trails-cool/trails
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix Grafana alert rules: proper threshold expressions

Browse source 
The threshold expressions were missing the 'expression' field referencing
the query refId, causing 'no variable specified for refId C' errors.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ullrich Schäfer 2026-03-27 20:23:46 +01:00
parent e866a1ad40
commit 3914da7a57
No known key found for this signature in database
GPG key ID: A32FF691A0F752D9
1 changed files with 17 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

34
infrastructure/grafana/provisioning/alerting/alerts.yml
View file

@ -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: