在 Batch 池中预配 Linux 计算节点

创建 Linux 池：Batch Python

以下代码片段示范如何使用用于 Python 的 Azure Batch 客户端库创建 Ubuntu Server 计算节点池。 有关 Batch Python 模块的更多详细信息，请查看参考文档。

此代码片段显式创建 BatchVmImageReference 并指定其每个属性（发布者、产品/服务、SKU、版本）。 不过，在生产代码中，我们建议您使用 list_supported_images 方法，在运行时从可用的映像与节点代理 SKU 组合中进行选择。

# Import the required modules from the
# Azure Batch Client Library for Python
from azure.batch import BatchClient, models
from azure.core.credentials import AzureNamedKeyCredential

# Specify Batch account credentials
account = "<batch-account-name>"
key = "<batch-account-key>"
account_endpoint = "<batch-account-url>"

# Pool settings
pool_id = "LinuxNodesSamplePoolPython"
vm_size = "STANDARD_D2_V3"
node_count = 1

# Initialize the Batch client
creds = AzureNamedKeyCredential(account, key)
client = BatchClient(endpoint=account_endpoint, credential=creds)

# Configure the start task for the pool
start_task = models.BatchStartTask(
    command_line="printenv AZ_BATCH_NODE_STARTUP_DIR",
    user_identity=models.UserIdentity(
        auto_user=models.AutoUserSpecification(
            elevation_level=models.ElevationLevel.ADMIN,
            scope=models.AutoUserScope.POOL,
        )
    ),
)

# Create an ImageReference which specifies the Marketplace
# virtual machine image to install on the nodes
ir = models.BatchVmImageReference(
    publisher="canonical",
    offer="0001-com-ubuntu-server-focal",
    sku="20_04-lts",
    version="latest")

# Create the VirtualMachineConfiguration, specifying
# the VM image reference and the Batch node agent
# to install on the node
vmc = models.VirtualMachineConfiguration(
    image_reference=ir,
    node_agent_sku_id="batch.node.ubuntu 20.04")

# Create the unbound pool
new_pool = models.BatchPoolCreateOptions(
    id=pool_id,
    vm_size=vm_size,
    target_dedicated_nodes=node_count,
    virtual_machine_configuration=vmc,
    start_task=start_task,
)

# Create pool in the Batch service
client.create_pool(pool=new_pool)

如前所述，我们建议使用 list_supported_images 方法从当前支持的节点代理/市场映像组合（而不是显式创建 BatchVmImageReference ）中动态选择。 以下 Python 代码片段演示如何使用此方法。

# Get the list of supported images from the Batch service
images = list(client.list_supported_images())

# Obtain the desired image reference
image = None
for img in images:
  if (img.image_reference.publisher.lower() == "canonical" and
        img.image_reference.offer.lower() == "0001-com-ubuntu-server-focal" and
        img.image_reference.sku.lower() == "20_04-lts"):
    image = img
    break

if image is None:
  raise RuntimeError('invalid image reference for desired configuration')

# Create the VirtualMachineConfiguration, specifying the VM image
# reference and the Batch node agent to be installed on the node
vmc = models.VirtualMachineConfiguration(
    image_reference=image.image_reference,
    node_agent_sku_id=image.node_agent_sku_id)

创建 Linux 池：批处理 .NET

以下代码片段展示了如何使用 Azure.Compute.Batch 和 Azure.ResourceManager.Batch 客户端库来创建 Ubuntu Server 计算节点池的示例。 有关更多详细信息，请参阅 参考文档。

以下代码片段使用 BatchClient.GetSupportedImages 方法从当前受支持的市场映像和节点代理 SKU 组合列表中选择。 建议使用这种方法，因为受支持组合的列表有时会发生变化。 通常会添加受支持的组合。

// Pool settings
const string poolId = "LinuxNodesSamplePoolDotNet";
const string vmSize = "STANDARD_D2_V3";
const int nodeCount = 1;

// Obtain a collection of all available node agent SKUs.
// This allows us to select from a list of supported
// VM image/node agent combinations.
List<BatchSupportedImage> images = new List<BatchSupportedImage>();
await foreach (BatchSupportedImage img in batchClient.GetSupportedImagesAsync())
{
    images.Add(img);
}

