Azure Monitor Baseline Alerts
Download AlertsGlossaryGitHubGitHub IssuesToggle Dark/Light/Auto modeToggle Dark/Light/Auto modeToggle Dark/Light/Auto modeBack to homepage

workspaces

NameTypeDescription
Failed RunsMetricNumber of runs failed for this workspace. Count is updated when a run fails.
Model Deploy FailedMetricNumber of model deployments that failed in this workspace.
Not Responding RunsMetricNumber of runs not responding for this workspace. Count is updated when a run enters Not Responding state.
Quota Utilization PercentageMetricPercent of quota utilized.
Unusable NodesMetricNumber of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.

Dashboards:

Click a tab to view the dashboard template

{
  "__inputs": [],
  "__elements": {},
  "__requires": [
    {
      "type": "panel",
      "id": "bargauge",
      "name": "Bar gauge",
      "version": ""
    },
    {
      "type": "grafana",
      "id": "grafana",
      "name": "Grafana",
      "version": "9.5.12"
    },
    {
      "type": "datasource",
      "id": "grafana-azure-monitor-datasource",
      "name": "Azure Monitor",
      "version": "1.0.0"
    }
  ],
  "title": "Workspaces",
  "editable": true,
  "links": [],
  "liveNow": false,
  "panels": [
    {
      "title": "Failed Runs",
      "datasource": {
        "type": "grafana-azure-monitor-datasource",
        "uid": "${ds}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "#808080",
                "value": null
              },
              {
                
                "color": "dark-green",                
                "value": 0
              },
              {
                
                "color": "dark-red",                
                "value": 0
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 0
      },
      "id": 1,
      "options": {
        "displayMode": "basic",
        "minVizHeight": 10,
        "minVizWidth": 0,
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "pluginVersion": "9.5.12",
      "targets": [
        {
          "azureLogAnalytics": {

            "query": "AzureMetrics\r\n| where _ResourceId has 'Microsoft.MachineLearningServices/workspaces'\r\n| where MetricName has 'Failed Runs'\r\n| summarize metric = avg(Total) by _ResourceId, Resource",
            "resources": [
              "/subscriptions/$sub"
            ]
          },
          "azureMonitor": {
            "allowedTimeGrainsMs": [],
            "timeGrain": "auto"
          },
          "datasource": {
            "type": "grafana-azure-monitor-datasource",
            "uid": "${ds}"
          },
          "queryType": "Azure Log Analytics",
          "refId": "A"
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "_ResourceId": true
            },
            "indexByName": {},
            "renameByName": {}
          }
        }
      ],
      "type": "bargauge"
    },
    {
      "title": "Model Deploy Failed",
      "datasource": {
        "type": "grafana-azure-monitor-datasource",
        "uid": "${ds}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "#808080",
                "value": null
              },
              {
                
                "color": "dark-green",                
                "value": 0
              },
              {
                
                "color": "dark-red",                
                "value": 0
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 0
      },
      "id": 2,
      "options": {
        "displayMode": "basic",
        "minVizHeight": 10,
        "minVizWidth": 0,
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "pluginVersion": "9.5.12",
      "targets": [
        {
          "azureLogAnalytics": {

            "query": "AzureMetrics\r\n| where _ResourceId has 'Microsoft.MachineLearningServices/workspaces'\r\n| where MetricName has 'Model Deploy Failed'\r\n| summarize metric = avg(Total) by _ResourceId, Resource",
            "resources": [
              "/subscriptions/$sub"
            ]
          },
          "azureMonitor": {
            "allowedTimeGrainsMs": [],
            "timeGrain": "auto"
          },
          "datasource": {
            "type": "grafana-azure-monitor-datasource",
            "uid": "${ds}"
          },
          "queryType": "Azure Log Analytics",
          "refId": "A"
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "_ResourceId": true
            },
            "indexByName": {},
            "renameByName": {}
          }
        }
      ],
      "type": "bargauge"
    },
    {
      "title": "Not Responding Runs",
      "datasource": {
        "type": "grafana-azure-monitor-datasource",
        "uid": "${ds}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "#808080",
                "value": null
              },
              {
                
                "color": "dark-green",                
                "value": 0
              },
              {
                
                "color": "dark-red",                
                "value": 0
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 8
      },
      "id": 3,
      "options": {
        "displayMode": "basic",
        "minVizHeight": 10,
        "minVizWidth": 0,
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "pluginVersion": "9.5.12",
      "targets": [
        {
          "azureLogAnalytics": {

            "query": "AzureMetrics\r\n| where _ResourceId has 'Microsoft.MachineLearningServices/workspaces'\r\n| where MetricName has 'Not Responding Runs'\r\n| summarize metric = avg(Total) by _ResourceId, Resource",
            "resources": [
              "/subscriptions/$sub"
            ]
          },
          "azureMonitor": {
            "allowedTimeGrainsMs": [],
            "timeGrain": "auto"
          },
          "datasource": {
            "type": "grafana-azure-monitor-datasource",
            "uid": "${ds}"
          },
          "queryType": "Azure Log Analytics",
          "refId": "A"
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "_ResourceId": true
            },
            "indexByName": {},
            "renameByName": {}
          }
        }
      ],
      "type": "bargauge"
    },
    {
      "title": "Quota Utilization Percentage",
      "datasource": {
        "type": "grafana-azure-monitor-datasource",
        "uid": "${ds}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "#808080",
                "value": null
              },
              {
                
                "color": "dark-green",                
                "value": 0
              },
              {
                
                "color": "dark-red",                
                "value": 90
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 8
      },
      "id": 4,
      "options": {
        "displayMode": "basic",
        "minVizHeight": 10,
        "minVizWidth": 0,
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "pluginVersion": "9.5.12",
      "targets": [
        {
          "azureLogAnalytics": {

            "query": "AzureMetrics\r\n| where _ResourceId has 'Microsoft.MachineLearningServices/workspaces'\r\n| where MetricName has 'Quota Utilization Percentage'\r\n| summarize metric = avg(Average) by _ResourceId, Resource",
            "resources": [
              "/subscriptions/$sub"
            ]
          },
          "azureMonitor": {
            "allowedTimeGrainsMs": [],
            "timeGrain": "auto"
          },
          "datasource": {
            "type": "grafana-azure-monitor-datasource",
            "uid": "${ds}"
          },
          "queryType": "Azure Log Analytics",
          "refId": "A"
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "_ResourceId": true
            },
            "indexByName": {},
            "renameByName": {}
          }
        }
      ],
      "type": "bargauge"
    },
    {
      "title": "Unusable Nodes",
      "datasource": {
        "type": "grafana-azure-monitor-datasource",
        "uid": "${ds}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "#808080",
                "value": null
              },
              {
                
                "color": "dark-green",                
                "value": 0
              },
              {
                
                "color": "dark-red",                
                "value": 0
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 16
      },
      "id": 5,
      "options": {
        "displayMode": "basic",
        "minVizHeight": 10,
        "minVizWidth": 0,
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "pluginVersion": "9.5.12",
      "targets": [
        {
          "azureLogAnalytics": {

            "query": "AzureMetrics\r\n| where _ResourceId has 'Microsoft.MachineLearningServices/workspaces'\r\n| where MetricName has 'Unusable Nodes'\r\n| summarize metric = avg(Total) by _ResourceId, Resource",
            "resources": [
              "/subscriptions/$sub"
            ]
          },
          "azureMonitor": {
            "allowedTimeGrainsMs": [],
            "timeGrain": "auto"
          },
          "datasource": {
            "type": "grafana-azure-monitor-datasource",
            "uid": "${ds}"
          },
          "queryType": "Azure Log Analytics",
          "refId": "A"
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "_ResourceId": true
            },
            "indexByName": {},
            "renameByName": {}
          }
        }
      ],
      "type": "bargauge"
    }
  ],
  "refresh": "",
  "schemaVersion": 38,
  "style": "dark",
  "tags": [],
  "templating": {
    "list": [
      {
        "current": {},
        "hide": 0,
        "includeAll": false,
        "label": "Datasource",
        "multi": false,
        "name": "ds",
        "options": [],
        "query": "grafana-azure-monitor-datasource",
        "queryValue": "",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "type": "datasource"
      },
      {
        "current": {},
        "datasource": {
          "type": "grafana-azure-monitor-datasource",
          "uid": "${ds}"
        },
        "definition": "",
        "hide": 0,
        "includeAll": false,
        "label": "Subscription",
        "multi": false,
        "name": "sub",
        "options": [],
        "query": {
          "azureLogAnalytics": {
            "query": "",
            "resources": []
          },
          "queryType": "Azure Subscriptions",
          "refId": "A"
        },
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "sort": 0,
        "type": "query"
      }
    ]
  },
  "time": {
    "from": "now-6h",
    "to": "now"
  },
  "timepicker": {},
  "timezone": "",
  "version": null
}



Failed Runs - Metric Alert

Number of runs failed for this workspace. Count is updated when a run fails.

Properties:

criterionTypeStaticThresholdCriterion
evaluationFrequencyPT1M
metricNameFailed Runs
metricNamespaceMicrosoft.MachineLearningServices/workspaces
operatorGreaterThan
severity3
threshold0
timeAggregationTotal
windowSizePT5M

References:

Templates:

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "alertName": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Name of the alert"
      }
    },
    "alertDescription": {
      "type": "string",
      "defaultValue": "Number of runs failed for this workspace. Count is updated when a run fails.",
      "metadata": {
        "description": "Description of alert"
      }
    },
    "targetResourceId": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name"
      }
    },
    "targetResourceRegion": {
      "type": "string",
      "metadata": {
        "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS"
      }
    },
    "targetResourceType": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Resource type of target resources to be monitored."
      }
    },
    "isEnabled": {
      "type": "bool",
      "defaultValue": true,
      "metadata": {
        "description": "Specifies whether the alert is enabled"
      }
    },
    "alertSeverity": {
      "type": "int",
      "defaultValue": 3,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThan",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "0",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Total",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT5M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H",
        "PT6H",
        "PT12H",
        "PT24H",
        "PT1D"
      ],
      "metadata": {
        "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format."
      }
    },
    "evaluationFrequency": {
      "type": "string",
      "defaultValue": "PT1M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H"
      ],
      "metadata": {
        "description": "how often the metric alert is evaluated represented in ISO 8601 duration format"
      }
    },
    "currentDateTimeUtcNow": {
      "type": "string",
      "defaultValue": "[utcNow()]",
      "metadata": {
          "description": "The current date and time using the utcNow function. Used for deployment name uniqueness"
      }
    },
    "telemetryOptOut": {
      "type": "string",
      "defaultValue": "No",
      "allowedValues": [
          "Yes",
          "No"
      ],
      "metadata": {
          "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry."
      }
    }
  },
  "variables": {
    "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]",
    "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]"
  },
  "resources": [
    {
      "type": "Microsoft.Insights/metricAlerts",
      "apiVersion": "2018-03-01",
      "name": "[parameters('alertName')]",
      "location": "global",
      "tags": {
        "_deployed_by_amba": true
      },
      "properties": {
        "description": "[parameters('alertDescription')]",
        "scopes": "[variables('varTargetResourceId')]",
        "targetResourceType": "[parameters('targetResourceType')]",
        "targetResourceRegion": "[parameters('targetResourceRegion')]",
        "severity": "[parameters('alertSeverity')]",
        "enabled": "[parameters('isEnabled')]",
        "evaluationFrequency": "[parameters('evaluationFrequency')]",
        "windowSize": "[parameters('windowSize')]",
        "criteria": {
          "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria",
          "allOf": [
            {
              "name": "1st criterion",
              "metricName": "Failed Runs",
              "dimensions": [],
              "operator": "[parameters('operator')]",
              "threshold": "[parameters('threshold')]",
              "timeAggregation": "[parameters('timeAggregation')]",
              "criterionType": "StaticThresholdCriterion"
            }
          ]
        }
      }
    },
    {
      "condition": "[equals(parameters('telemetryOptOut'), 'No')]",
      "apiVersion": "2020-06-01",
      "name": "[variables('pidDeploymentName')]",
      "type": "Microsoft.Resources/deployments",
      "properties": {
          "mode": "Incremental",
          "template": {
              "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
              "contentVersion": "1.0.0.0",
              "resources": []
          }
      }
    }
  ]
}
@description('Name of the alert')
@minLength(1)
param alertName string

@description('Description of alert')
param alertDescription string = 'Number of runs failed for this workspace. Count is updated when a run fails.'

@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name')
@minLength(1)
param targetResourceId array

@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS')
param targetResourceRegion string

@description('Resource type of target resources to be monitored.')
@minLength(1)
param targetResourceType string

@description('Specifies whether the alert is enabled')
param isEnabled bool = true

@description('Severity of alert {0,1,2,3,4}')
@allowed([
  0
  1
  2
  3
  4
])
param alertSeverity int = 3

@description('Operator comparing the current value with the threshold value.')
@allowed([
  'Equals'
  'GreaterThan'
  'GreaterThanOrEqual'
  'LessThan'
  'LessThanOrEqual'
])
param operator string = 'GreaterThan'

@description('The threshold value at which the alert is activated.')
param threshold int = 0

@description('How the data that is collected should be combined over time.')
@allowed([
  'Average'
  'Minimum'
  'Maximum'
  'Total'
  'Count'
])
param timeAggregation string = 'Total'

@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
  'PT6H'
  'PT12H'
  'PT24H'
  'P1D'
])
param windowSize string = 'PT5M'

@description('how often the metric alert is evaluated represented in ISO 8601 duration format')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
])
param evaluationFrequency string = 'PT1M'

@description('"The current date and time using the utcNow function. Used for deployment name uniqueness')
param currentDateTimeUtcNow string = utcNow()

@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.')
@allowed([
  'Yes'
  'No'
])
param telemetryOptOut string = 'No'

resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = {
  name: alertName
  location: 'global'
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    description: alertDescription
    scopes: targetResourceId
    targetResourceType: targetResourceType
    targetResourceRegion: targetResourceRegion
    severity: alertSeverity
    enabled: isEnabled
    evaluationFrequency: evaluationFrequency
    windowSize: windowSize
    criteria: {
      'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria'
      allOf: [
        {
          name: '1st criterion'
          metricName: 'Failed Runs'
          dimensions: [[]]
          operator: operator
          threshold: threshold
          timeAggregation: timeAggregation
          criterionType: 'StaticThresholdCriterion'
        }
      ]
    }
  }
}

var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}'
resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' =  if (telemetryOptOut == 'No') {
  name: ambaTelemetryPidName
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    mode: 'Incremental'
    template: {
      '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#'
      contentVersion: '1.0.0.0'
      resources: []
    }
  }
}
{
  "type": "Microsoft.Authorization/policyDefinitions",
  "apiVersion": "2021-06-01",
  "name": "c897902c-40a5-497b-a0ce-86c3eda7c61d",
  "properties": {
    "policyType": "Custom",
    "mode": "All",
    "displayName": "Deploy MachineLearningServices workspaces Failed Runs Alert",
    "description": "Policy to Audit/Deploy MachineLearningServices workspaces Failed Runs Alert",
    "metadata": {
      "version": "1.0.0-preview",
      "category": "MachineLearningServices",
      "preview": true,
      "source": "https://github.com/Azure/azure-monitor-baseline-alerts/",
      "alzCloudEnvironments": [
        "AzureCloud"
      ],
      "_deployed_by_amba": "True"
    },
    "parameters": {
      "severity": {
        "type": "String",
        "metadata": {
          "displayName": "Severity",
          "description": "Severity of the Alert"
        },
        "allowedValues": [
          "0",
          "1",
          "2",
          "3",
          "4"
        ],
        "defaultValue": "3"
      },
      "windowSize": {
        "type": "String",
        "metadata": {
          "displayName": "Window Size",
          "description": "Window size for the alert"
        },
        "allowedValues": [
          "PT1M",
          "PT5M",
          "PT15M",
          "PT30M",
          "PT1H",
          "PT6H",
          "PT12H",
          "P1D"
        ],
        "defaultValue": "PT5M"
      },
      "evaluationFrequency": {
        "type": "String",
        "metadata": {
          "displayName": "Evaluation Frequency",
          "description": "Evaluation frequency for the alert"
        },
        "allowedValues": [
          "PT1M",
          "PT5M",
          "PT15M",
          "PT30M",
          "PT1H"
        ],
        "defaultValue": "PT1M"
      },
      "autoMitigate": {
        "type": "String",
        "metadata": {
          "displayName": "Auto Mitigate",
          "description": "Auto Mitigate for the alert"
        },
        "allowedValues": [
          "true",
          "false"
        ],
        "defaultValue": "true"
      },
      "enabled": {
        "type": "String",
        "metadata": {
          "displayName": "Alert State",
          "description": "Alert state for the alert"
        },
        "allowedValues": [
          "true",
          "false"
        ],
        "defaultValue": "true"
      },
      "threshold": {
        "type": "String",
        "metadata": {
          "displayName": "Threshold",
          "description": "Threshold for the alert"
        },
        "defaultValue": "0"
      },
      "effect": {
        "type": "String",
        "metadata": {
          "displayName": "Effect",
          "description": "Effect of the policy"
        },
        "allowedValues": [
          "deployIfNotExists",
          "disabled"
        ],
        "defaultValue": "deployIfNotExists"
      },
      "MonitorDisableTagName": {
        "type": "String",
        "metadata": {
          "displayName": "Monitoring disabled tag name",
          "description": "Tag name used to disable monitoring at the resource level. Set to true if monitoring should be disabled."
        },
        "defaultValue": "MonitorDisable"
      },
      "MonitorDisableTagValues": {
        "type": "Array",
        "metadata": {
          "displayName": "Monitoring disabled tag values(s)",
          "description": "Tag value(s) used to disable monitoring at the resource level. Set to true if monitoring should be disabled."
        },
        "defaultValue": [
          "true",
          "Test",
          "Dev",
          "Sandbox"
        ]
      }
    },
    "policyRule": {
      "if": {
        "allOf": [
          {
            "field": "type",
            "equals": "Microsoft.MachineLearningServices/workspaces"
          },
          {
            "field": "[[concat('tags[', parameters('MonitorDisableTagName'), ']')]",
            "notIn": "[[parameters('MonitorDisableTagValues')]"
          }
        ]
      },
      "then": {
        "effect": "[[parameters('effect')]",
        "details": {
          "roleDefinitionIds": [
            "/providers/Microsoft.Authorization/roleDefinitions/b24988ac-6180-42a0-ab88-20f7382dd24c"
          ],
          "type": "Microsoft.Insights/metricAlerts",
          "existenceCondition": {
            "allOf": [
              {
                "field": "Microsoft.Insights/metricAlerts/criteria.Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria.allOf[*].metricNamespace",
                "equals": "Microsoft.MachineLearningServices/workspaces"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/criteria.Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria.allOf[*].metricName",
                "equals": "Failed Runs"
              },
              {
                "field": "Microsoft.Insights/metricalerts/scopes[*]",
                "equals": "[[concat(subscription().id, '/resourceGroups/', resourceGroup().name, '/providers/Microsoft.MachineLearningServices/workspaces/', field('fullName'))]"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/enabled",
                "equals": "[[parameters('enabled')]"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/evaluationFrequency",
                "equals": "[[parameters('evaluationFrequency')]"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/windowSize",
                "equals": "[[parameters('windowSize')]"
              },
              {
                "field": "Microsoft.Insights/metricalerts/severity",
                "equals": "[[parameters('severity')]"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/autoMitigate",
                "equals": "[[parameters('autoMitigate')]"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/criteria.Microsoft-Azure-Monitor-SingleResourceMultipleMetricCriteria.allOf[*].timeAggregation",
                "equals": "Total"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/criteria.Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria.allOf[*].StaticThresholdCriterion.operator",
                "equals": "GreaterThan"
              },
              {
                "field": "Microsoft.Insights/metricAlerts/criteria.Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria.allOf[*].StaticThresholdCriterion.threshold",
                "equals": "[[if(contains(field('tags'), '_amba-Failed Runs-threshold-Override_'), field('tags._amba-Failed Runs-threshold-Override_'), parameters('threshold'))]"
              }
            ]
          },
          "deployment": {
            "properties": {
              "mode": "incremental",
              "template": {
                "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
                "contentVersion": "1.0.0.0",
                "parameters": {
                  "resourceName": {
                    "type": "String",
                    "metadata": {
                      "displayName": "resourceName",
                      "description": "Name of the resource"
                    }
                  },
                  "resourceId": {
                    "type": "String",
                    "metadata": {
                      "displayName": "resourceId",
                      "description": "Resource ID of the resource emitting the metric that will be used for the comparison"
                    }
                  },
                  "severity": {
                    "type": "String"
                  },
                  "windowSize": {
                    "type": "String"
                  },
                  "evaluationFrequency": {
                    "type": "String"
                  },
                  "autoMitigate": {
                    "type": "String"
                  },
                  "enabled": {
                    "type": "String"
                  },
                  "threshold": {
                    "type": "String"
                  }
                },
                "variables": {},
                "resources": [
                  {
                    "type": "Microsoft.Insights/metricAlerts",
                    "apiVersion": "2018-03-01",
                    "name": "[[concat(parameters('resourceName'), '-Failed Runs')]",
                    "location": "global",
                    "tags": {
                      "_deployed_by_amba": true
                    },
                    "properties": {
                      "description": "Metric Alert for MachineLearningServices workspaces Failed Runs",
                      "severity": "[[parameters('severity')]",
                      "enabled": "[[parameters('enabled')]",
                      "scopes": [
                        "[[parameters('resourceId')]"
                      ],
                      "evaluationFrequency": "[[parameters('evaluationFrequency')]",
                      "windowSize": "[[parameters('windowSize')]",
                      "criteria": {
                        "allOf": [
                          {
                            "name": "Failed Runs",
                            "metricNamespace": "Microsoft.MachineLearningServices/workspaces",
                            "metricName": "Failed Runs",
                            "operator": "GreaterThan",
                            "threshold": "[[parameters('threshold')]",
                            "timeAggregation": "Total",
                            "criterionType": "StaticThresholdCriterion"
                          }
                        ],
                        "odata.type": "Microsoft.Azure.Monitor.SingleResourceMultipleMetricCriteria"
                      },
                      "autoMitigate": "[[parameters('autoMitigate')]",
                      "parameters": {
                        "severity": {
                          "value": "[[parameters('severity')]"
                        },
                        "windowSize": {
                          "value": "[[parameters('windowSize')]"
                        },
                        "evaluationFrequency": {
                          "value": "[[parameters('evaluationFrequency')]"
                        },
                        "autoMitigate": {
                          "value": "[[parameters('autoMitigate')]"
                        },
                        "enabled": {
                          "value": "[[parameters('enabled')]"
                        },
                        "threshold": {
                          "value": "[[parameters('threshold')]"
                        }
                      }
                    }
                  }
                ]
              },
              "parameters": {
                "resourceName": {
                  "value": "[[field('name')]"
                },
                "resourceId": {
                  "value": "[[field('id')]"
                },
                "severity": {
                  "value": "[[parameters('severity')]"
                },
                "windowSize": {
                  "value": "[[parameters('windowSize')]"
                },
                "evaluationFrequency": {
                  "value": "[[parameters('evaluationFrequency')]"
                },
                "autoMitigate": {
                  "value": "[[parameters('autoMitigate')]"
                },
                "enabled": {
                  "value": "[[parameters('enabled')]"
                },
                "threshold": {
                  "value": "[[if(contains(field('tags'), '_amba-Failed Runs-threshold-Override_'), field('tags._amba-Failed Runs-threshold-Override_'), parameters('threshold'))]"
                }
              }
            }
          }
        }
      }
    }
  }
}



Model Deploy Failed - Metric Alert

Number of model deployments that failed in this workspace.

