crawler_alert, monitoring: AI crawler metrics and dashboards
Some checks failed
deploy / ansible (push) Failing after 1m17s
Some checks failed
deploy / ansible (push) Failing after 1m17s
crawler-alert.py --metrics (5-minute timer) reads what the Traefik access log gained since the last run, judges every request that names an AI bot exactly like the weekly report (vendor IP ranges, forward- confirmed rDNS, Meta's ASN) and writes cumulative counters to the node_exporter textfile directory. Verdicts are cached per bot and IP for a week, so DNS only sees new addresses; range files are refetched once a day. It covers every router, while the mails keep watching Forgejo only. New dashboard "AI crawlers", and a row of it on the overview. The overview's load gauge divided node_load1 by a count with fewer labels, which matches nothing; aggregate both sides by host. Assisted-by: Claude:opus-5-5
This commit is contained in:
parent
3b25f4ae25
commit
bc0dac9188
GPG key ID:
4F8851660FA4121B
7 changed files with 1924 additions and 6 deletions
1148
ansible/roles/monitoring/files/dashboards/Services/crawlers.json
Normal file
1148
ansible/roles/monitoring/files/dashboards/Services/crawlers.json
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -403,7 +403,7 @@
|
|||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "node_load1 / count by (host) (node_cpu_seconds_total{mode=\"idle\"})",
|
||||
"expr": "sum by (host) (node_load1) / count by (host) (node_cpu_seconds_total{mode=\"idle\"})",
|
||||
"legendFormat": "{{host}}",
|
||||
"refId": "A",
|
||||
"instant": true,
|
||||
|
|
@ -769,7 +769,7 @@
|
|||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "topk(12, container_memory_working_set_bytes{name!=\"\"})",
|
||||
"legendFormat": "{{host}} \u00b7 {{name}}",
|
||||
"legendFormat": "{{host}} · {{name}}",
|
||||
"refId": "A",
|
||||
"instant": true,
|
||||
"range": false
|
||||
|
|
@ -826,7 +826,7 @@
|
|||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "topk(8, sum by (host, name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[$__rate_interval])))",
|
||||
"legendFormat": "{{host}} \u00b7 {{name}}",
|
||||
"legendFormat": "{{host}} · {{name}}",
|
||||
"refId": "A",
|
||||
"instant": false,
|
||||
"range": true
|
||||
|
|
@ -1321,7 +1321,7 @@
|
|||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "(time() - restic_backup_last_success_timestamp_seconds) / 3600",
|
||||
"legendFormat": "restic \u00b7 {{host}} \u00b7 {{repo}}",
|
||||
"legendFormat": "restic · {{host}} · {{repo}}",
|
||||
"refId": "A",
|
||||
"instant": true,
|
||||
"range": false
|
||||
|
|
@ -1332,7 +1332,7 @@
|
|||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "(time() - s3_replicate_last_success_timestamp_seconds) / 3600",
|
||||
"legendFormat": "replica hel1 \u2192 fsn1",
|
||||
"legendFormat": "replica hel1 → fsn1",
|
||||
"refId": "B",
|
||||
"instant": true,
|
||||
"range": false
|
||||
|
|
@ -1488,6 +1488,579 @@
|
|||
"enableLogDetails": true,
|
||||
"dedupStrategy": "signature"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "row",
|
||||
"title": "AI crawlers",
|
||||
"id": 30,
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 59
|
||||
},
|
||||
"panels": []
|
||||
},
|
||||
{
|
||||
"type": "piechart",
|
||||
"title": "Who is asking (time range)",
|
||||
"id": 31,
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_ai_requests_total{verdict=\"verified\"}[$__range]))",
|
||||
"legendFormat": "AI · verified",
|
||||
"refId": "A",
|
||||
"instant": true,
|
||||
"range": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_ai_requests_total{verdict=\"spoofed\"}[$__range]))",
|
||||
"legendFormat": "AI · spoofed",
|
||||
"refId": "B",
|
||||
"instant": true,
|
||||
"range": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_ai_requests_total{verdict=~\"unknown|proxied|private\"}[$__range]))",
|
||||
"legendFormat": "AI · unverifiable",
|
||||
"refId": "C",
|
||||
"instant": true,
|
||||
"range": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_class_requests_total{class=\"other-bot\"}[$__range]))",
|
||||
"legendFormat": "other bots",
|
||||
"refId": "D",
|
||||
"instant": true,
|
||||
"range": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_class_requests_total{class=\"browser-like\"}[$__range]))",
|
||||
"legendFormat": "browser-like",
|
||||
"refId": "E",
|
||||
"instant": true,
|
||||
"range": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum(increase(crawler_class_requests_total{class=\"none\"}[$__range]))",
|
||||
"legendFormat": "no user agent",
|
||||
"refId": "F",
|
||||
"instant": true,
|
||||
"range": false
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 6,
|
||||
"x": 0,
|
||||
"y": 60
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "verified"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "green"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "spoofed"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "red"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "proxied"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "blue"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "unknown"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "yellow"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "private"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "purple"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · verified"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "green"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · spoofed"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "red"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · unverifiable"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "yellow"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "other bots"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "orange"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "browser-like"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "purple"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "no user agent"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "text"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"pieType": "donut",
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"values": [
|
||||
"value",
|
||||
"percent"
|
||||
]
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"description": "From the Traefik access log, every router (crawler-alert.py --metrics, 5-minute timer). A request naming an AI bot counts as verified only if its source IP is in the vendor's published ranges, or passes forward-confirmed reverse DNS, or (Meta) sits in the vendor's own ASN. spoofed = the claim failed that check; unverifiable = via Cloudflare, no PTR, or over the DNS budget.",
|
||||
"links": [
|
||||
{
|
||||
"title": "Crawler details",
|
||||
"url": "/d/asxpio-crawlers?${__url_time_range}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "AI crawler requests by verdict (per minute)",
|
||||
"id": 32,
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sum by (verdict) (rate(crawler_ai_requests_total[$__rate_interval])) * 60",
|
||||
"legendFormat": "{{verdict}}",
|
||||
"refId": "A",
|
||||
"instant": false,
|
||||
"range": true
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 9,
|
||||
"x": 6,
|
||||
"y": 60
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"stacking": {
|
||||
"mode": "normal"
|
||||
},
|
||||
"fillOpacity": 40,
|
||||
"lineWidth": 1
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "verified"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "green"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "spoofed"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "red"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "proxied"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "blue"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "unknown"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "yellow"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "private"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "purple"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · verified"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "green"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · spoofed"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "red"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "AI · unverifiable"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "yellow"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "other bots"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "orange"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "browser-like"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "purple"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "no user agent"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "text"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"description": "From the Traefik access log, every router (crawler-alert.py --metrics, 5-minute timer). A request naming an AI bot counts as verified only if its source IP is in the vendor's published ranges, or passes forward-confirmed reverse DNS, or (Meta) sits in the vendor's own ASN. spoofed = the claim failed that check; unverifiable = via Cloudflare, no PTR, or over the DNS budget."
|
||||
},
|
||||
{
|
||||
"type": "bargauge",
|
||||
"title": "Verified AI crawlers by vendor (time range)",
|
||||
"id": 33,
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "prometheus"
|
||||
},
|
||||
"expr": "sort_desc(sum by (vendor) (increase(crawler_ai_requests_total{verdict=\"verified\"}[$__range])))",
|
||||
"legendFormat": "{{vendor}}",
|
||||
"refId": "A",
|
||||
"instant": true,
|
||||
"range": false
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 9,
|
||||
"x": 15,
|
||||
"y": 60
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "continuous-GrYlRd"
|
||||
},
|
||||
"unit": "short",
|
||||
"decimals": 0,
|
||||
"min": 0
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"displayMode": "gradient",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"values": false
|
||||
},
|
||||
"showUnfilled": true,
|
||||
"valueMode": "color"
|
||||
}
|
||||
}
|
||||
],
|
||||
"graphTooltip": 1,
|
||||
|
|
@ -1501,4 +2074,4 @@
|
|||
"tags": []
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue