XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-22 09:27:26 +08:00
Code Issues Projects Releases Packages Wiki Activity

adding alerts to promtail and loki (#241)

Browse source 
Co-authored-by: apmbktf <andre.pasqualinoto-martins@itau-unibanco.com.br>
Co-authored-by: Samuel Berthe <dev@samuel-berthe.fr>
This commit is contained in:
Andre Martins 2021-10-03 17:12:59 -03:00 committed by GitHub
parent dc85963ae5
commit 36ca52e598
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 29 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -74,6 +74,7 @@ Collection available here: **[https://awesome-prometheus-alerts.grep.to](https:/
- [Thanos](https://awesome-prometheus-alerts.grep.to/rules#thanos)
- [Loki](https://awesome-prometheus-alerts.grep.to/rules#loki)
- [Promtail](https://awesome-prometheus-alerts.grep.to/rules#promtail)
- [Cortex](https://awesome-prometheus-alerts.grep.to/rules#cortex)
## 🤝 Contributing

28
_data/rules.yml
View file

@ -2031,6 +2031,34 @@ groups:
description: A loki process had too many restarts (target {{ $labels.instance }})
query: changes(process_start_time_seconds{job=~"loki"}[15m]) > 2
severity: warning
- name: Loki request errors
description: The {{ $labels.job }} and {{ $labels.route }} are experiencing errors
query: '100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) > 10'
severity: critical
for: 15m
- name: Loki request panic
description: The {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics
query: sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
severity: critical
for: 5m
- name: Loki request latency
description: The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency
query: (histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{route!~"(?i).*tail.*"}[5m])) by (le))) > 1
severity: critical
for: 5m
- name: Promtail
exporters:
- rules:
- name: Promtail request errors
description: The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors.
query: '100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10'
severity: critical
for: 5m
- name: Promtail request latency
description: The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency.
query: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1
severity: critical
for: 5m
- name: Cortex
exporters:
- rules: