVersion": 27,
+  "style": "dark",
+  "tags": [],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Kilo",
+  "uid": "R8Lja3H7z",
+  "version": 11
+}

docs/monitoring.md

@@ -0,0 +1,100 @@
+# Monitoring
+
+The following assumes that you have applied the [kube-prometheus](https://github.com/prometheus-operator/kube-prometheus) monitoring stack onto your cluster.
+
+## Kilo
+
+Monitor the Kilo DaemonSet with:
+```shell
+kubectl apply -f https://raw.githubusercontent.com/squat/kilo/main/manifests/podmonitor.yaml
+```
+
+## WireGuard
+
+Monitor the WireGuard interfaces with:
+```shell
+kubectl create ns kilo
+kubectl apply -f https://raw.githubusercontent.com/squat/kilo/main/manifests/wg-exporter.yaml
+```
+
+The manifest will deploy the [Prometheus WireGuard Exporter](https://github.com/MindFlavor/prometheus_wireguard_exporter) as a DaemonSet and a [PodMonitor](https://docs.openshift.com/container-platform/4.8/rest_api/monitoring_apis/podmonitor-monitoring-coreos-com-v1.html).
+
+By default the kube-prometheus stack only monitors the `default`, `kube-system` and `monitoring` namespaces.
+In order to allow Prometheus to monitor the `kilo` namespace, apply the Role and RoleBinding with:
+```shell
+kubectl apply -f https://raw.githubusercontent.com/squat/kilo/main/manifests/wg-exporter-role-kube-prometheus.yaml
+```
+
+## Metrics
+
+### Kilo
+
+Kilo exports some standard metrics with the Prometheus GoCollector and ProcessCollector.
+It also exposes some Kilo-specific metrics.
+
+```
+# HELP kilo_errors_total Number of errors that occurred while administering the mesh.
+# TYPE kilo_errors_total counter
+
+# HELP kilo_leader Leadership status of the node.
+# TYPE kilo_leader gauge
+
+# HELP kilo_nodes Number of nodes in the mesh.
+# TYPE kilo_nodes gauge
+
+# HELP kilo_peers Number of peers in the mesh.
+# TYPE kilo_peers gauge
+
+# HELP kilo_reconciles_total Number of reconciliation attempts.
+# TYPE kilo_reconciles_total counter
+```
+
+### WireGuard
+
+The [Prometheus WireGuard Exporter](https://github.com/MindFlavor/prometheus_wireguard_exporter) exports the following metrics:
+
+```
+# HELP wireguard_sent_bytes_total Bytes sent to the peer
+# TYPE wireguard_sent_bytes_total counter
+
+# HELP wireguard_received_bytes_total Bytes received from the peer
+# TYPE wireguard_received_bytes_total counter
+
+# HELP wireguard_latest_handshake_seconds Seconds from the last handshake
+# TYPE wireguard_latest_handshake_seconds gauge
+```
+
+## Display some Metrics
+
+If your laptop is a Kilo peer of the cluster you can access the Prometheus UI by navigating your browser directly to the cluster IP of the `prometheus-k8s` service.
+Otherwise use `port-forward`:
+```shell
+kubectl -n monitoring port-forward svc/prometheus-k8s 9090
+```
+and navigate your browser to `localhost:9090`.
+Check if you can see the PodMonitors for Kilo and the WireGuard Exporter under **Status** -> **Targets** in the Prometheus web UI.
+
+If you don't see them, check the logs of the `prometheus-k8s` Pods; it may be that Prometheus doesn't have the permission to get Pods in the `kilo` namespace.
+In this case, you need to apply the Role and RoleBinding from above.
+
+Navigate to **Graph** and try to execute a simple query, e.g. type `kilo_nodes` and click on `execute`.
+You should see some data.
+
+## Using Grafana
+
+Let's navigate to the Grafana dashboard.
+Again, if your laptop is not a Kilo peer, use `port-forward`:
+```shell
+kubectl -n monitoring port-forward svc/grafana 3000
+```
+
+Now navigate your browser to `localhost:3000`.
+The default user and password is `admin` `admin`.
+
+An example configuration for a dashboard displaying Kilo metrics can be found [here](https://raw.githubusercontent.com/squat/kilo/main/docs/grafana/kilo.json).
+You can import this dashboard by hitting **+** -> **Import** on the Grafana dashboard.
+
+The dashboard looks like this:
+
+<img src="./graphs/kilo.png" />
+

manifests/wg-exporter-role-kube-prometheus.yaml

@@ -0,0 +1,56 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  labels:
+    app.kubernetes.io/component: prometheus
+    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 2.26.0
+  name: prometheus-k8s
+  namespace: kilo
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - services
+  - endpoints
+  - pods
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - extensions
+  resources:
+  - ingresses
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - networking.k8s.io
+  resources:
+  - ingresses
+  verbs:
+  - get
+  - list
+  - watch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  labels:
+    app.kubernetes.io/component: prometheus
+    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 2.26.0
+  name: prometheus-k8s
+  namespace: kilo
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: prometheus-k8s
+subjects:
+- kind: ServiceAccount
+  name: prometheus-k8s
+  namespace: monitoring

manifests/wg-exporter.yaml

@@ -0,0 +1,67 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PodMonitor
+metadata:
+  labels:
+    app.kubernetes.io/name: wg-exporter
+    app.kubernetes.io/part-of: kilo
+  name: wg-exporter
+  namespace: kilo
+spec:
+  namespaceSelector:
+    matchNames:
+    - kilo
+  podMetricsEndpoints:
+  - interval: 15s
+    port: metrics
+    path: /metrics
+  selector:
+    matchLabels:
+      app.kubernetes.io/part-of: kilo
+      app.kubernetes.io/name: wg-exporter
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  labels:
+    app.kubernetes.io/name: wg-exporter
+    app.kubernetes.io/part-of: kilo
+  name: wg-exporter
+  namespace: kilo
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: wg-exporter
+      app.kubernetes.io/part-of: kilo
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: wg-exporter
+        app.kubernetes.io/part-of: kilo
+    spec:
+      containers:
+      - args:
+        - -a
+        - -i=kilo0
+        - -p=9586
+        image: mindflavor/prometheus-wireguard-exporter
+        name: wg-exporter
+        ports:
+        - containerPort: 9586
+          name: metrics
+          protocol: TCP
+        securityContext:
+          privileged: true
+        terminationMessagePath: /dev/termination-log
+        terminationMessagePolicy: File
+        volumeMounts:
+        - name: wireguard
+          mountPath: /var/run/wireguard
+      volumes:
+      - name: wireguard
+        hostPath:
+          path: /var/run/wireguard
+      tolerations:
+      - effect: NoSchedule
+        operator: Exists
+      - effect: NoExecute
+        operator: Exists

website/docs/monitoring

@@ -0,0 +1,5 @@
+---
+id: monitoring
+title: Monitoring
+hide_title: true
+---

website/sidebars.js

@@ -7,7 +7,7 @@ module.exports = {
     {
       type: 'category',
       label: 'Guides',
-      items: ['topology', 'vpn', 'vpn-server', 'multi-cluster-services', 'network-policies', 'userspace-wireguard', 'peer-validation'],
+      items: ['topology', 'vpn', 'vpn-server', 'multi-cluster-services', 'network-policies', 'userspace-wireguard', 'peer-validation', 'monitoring'],
     },
     {
       type: 'category',