扇出/扇入情景

• 完成快速入门文章
• 从 GitHub 克隆或下载示例项目

• 完成快速入门文章
• 从 GitHub 克隆或下载示例项目

• 完成快速入门文章
• 从 GitHub 克隆或下载示例项目

下面的代码实现协调器函数：

        [FunctionName("E2_BackupSiteContent")]
        public static async Task<long> Run(
            [OrchestrationTrigger] IDurableOrchestrationContext backupContext)
        {
            string rootDirectory = backupContext.GetInput<string>()?.Trim();
            if (string.IsNullOrEmpty(rootDirectory))
            {
                rootDirectory = Directory.GetParent(typeof(BackupSiteContent).Assembly.Location).FullName;
            }

            string[] files = await backupContext.CallActivityAsync<string[]>(
                "E2_GetFileList",
                rootDirectory);

            var tasks = new Task<long>[files.Length];
            for (int i = 0; i < files.Length; i++)
            {
                tasks[i] = backupContext.CallActivityAsync<long>(
                    "E2_CopyFileToBlob",
                    files[i]);
            }

            await Task.WhenAll(tasks);

            long totalBytes = tasks.Sum(t => t.Result);
            return totalBytes;
        }

请注意 await Task.WhenAll(tasks); 行。 代码不会等待单个对 E2_CopyFileToBlob 的调用，因此它们并行运行。 当协调器将任务数组传递给 Task.WhenAll 时，它会返回一个任务，该任务只有在所有复制操作完成后才会完成。 如果熟悉.NET中的任务并行库（TPL），则此模式很熟悉。 区别在于，这些任务可以同时在多个虚拟机上运行，而Durable Functions扩展可确保端到端执行具备对进程回收的耐受性。

协调器等待 Task.WhenAll后，所有函数调用都已完成且返回值已经生成。 每次调用 E2_CopyFileToBlob 时都会返回上传的字节数。 通过添加返回值计算总计。

协调器函数使用标准的 function.json。

{
  "scriptFile": "__init__.py",
  "bindings": [
    {
      "name": "context",
      "type": "orchestrationTrigger",
      "direction": "in"
    }
  ]
}

下面的代码实现协调器函数：

import azure.functions as func
import azure.durable_functions as df


def orchestrator_function(context: df.DurableOrchestrationContext):

    root_directory: str = context.get_input()

    if not root_directory:
        raise Exception("A directory path is required as input")

    files = yield context.call_activity("E2_GetFileList", root_directory)
    tasks = []
    for file in files:
        tasks.append(context.call_activity("E2_CopyFileToBlob", file))

    results = yield context.task_all(tasks)
    total_bytes = sum(results)
    return total_bytes

main = df.Orchestrator.create(orchestrator_function)

请注意 yield context.task_all(tasks); 行。 代码不会引发对 E2_CopyFileToBlob 的单独调用，以便它们并行运行。 当协调器将任务数组传递给 context.task_all 时，它会返回一个任务，该任务只有在所有复制操作完成后才会完成。 如果你熟悉 Python 中的 asyncio.gather，则这不是新手。 区别在于，这些任务可以同时在多个虚拟机上运行，而Durable Functions扩展可确保端到端执行具备对进程回收的耐受性。

业务流程协调程序生成 context.task_all后，所有函数调用都已完成并返回值。 每次调用 E2_CopyFileToBlob 都会返回已上传字节数，因此，将所有这些返回值相加就能计算出字节数总和。

PowerShell 示例尚不可用。

Java示例尚不可用。

using Microsoft.DurableTask;
using System.Collections.Generic;
using System.Threading.Tasks;

[DurableTask]
public class ParallelProcessingOrchestration : TaskOrchestrator<List<string>, Dictionary<string, int>>
{
    public override async Task<Dictionary<string, int>> RunAsync(
        TaskOrchestrationContext context, List<string> workItems)
    {
        // Step 1: Fan-out by creating a task for each work item in parallel
        var processingTasks = new List<Task<Dictionary<string, int>>>();

        foreach (string workItem in workItems)
        {
            // Create a task for each work item (fan-out)
            Task<Dictionary<string, int>> task = context.CallActivityAsync<Dictionary<string, int>>(
                nameof(ProcessWorkItemActivity), workItem);
            processingTasks.Add(task);
        }

        // Step 2: Wait for all parallel tasks to complete
        Dictionary<string, int>[] results = await Task.WhenAll(processingTasks);

        // Step 3: Fan-in by aggregating all results
        Dictionary<string, int> aggregatedResults = await context.CallActivityAsync<Dictionary<string, int>>(
            nameof(AggregateResultsActivity), results);

        return aggregatedResults;
    }
}

用于 Task.WhenAll() 等待所有并行任务完成。 Durable Task SDK 确保任务可以在多台计算机上并发运行，并且执行具有恢复能力，能够应对进程重启。

import {
  OrchestrationContext,
  TOrchestrator,
  whenAll,
} from "@microsoft/durabletask-js";

const fanOutFanInOrchestrator: TOrchestrator = async function* (
  ctx: OrchestrationContext,
  workItems: string[]
): any {
  // Fan-out: create a task for each work item in parallel
  const tasks = workItems.map((item) => ctx.callActivity(processWorkItem, item));

  // Wait for all parallel tasks to complete
  const results: number[] = yield whenAll(tasks);

  // Fan-in: aggregate all results
  const aggregatedResult = yield ctx.callActivity(aggregateResults, results);

  return aggregatedResult;
};

用于 whenAll() 等待所有并行任务完成。 Durable Task SDK 确保任务可以在多台计算机上并发运行，并且执行具有恢复能力，能够应对进程重启。

from durabletask import task

def fan_out_fan_in_orchestrator(ctx: task.OrchestrationContext, work_items: list) -> dict:
    """Orchestrator that demonstrates fan-out/fan-in pattern."""

    # Fan-out: Create a task for each work item
    parallel_tasks = []
    for item in work_items:
        parallel_tasks.append(ctx.call_activity(process_work_item, input=item))

    # Wait for all tasks to complete
    results = yield task.when_all(parallel_tasks)

    # Fan-in: Aggregate all the results
    final_result = yield ctx.call_activity(aggregate_results, input=results)

    return final_result

用于 task.when_all() 等待所有并行任务完成。 Durable Task SDK 确保任务可以在多台计算机上并发运行，并且执行具有恢复能力，能够应对进程重启。

此示例适用于 .NET、JavaScript、Java 和 Python。

import com.microsoft.durabletask.*;
import java.util.List;
import java.util.stream.Collectors;

DurableTaskGrpcWorker worker = DurableTaskSchedulerWorkerExtensions.createWorkerBuilder(connectionString)
    .addOrchestration(new TaskOrchestrationFactory() {
        @Override
        public String getName() { return "FanOutFanIn_WordCount"; }

        @Override
        public TaskOrchestration create() {
            return ctx -> {
                List<?> inputs = ctx.getInput(List.class);

                // Fan-out: Create a task for each input item
                List<Task<Integer>> tasks = inputs.stream()
                    .map(input -> ctx.callActivity("CountWords", input.toString(), Integer.class))
                    .collect(Collectors.toList());

                // Wait for all parallel tasks to complete
                List<Integer> allResults = ctx.allOf(tasks).await();

                // Fan-in: Aggregate results
                int totalCount = allResults.stream().mapToInt(Integer::intValue).sum();

                ctx.complete(totalCount);
            };
        }
    })
    .build();

用于 ctx.allOf(tasks).await() 等待所有并行任务完成。 Durable Task SDK 确保任务可以在多台计算机上并发运行，并且执行具有恢复能力，能够应对进程重启。

        [FunctionName("E2_GetFileList")]
        public static string[] GetFileList(
            [ActivityTrigger] string rootDirectory, 
            ILogger log)
        {
            log.LogInformation($"Searching for files under '{rootDirectory}'...");
            string[] files = Directory.GetFiles(rootDirectory, "*", SearchOption.AllDirectories);
            log.LogInformation($"Found {files.Length} file(s) under {rootDirectory}.");

            return files;
        }

function.json文件 E2_GetFileList如以下示例所示：

{
  "scriptFile": "__init__.py",
  "bindings": [
    {
      "name": "rootDirectory",
      "type": "activityTrigger",
      "direction": "in"
    }
  ]
}

下面是实现：

import os
from os.path import dirname
from typing import List

def main(rootDirectory: str) -> List[str]:

    all_file_paths = []
    # We walk the file system
    for path, _, files in os.walk(rootDirectory):
        # We copy the code for activities and orchestrators
        if "E2_" in path:
            # For each file, we add their full-path to the list
            for name in files:
                if name == "__init__.py" or name == "function.json":
                    file_path = os.path.join(path, name)
                    all_file_paths.append(file_path)

    return all_file_paths

即将推出 PowerShell 示例。

即将推出Java示例。

        [FunctionName("E2_CopyFileToBlob")]
        public static async Task<long> CopyFileToBlob(
            [ActivityTrigger] string filePath,
            Binder binder,
            ILogger log)
        {
            long byteCount = new FileInfo(filePath).Length;

