sql-server - Terraform - Azure - 一起使用 "azurerm_windows_virtual_machine"和 "azurerm_mssql_virtual_machine"- 但 SQL 存储未配置

Question

这是关于 Azure 上的 Terraform。在我之前的项目中，我使用旧的“azurerm_virtual_machine”资源+ ARM 模板来配置“Microsoft.SqlVirtualMachine/SqlVirtualMachines”资源并配置数据磁盘、luns。

这效果很好。
在我当前的项目中，我们正在同时使用较新的资源“azurerm_windows_virtual_machine”+“azurerm_mssql_virtual_machine”来启动 SQL VM。然而，到目前为止，它一直是一个哑弹。

Terraform 文档示例使用旧资源“azurerm_windows_virtual_machine”。

问题

• 在“azurerm_windows_virtual_machine”中找不到描述数据磁盘和lun id的方法，结果

• 当我没有在“azurerm_mssql_virtual_machine”中提及 storage_configuration block 时，Azure 门户显示“在卷列表中找不到驱动器”。在 SQL 虚拟机资源(不是虚拟机资源)> 配置部分下。我已附上屏幕截图。

• 请参阅以下错误:

• 如果我尝试在“azurerm_mssql_virtual_machine”的 storage_configuration block 中提及​​数据磁盘和 lun，则配置会失败并出现错误
  

  creating Sql Virtual Machine (Sql Virtual Machine Name "ASQLVM" / Resource Group "a-resource-group"): 
  sqlvirtualmachine.SQLVirtualMachinesClient#CreateOrUpdate: Failure sending request: StatusCode=0 -- 
  Original Error: Code="InvalidDefaultFilePath" Message="Invalid Default File Path"
  

有没有一种好方法可以同时使用新的“azurerm_windows_virtual_machine”+“azurerm_mssql_virtual_machine”来配置 SQL 虚拟机？

Answer 1

查看以下代码。如果您还没有成功，我希望它能回答您的问题。

resource "azurerm_windows_virtual_machine" "vm" {    
    count   = length(var.instances)
    name    = upper(element(var.instances, count.index))
    location                = azurerm_resource_group.resourcegroup[count.index].location
    resource_group_name     = azurerm_resource_group.resourcegroup[count.index].name
    network_interface_ids   = [azurerm_network_interface.nic[count.index].id]
    size                    = var.instancesize
    zone                    = var.instancezone
    admin_username  = var.vmadmin
    admin_password  = data.azurerm_key_vault_secret.vmadminpwd.value
    enable_automatic_updates    = "false"
    patch_mode                  = "Manual"
    provision_vm_agent          = "true"
    tags                        = var.tags

    source_image_reference {
        publisher = "MicrosoftSQLServer"
        offer     = "sql2019-ws2019"
        sku       = "enterprise"
        version   = "latest"
    }
        
    os_disk {
        name                    = "${element(var.instances, count.index)}-osdisk"
        caching                 = "ReadWrite"
        storage_account_type    = "StandardSSD_LRS"
        disk_size_gb            = 250
    }
}

# add a data disk - we were going to iterate through a collection, but this is easier for now
resource "azurerm_managed_disk" "datadisk" {
    count = length(var.instances)
    name                    = "${azurerm_windows_virtual_machine.vm[count.index].name}-data-disk01" 
    location                = azurerm_resource_group.resourcegroup[count.index].location
    resource_group_name     = azurerm_resource_group.resourcegroup[count.index].name
    storage_account_type    = "Premium_LRS"
    zones                   = [var.instancezone]
    create_option           = "Empty"
    disk_size_gb            = 1000
    tags                    = var.tags
}

resource "azurerm_virtual_machine_data_disk_attachment" "datadisk_attach" {
    count = length(var.instances)
    managed_disk_id    = azurerm_managed_disk.datadisk[count.index].id
    virtual_machine_id = azurerm_windows_virtual_machine.vm[count.index].id
    lun                = 1
    caching            = "ReadWrite"
}

# add a log disk - we were going to iterate through a collection, but this is easier for now
resource "azurerm_managed_disk" "logdisk" {
    count = length(var.instances)
    name                    = "${azurerm_windows_virtual_machine.vm[count.index].name}-log-disk01" 
    location                = azurerm_resource_group.resourcegroup[count.index].location
    resource_group_name     = azurerm_resource_group.resourcegroup[count.index].name
    storage_account_type    = "Premium_LRS"
    zones                    = [var.instancezone]
    create_option           = "Empty"
    disk_size_gb            = 500
    tags                    = var.tags
}

resource "azurerm_virtual_machine_data_disk_attachment" "logdisk_attach" {
    count = length(var.instances)
    managed_disk_id    = azurerm_managed_disk.logdisk[count.index].id
    virtual_machine_id = azurerm_windows_virtual_machine.vm[count.index].id
    lun                = 2
    caching            = "ReadWrite"
}

# configure the SQL side of the deployment
resource "azurerm_mssql_virtual_machine" "sqlvm" {
    count = length(var.instances)
    virtual_machine_id               = azurerm_windows_virtual_machine.vm[count.index].id
    sql_license_type                 = "PAYG"
    r_services_enabled               = true
    sql_connectivity_port            = 1433
    sql_connectivity_type            = "PRIVATE"
    sql_connectivity_update_username = var.sqladmin
    sql_connectivity_update_password = data.azurerm_key_vault_secret.sqladminpwd.value

    #The storage_configuration block supports the following:
    storage_configuration {
        disk_type               = "NEW"                         # (Required) The type of disk configuration to apply to the SQL Server. Valid values include NEW, EXTEND, or ADD.
        storage_workload_type   = "OLTP"                        # (Required) The type of storage workload. Valid values include GENERAL, OLTP, or DW.

        # The storage_settings block supports the following:
        data_settings {
            default_file_path = var.sqldatafilepath     # (Required) The SQL Server default path
            luns = [azurerm_virtual_machine_data_disk_attachment.datadisk_attach[count.index].lun]
        }

        log_settings {
            default_file_path = var.sqllogfilepath     # (Required) The SQL Server default path
            luns = [azurerm_virtual_machine_data_disk_attachment.logdisk_attach[count.index].lun]                                 # (Required) A list of Logical Unit Numbers for the disks.
        }

#        temp_db_settings {
#            default_file_path = var.sqltempdbfilepath   #- (Required) The SQL Server default path
#            luns = [3] #- (Required) A list of Logical Unit Numbers for the disks.
#        }

    }

}