多个Web请求的最佳多线程方法

Question

我想创建一个程序来抓取并检查我的网站是否存在http错误和其他内容.我想用多个线程来做这件事,这些线程应该接受像抓取的url这样的参数.虽然我希望X线程处于活动状态,但是已经有Y任务等待执行.

现在我想知道执行此操作的最佳策略是什么:ThreadPool,Tasks,Threads甚至是其他什么？

Answer 1

这是一个示例,显示如何排队一堆任务但限制同时运行的数量.它使用a Queue来跟踪准备运行的任务,并使用a Dictionary来跟踪正在运行的任务.当任务完成时,它会调用一个回调方法来从中删除自己Dictionary.一种async方法是使用空间可用来启动排队的任务.

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

namespace MinimalTaskDemo
{
    class Program
    {
        private static readonly Queue<Task> WaitingTasks = new Queue<Task>();
        private static readonly Dictionary<int, Task> RunningTasks = new Dictionary<int, Task>();
        public static int MaxRunningTasks = 100; // vary this to dynamically throttle launching new tasks 

        static void Main(string[] args)
        {
            var tokenSource = new CancellationTokenSource();
            var token = tokenSource.Token;
            Worker.Done = new Worker.DoneDelegate(WorkerDone);
            for (int i = 0; i < 1000; i++)  // queue some tasks
            {
                // task state (i) will be our key for RunningTasks
                WaitingTasks.Enqueue(new Task(id => new Worker().DoWork((int)id, token), i, token));
            }
            LaunchTasks();
            Console.ReadKey();
            if (RunningTasks.Count > 0)
            {
                lock (WaitingTasks) WaitingTasks.Clear();
                tokenSource.Cancel();
                Console.ReadKey();
            }
        }

        static async void LaunchTasks()
        {
            // keep checking until we're done
            while ((WaitingTasks.Count > 0) || (RunningTasks.Count > 0))
            {
                // launch tasks when there's room
                while ((WaitingTasks.Count > 0) && (RunningTasks.Count < MaxRunningTasks))
                {
                    Task task = WaitingTasks.Dequeue();
                    lock (RunningTasks) RunningTasks.Add((int)task.AsyncState, task);
                    task.Start();
                }
                UpdateConsole();
                await Task.Delay(300); // wait before checking again
            }
            UpdateConsole();    // all done
        }

        static void UpdateConsole()
        {
            Console.Write(string.Format("\rwaiting: {0,3:##0}  running: {1,3:##0} ", WaitingTasks.Count, RunningTasks.Count));
        }

        // callback from finished worker
        static void WorkerDone(int id)
        {
            lock (RunningTasks) RunningTasks.Remove(id);
        }
    }

    internal class Worker
    {
        public delegate void DoneDelegate(int taskId);
        public static DoneDelegate Done { private get; set; }
        private static readonly Random Rnd = new Random();

        public async void DoWork(object id, CancellationToken token)
        {
            for (int i = 0; i < Rnd.Next(20); i++)
            {
                if (token.IsCancellationRequested) break;
                await Task.Delay(100);  // simulate work
            }
            Done((int)id);
        }
    }
}