diff --git a/nixos/modules/monitoring/server/grafana-dashboards/meta-monitoring.json b/nixos/modules/monitoring/server/grafana-dashboards/meta-monitoring.json new file mode 100644 index 0000000000000000000000000000000000000000..c1d27b28965eae82939d2dfefdb7f9a709bfd486 --- /dev/null +++ b/nixos/modules/monitoring/server/grafana-dashboards/meta-monitoring.json @@ -0,0 +1,180 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Watching the watchers", + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": 22, + "links": [], + "panels": [ + { + "alert": { + "alertRuleTags": {}, + "conditions": [ + { + "evaluator": { + "params": [ + 0 + ], + "type": "gt" + }, + "operator": { + "type": "and" + }, + "query": { + "params": [ + "A", + "5m", + "now" + ] + }, + "reducer": { + "params": [], + "type": "avg" + }, + "type": "query" + } + ], + "executionErrorState": "alerting", + "for": "5m", + "frequency": "1m", + "handler": 1, + "name": "Scraping down", + "noDataState": "no_data", + "notifications": [] + }, + "aliasColors": {}, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": null, + "description": "Is Prometheus having problems scraping our instances? Should be zero.", + "fieldConfig": { + "defaults": {}, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 0 + }, + "hiddenSeries": false, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": false, + "linewidth": 1, + "nullPointMode": "null", + "options": { + "alertThreshold": false + }, + "percentage": false, + "pluginVersion": "7.5.10", + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "exemplar": true, + "expr": "count by (job, instance) (up == 0)", + "hide": false, + "interval": "", + "legendFormat": "{{job}}/{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": false, + "line": false, + "op": "gt", + "value": 0, + "visible": true + } + ], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Scraping failures", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": false, + "schemaVersion": 27, + "style": "dark", + "tags": [], + "templating": { + "list": [] + }, + "time": { + "from": "now-30m", + "to": "now" + }, + "timepicker": {}, + "timezone": "", + "title": "Meta monitoring", + "uid": "MetaMonitoring", + "version": 1 +}