contrib/kube-prometheus: Run jb update and generate all manifests
This commit is contained in:
@@ -838,7 +838,7 @@ spec:
|
||||
the limit of 110.
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods
|
||||
expr: |
|
||||
kubelet_running_pod_count{job="kubelet"} > 100
|
||||
kubelet_running_pod_count{job="kubelet"} > 110 * 0.9
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -914,8 +914,8 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerDownOrMissing
|
||||
annotations:
|
||||
description: An unexpected number of Alertmanagers are scraped or Alertmanagers
|
||||
disappeared from discovery.
|
||||
description: An unexpected number of Alertmanagers were scraped or disappeared
|
||||
from discovery.
|
||||
summary: Alertmanager down or missing
|
||||
expr: |
|
||||
label_replace(prometheus_operator_alertmanager_spec_replicas{job="prometheus-operator"}, "job", "alertmanager-$1", "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up{job="alertmanager-main"}) BY (job) != 1
|
||||
@@ -936,7 +936,7 @@ spec:
|
||||
rules:
|
||||
- alert: TargetDown
|
||||
annotations:
|
||||
description: '{{ $value }}% of {{ $labels.job }} targets are down.'
|
||||
description: '{{ $value }}% of the {{ $labels.job }} targets are down.'
|
||||
summary: Targets are down
|
||||
expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10
|
||||
for: 10m
|
||||
@@ -944,7 +944,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: DeadMansSwitch
|
||||
annotations:
|
||||
description: This is a DeadMansSwitch meant to ensure that the entire Alerting
|
||||
description: This is a DeadMansSwitch meant to ensure that the entire alerting
|
||||
pipeline is functional.
|
||||
summary: Alerting DeadMansSwitch
|
||||
expr: vector(1)
|
||||
@@ -955,7 +955,7 @@ spec:
|
||||
- alert: NodeDiskRunningFull
|
||||
annotations:
|
||||
message: Device {{ $labels.device }} of node-exporter {{ $labels.namespace
|
||||
}}/{{ $labels.pod }} is running full within the next 24 hours.
|
||||
}}/{{ $labels.pod }} will be full within the next 24 hours.
|
||||
expr: |
|
||||
(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[6h], 3600 * 24) < 0)
|
||||
for: 30m
|
||||
@@ -964,7 +964,7 @@ spec:
|
||||
- alert: NodeDiskRunningFull
|
||||
annotations:
|
||||
message: Device {{ $labels.device }} of node-exporter {{ $labels.namespace
|
||||
}}/{{ $labels.pod }} is running full within the next 2 hours.
|
||||
}}/{{ $labels.pod }} will be full within the next 2 hours.
|
||||
expr: |
|
||||
(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[30m], 3600 * 2) < 0)
|
||||
for: 10m
|
||||
@@ -1071,3 +1071,29 @@ spec:
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: prometheus-operator
|
||||
rules:
|
||||
- alert: PrometheusOperatorAlertmanagerReconcileErrors
|
||||
annotations:
|
||||
message: Errors while reconciling Alertmanager in {{$labels.namespace}} namespace.
|
||||
expr: |
|
||||
rate(prometheus_operator_alertmanager_reconcile_errors_total{job="prometheus-operator"}[5m]) > 0.01
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorPrometheusReconcileErrors
|
||||
annotations:
|
||||
message: Errors while reconciling Prometheus in {{$labels.namespace}} namespace.
|
||||
expr: |
|
||||
rate(prometheus_operator_prometheus_reconcile_errors_total{job="prometheus-operator"}[5m]) > 0.01
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorNodeLookupErrors
|
||||
annotations:
|
||||
message: Errors while reconciling Prometheus in {{$labels.namespace}} namespace.
|
||||
expr: |
|
||||
rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator"}[5m]) > 0.01
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
|
Reference in New Issue
Block a user