Skip to content

feat(grafana): add Ogmios tip-stale alert and dashboard panel #61

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 21, 2026
+226 −0
Merged

feat(grafana): add Ogmios tip-stale alert and dashboard panel #61

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/ogmios.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,130 @@
"notification_settings": {
"receiver": "#infra-alerts"
}
},
{
"uid": "bkl0ogtipstale",
"title": "Ogmios tip 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(ogmios_tip_slot[15m]) and on (pod) (ogmios_connected == 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": "An Ogmios instance is connected to its cardano-node backend but its chain tip (ogmios_tip_slot) has not advanced for at least 15 minutes, meaning it is serving a stale tip 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: {{ $v.Labels.pod }} tip slot is not advancing\n{{ end }}\n{{ end }}"
},
"labels": {},
"isPaused": false,
"notification_settings": {
"receiver": "#infra-alerts"
}
}
]
}
Expand Down
102 changes: 102 additions & 0 deletions grafana/dashboards/shared/ogmios.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1636,6 +1636,108 @@
],
"title": "Request count by Code (green)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "$datasource"
},
"description": "Number of times each Ogmios instance's chain tip (ogmios_tip_slot) advanced in the last 15 minutes. A healthy, synced instance advances continuously; a value of 0 means the tip is frozen (wedged chain-sync) and the pod is serving a stale tip. This is the signal behind the \"Ogmios tip is stale\" alert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "tip 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": 71
},
"options": {
"legend": {
"calcs": [
"lastNotNull",
"min"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "asc"
}
},
"pluginVersion": "12.4.0-21024277089.patch2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$datasource"
},
"editorMode": "code",
"expr": "changes(ogmios_tip_slot{namespace=\"$namespace\", pod=~\".*(cardano-)?$network-.*\"}[15m]) and on (pod) (ogmios_connected{namespace=\"$namespace\", pod=~\".*(cardano-)?$network-.*\"} == 1)",
"legendFormat": "{{pod}}",
"range": true,
"refId": "A"
}
],
"title": "Tip Slot Advancement (changes / 15m)",
"type": "timeseries"
}
],
"refresh": "5s",
Expand Down
Loading