services/ContainerService/managedClusters/alerts.yaml

- name: node_cpu_usage_percentage
  description: Aggregated average CPU utilization measured in percentage across the
    cluster
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-58888
  properties:
    metricName: node_cpu_usage_percentage
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT5M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 95.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: 1303e91d-bc80-4ec2-937e-1d179fc32b43
- name: node_memory_working_set_percentage
  description: Container working set memory used in percent
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-56669
  properties:
    metricName: node_memory_working_set_percentage
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT5M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 100.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: 9ae2dfbf-d69b-4802-8497-8b7836bef5e9
- name: node_disk_usage_percentage
  description: Disk space used in percent by device
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-3850
  properties:
    metricName: node_disk_usage_percentage
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 2
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 80.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: aa3c5697-5cca-4c16-a37e-94f1d580701e
- name: kube_pod_status_phase
  description: Number of pods by phase
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-2360
  properties:
    metricName: kube_pod_status_phase
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    dimensions:
    - operator: include
      name: phase
      values:
      - failed
    threshold: 0.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: e38e6e11-ac88-4014-98c8-8e64f70b832a
- name: node_memory_rss_percentage
  description: Container RSS memory used in percent
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-2198
  properties:
    metricName: node_memory_rss_percentage
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 90.0
    enabled: true
  guid: e89e023e-117b-4db4-bfb2-853849e273f5
- name: cluster_autoscaler_unschedulable_pods_count
  description: Number of pods that are currently unschedulable in the cluster
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-1383
  properties:
    metricName: cluster_autoscaler_unschedulable_pods_count
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 0.0
    enabled: true
  guid: 301ca0e3-fc88-4285-be99-a2a587c412f5
- name: cluster_autoscaler_cluster_safe_to_autoscale
  description: Determines whether or not cluster autoscaler will take action on the
    cluster
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-1311
  properties:
    metricName: cluster_autoscaler_cluster_safe_to_autoscale
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: LessThan
    criterionType: StaticThresholdCriterion
    threshold: 1.0
    enabled: true
  guid: 49fd8bac-d061-459d-8d80-a048c4c8ba56
- name: kube_node_status_condition
  description: Statuses for various node conditions
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-1128
  properties:
    metricName: kube_node_status_condition
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Total
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    dimensions:
    - operator: include
      name: status2
      values:
      - notready
      - unknown
    threshold: 0.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: ebbbbb92-5208-4d52-b407-6bea8e4473b9
- name: kube_pod_status_ready
  description: Number of pods in Ready state
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-564
  properties:
    metricName: kube_pod_status_ready
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 2
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: LessThan
    criterionType: StaticThresholdCriterion
    threshold: 1.0
    enabled: true
  references:
  - name: Recommended alert rules
    url: https://learn.microsoft.com/azure/azure-monitor/containers/container-insights-metric-alerts?tabs=arm-template%2Cazure-portal#recommended-alert-rules
  guid: cebf00b7-7294-4cf7-bc50-108f999d0c67
- name: kube_node_status_allocatable_memory_bytes
  description: Total amount of available memory in a managed cluster
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-460
  properties:
    metricName: kube_node_status_allocatable_memory_bytes
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: LessThan
    criterionType: StaticThresholdCriterion
    threshold: 2147483648.0
    enabled: true
  guid: 14fa63fb-7da9-4d2e-9de9-203c4a3e0401
- name: kube_node_status_allocatable_cpu_cores
  description: Total number of available cpu cores in a managed cluster
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-314
  properties:
    metricName: kube_node_status_allocatable_cpu_cores
    metricNamespace: Microsoft.ContainerService/managedClusters
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: LessThan
    criterionType: StaticThresholdCriterion
    threshold: 2.0
    enabled: true
  guid: 64a872f9-5ec6-4121-acad-edd12f4c3466