adding alerts to promtail and loki

This commit is contained in:
apmbktf 2021-08-20 07:56:30 -03:00
parent a225087b06
commit 4e5fe06933

View file

@ -2031,6 +2031,34 @@ groups:
description: A loki process had too many restarts (target {{ $labels.instance }}) description: A loki process had too many restarts (target {{ $labels.instance }})
query: changes(process_start_time_seconds{job=~"loki"}[15m]) > 2 query: changes(process_start_time_seconds{job=~"loki"}[15m]) > 2
severity: warning 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: 15m
- 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: 15m
- name: Cortex - name: Cortex
exporters: exporters:
- rules: - rules: