@leverege/build-tools 2.65.1 → 2.66.1

package/src/helm-charts/prom-operator/rules/kubernetes-rules.yaml

@@ -1,109 +0,0 @@
-apiVersion: monitoring.coreos.com/v1
-kind: PrometheusRule
-metadata:
-  name: kubernetes-rules
-  namespace: prometheus
-
-spec:
-  groups:
-  - name: Kubernetes
-    rules:
-    - alert: KubernetesNodeNotReady
-      expr: kube_node_status_condition{condition="Ready",status="true"} == 0
-      for: 5m
-      labels:
-        severity: page
-        priority: P3
-      annotations:
-        summary: "Kubernetes Node is not ready"
-        description: "Node {{ $labels.node }} is stuck in unready state for more than 5m"
-        dashboard: "Check GKE or EKS node status"
-
-    - alert: KubernetesMemoryPressure
-      expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Kubernetes memory pressure"
-        description: "{{ $labels.node }} has a MemoryPressure condition"
-        dashboard: "Check GKE or EKS node status"
-
-    - alert: KubernetesDiskPressure
-      expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Kubernetes disk pressure"
-        description: "{{ $labels.node }} has DiskPressure condition"
-        dashboard: "Check GKE or EKS node status"
-
-    - alert: KubernetesOutOfDisk
-      expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Kubernetes out of disk"
-        description: "{{ $labels.node }} has is out of disk space"
-        dashboard: "Check GKE or EKS node status"
-
-    - alert: KubernetesVolumeOutOfDiskSpace
-      expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
-      for: 5m
-      labels:
-        severity: error
-        priority: P2
-      annotations:
-        summary: "Kubernetes PVC Free Space < 10%"
-        description: "PVC volume {{ $labels.persistentvolumeclaim }} is almost full - down to {{ $value | humanize }}% available"
-
-#   - alert: KubernetesVolumeFullInFourDays
-#     expr: predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0
-#     for: 5m
-#     labels:
-#       severity: error
-#     annotations:
-#       summary: "Kubernetes Volume full in four days "
-#       description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."
-
-    - alert: KubernetesPersistentvolumeError
-      expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Kubernetes PersistentVolume error "
-        description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is stuck pending"
-        dashboard: "Check GKE or EKS PVC/storage status"
-
-    - alert: KubernetesHpaScaleCapability
-      expr: kube_hpa_status_desired_replicas >= kube_hpa_spec_max_replicas
-      for: 15m
-      labels:
-        severity: warning
-      annotations:
-        summary: "Kubernetes HPA scale capability"
-        description: "Kubernetes has scaled {{ $labels.hpa }} to max number of scaled pods."
-
-    - alert: KubernetesPodNotHealthy
-      expr: kube_pod_status_phase{phase=~"Pending|Unknown|Failed"} == 1
-      for: 20m
-      labels:
-        severity: error
-      annotations:
-        summary: "Kubernetes Pod not healthy"
-        description: "Pod {{ $labels.pod }} has been in a non-ready state for longer than 20 minutes."
-        dashboard: "Check the pod status using the Kubernetes UI"
-
-    - alert: KubernetesPodCrashLooping
-      expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 5 > 5
-      for: 5m
-      labels:
-        severity: page
-        priority: P2
-      annotations:
-        summary: "Kubernetes pod crash looping"
-        description: "{{ $labels.pod }} is in a crash loop"
-        dashboard: "Check the pod status using the Kubernetes UI"