XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 17:07:24 +08:00
Code Issues Projects Releases Packages Wiki Activity

Adding an alert for prometheus internals: rule evaluation slowing down

Browse source
This commit is contained in:
Samuel Berthe 2020-03-08 15:08:11 +01:00
parent 072a435f32
commit 718a039313
No known key found for this signature in database
GPG key ID: 9D7813625412A946
1 changed files with 5 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
_data/rules.yml
View file

@ -19,13 +19,17 @@ services:
query: "up == 0"
severity: error
- name: Prometheus rule evaluation failures
description: 'Prometheus encountered {{ $value }} rule evaluation failures. leading to potentially ignored alerts.'
description: 'Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.'
query: 'increase(prometheus_rule_evaluation_failures_total[3m]) > 0'
severity: error
- name: Prometheus template text expansion failures
description: 'Prometheus encountered {{ $value }} template text expansion failures'
query: 'increase(prometheus_template_text_expansion_failures_total[3m]) > 0'
severity: error
- name: Prometheus rule evaluation slow
description: 'Prometheus rule evaluation took more time than the scheduled interval. I indicates a slower storage backend access or too complex query.'
query: 'prometheus_rule_group_last_duration_seconds < prometheus_rule_group_interval_seconds'
severity: error
- name: Prometheus TSDB checkpoint creation failures
description: 'Prometheus encountered {{ $value }} checkpoint creation failures'
query: 'increase(prometheus_tsdb_checkpoint_creations_failed_total[3m]) > 0'