Clément Désiles
f6c4d36bbe
- backup role emits last-success/run metrics into node_exporter's textfile collector
- node_exporter enables systemd and textfile collectors
- prometheus deploys BackupStale/BackupTimerSilent/SystemdUnitFailed alert rules
- grafana gains Backups - Restic and Systemd dashboards
- fix prometheus.yml params rendering (quote values so {job=...} stays a string)
62 lines
3.1 KiB
JSON
62 lines
3.1 KiB
JSON
{
|
|
"title": "Backups - Restic",
|
|
"uid": "backup-restic",
|
|
"tags": ["backup", "restic"],
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"refresh": "1m",
|
|
"time": { "from": "now-30d", "to": "now" },
|
|
"timezone": "browser",
|
|
"editable": true,
|
|
"graphTooltip": 1,
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "instance",
|
|
"label": "Host",
|
|
"type": "query",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"query": { "query": "query_result(count by (instance) (backup_last_success_timestamp_seconds))", "refId": "A" },
|
|
"regex": "/.*instance=\"([^\"]+)\".*/",
|
|
"refresh": 2,
|
|
"multi": true,
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"sort": 1,
|
|
"current": { "selected": true, "text": "All", "value": "$__all" }
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "stat",
|
|
"title": "Last backup age",
|
|
"gridPos": { "h": 6, "w": 12, "x": 0, "y": 0 },
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": { "defaults": { "unit": "dtdhms", "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 172800 }, { "color": "red", "value": 1209600 } ] } }, "overrides": [] },
|
|
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
|
"targets": [ { "refId": "A", "expr": "time() - backup_last_success_timestamp_seconds{instance=~\"$instance\"}", "legendFormat": "{{backup_job}} / {{repo}}" } ]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "stat",
|
|
"title": "Failing backups (14d)",
|
|
"gridPos": { "h": 6, "w": 12, "x": 12, "y": 0 },
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": { "defaults": { "unit": "short", "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] } }, "overrides": [] },
|
|
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
|
"targets": [ { "refId": "A", "expr": "count(backup_last_run_timestamp_seconds{instance=~\"$instance\",result=\"fail\"} > (time() - 14 * 86400)) or vector(0)" } ]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "timeseries",
|
|
"title": "Backup success history",
|
|
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 6 },
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": { "defaults": { "unit": "dateTimeAsIso", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 0, "lineWidth": 1, "drawStyle": "line", "showPoints": "always", "pointSize": 5 } }, "overrides": [] },
|
|
"targets": [ { "refId": "A", "expr": "backup_last_success_timestamp_seconds{instance=~\"$instance\"}", "legendFormat": "{{backup_job}} / {{repo}}" } ]
|
|
}
|
|
]
|
|
}
|