Properties:

criterionTypeStaticThresholdCriterion
evaluationFrequencyPT1M
metricNameModel Deploy Failed
metricNamespaceMicrosoft.MachineLearningServices/workspaces
operatorGreaterThan
severity3
threshold0
timeAggregationTotal
windowSizePT5M

References:

Templates:

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "alertName": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Name of the alert"
      }
    },
    "alertDescription": {
      "type": "string",
      "defaultValue": "Number of model deployments that failed in this workspace.",
      "metadata": {
        "description": "Description of alert"
      }
    },
    "targetResourceId": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name"
      }
    },
    "targetResourceRegion": {
      "type": "string",
      "metadata": {
        "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS"
      }
    },
    "targetResourceType": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Resource type of target resources to be monitored."
      }
    },
    "isEnabled": {
      "type": "bool",
      "defaultValue": true,
      "metadata": {
        "description": "Specifies whether the alert is enabled"
      }
    },
    "alertSeverity": {
      "type": "int",
      "defaultValue": 3,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThan",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "0",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Total",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT5M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H",
        "PT6H",
        "PT12H",
        "PT24H",
        "PT1D"
      ],
      "metadata": {
        "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format."
      }
    },
    "evaluationFrequency": {
      "type": "string",
      "defaultValue": "PT1M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H"
      ],
      "metadata": {
        "description": "how often the metric alert is evaluated represented in ISO 8601 duration format"
      }
    },
    "currentDateTimeUtcNow": {
      "type": "string",
      "defaultValue": "[utcNow()]",
      "metadata": {
          "description": "The current date and time using the utcNow function. Used for deployment name uniqueness"
      }
    },
    "telemetryOptOut": {
      "type": "string",
      "defaultValue": "No",
      "allowedValues": [
          "Yes",
          "No"
      ],
      "metadata": {
          "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry."
      }
    }
  },
  "variables": {
    "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]",
    "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]"
  },
  "resources": [
    {
      "type": "Microsoft.Insights/metricAlerts",
      "apiVersion": "2018-03-01",
      "name": "[parameters('alertName')]",
      "location": "global",
      "tags": {
        "_deployed_by_amba": true
      },
      "properties": {
        "description": "[parameters('alertDescription')]",
        "scopes": "[variables('varTargetResourceId')]",
        "targetResourceType": "[parameters('targetResourceType')]",
        "targetResourceRegion": "[parameters('targetResourceRegion')]",
        "severity": "[parameters('alertSeverity')]",
        "enabled": "[parameters('isEnabled')]",
        "evaluationFrequency": "[parameters('evaluationFrequency')]",
        "windowSize": "[parameters('windowSize')]",
        "criteria": {
          "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria",
          "allOf": [
            {
              "name": "1st criterion",
              "metricName": "Model Deploy Failed",
              "dimensions": [],
              "operator": "[parameters('operator')]",
              "threshold": "[parameters('threshold')]",
              "timeAggregation": "[parameters('timeAggregation')]",
              "criterionType": "StaticThresholdCriterion"
            }
          ]
        }
      }
    },
    {
      "condition": "[equals(parameters('telemetryOptOut'), 'No')]",
      "apiVersion": "2020-06-01",
      "name": "[variables('pidDeploymentName')]",
      "type": "Microsoft.Resources/deployments",
      "properties": {
          "mode": "Incremental",
          "template": {
              "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
              "contentVersion": "1.0.0.0",
              "resources": []
          }
      }
    }
  ]
}
@description('Name of the alert')
@minLength(1)
param alertName string

@description('Description of alert')
param alertDescription string = 'Number of model deployments that failed in this workspace.'

@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name')
@minLength(1)
param targetResourceId array

@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS')
param targetResourceRegion string

@description('Resource type of target resources to be monitored.')
@minLength(1)
param targetResourceType string

@description('Specifies whether the alert is enabled')
param isEnabled bool = true

@description('Severity of alert {0,1,2,3,4}')
@allowed([
  0
  1
  2
  3
  4
])
param alertSeverity int = 3

@description('Operator comparing the current value with the threshold value.')
@allowed([
  'Equals'
  'GreaterThan'
  'GreaterThanOrEqual'
  'LessThan'
  'LessThanOrEqual'
])
param operator string = 'GreaterThan'

@description('The threshold value at which the alert is activated.')
param threshold int = 0

@description('How the data that is collected should be combined over time.')
@allowed([
  'Average'
  'Minimum'
  'Maximum'
  'Total'
  'Count'
])
param timeAggregation string = 'Total'

@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
  'PT6H'
  'PT12H'
  'PT24H'
  'P1D'
])
param windowSize string = 'PT5M'

@description('how often the metric alert is evaluated represented in ISO 8601 duration format')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
])
param evaluationFrequency string = 'PT1M'

@description('"The current date and time using the utcNow function. Used for deployment name uniqueness')
param currentDateTimeUtcNow string = utcNow()

@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.')
@allowed([
  'Yes'
  'No'
])
param telemetryOptOut string = 'No'

resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = {
  name: alertName
  location: 'global'
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    description: alertDescription
    scopes: targetResourceId
    targetResourceType: targetResourceType
    targetResourceRegion: targetResourceRegion
    severity: alertSeverity
    enabled: isEnabled
    evaluationFrequency: evaluationFrequency
    windowSize: windowSize
    criteria: {
      'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria'
      allOf: [
        {
          name: '1st criterion'
          metricName: 'Model Deploy Failed'
          dimensions: [[]]
          operator: operator
          threshold: threshold
          timeAggregation: timeAggregation
          criterionType: 'StaticThresholdCriterion'
        }
      ]
    }
  }
}

var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}'
resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' =  if (telemetryOptOut == 'No') {
  name: ambaTelemetryPidName
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    mode: 'Incremental'
    template: {
      '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#'
      contentVersion: '1.0.0.0'
      resources: []
    }
  }
}



Not Responding Runs - Metric Alert

Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.

Properties:

criterionTypeStaticThresholdCriterion
evaluationFrequencyPT1M
metricNameNot Responding Runs
metricNamespaceMicrosoft.MachineLearningServices/workspaces
operatorGreaterThan
severity3
threshold0
timeAggregationTotal
windowSizePT5M

References:

Templates:

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "alertName": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Name of the alert"
      }
    },
    "alertDescription": {
      "type": "string",
      "defaultValue": "Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.",
      "metadata": {
        "description": "Description of alert"
      }
    },
    "targetResourceId": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name"
      }
    },
    "targetResourceRegion": {
      "type": "string",
      "metadata": {
        "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS"
      }
    },
    "targetResourceType": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Resource type of target resources to be monitored."
      }
    },
    "isEnabled": {
      "type": "bool",
      "defaultValue": true,
      "metadata": {
        "description": "Specifies whether the alert is enabled"
      }
    },
    "alertSeverity": {
      "type": "int",
      "defaultValue": 3,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThan",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "0",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Total",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT5M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H",
        "PT6H",
        "PT12H",
        "PT24H",
        "PT1D"
      ],
      "metadata": {
        "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format."
      }
    },
    "evaluationFrequency": {
      "type": "string",
      "defaultValue": "PT1M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H"
      ],
      "metadata": {
        "description": "how often the metric alert is evaluated represented in ISO 8601 duration format"
      }
    },
    "currentDateTimeUtcNow": {
      "type": "string",
      "defaultValue": "[utcNow()]",
      "metadata": {
          "description": "The current date and time using the utcNow function. Used for deployment name uniqueness"
      }
    },
    "telemetryOptOut": {
      "type": "string",
      "defaultValue": "No",
      "allowedValues": [
          "Yes",
          "No"
      ],
      "metadata": {
          "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry."
      }
    }
  },
  "variables": {
    "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]",
    "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]"
  },
  "resources": [
    {
      "type": "Microsoft.Insights/metricAlerts",
      "apiVersion": "2018-03-01",
      "name": "[parameters('alertName')]",
      "location": "global",
      "tags": {
        "_deployed_by_amba": true
      },
      "properties": {
        "description": "[parameters('alertDescription')]",
        "scopes": "[variables('varTargetResourceId')]",
        "targetResourceType": "[parameters('targetResourceType')]",
        "targetResourceRegion": "[parameters('targetResourceRegion')]",
        "severity": "[parameters('alertSeverity')]",
        "enabled": "[parameters('isEnabled')]",
        "evaluationFrequency": "[parameters('evaluationFrequency')]",
        "windowSize": "[parameters('windowSize')]",
        "criteria": {
          "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria",
          "allOf": [
            {
              "name": "1st criterion",
              "metricName": "Not Responding Runs",
              "dimensions": [],
              "operator": "[parameters('operator')]",
              "threshold": "[parameters('threshold')]",
              "timeAggregation": "[parameters('timeAggregation')]",
              "criterionType": "StaticThresholdCriterion"
            }
          ]
        }
      }
    },
    {
      "condition": "[equals(parameters('telemetryOptOut'), 'No')]",
      "apiVersion": "2020-06-01",
      "name": "[variables('pidDeploymentName')]",
      "type": "Microsoft.Resources/deployments",
      "properties": {
          "mode": "Incremental",
          "template": {
              "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
              "contentVersion": "1.0.0.0",
              "resources": []
          }
      }
    }
  ]
}
@description('Name of the alert')
@minLength(1)
param alertName string

@description('Description of alert')
param alertDescription string = 'Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.'

@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name')
@minLength(1)
param targetResourceId array

@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS')
param targetResourceRegion string

@description('Resource type of target resources to be monitored.')
@minLength(1)
param targetResourceType string

@description('Specifies whether the alert is enabled')
param isEnabled bool = true

@description('Severity of alert {0,1,2,3,4}')
@allowed([
  0
  1
  2
  3
  4
])
param alertSeverity int = 3

@description('Operator comparing the current value with the threshold value.')
@allowed([
  'Equals'
  'GreaterThan'
  'GreaterThanOrEqual'
  'LessThan'
  'LessThanOrEqual'
])
param operator string = 'GreaterThan'

@description('The threshold value at which the alert is activated.')
param threshold int = 0

@description('How the data that is collected should be combined over time.')
@allowed([
  'Average'
  'Minimum'
  'Maximum'
  'Total'
  'Count'
])
param timeAggregation string = 'Total'

@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
  'PT6H'
  'PT12H'
  'PT24H'
  'P1D'
])
param windowSize string = 'PT5M'

@description('how often the metric alert is evaluated represented in ISO 8601 duration format')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
])
param evaluationFrequency string = 'PT1M'

@description('"The current date and time using the utcNow function. Used for deployment name uniqueness')
param currentDateTimeUtcNow string = utcNow()

@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.')
@allowed([
  'Yes'
  'No'
])
param telemetryOptOut string = 'No'

resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = {
  name: alertName
  location: 'global'
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    description: alertDescription
    scopes: targetResourceId
    targetResourceType: targetResourceType
    targetResourceRegion: targetResourceRegion
    severity: alertSeverity
    enabled: isEnabled
    evaluationFrequency: evaluationFrequency
    windowSize: windowSize
    criteria: {
      'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria'
      allOf: [
        {
          name: '1st criterion'
          metricName: 'Not Responding Runs'
          dimensions: [[]]
          operator: operator
          threshold: threshold
          timeAggregation: timeAggregation
          criterionType: 'StaticThresholdCriterion'
        }
      ]
    }
  }
}

var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}'
resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' =  if (telemetryOptOut == 'No') {
  name: ambaTelemetryPidName
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    mode: 'Incremental'
    template: {
      '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#'
      contentVersion: '1.0.0.0'
      resources: []
    }
  }
}



Quota Utilization Percentage - Metric Alert

Percent of quota utilized.