            // strip the drive letter prefix and convert to forward slashes
            string blobPath = filePath
                .Substring(Path.GetPathRoot(filePath).Length)
                .Replace('\\', '/');
            string outputLocation = $"backups/{blobPath}";

            log.LogInformation($"Copying '{filePath}' to '{outputLocation}'. Total bytes = {byteCount}.");

            // copy the file contents into a blob
            using (Stream source = File.Open(filePath, FileMode.Open, FileAccess.Read, FileShare.Read))
            using (Stream destination = await binder.BindAsync<CloudBlobStream>(
                new BlobAttribute(outputLocation, FileAccess.Write)))
            {
                await source.CopyToAsync(destination);
            }

            return byteCount;
        }

该函数使用Azure Functions绑定功能，如 Binder 参数。 本演练不需要这些详细信息。

function.json 文件对 E2_CopyFileToBlob 同样很简单：

{
  "scriptFile": "__init__.py",
  "bindings": [
    {
      "name": "filePath",
      "type": "activityTrigger",
      "direction": "in"
    }
  ]
}

Python实现使用 Azure Storage SDK for Python将文件上传到Azure Blob Storage。

import os
import pathlib
from azure.storage.blob import BlobServiceClient
from azure.core.exceptions import ResourceExistsError

connect_str = os.getenv('AzureWebJobsStorage')

def main(filePath: str) -> str:
    # Create the BlobServiceClient object which will be used to create a container client
    blob_service_client = BlobServiceClient.from_connection_string(connect_str)

    # Create a unique name for the container
    container_name = "backups"

    # Create the container if it does not exist
    try:
        blob_service_client.create_container(container_name)
    except ResourceExistsError:
        pass

    # Create a blob client using the local file name as the name for the blob
    parent_dir, fname = pathlib.Path(filePath).parts[-2:] # Get last two path components
    blob_name = parent_dir + "_" + fname
    blob_client = blob_service_client.get_blob_client(container=container_name, blob=blob_name)

    # Count bytes in file
    byte_count = os.path.getsize(filePath)

    # Upload the created file
    with open(filePath, "rb") as data:
        blob_client.upload_blob(data)

    return byte_count

即将推出 PowerShell 示例。

即将推出Java示例。

using Microsoft.DurableTask;
using Microsoft.Extensions.Logging;
using System.Collections.Generic;
using System.Threading.Tasks;

[DurableTask]
public class ProcessWorkItemActivity : TaskActivity<string, Dictionary<string, int>>
{
    private readonly ILogger<ProcessWorkItemActivity> _logger;

    public ProcessWorkItemActivity(ILogger<ProcessWorkItemActivity> logger)
    {
        _logger = logger;
    }

    public override Task<Dictionary<string, int>> RunAsync(TaskActivityContext context, string workItem)
    {
        _logger.LogInformation("Processing work item: {WorkItem}", workItem);

        // Process the work item (this is where you do the actual work)
        var result = new Dictionary<string, int>
        {
            { workItem, workItem.Length }
        };

        return Task.FromResult(result);
    }
}

import { ActivityContext } from "@microsoft/durabletask-js";

const processWorkItem = async (
  _ctx: ActivityContext,
  item: string
): Promise<number> => {
  console.log(`Processing work item: "${item}"`);
  return item.length;
};

与业务流程协调程序不同，活动可以执行 I/O作，例如 HTTP 调用、数据库查询和文件访问。

from durabletask import task

def process_work_item(ctx: task.ActivityContext, item: int) -> dict:
    """Activity that processes a single work item."""
    # Process the work item (this is where you do the actual work)
    result = item * item
    return {"item": item, "result": result}

此示例适用于 .NET、JavaScript、Java 和 Python。

import java.util.StringTokenizer;

// Activity registration
.addActivity(new TaskActivityFactory() {
    @Override
    public String getName() { return "CountWords"; }

    @Override
    public TaskActivity create() {
        return ctx -> {
            String input = ctx.getInput(String.class);
            StringTokenizer tokenizer = new StringTokenizer(input);
            return tokenizer.countTokens();
        };
    }
})

using Microsoft.DurableTask;
using Microsoft.Extensions.Logging;
using System.Collections.Generic;
using System.Threading.Tasks;

