Merge pull request #384 from didayal-msft/azmlworkspace

Added alerts for Microsoft.MachineLearningServices/workspaces
Azure · Oct 18, 2024 · cf08983 · cf08983
2 parents f530689 + 70e98a4
commit cf08983
Showing 1 changed file with 63 additions and 0 deletions.
diff --git a/services/MachineLearningServices/workspaces/alerts.yaml b/services/MachineLearningServices/workspaces/alerts.yaml
@@ -18,3 +18,66 @@
     criterionType: StaticThresholdCriterion
     threshold: 0.0
   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
+  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
+  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
+  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