Properties:

criterionTypeStaticThresholdCriterion
evaluationFrequencyPT1M
metricNameQuota Utilization Percentage
metricNamespaceMicrosoft.MachineLearningServices/workspaces
operatorGreaterThan
severity3
threshold90
timeAggregationAverage
windowSizePT5M

References:

Templates:

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "alertName": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Name of the alert"
      }
    },
    "alertDescription": {
      "type": "string",
      "defaultValue": "Percent of quota utilized.",
      "metadata": {
        "description": "Description of alert"
      }
    },
    "targetResourceId": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name"
      }
    },
    "targetResourceRegion": {
      "type": "string",
      "metadata": {
        "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS"
      }
    },
    "targetResourceType": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Resource type of target resources to be monitored."
      }
    },
    "isEnabled": {
      "type": "bool",
      "defaultValue": true,
      "metadata": {
        "description": "Specifies whether the alert is enabled"
      }
    },
    "alertSeverity": {
      "type": "int",
      "defaultValue": 3,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThan",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "90",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Average",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT5M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H",
        "PT6H",
        "PT12H",
        "PT24H",
        "PT1D"
      ],
      "metadata": {
        "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format."
      }
    },
    "evaluationFrequency": {
      "type": "string",
      "defaultValue": "PT1M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H"
      ],
      "metadata": {
        "description": "how often the metric alert is evaluated represented in ISO 8601 duration format"
      }
    },
    "currentDateTimeUtcNow": {
      "type": "string",
      "defaultValue": "[utcNow()]",
      "metadata": {
          "description": "The current date and time using the utcNow function. Used for deployment name uniqueness"
      }
    },
    "telemetryOptOut": {
      "type": "string",
      "defaultValue": "No",
      "allowedValues": [
          "Yes",
          "No"
      ],
      "metadata": {
          "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry."
      }
    }
  },
  "variables": {
    "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]",
    "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]"
  },
  "resources": [
    {
      "type": "Microsoft.Insights/metricAlerts",
      "apiVersion": "2018-03-01",
      "name": "[parameters('alertName')]",
      "location": "global",
      "tags": {
        "_deployed_by_amba": true
      },
      "properties": {
        "description": "[parameters('alertDescription')]",
        "scopes": "[variables('varTargetResourceId')]",
        "targetResourceType": "[parameters('targetResourceType')]",
        "targetResourceRegion": "[parameters('targetResourceRegion')]",
        "severity": "[parameters('alertSeverity')]",
        "enabled": "[parameters('isEnabled')]",
        "evaluationFrequency": "[parameters('evaluationFrequency')]",
        "windowSize": "[parameters('windowSize')]",
        "criteria": {
          "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria",
          "allOf": [
            {
              "name": "1st criterion",
              "metricName": "Quota Utilization Percentage",
              "dimensions": [],
              "operator": "[parameters('operator')]",
              "threshold": "[parameters('threshold')]",
              "timeAggregation": "[parameters('timeAggregation')]",
              "criterionType": "StaticThresholdCriterion"
            }
          ]
        }
      }
    },
    {
      "condition": "[equals(parameters('telemetryOptOut'), 'No')]",
      "apiVersion": "2020-06-01",
      "name": "[variables('pidDeploymentName')]",
      "type": "Microsoft.Resources/deployments",
      "properties": {
          "mode": "Incremental",
          "template": {
              "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
              "contentVersion": "1.0.0.0",
              "resources": []
          }
      }
    }
  ]
}
@description('Name of the alert')
@minLength(1)
param alertName string

@description('Description of alert')
param alertDescription string = 'Percent of quota utilized.'

@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name')
@minLength(1)
param targetResourceId array

@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS')
param targetResourceRegion string

@description('Resource type of target resources to be monitored.')
@minLength(1)
param targetResourceType string

@description('Specifies whether the alert is enabled')
param isEnabled bool = true

@description('Severity of alert {0,1,2,3,4}')
@allowed([
  0
  1
  2
  3
  4
])
param alertSeverity int = 3

@description('Operator comparing the current value with the threshold value.')
@allowed([
  'Equals'
  'GreaterThan'
  'GreaterThanOrEqual'
  'LessThan'
  'LessThanOrEqual'
])
param operator string = 'GreaterThan'

@description('The threshold value at which the alert is activated.')
param threshold int = 90

@description('How the data that is collected should be combined over time.')
@allowed([
  'Average'
  'Minimum'
  'Maximum'
  'Total'
  'Count'
])
param timeAggregation string = 'Average'

@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
  'PT6H'
  'PT12H'
  'PT24H'
  'P1D'
])
param windowSize string = 'PT5M'

@description('how often the metric alert is evaluated represented in ISO 8601 duration format')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
])
param evaluationFrequency string = 'PT1M'

@description('"The current date and time using the utcNow function. Used for deployment name uniqueness')
param currentDateTimeUtcNow string = utcNow()

@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.')
@allowed([
  'Yes'
  'No'
])
param telemetryOptOut string = 'No'

resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = {
  name: alertName
  location: 'global'
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    description: alertDescription
    scopes: targetResourceId
    targetResourceType: targetResourceType
    targetResourceRegion: targetResourceRegion
    severity: alertSeverity
    enabled: isEnabled
    evaluationFrequency: evaluationFrequency
    windowSize: windowSize
    criteria: {
      'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria'
      allOf: [
        {
          name: '1st criterion'
          metricName: 'Quota Utilization Percentage'
          dimensions: [[]]
          operator: operator
          threshold: threshold
          timeAggregation: timeAggregation
          criterionType: 'StaticThresholdCriterion'
        }
      ]
    }
  }
}

var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}'
resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' =  if (telemetryOptOut == 'No') {
  name: ambaTelemetryPidName
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    mode: 'Incremental'
    template: {
      '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#'
      contentVersion: '1.0.0.0'
      resources: []
    }
  }
}



Unusable Nodes - Metric Alert

Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.

