mirrors/monitoring-mixins-website
1
0
Fork 0
mirror of https://github.com/monitoring-mixins/website.git synced 2024-12-14 11:37:31 +00:00
Code Activity

assets,site/content: daily assets regeneration

Browse source
This commit is contained in:
github-actions[bot] 2022-08-10 03:41:49 +00:00
parent 9ec2f873d5
commit 04f72fdce5
2 changed files with 38 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
assets/thanos/alerts.yaml
View file

@ -170,6 +170,22 @@ groups:
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
- alert: ThanosQueryOverload
annotations:
description: Thanos Query {{$labels.job}} has been overloaded for more than
15 minutes. This may be a symptom of excessive simultanous complex requests,
low performance of the Prometheus API, or failures within these components.
Assess the health of the Thanos query instances, the connnected Prometheus
instances, look for potential senders of these requests and then contact support.
runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosqueryoverload
summary: Thanos query reaches its maximum capacity serving concurrent requests.
expr: |
(
max_over_time(thanos_query_concurrent_gate_queries_max[5m]) - avg_over_time(thanos_query_concurrent_gate_queries_in_flight[5m]) < 1
)
for: 15m
labels:
severity: warning
- name: thanos-receive - name: thanos-receive
rules: rules:
- alert: ThanosReceiveHttpRequestErrorRateHigh - alert: ThanosReceiveHttpRequestErrorRateHigh

22
site/content/thanos/_index.md
View file

@ -258,6 +258,28 @@ labels:
severity: critical severity: critical
{{< /code >}} {{< /code >}}
##### ThanosQueryOverload
https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosqueryoverload
{{< code lang="yaml" >}}
alert: ThanosQueryOverload
annotations:
description: Thanos Query {{$labels.job}} has been overloaded for more than 15 minutes.
This may be a symptom of excessive simultanous complex requests, low performance
of the Prometheus API, or failures within these components. Assess the health
of the Thanos query instances, the connnected Prometheus instances, look for potential
senders of these requests and then contact support.
runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanosqueryoverload
summary: Thanos query reaches its maximum capacity serving concurrent requests.
expr: |
(
max_over_time(thanos_query_concurrent_gate_queries_max[5m]) - avg_over_time(thanos_query_concurrent_gate_queries_in_flight[5m]) < 1
)
for: 15m
labels:
severity: warning
{{< /code >}}
### thanos-receive ### thanos-receive
##### ThanosReceiveHttpRequestErrorRateHigh ##### ThanosReceiveHttpRequestErrorRateHigh