From 9f28447bdaae7ac10067ada4cbbba8793165453a Mon Sep 17 00:00:00 2001
From: Divyadeep Dayal <didayal@microsoft.com>
Date: Thu, 31 Oct 2024 09:38:03 +0530
Subject: [PATCH] adding alert for not responding runs after discussion with ML
 PG

---
 .../workspaces/alerts.yaml                     | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/services/MachineLearningServices/workspaces/alerts.yaml b/services/MachineLearningServices/workspaces/alerts.yaml
index d8a39f869..3e6283716 100644
--- a/services/MachineLearningServices/workspaces/alerts.yaml
+++ b/services/MachineLearningServices/workspaces/alerts.yaml
@@ -81,3 +81,21 @@
   - 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
+  guid: d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a