Merge pull request #109 from trails-cool/fix-grafana-alerts-v2
Fix Grafana alert rule expressions
This commit is contained in:
commit
4801c40e04
1 changed files with 17 additions and 17 deletions
|
|
@ -8,22 +8,22 @@ groups:
|
|||
rules:
|
||||
- uid: disk-usage-high
|
||||
title: Disk usage > 80%
|
||||
condition: C
|
||||
condition: B
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange: { from: 600, to: 0 }
|
||||
datasourceUid: prometheus
|
||||
model:
|
||||
expr: (1 - node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100
|
||||
intervalMs: 60000
|
||||
maxDataPoints: 43200
|
||||
- refId: C
|
||||
relativeTimeRange: { from: 600, to: 0 }
|
||||
instant: true
|
||||
- refId: B
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
type: threshold
|
||||
expression: A
|
||||
conditions:
|
||||
- evaluator: { params: [80], type: gt }
|
||||
operator: { type: and }
|
||||
reducer: { type: last }
|
||||
for: 15m
|
||||
annotations:
|
||||
|
|
@ -31,22 +31,22 @@ groups:
|
|||
|
||||
- uid: app-health-failing
|
||||
title: App health check failing
|
||||
condition: C
|
||||
condition: B
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange: { from: 300, to: 0 }
|
||||
datasourceUid: prometheus
|
||||
model:
|
||||
expr: up{job=~"journal|planner"} == 0
|
||||
intervalMs: 15000
|
||||
maxDataPoints: 43200
|
||||
- refId: C
|
||||
relativeTimeRange: { from: 300, to: 0 }
|
||||
expr: up{job=~"journal|planner"}
|
||||
instant: true
|
||||
- refId: B
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
type: threshold
|
||||
expression: A
|
||||
conditions:
|
||||
- evaluator: { params: [0], type: gt }
|
||||
- evaluator: { params: [1], type: lt }
|
||||
operator: { type: and }
|
||||
reducer: { type: last }
|
||||
for: 2m
|
||||
annotations:
|
||||
|
|
@ -54,22 +54,22 @@ groups:
|
|||
|
||||
- uid: error-rate-high
|
||||
title: Error rate > 5%
|
||||
condition: C
|
||||
condition: B
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange: { from: 600, to: 0 }
|
||||
datasourceUid: prometheus
|
||||
model:
|
||||
expr: sum(rate(http_request_duration_seconds_count{status=~"5.."}[5m])) / sum(rate(http_request_duration_seconds_count[5m])) * 100
|
||||
intervalMs: 60000
|
||||
maxDataPoints: 43200
|
||||
- refId: C
|
||||
relativeTimeRange: { from: 600, to: 0 }
|
||||
instant: true
|
||||
- refId: B
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
type: threshold
|
||||
expression: A
|
||||
conditions:
|
||||
- evaluator: { params: [5], type: gt }
|
||||
operator: { type: and }
|
||||
reducer: { type: last }
|
||||
for: 5m
|
||||
annotations:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue