mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-26 11:27:00 +08:00
fix(argocd): move contrib into _data/rules.yml instead of dist/...
This commit is contained in:
parent
fd076f3028
commit
2bfb8d8ddc
2 changed files with 19 additions and 26 deletions
|
|
@ -27,7 +27,7 @@ groups:
|
||||||
query: 'sum by (job) (up) == 0'
|
query: 'sum by (job) (up) == 0'
|
||||||
severity: critical
|
severity: critical
|
||||||
- name: Prometheus target missing with warmup time
|
- name: Prometheus target missing with warmup time
|
||||||
description: Allow a job time to start up (10 minutes) before alerting that it's down.
|
description: Allow a job time to start up (10 minutes) before alerting that it's down.
|
||||||
query: 'sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))'
|
query: 'sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))'
|
||||||
severity: critical
|
severity: critical
|
||||||
- name: Prometheus configuration reload failure
|
- name: Prometheus configuration reload failure
|
||||||
|
|
@ -1952,6 +1952,24 @@ groups:
|
||||||
query: 'sum(rate(pilot_duplicate_envoy_clusters{}[5m])) > 0'
|
query: 'sum(rate(pilot_duplicate_envoy_clusters{}[5m])) > 0'
|
||||||
severity: critical
|
severity: critical
|
||||||
|
|
||||||
|
- name: ArgoCD
|
||||||
|
exporters:
|
||||||
|
- name: Embedded exporter
|
||||||
|
slug: embedded-exporter
|
||||||
|
doc_url: https://argo-cd.readthedocs.io/en/stable/operator-manual/metrics/
|
||||||
|
rules:
|
||||||
|
- name: ArgoCD service not synced
|
||||||
|
description: Service {{ $labels.name }} run by argo is currently not in sync.
|
||||||
|
query: 'argocd_app_info{sync_status!="Synced"} != 0'
|
||||||
|
severity: warning
|
||||||
|
for: 15m
|
||||||
|
- name: ArgoCD service unhealthy
|
||||||
|
description: Service {{ $labels.name }} run by argo is currently not healthy.
|
||||||
|
query: 'argocd_app_info{health_status!="Healthy"} != 0'
|
||||||
|
severity: warning
|
||||||
|
for: 15m
|
||||||
|
|
||||||
|
|
||||||
- name: Network, security and storage
|
- name: Network, security and storage
|
||||||
services:
|
services:
|
||||||
- name: Ceph
|
- name: Ceph
|
||||||
|
|
|
||||||
25
dist/rules/argocd/argocd.yml
vendored
25
dist/rules/argocd/argocd.yml
vendored
|
|
@ -1,25 +0,0 @@
|
||||||
groups:
|
|
||||||
|
|
||||||
- name: ArgoCD
|
|
||||||
|
|
||||||
rules:
|
|
||||||
|
|
||||||
- alert: ServiceUnSynced
|
|
||||||
expr: argocd_app_info{sync_status!="Synced"} != 0
|
|
||||||
for: 20m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
annotations:
|
|
||||||
summary: ArgoCD Service (name {{ $labels.name }}) unsynced.
|
|
||||||
description: "Service {{ $labels.name }} run by argo is currently not in sync please check"
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
- alert: ServiceUnhealthy
|
|
||||||
expr: argocd_app_info{health_status!="Healthy"} != 0
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: critical
|
|
||||||
annotations:
|
|
||||||
summary: ArgoCD Service (name {{ $labels.name }}) unhealthy.
|
|
||||||
description: "Service {{ $labels.name }} run by argo is currently not in healthy please check"
|
|
||||||
Loading…
Reference in a new issue