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

Enable Multi Cluster alerts by default (#2099)

Browse Source
This commit is contained in:
Jan-Otto Kröpke
2023-05-22 17:26:44 +02:00
committed by GitHub
parent 5ac666d809
commit 09135ee9b3
8 changed files with 1418 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
manifests/kubernetesControlPlane-prometheusRule.yaml
View File

@@ -247,50 +247,50 @@ spec:
rules:
- alert: KubeCPUOvercommit
annotations:
description: Cluster has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |
sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) - max(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})) > 0
sum(namespace_cpu:kube_pod_container_resource_requests:sum{job="kube-state-metrics",}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
and
(sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) - max(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})) > 0
(sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
for: 10m
labels:
severity: warning
- alert: KubeMemoryOvercommit
annotations:
description: Cluster has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.
description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
sum(namespace_memory:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})) > 0
sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
and
(sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})) > 0
(sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
for: 10m
labels:
severity: warning
- alert: KubeCPUQuotaOvercommit
annotations:
description: Cluster has overcommitted CPU resource requests for Namespaces.
description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"}))
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster)
/
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster)
> 1.5
for: 5m
labels:
severity: warning
- alert: KubeMemoryQuotaOvercommit
annotations:
description: Cluster has overcommitted memory resource requests for Namespaces.
description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Namespaces.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"}))
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster)
/
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)
> 1.5
for: 5m
labels: