vaults

{
  "type": "Microsoft.Authorization/policyDefinitions",
  "apiVersion": "2021-06-01",
  "name": "Deploy_RecoveryVault_BackupHealthMonitor_Alert",
  "properties": {
    "policyType": "Custom",
    "mode": "All",
    "displayName": "Deploy RV Backup Health Monitoring Alerts",
    "description": "Policy to audit/update Recovery Vault Backup Health Alerting to Azure monitor alerts",
    "metadata": {
      "version": "1.0.0",
      "category": "Site Recovery",
      "source": "https://github.com/Azure/azure-monitor-baseline-alerts/",
      "alzCloudEnvironments": [
        "AzureCloud"
      ],
      "_deployed_by_amba": "True"
    },
    "parameters": {
      "effect": {
        "type": "String",
        "metadata": {
          "displayName": "Effect",
          "description": "Effect of the policy"
        },
        "allowedValues": [
          "modify",
          "audit",
          "disabled"
        ],
        "defaultValue": "modify"
      },
      "MonitorDisable": {
        "type": "String",
        "metadata": {
          "displayName": "Effect",
          "description": "Tag name to disable monitoring resource. Set to true if monitoring should be disabled"
        },
        "defaultValue": "MonitorDisable"
      }
    },
    "policyRule": {
      "if": {
        "allOf": [
          {
            "field": "type",
            "equals": "Microsoft.RecoveryServices/Vaults"
          },
          {
            "field": "[[concat('tags[', parameters('MonitorDisable'), ']')]",
            "notEquals": "true"
          },
          {
            "field": "Microsoft.RecoveryServices/vaults/monitoringSettings.azureMonitorAlertSettings.alertsForAllJobFailures",
            "notEquals": "Enabled"
          }
        ]
      },
      "then": {
        "effect": "[[parameters('effect')]",
        "details": {
          "roleDefinitionIds": [
            "/providers/Microsoft.Authorization/roleDefinitions/b24988ac-6180-42a0-ab88-20f7382dd24c"
          ],
          "conflictEffect": "audit",
          "operations": [
            {
              "operation": "addOrReplace",
              "field": "Microsoft.RecoveryServices/vaults/monitoringSettings.classicAlertSettings.alertsForCriticalOperations",
              "value": "Disabled"
            },
            {
              "operation": "addOrReplace",
              "field": "Microsoft.RecoveryServices/vaults/monitoringSettings.azureMonitorAlertSettings.alertsForAllJobFailures",
              "value": "Enabled"
            }
          ]
        }
      }
    }
  }
}

{
  "$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": "The count of health events pertaining to backup job health",
      "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": "Count",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "P1D",
      "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": "PT1H",
      "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": "BackupHealthEvent",
              "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 = 'The count of health events pertaining to backup job health'

@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 = 'Count'

@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 = 'P1D'

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

@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: 'BackupHealthEvent'
          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: []
    }
  }
}

{
  "$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": "The count of health events pertaining to restore job health",
      "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": 2,
      "allowedValues": [
        0,
        1,
        2,
        3,
        4
      ],
      "metadata": {
        "description": "Severity of alert {0,1,2,3,4}"
      }
    },
    "operator": {
      "type": "string",
      "defaultValue": "GreaterThanOrEqual",
      "allowedValues": [
        "Equals",
        "GreaterThan",
        "GreaterThanOrEqual",
        "LessThan",
        "LessThanOrEqual"
      ],
      "metadata": {
        "description": "Operator comparing the current value with the threshold value."
      }
    },
    "threshold": {
      "type": "string",
      "defaultValue": "1",
      "metadata": {
        "description": "The threshold value at which the alert is activated."
      }
    },
    "timeAggregation": {
      "type": "string",
      "defaultValue": "Count",
      "allowedValues": [
        "Average",
        "Minimum",
        "Maximum",
        "Total",
        "Count"
      ],
      "metadata": {
        "description": "How the data that is collected should be combined over time."
      }
    },
    "windowSize": {
      "type": "string",
      "defaultValue": "PT15M",
      "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": "PT15M",
      "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": "RestoreHealthEvent",
              "dimensions": [
                {
                  "name": "0",
                  "operator": "exclude",
                  "values": ["healthy"]
                }
              ],
              "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 = 'The count of health events pertaining to restore job health'

@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 = 2

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

@description('The threshold value at which the alert is activated.')
param threshold int = 1

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

@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 = 'PT15M'

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

@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: 'RestoreHealthEvent'
          dimensions: [
            {
              name: '0'
              operator: 'exclude'
              values: ['healthy']
            }
          ]
          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: []
    }
  }
}