mirror of
https://github.com/monitoring-mixins/website.git
synced 2024-12-14 11:37:31 +00:00
assets,site/content: daily assets regeneration
This commit is contained in:
parent
763258c7bb
commit
16f1c7dd05
4 changed files with 43 additions and 14 deletions
|
@ -1051,8 +1051,20 @@ groups:
|
|||
}}, the configuration may not be supported
|
||||
summary: The number of subsystems defined to the gateway exceeds supported values
|
||||
on cluster {{ $labels.cluster }}
|
||||
expr: count by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_metadata,"gateway_host","$1","instance","(.*):.*"))
|
||||
> 16.00
|
||||
expr: count by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_metadata,"gateway_host","$1","instance","(.*?)(?::.*)?"))
|
||||
> 128.00
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
type: ceph_default
|
||||
- alert: NVMeoFTooManyNamespaces
|
||||
annotations:
|
||||
description: Although you may continue to create namespaces in {{ $labels.gateway_host
|
||||
}}, the configuration may not be supported
|
||||
summary: The number of namespaces defined to the gateway exceeds supported values
|
||||
on cluster {{ $labels.cluster }}
|
||||
expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*?)(?::.*)?"))
|
||||
> 1024.00
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
|
|
|
@ -52,10 +52,10 @@ groups:
|
|||
severity: warning
|
||||
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
|
||||
annotations:
|
||||
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus
|
||||
{{$labels.instance}} to Alertmanager {{$labels.alertmanager}}.'
|
||||
summary: Prometheus has encountered more than 1% errors sending alerts to a
|
||||
specific Alertmanager.
|
||||
description: '{{ printf "%.1f" $value }}% of alerts sent by Prometheus {{$labels.instance}}
|
||||
to Alertmanager {{$labels.alertmanager}} were affected by errors.'
|
||||
summary: More than 1% of alerts sent by Prometheus to a specific Alertmanager
|
||||
were affected by errors.
|
||||
expr: |
|
||||
(
|
||||
rate(prometheus_notifications_errors_total{job="prometheus"}[5m])
|
||||
|
|
|
@ -1407,8 +1407,25 @@ annotations:
|
|||
}}, the configuration may not be supported
|
||||
summary: The number of subsystems defined to the gateway exceeds supported values
|
||||
on cluster {{ $labels.cluster }}
|
||||
expr: count by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_metadata,"gateway_host","$1","instance","(.*):.*"))
|
||||
> 16.00
|
||||
expr: count by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_metadata,"gateway_host","$1","instance","(.*?)(?::.*)?"))
|
||||
> 128.00
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
type: ceph_default
|
||||
{{< /code >}}
|
||||
|
||||
##### NVMeoFTooManyNamespaces
|
||||
|
||||
{{< code lang="yaml" >}}
|
||||
alert: NVMeoFTooManyNamespaces
|
||||
annotations:
|
||||
description: Although you may continue to create namespaces in {{ $labels.gateway_host
|
||||
}}, the configuration may not be supported
|
||||
summary: The number of namespaces defined to the gateway exceeds supported values
|
||||
on cluster {{ $labels.cluster }}
|
||||
expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*?)(?::.*)?"))
|
||||
> 1024.00
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
|
|
|
@ -89,17 +89,17 @@ labels:
|
|||
{{< /code >}}
|
||||
|
||||
##### PrometheusErrorSendingAlertsToSomeAlertmanagers
|
||||
'{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus
|
||||
'{{ printf "%.1f" $value }}% of alerts sent by Prometheus {{$labels.instance}}
|
||||
|
||||
Prometheus has encountered more than 1% errors sending alerts to a specific
|
||||
More than 1% of alerts sent by Prometheus to a specific Alertmanager were
|
||||
|
||||
{{< code lang="yaml" >}}
|
||||
alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
|
||||
annotations:
|
||||
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus
|
||||
{{$labels.instance}} to Alertmanager {{$labels.alertmanager}}.'
|
||||
summary: Prometheus has encountered more than 1% errors sending alerts to a specific
|
||||
Alertmanager.
|
||||
description: '{{ printf "%.1f" $value }}% of alerts sent by Prometheus {{$labels.instance}}
|
||||
to Alertmanager {{$labels.alertmanager}} were affected by errors.'
|
||||
summary: More than 1% of alerts sent by Prometheus to a specific Alertmanager were
|
||||
affected by errors.
|
||||
expr: |
|
||||
(
|
||||
rate(prometheus_notifications_errors_total{job="prometheus"}[5m])
|
||||
|
|
Loading…
Reference in a new issue