Skip to content

feat(grafana): add kupo mornitoring dashboard using dolos #48

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
Jun 11, 2026
+1,285 −0
Merged

feat(grafana): add kupo mornitoring dashboard using dolos #48

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
164 changes: 164 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 @@ -460,6 +460,170 @@
"notification_settings": {
"receiver": "#infra-alerts"
}
},
{
"uid": "kupo-dolos-disconnected",
"title": "Kupo Disconnected from Dolos",
"condition": "C",
"data": [
{
"refId": "A",
"relativeTimeRange": { "from": 300, "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": "min(kupo_connection_status) by (pod)",
"instant": false,
"intervalMs": 1000,
"legendFormat": "__auto",
"maxDataPoints": 43200,
"range": true,
"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": "avg" },
"type": "query"
}
],
"datasource": { "name": "Expression", "type": "__expr__", "uid": "__expr__" },
"expression": "A",
"intervalMs": 1000,
"maxDataPoints": 43200,
"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",
"intervalMs": 1000,
"maxDataPoints": 43200,
"refId": "C",
"type": "threshold"
}
}
],
"noDataState": "OK",
"execErrState": "KeepLast",
"for": "2m",
"annotations": {
"description": "Kupo has lost its connection to the Dolos backend node.",
"summary": "{{ range $k, $v := $values -}}\n{{ if (match \"C[0-9]+\" $k) -}}\nPod: {{ $v.Labels.pod }} is disconnected from Dolos.\n{{ end }}\n{{ end }}"
},
"isPaused": false,
"notification_settings": {
"receiver": "#infra-alerts"
}
},
{
"uid": "kupo-dolos-high-lag",
"title": "Kupo High Indexing Lag (Dolos)",
"condition": "C",
"data": [
{
"refId": "A",
"relativeTimeRange": { "from": 600, "to": 0 },
"datasourceUid": "${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": "max(dolos_tip_slot) by (pod) - max(kupo_most_recent_point_slot_no) by (pod)",
"instant": false,
"intervalMs": 1000,
"legendFormat": "__auto",
"maxDataPoints": 43200,
"range": true,
"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": "avg" },
"type": "query"
}
],
"datasource": { "name": "Expression", "type": "__expr__", "uid": "__expr__" },
"expression": "A",
"intervalMs": 1000,
"maxDataPoints": 43200,
"reducer": "last",
"refId": "B",
"type": "reduce"
}
},
{
"refId": "C",
"relativeTimeRange": { "from": 0, "to": 0 },
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": { "params": [10000, 0], "type": "gt" },
"operator": { "type": "and" },
"query": { "params": [] },
"reducer": { "params": [], "type": "avg" },
"type": "query"
}
],
"datasource": { "name": "Expression", "type": "__expr__", "uid": "__expr__" },
"expression": "B",
"intervalMs": 1000,
"maxDataPoints": 43200,
"refId": "C",
"type": "threshold"
}
}
],
"noDataState": "NoData",
"execErrState": "KeepLast",
"for": "5m",
"annotations": {
"description": "Kupo indexing lag vs Dolos chain tip has exceeded 10,000 slots for more than 5 minutes.",
"summary": "{{ range $k, $v := $values -}}\n{{ if (match \"C[0-9]+\" $k) -}}\nPod: {{ $v.Labels.pod }}\nLag: {{ humanize $v.Value }} slots\n{{ end }}\n{{ end }}"
},
"isPaused": false,
"notification_settings": {
"receiver": "#infra-alerts"
}
}
]
}
Expand Down
Loading
Loading