Properties:

criterionTypeStaticThresholdCriterion
evaluationFrequencyPT1M
metricNameUnusable Nodes
metricNamespaceMicrosoft.MachineLearningServices/workspaces
operatorGreaterThan
severity3
threshold0
timeAggregationTotal
windowSizePT5M

References:

Templates:

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "alertName": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Name of the alert"
      }
    },
    "alertDescription": {
      "type": "string",
      "defaultValue": "Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.",
      "metadata": {
        "description": "Description of alert"
      }
    },
    "targetResourceId": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name"
      }
    },
    "targetResourceRegion": {
      "type": "string",
      "metadata": {
        "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS"
      }
    },
    "targetResourceType": {
      "type": "string",
      "minLength": 1,
      "metadata": {
        "description": "Resource type of target resources to be monitored."
      }
    },
    "isEnabled": {
      "type": "bool",
      "defaultValue": true,
      "metadata": {
        "description": "Specifies whether the alert is enabled"
      }
    },
    "alertSeverity": {
      "type": "int",
      "defaultValue": 3,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThan",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "0",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Total",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT5M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H",
        "PT6H",
        "PT12H",
        "PT24H",
        "PT1D"
      ],
      "metadata": {
        "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format."
      }
    },
    "evaluationFrequency": {
      "type": "string",
      "defaultValue": "PT1M",
      "allowedValues": [
        "PT1M",
        "PT5M",
        "PT15M",
        "PT30M",
        "PT1H"
      ],
      "metadata": {
        "description": "how often the metric alert is evaluated represented in ISO 8601 duration format"
      }
    },
    "currentDateTimeUtcNow": {
      "type": "string",
      "defaultValue": "[utcNow()]",
      "metadata": {
          "description": "The current date and time using the utcNow function. Used for deployment name uniqueness"
      }
    },
    "telemetryOptOut": {
      "type": "string",
      "defaultValue": "No",
      "allowedValues": [
          "Yes",
          "No"
      ],
      "metadata": {
          "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry."
      }
    }
  },
  "variables": {
    "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]",
    "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]"
  },
  "resources": [
    {
      "type": "Microsoft.Insights/metricAlerts",
      "apiVersion": "2018-03-01",
      "name": "[parameters('alertName')]",
      "location": "global",
      "tags": {
        "_deployed_by_amba": true
      },
      "properties": {
        "description": "[parameters('alertDescription')]",
        "scopes": "[variables('varTargetResourceId')]",
        "targetResourceType": "[parameters('targetResourceType')]",
        "targetResourceRegion": "[parameters('targetResourceRegion')]",
        "severity": "[parameters('alertSeverity')]",
        "enabled": "[parameters('isEnabled')]",
        "evaluationFrequency": "[parameters('evaluationFrequency')]",
        "windowSize": "[parameters('windowSize')]",
        "criteria": {
          "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria",
          "allOf": [
            {
              "name": "1st criterion",
              "metricName": "Unusable Nodes",
              "dimensions": [],
              "operator": "[parameters('operator')]",
              "threshold": "[parameters('threshold')]",
              "timeAggregation": "[parameters('timeAggregation')]",
              "criterionType": "StaticThresholdCriterion"
            }
          ]
        }
      }
    },
    {
      "condition": "[equals(parameters('telemetryOptOut'), 'No')]",
      "apiVersion": "2020-06-01",
      "name": "[variables('pidDeploymentName')]",
      "type": "Microsoft.Resources/deployments",
      "properties": {
          "mode": "Incremental",
          "template": {
              "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
              "contentVersion": "1.0.0.0",
              "resources": []
          }
      }
    }
  ]
}
@description('Name of the alert')
@minLength(1)
param alertName string

@description('Description of alert')
param alertDescription string = 'Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.'

@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name')
@minLength(1)
param targetResourceId array

@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS')
param targetResourceRegion string

@description('Resource type of target resources to be monitored.')
@minLength(1)
param targetResourceType string

@description('Specifies whether the alert is enabled')
param isEnabled bool = true

@description('Severity of alert {0,1,2,3,4}')
@allowed([
  0
  1
  2
  3
  4
])
param alertSeverity int = 3

@description('Operator comparing the current value with the threshold value.')
@allowed([
  'Equals'
  'GreaterThan'
  'GreaterThanOrEqual'
  'LessThan'
  'LessThanOrEqual'
])
param operator string = 'GreaterThan'

@description('The threshold value at which the alert is activated.')
param threshold int = 0

@description('How the data that is collected should be combined over time.')
@allowed([
  'Average'
  'Minimum'
  'Maximum'
  'Total'
  'Count'
])
param timeAggregation string = 'Total'

@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
  'PT6H'
  'PT12H'
  'PT24H'
  'P1D'
])
param windowSize string = 'PT5M'

@description('how often the metric alert is evaluated represented in ISO 8601 duration format')
@allowed([
  'PT1M'
  'PT5M'
  'PT15M'
  'PT30M'
  'PT1H'
])
param evaluationFrequency string = 'PT1M'

@description('"The current date and time using the utcNow function. Used for deployment name uniqueness')
param currentDateTimeUtcNow string = utcNow()

@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.')
@allowed([
  'Yes'
  'No'
])
param telemetryOptOut string = 'No'

resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = {
  name: alertName
  location: 'global'
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    description: alertDescription
    scopes: targetResourceId
    targetResourceType: targetResourceType
    targetResourceRegion: targetResourceRegion
    severity: alertSeverity
    enabled: isEnabled
    evaluationFrequency: evaluationFrequency
    windowSize: windowSize
    criteria: {
      'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria'
      allOf: [
        {
          name: '1st criterion'
          metricName: 'Unusable Nodes'
          dimensions: [[]]
          operator: operator
          threshold: threshold
          timeAggregation: timeAggregation
          criterionType: 'StaticThresholdCriterion'
        }
      ]
    }
  }
}

var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}'
resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' =  if (telemetryOptOut == 'No') {
  name: ambaTelemetryPidName
  tags: {
    _deployed_by_amba: 'true'
  }
  properties: {
    mode: 'Incremental'
    template: {
      '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#'
      contentVersion: '1.0.0.0'
      resources: []
    }
  }
}