Skip to content

feat(grafana): add Kupo checkpoint-stale alert and dashboard panel #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tripura-repalle merged 1 commit into from
Aug 24, 2026
+227 −0
Merged

feat(grafana): add Kupo checkpoint-stale alert and dashboard panel #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
124 changes: 124 additions & 0 deletions grafana/alerts/demeter/kupo.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -624,6 +624,130 @@
"notification_settings": {
"receiver": "#infra-alerts"
}
},
{
"uid": "bkl0kupockpstale",
"title": "Kupo checkpoint is stale",
"condition": "C",
"for": "10m",
"data": [
{
"refId": "A",
"relativeTimeRange": {
"from": 900,
"to": 0
},
"datasourceUid": "${datasource_uid_map.gke_blinklabs-demeter_us-central1_dmtr-cluster-prometheus}",
"model": {
"datasource": {
"type": "prometheus",
"uid": "${datasource_uid_map.gke_blinklabs-demeter_us-central1_dmtr-cluster-prometheus}"
},
"editorMode": "code",
"expr": "changes(kupo_most_recent_checkpoint[15m]) and on (pod) (kupo_connection_status == 1)",
"instant": true,
"intervalMs": 1000,
"legendFormat": "__auto",
"maxDataPoints": 43200,
"range": false,
"refId": "A"
}
},
{
"refId": "B",
"relativeTimeRange": {
"from": 0,
"to": 0
},
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": {
"params": [
0,
0
],
"type": "gt"
},
"operator": {
"type": "and"
},
"query": {
"params": []
},
"reducer": {
"params": [],
"type": "last"
},
"type": "query"
}
],
"datasource": {
"name": "Expression",
"type": "__expr__",
"uid": "__expr__"
},
"expression": "A",
"hide": false,
"reducer": "last",
"refId": "B",
"type": "reduce"
}
},
{
"refId": "C",
"relativeTimeRange": {
"from": 0,
"to": 0
},
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": {
"params": [
1,
0
],
"type": "lt"
},
"operator": {
"type": "and"
},
"query": {
"params": []
},
"reducer": {
"params": [],
"type": "avg"
},
"type": "query"
}
],
"datasource": {
"name": "Expression",
"type": "__expr__",
"uid": "__expr__"
},
"expression": "B",
"hide": false,
"refId": "C",
"type": "threshold"
}
}
],
"noDataState": "OK",
"execErrState": "KeepLast",
"annotations": {
"description": "A Kupo instance is connected to its node backend but its most recent checkpoint (kupo_most_recent_checkpoint) has not advanced for at least 15 minutes, meaning it is serving a stale index to clients. This usually indicates a wedged chain-sync session that a pod restart will clear.",
"summary": "{{ range $k, $v := $values -}}\n{{ if (match \"C[0-9]+\" $k) -}}\nPod: {{ $v.Labels.pod }} checkpoint is not advancing\n{{ end }}\n{{ end }}"
},
"labels": {},
"isPaused": false,
"notification_settings": {
"receiver": "#infra-alerts"
}
}
]
}
Expand Down
103 changes: 103 additions & 0 deletions grafana/dashboards/shared/kupo.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1129,6 +1129,109 @@
],
"title": "Container Restarts",
"type": "state-timeline"
},
{
"datasource": {
"type": "prometheus",
"uid": "$datasource"
},
"description": "Number of times each Kupo instance's most recent checkpoint (kupo_most_recent_checkpoint) advanced in the last 15 minutes. A healthy, synced instance advances continuously; a value of 0 means the checkpoint is frozen (wedged chain-sync) and the pod is serving a stale index. This is the signal behind the \"Kupo checkpoint is stale\" alert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "checkpoint changes / 15m",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
},
{
"color": "green",
"value": 1
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 50
},
"id": 30,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"min"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "asc"
}
},
"pluginVersion": "13.1.0-25668120414",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$datasource"
},
"editorMode": "code",
"expr": "changes(kupo_most_recent_checkpoint{pod=~\".*$pod.*\"}[15m]) and on (pod) (kupo_connection_status{pod=~\".*$pod.*\"} == 1)",
"legendFormat": "{{pod}}",
"range": true,
"refId": "A"
}
],
"title": "Checkpoint Advancement (changes / 15m)",
"type": "timeseries"
}
],
"title": "Instances",
Expand Down
Loading