easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add runbook_url annotation to all alerts

Browse Source 
Signed-off-by: ArthurSens <arthursens2005@gmail.com>
This commit is contained in:
ArthurSens
2021-03-05 12:54:03 +00:00
parent ebd4b28b91
commit e586afb280
10 changed files with 72 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
manifests/prometheus-operator-prometheusRule.yaml
View File

@@ -17,6 +17,7 @@ spec:
- alert: PrometheusOperatorListErrors
annotations:
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatorlisterrors
summary: Errors while performing list operations in controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
@@ -26,6 +27,7 @@ spec:
- alert: PrometheusOperatorWatchErrors
annotations:
description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatorwatcherrors
summary: Errors while performing watch operations in controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
@@ -35,6 +37,7 @@ spec:
- alert: PrometheusOperatorSyncFailed
annotations:
description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatorsyncfailed
summary: Last controller reconciliation failed
expr: |
min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
@@ -44,6 +47,7 @@ spec:
- alert: PrometheusOperatorReconcileErrors
annotations:
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatorreconcileerrors
summary: Errors while reconciling controller.
expr: |
(sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring"}[5m]))) > 0.1
@@ -53,6 +57,7 @@ spec:
- alert: PrometheusOperatorNodeLookupErrors
annotations:
description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatornodelookuperrors
summary: Errors while reconciling Prometheus.
expr: |
rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
@@ -62,6 +67,7 @@ spec:
- alert: PrometheusOperatorNotReady
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatornotready
summary: Prometheus operator not ready
expr: |
min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m]) == 0)
@@ -71,6 +77,7 @@ spec:
- alert: PrometheusOperatorRejectedResources
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/prometheusoperatorrejectedresources
summary: Resources rejected by Prometheus operator
expr: |
min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m]) > 0