steve/restic-manager
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases 1 Wiki Activity
Files
4f1ca2fed8d25bd5efc7fef2e01ad06455b0e8b6
restic-manager/deploy/grafana/restic-manager-dashboard.json
T
steve 73e733be61
CI / Test (rest) (pull_request) Successful in 41s
Details
CI / Test (store) (pull_request) Successful in 43s
Details
CI / Lint (pull_request) Successful in 29s
Details
CI / Build (windows/amd64) (pull_request) Successful in 44s
Details
CI / Test (server-http) (pull_request) Successful in 1m47s
Details
CI / Build (linux/arm64) (pull_request) Successful in 43s
Details
CI / Build (linux/amd64) (pull_request) Successful in 2m1s
Details
P6-04+05: Prometheus /metrics endpoint + Grafana dashboard 
New internal/server/metrics package emits the legacy text/plain
exposition format directly, so we don't pull in
prometheus/client_golang. Endpoint is opt-in via RM_METRICS_TOKEN
and/or RM_METRICS_TRUSTED_CIDR; route is not mounted at all if
neither gate is set. Both gates ANDed when both configured.

Per-host gauges (online, last_backup_*, repo_size_bytes,
snapshot_count, open_alerts, repo_status), server gauges
(hosts_total/online, active_alerts by severity, build_info), and
an in-memory job-duration histogram observed from the existing
MsgJobFinished branch in the WS handler.

Docs in docs/prometheus.md (enable + scrape config + metric
reference + dashboard import). Sample dashboard at
deploy/grafana/restic-manager-dashboard.json - six panels,
Grafana schema 39, single Prometheus datasource variable.

Tests: golden render, concurrent observe, bucket boundaries in
the metrics package; auth matrix (no auth -> 404, token gate,
CIDR gate, both required) in the HTTP layer.
2026-05-07 23:17:15 +01:00

326 lines
9.2 KiB
JSON
Raw Blame History

{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": { "type": "grafana", "uid": "-- Grafana --" },
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "restic-manager fleet overview. Imports against any Prometheus data source.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"id": 1,
"title": "Fleet status",
"type": "stat",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 6, "w": 6, "x": 0, "y": 0 },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "red", "value": null },
{ "color": "green", "value": 1 }
]
},
"unit": "short"
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_hosts_online",
"legendFormat": "online",
"refId": "A"
},
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_hosts_total",
"legendFormat": "total",
"refId": "B"
}
]
},
{
"id": 2,
"title": "Open alerts",
"type": "stat",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 6, "w": 6, "x": 6, "y": 0 },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 1 },
{ "color": "red", "value": 5 }
]
},
"unit": "short"
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "none",
"orientation": "horizontal",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "sum by (severity) (rm_active_alerts)",
"legendFormat": "{{severity}}",
"refId": "A"
}
]
},
{
"id": 3,
"title": "Backups failing (last reported run)",
"type": "stat",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 6, "w": 6, "x": 12, "y": 0 },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "red", "value": 1 }
]
},
"unit": "short"
},
"overrides": []
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "count(rm_host_last_backup_success == 0)",
"legendFormat": "failing",
"refId": "A"
}
]
},
{
"id": 4,
"title": "Hosts",
"type": "table",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 6 },
"fieldConfig": {
"defaults": {
"custom": { "align": "auto", "displayMode": "auto" }
},
"overrides": [
{
"matcher": { "id": "byName", "options": "Value #B" },
"properties": [
{ "id": "displayName", "value": "Last backup (s ago)" },
{ "id": "unit", "value": "s" }
]
},
{
"matcher": { "id": "byName", "options": "Value #C" },
"properties": [
{ "id": "displayName", "value": "Repo size" },
{ "id": "unit", "value": "bytes" }
]
},
{
"matcher": { "id": "byName", "options": "Value #D" },
"properties": [
{ "id": "displayName", "value": "Snapshots" }
]
},
{
"matcher": { "id": "byName", "options": "Value #A" },
"properties": [
{ "id": "displayName", "value": "Online" }
]
},
{
"matcher": { "id": "byName", "options": "Value #E" },
"properties": [
{ "id": "displayName", "value": "Open alerts" }
]
}
]
},
"options": { "showHeader": true },
"transformations": [
{
"id": "merge",
"options": {}
}
],
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_host_agent_online",
"format": "table",
"instant": true,
"refId": "A"
},
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "time() - rm_host_last_backup_timestamp_seconds",
"format": "table",
"instant": true,
"refId": "B"
},
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_host_repo_size_bytes",
"format": "table",
"instant": true,
"refId": "C"
},
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_host_snapshot_count",
"format": "table",
"instant": true,
"refId": "D"
},
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_host_open_alerts",
"format": "table",
"instant": true,
"refId": "E"
}
]
},
{
"id": 5,
"title": "Repo size over time",
"type": "timeseries",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisLabel": "",
"drawStyle": "line",
"fillOpacity": 10,
"lineWidth": 1,
"pointSize": 5,
"showPoints": "never"
},
"unit": "bytes"
},
"overrides": []
},
"options": {
"legend": { "calcs": ["last"], "displayMode": "list", "placement": "bottom", "showLegend": true },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "rm_host_repo_size_bytes",
"legendFormat": "{{host}}",
"refId": "A"
}
]
},
{
"id": 6,
"title": "Job duration p95 (last 1h, by kind)",
"type": "timeseries",
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"drawStyle": "line",
"fillOpacity": 5,
"lineWidth": 1,
"pointSize": 4,
"showPoints": "never"
},
"unit": "s"
},
"overrides": []
},
"options": {
"legend": { "calcs": ["last"], "displayMode": "list", "placement": "bottom", "showLegend": true },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"expr": "histogram_quantile(0.95, sum by (kind, le) (rate(rm_job_duration_seconds_bucket[1h])))",
"legendFormat": "{{kind}}",
"refId": "A"
}
]
}
],
"refresh": "30s",
"schemaVersion": 39,
"style": "dark",
"tags": ["restic-manager", "backups"],
"templating": {
"list": [
{
"current": {},
"hide": 0,
"includeAll": false,
"label": "Prometheus",
"multi": false,
"name": "DS_PROMETHEUS",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
}
]
},
"time": { "from": "now-6h", "to": "now" },
"timepicker": {},
"timezone": "",
"title": "restic-manager — fleet",
"uid": "rm-fleet-overview",
"version": 1,
"weekStart": ""
}
Reference in New Issue View Git Blame Copy Permalink