kube-prometheus: drop conntrack alerts and direct up alerts
This commit is contained in:
@@ -1,14 +1,3 @@
|
||||
ALERT K8SNodeDown
|
||||
IF up{job="kubelet"} == 0
|
||||
FOR 1h
|
||||
LABELS {
|
||||
severity = "warning"
|
||||
}
|
||||
ANNOTATIONS {
|
||||
summary = "Kubelet cannot be scraped",
|
||||
description = "Prometheus could not scrape a {{ $labels.job }} for more than one hour",
|
||||
}
|
||||
|
||||
ALERT K8SNodeNotReady
|
||||
IF kube_node_status_ready{condition="true"} == 0
|
||||
FOR 1h
|
||||
@@ -39,15 +28,25 @@ ALERT K8SManyNodesNotReady
|
||||
}
|
||||
|
||||
ALERT K8SKubeletDown
|
||||
IF absent(up{job="kubelet"}) or count by (cluster) (up{job="kubelet"} == 0) / count by (cluster) (up{job="kubelet"}) > 0.1
|
||||
IF count by (cluster) (up{job="kubelet"} == 0) / count by (cluster) (up{job="kubelet"}) > 0.03
|
||||
FOR 1h
|
||||
LABELS {
|
||||
service = "k8s",
|
||||
severity = "critical"
|
||||
severity = "warning",
|
||||
}
|
||||
ANNOTATIONS {
|
||||
summary = "Many Kubelets cannot be scraped",
|
||||
description = "Prometheus failed to scrape more than 10% of kubelets, or all Kubelets have disappeared from service discovery.",
|
||||
description = "Prometheus failed to scrape {{ $value }}% of kubelets.",
|
||||
}
|
||||
|
||||
ALERT K8SKubeletDown
|
||||
IF absent(up{job="kubelet"}) or count by (cluster) (up{job="kubelet"} == 0) / count by (cluster) (up{job="kubelet"}) > 0.1
|
||||
FOR 1h
|
||||
LABELS {
|
||||
severity = "critical",
|
||||
}
|
||||
ANNOTATIONS {
|
||||
summary = "Many Kubelets cannot be scraped",
|
||||
description = "Prometheus failed to scrape {{ $value }}% of kubelets, or all Kubelets have disappeared from service discovery.",
|
||||
}
|
||||
|
||||
ALERT K8SKubeletTooManyPods
|
||||
|
||||
Reference in New Issue
Block a user