[DurableTask]
public class AggregateResultsActivity : TaskActivity<Dictionary<string, int>[], Dictionary<string, int>>
{
    private readonly ILogger<AggregateResultsActivity> _logger;

    public AggregateResultsActivity(ILogger<AggregateResultsActivity> logger)
    {
        _logger = logger;
    }

    public override Task<Dictionary<string, int>> RunAsync(
        TaskActivityContext context, Dictionary<string, int>[] results)
    {
        _logger.LogInformation("Aggregating {Count} results", results.Length);

        // Combine all results into one aggregated result
        var aggregatedResult = new Dictionary<string, int>();

        foreach (var result in results)
        {
            foreach (var kvp in result)
            {
                aggregatedResult[kvp.Key] = kvp.Value;
            }
        }

        return Task.FromResult(aggregatedResult);
    }
}

import { ActivityContext } from "@microsoft/durabletask-js";

const aggregateResults = async (
  _ctx: ActivityContext,
  results: number[]
): Promise<object> => {
  const total = results.reduce((sum, val) => sum + val, 0);
  return {
    totalItems: results.length,
    sum: total,
    average: results.length > 0 ? total / results.length : 0,
  };
};

与业务流程协调程序不同，活动可以执行 I/O作，例如 HTTP 调用、数据库查询和文件访问。

from durabletask import task

def aggregate_results(ctx: task.ActivityContext, results: list) -> dict:
    """Activity that aggregates results from multiple work items."""
    sum_result = sum(item["result"] for item in results)
    return {
        "total_items": len(results),
        "sum": sum_result,
        "average": sum_result / len(results) if results else 0
    }

此示例适用于 .NET、JavaScript、Java 和 Python。

在Java示例中，业务流程协调程序在ctx.allOf(tasks).await()返回后聚合结果。

// Schedule the orchestration with a list of work items
var workItems = new List<string> { "item1", "item2", "item3", "item4", "item5" };
string instanceId = await client.ScheduleNewOrchestrationInstanceAsync(
    nameof(ParallelProcessingOrchestration), workItems);

// Wait for completion
var result = await client.WaitForInstanceCompletionAsync(instanceId, getInputsAndOutputs: true);
Console.WriteLine($"Result: {result.ReadOutputAs<Dictionary<string, int>>().Count} items processed");

import {
  DurableTaskAzureManagedClientBuilder,
} from "@microsoft/durabletask-js-azuremanaged";

const connectionString =
  process.env.DURABLE_TASK_SCHEDULER_CONNECTION_STRING ||
  "Endpoint=http://localhost:8080;Authentication=None;TaskHub=default";

const client = new DurableTaskAzureManagedClientBuilder()
  .connectionString(connectionString)
  .build();

const workItems = ["item1", "item2", "item3", "item4", "item5"];
const instanceId = await client.scheduleNewOrchestration(fanOutFanInOrchestrator, workItems);
const state = await client.waitForOrchestrationCompletion(instanceId, true, 30);
console.log(`Result: ${state?.serializedOutput}`);

使用指向持久任务计划程序的连接字符串创建 DurableTaskAzureManagedClientBuilder。 使用 scheduleNewOrchestration 启动编排，并使用 waitForOrchestrationCompletion 等待完成。

# Schedule the orchestration with a list of work items
work_items = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
instance_id = client.schedule_new_orchestration(fan_out_fan_in_orchestrator, input=work_items)

# Wait for completion
result = client.wait_for_orchestration_completion(instance_id, timeout=60)
print(f"Result: {result.serialized_output}")

此示例适用于 .NET、JavaScript、Java 和 Python。

import java.time.Duration;
import java.util.Arrays;
import java.util.List;

// Schedule the orchestration with a list of strings
List<String> sentences = Arrays.asList(
    "Hello, world!",
    "The quick brown fox jumps over the lazy dog.",
    "Always remember that you are absolutely unique.");

String instanceId = client.scheduleNewOrchestrationInstance(
    "FanOutFanIn_WordCount",
    new NewOrchestrationInstanceOptions().setInput(sentences));

// Wait for completion
OrchestrationMetadata result = client.waitForInstanceCompletion(instanceId, Duration.ofSeconds(30), true);
System.out.println("Total word count: " + result.readOutputAs(int.class));