services/MachineLearningServices/workspaces/alerts.yaml

- name: Failed Runs
  description: Number of runs failed for this workspace. Count is updated when a run
    fails.
  type: Metric
  verified: false
  visible: true
  tags:
  - auto-generated
  - agc-297
  properties:
    metricName: Failed Runs
    metricNamespace: Microsoft.MachineLearningServices/workspaces
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Total
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 0.0
    enabled: true
  guid: c897902c-40a5-497b-a0ce-86c3eda7c61d
- name: Model Deploy Failed
  description: Number of model deployments that failed in this workspace.
  type: Metric
  verified: true
  visible: true
  tags:
  - manual
  properties:
    metricName: Model Deploy Failed
    metricNamespace: Microsoft.MachineLearningServices/workspaces
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Total
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 0.0
    enabled: true
  references:
  - name: Monitor Azure Machine Learning
    url: https://learn.microsoft.com/en-us/azure/machine-learning/monitor-azure-machine-learning?view=azureml-api-2#machine-learning-alert-rules
  guid: 0337a76f-238e-4d4d-9cd1-48b205874dbb
- name: Quota Utilization Percentage
  description: Percent of quota utilized.
  type: Metric
  verified: true
  visible: true
  tags:
  - manual
  properties:
    metricName: Quota Utilization Percentage
    metricNamespace: Microsoft.MachineLearningServices/workspaces
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Average
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 90.0
    enabled: true
  references:
  - name: Monitor Azure Machine Learning
    url: https://learn.microsoft.com/en-us/azure/machine-learning/monitor-azure-machine-learning?view=azureml-api-2#machine-learning-alert-rules
  guid: be3f1bfc-c21a-4399-9b9f-a33ebdc470cb
- name: Unusable Nodes
  description: Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.
  type: Metric
  verified: true
  visible: true
  tags:
  - manual
  properties:
    metricName: Unusable Nodes
    metricNamespace: Microsoft.MachineLearningServices/workspaces
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Total
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 0.0
    enabled: true
  references:
  - name: Monitor Azure Machine Learning
    url: https://learn.microsoft.com/en-us/azure/machine-learning/monitor-azure-machine-learning?view=azureml-api-2#machine-learning-alert-rules
  guid: a171bc0c-676f-464b-a7b5-e50cd6c612a2
- name: Not Responding Runs
  description: Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.
  type: Metric
  verified: true
  visible: true
  tags:
  - manual
  properties:
    metricName: Not Responding Runs
    metricNamespace: Microsoft.MachineLearningServices/workspaces
    severity: 3
    windowSize: PT5M
    evaluationFrequency: PT1M
    timeAggregation: Total
    operator: GreaterThan
    criterionType: StaticThresholdCriterion
    threshold: 0.0
    enabled: true
  guid: d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a