Skip to content
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

Fix nodata error alert #16

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Fix nodata error alert #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f6c735a
Fix nodata error in alert
antoinebhs Jun 4, 2024
e90faad
Add error events alert
antoinebhs Jun 4, 2024
61485ad
Change nodata state to OK
antoinebhs Jun 4, 2024
f598373
Fix error
antoinebhs Jun 4, 2024
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
127 changes: 127 additions & 0 deletions resources/grafana/alert-rules/error_events.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,127 @@
{
"orgID": 1,
"folderUID": "{{FOLDER_UID}}",
"ruleGroup": "30sEval",
"title": "Error events",
"condition": "C",
"data": [
{
"refId": "A",
"queryType": "",
"relativeTimeRange": {
"from": 1800,
"to": 0
},
"datasourceUid": "{{DATASOURCE_UID}}",
"model": {
"datasource": {
"type": "prometheus",
"uid": "{{DATASOURCE_UID}}"
},
"editorMode": "code",
"expr": "(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason=\"Error\"}[10m]) == 1",
"instant": false,
"interval": "",
"intervalMs": 15000,
"legendFormat": "{{pod}}",
"maxDataPoints": 43200,
"range": true,
"refId": "A"
}
},
{
"refId": "B",
"queryType": "",
"relativeTimeRange": {
"from": 1800,
"to": 0
},
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": {
"params": [],
"type": "gt"
},
"operator": {
"type": "and"
},
"query": {
"params": [
"B"
]
},
"reducer": {
"params": [],
"type": "last"
},
"type": "query"
}
],
"datasource": {
"type": "__expr__",
"uid": "__expr__"
},
"expression": "A",
"intervalMs": 1000,
"maxDataPoints": 43200,
"reducer": "last",
"refId": "B",
"type": "reduce"
}
},
{
"refId": "C",
"queryType": "",
"relativeTimeRange": {
"from": 1800,
"to": 0
},
"datasourceUid": "__expr__",
"model": {
"conditions": [
{
"evaluator": {
"params": [
0
],
"type": "gt"
},
"operator": {
"type": "and"
},
"query": {
"params": [
"C"
]
},
"reducer": {
"params": [],
"type": "last"
},
"type": "query"
}
],
"datasource": {
"type": "__expr__",
"uid": "__expr__"
},
"expression": "B",
"intervalMs": 1000,
"maxDataPoints": 43200,
"refId": "C",
"type": "threshold"
}
}
],
"noDataState": "OK",
"execErrState": "Error",
"for": "5m",
"annotations": {
"__dashboardUid__": "a24365d3-fb9c-407b-99d6-5b0b14de5adc",
"__panelId__": "50",
"summary": "Triggered when a pod is restarted because of an error"
},
"isPaused": false
}
4 changes: 2 additions & 2 deletions ...urces/grafana/alert-rules/oom_killed.json → ...rafana/alert-rules/oom_killed_events.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
"uid": "{{DATASOURCE_UID}}"
},
"editorMode": "code",
"expr": "(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason=\"OOMKilled\"}[10m]) == 1",
"expr": "(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason=\"OOMKilled\"}[10m]) == 1",
"instant": false,
"interval": "",
"intervalMs": 15000,
Expand Down Expand Up @@ -115,7 +115,7 @@
}
}
],
"noDataState": "NoData",
"noDataState": "OK",
"execErrState": "Error",
"for": "5m",
"annotations": {
Expand Down
Loading