---
# Source: kube-prometheus-stack/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: kube-prometheus-stack-kubernetes-resources
  namespace: kube-prometheus-stack
  labels:
    app: kube-prometheus-stack
    app.kubernetes.io/managed-by: Helm
    app.kubernetes.io/instance: kube-prometheus-stack
    app.kubernetes.io/version: "79.11.0"
    app.kubernetes.io/part-of: kube-prometheus-stack
    chart: kube-prometheus-stack-79.11.0
    release: "kube-prometheus-stack"
    heritage: "Helm"
spec:
  groups:
    - name: kubernetes-resources
      rules:
        - alert: KubeCPUOvercommit
          annotations:
            description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ printf "%.2f" $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: |-
            # Non-HA clusters.
            (
              (
                sum by (cluster) (namespace_cpu:kube_pod_container_resource_requests:sum{})
                -
                sum by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) > 0
              )
              and
              count by (cluster) (max by (cluster, node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3
            )
            or
            # HA clusters.
            (
              sum by (cluster) (namespace_cpu:kube_pod_container_resource_requests:sum{})
              -
              (
                # Skip clusters with only one allocatable node.
                (
                  sum by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"})
                  -
                  max by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"})
                ) > 0
              ) > 0
            )
          for: 10m
          labels:
            severity: warning
        - alert: KubeMemoryOvercommit
          annotations:
            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: |-
            # Non-HA clusters.
            (
              (
                sum by (cluster) (namespace_memory:kube_pod_container_resource_requests:sum{})
                -
                sum by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="memory"}) > 0
              )
              and
              count by (cluster) (max by (cluster, node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3
            )
            or
            # HA clusters.
            (
              sum by (cluster) (namespace_memory:kube_pod_container_resource_requests:sum{})
              -
              (
                # Skip clusters with only one allocatable node.
                (
                  sum by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="memory"})
                  -
                  max by (cluster) (kube_node_status_allocatable{job="kube-state-metrics",resource="memory"})
                ) > 0
              ) > 0
            )
          for: 10m
          labels:
            severity: warning
        - alert: KubeCPUQuotaOvercommit
          annotations:
            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 by (cluster) (
              min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})
            )
            /
            sum by (cluster) (
              kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}
            ) > 1.5
          for: 5m
          labels:
            severity: warning
        - alert: KubeMemoryQuotaOvercommit
          annotations:
            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 by (cluster) (
              min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})
            )
            /
            sum by (cluster) (
              kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}
            ) > 1.5
          for: 5m
          labels:
            severity: warning
        - alert: KubeQuotaAlmostFull
          annotations:
            description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.
            runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
            summary: Namespace quota is going to be full.
          expr: |-
            max without (instance, job, type) (
              kube_resourcequota{job="kube-state-metrics", type="used"}
            )
            / on (cluster, namespace, resource, resourcequota) group_left()
            (
              max without (instance, job, type) (
                kube_resourcequota{job="kube-state-metrics", type="hard"}
              ) > 0
            )
            > 0.9 < 1
          for: 15m
          labels:
            severity: info
        - alert: KubeQuotaFullyUsed
          annotations:
            description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.
            runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
            summary: Namespace quota is fully used.
          expr: |-
            max without (instance, job, type) (
              kube_resourcequota{job="kube-state-metrics", type="used"}
            )
            / on (cluster, namespace, resource, resourcequota) group_left()
            (
              max without (instance, job, type) (
                kube_resourcequota{job="kube-state-metrics", type="hard"}
              ) > 0
            )
            == 1
          for: 15m
          labels:
            severity: info
        - alert: KubeQuotaExceeded
          annotations:
            description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.
            runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
            summary: Namespace quota has exceeded the limits.
          expr: |-
            max without (instance, job, type) (
              kube_resourcequota{job="kube-state-metrics", type="used"}
            )
            / on (cluster, namespace, resource, resourcequota) group_left()
            (
              max without (instance, job, type) (
                kube_resourcequota{job="kube-state-metrics", type="hard"}
              ) > 0
            ) > 1
          for: 15m
          labels:
            severity: warning
        - alert: CPUThrottlingHigh
          annotations:
            description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }} on cluster {{ $labels.cluster }}.'
            runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
            summary: Processes experience elevated CPU throttling.
          expr: |-
            sum without (id, metrics_path, name, image, endpoint, job, node) (
              topk by (cluster, namespace, pod, container, instance) (1,
                increase(
                  container_cpu_cfs_throttled_periods_total{container!="", job="kubelet", metrics_path="/metrics/cadvisor", }
                [5m])
              )
            )
            / on (cluster, namespace, pod, container, instance) group_left
            sum without (id, metrics_path, name, image, endpoint, job, node) (
              topk by (cluster, namespace, pod, container, instance) (1,
                increase(
                  container_cpu_cfs_periods_total{job="kubelet", metrics_path="/metrics/cadvisor", }
                [5m])
              )
            )
            > ( 25 / 100 )
          for: 15m
          labels:
            severity: info