Update gojsontoyaml release and generate manifests (#2043)
* dep: Bump to release v0.1.0 of gojsontoyaml * make: Generate
This commit is contained in:
@@ -17,8 +17,7 @@ spec:
|
||||
rules:
|
||||
- alert: AlertmanagerFailedReload
|
||||
annotations:
|
||||
description: Configuration has failed to load for {{ $labels.namespace }}/{{
|
||||
$labels.pod}}.
|
||||
description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload
|
||||
summary: Reloading an Alertmanager configuration has failed.
|
||||
expr: |
|
||||
@@ -30,11 +29,9 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerMembersInconsistent
|
||||
annotations:
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only
|
||||
found {{ $value }} members of the {{$labels.job}} cluster.
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent
|
||||
summary: A member of an Alertmanager cluster has not found all other cluster
|
||||
members.
|
||||
summary: A member of an Alertmanager cluster has not found all other cluster members.
|
||||
expr: |
|
||||
# Without max_over_time, failed scrapes could create false negatives, see
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
||||
@@ -46,9 +43,7 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerFailedToSendAlerts
|
||||
annotations:
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed
|
||||
to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration
|
||||
}}.
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts
|
||||
summary: An Alertmanager instance failed to send notifications.
|
||||
expr: |
|
||||
@@ -63,12 +58,9 @@ spec:
|
||||
severity: warning
|
||||
- alert: AlertmanagerClusterFailedToSendAlerts
|
||||
annotations:
|
||||
description: The minimum notification failure rate to {{ $labels.integration
|
||||
}} sent from any instance in the {{$labels.job}} cluster is {{ $value |
|
||||
humanizePercentage }}.
|
||||
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications
|
||||
to a critical integration.
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
|
||||
expr: |
|
||||
min by (namespace,service, integration) (
|
||||
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m])
|
||||
@@ -81,12 +73,9 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterFailedToSendAlerts
|
||||
annotations:
|
||||
description: The minimum notification failure rate to {{ $labels.integration
|
||||
}} sent from any instance in the {{$labels.job}} cluster is {{ $value |
|
||||
humanizePercentage }}.
|
||||
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications
|
||||
to a non-critical integration.
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
|
||||
expr: |
|
||||
min by (namespace,service, integration) (
|
||||
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m])
|
||||
@@ -99,8 +88,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: AlertmanagerConfigInconsistent
|
||||
annotations:
|
||||
description: Alertmanager instances within the {{$labels.job}} cluster have
|
||||
different configurations.
|
||||
description: Alertmanager instances within the {{$labels.job}} cluster have different configurations.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent
|
||||
summary: Alertmanager instances within the same cluster have different configurations.
|
||||
expr: |
|
||||
@@ -113,12 +101,9 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterDown
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances
|
||||
within the {{$labels.job}} cluster have been up for less than half of the
|
||||
last 5m.'
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown
|
||||
summary: Half or more of the Alertmanager instances within the same cluster
|
||||
are down.
|
||||
summary: Half or more of the Alertmanager instances within the same cluster are down.
|
||||
expr: |
|
||||
(
|
||||
count by (namespace,service) (
|
||||
@@ -135,12 +120,9 @@ spec:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterCrashlooping
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances
|
||||
within the {{$labels.job}} cluster have restarted at least 5 times in the
|
||||
last 10m.'
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping
|
||||
summary: Half or more of the Alertmanager instances within the same cluster
|
||||
are crashlooping.
|
||||
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
|
||||
expr: |
|
||||
(
|
||||
count by (namespace,service) (
|
||||
|
||||
Reference in New Issue
Block a user