// Find the appropriate image information
BatchSupportedImage image = null;
foreach (var img in images)
{
    if (img.ImageReference.Publisher == "canonical" &&
        img.ImageReference.Offer == "0001-com-ubuntu-server-focal" &&
        img.ImageReference.Sku == "20_04-lts")
    {
        image = img;
        break;
    }
}

// Create the BatchVmConfiguration for use when actually creating the pool.
// Note that the data-plane discovery uses Azure.Compute.Batch.BatchVmImageReference
// but the ARM pool data type uses Azure.ResourceManager.Batch.Models.BatchImageReference.
BatchVmConfiguration vmConfiguration = new BatchVmConfiguration(
    imageReference: new BatchImageReference()
    {
        Publisher = image.ImageReference.Publisher,
        Offer = image.ImageReference.Offer,
        Sku = image.ImageReference.Sku,
        Version = image.ImageReference.Version
    },
    nodeAgentSkuId: image.NodeAgentSkuId);

BatchAccountPoolData poolData = new BatchAccountPoolData()
{
    VmSize = vmSize,
    DeploymentConfiguration = new BatchDeploymentConfiguration() { VmConfiguration = vmConfiguration },
    ScaleSettings = new BatchAccountPoolScaleSettings()
    {
        FixedScale = new BatchAccountFixedScaleSettings() { TargetDedicatedNodes = nodeCount }
    }
};

// Commit the pool to the Batch service via Azure.ResourceManager.Batch.
await batchAccount.GetBatchAccountPools().CreateOrUpdateAsync(WaitUntil.Completed, poolId, poolData);

尽管前面的代码片段使用 BatchClient.GetSupportedImages 方法动态列出并从支持的映像和节点代理 SKU 组合中进行选择（建议），但也可以显式配置 BatchVmImageReference ：

BatchImageReference imageReference = new BatchImageReference()
{
    Publisher = "canonical",
    Offer = "0001-com-ubuntu-server-focal",
    Sku = "20_04-lts",
    Version = "latest"
};

以下 Python 代码片段会在池中的每个节点上创建一个用户（远程连接时需要）。 然后打印每个节点的安全 Shell（SSH）连接信息。

import datetime
import getpass
from azure.batch import BatchClient, models
from azure.core.credentials import AzureNamedKeyCredential

# Specify your own account credentials
batch_account_name = ''
batch_account_key = ''
batch_account_url = ''

# Specify the ID of an existing pool containing Linux nodes
# currently in the 'idle' state
pool_id = ''

# Specify the username and prompt for a password
username = 'linuxuser'
password = getpass.getpass()

# Create a BatchClient
credentials = AzureNamedKeyCredential(
    batch_account_name,
    batch_account_key
)
batch_client = BatchClient(
    endpoint=batch_account_url,
    credential=credentials
)

# Create the user that will be added to each node in the pool
user = models.BatchNodeUserCreateOptions(
    name=username,
    password=password,
    is_admin=True,
    expiry_time=(datetime.datetime.utcnow() + datetime.timedelta(days=30)),
)

# Get the list of nodes in the pool
nodes = batch_client.list_nodes(pool_id=pool_id)

# Add the user to each node in the pool and print
# the connection information for the node
for node in nodes:
    # Add the user to the node
    batch_client.create_node_user(pool_id=pool_id, node_id=node.id, user=user)

    # Obtain SSH login information for the node
    login = batch_client.get_node_remote_login_settings(pool_id=pool_id,
                                                        node_id=node.id)

    # Print the connection info for the node
    print("{0} | {1} | {2} | {3}".format(node.id,
                                         node.state,
                                         login.remote_login_ip_address,
                                         login.remote_login_port))

此代码将会有类似于以下示例的输出。 在本例中，该池包含四个 Linux 节点。

Password:
tvm-1219235766_1-20160414t192511z | ComputeNodeState.idle | 13.91.7.57 | 50000
tvm-1219235766_2-20160414t192511z | ComputeNodeState.idle | 13.91.7.57 | 50003
tvm-1219235766_3-20160414t192511z | ComputeNodeState.idle | 13.91.7.57 | 50002
tvm-1219235766_4-20160414t192511z | ComputeNodeState.idle | 13.91.7.57 | 50001

在 Python SDK 中，在 BatchNodeUserCreateOptions 上使用 ssh_public_key 参数。

在.NET中，使用 BatchNodeUserCreateOptions.SshPublicKey 属性。