c# - 测试显示 "await"明显更慢，即使等待的对象已经完成

Question

我想通过使用 await/async 来测试程序的开销。

为了对此进行测试，我编写了以下测试类:

public class Entity : INotifyCompletion {
    private Action continuation;
    private int i;

    public void OnCompleted(Action continuation) {
        this.continuation = continuation;
    }

    public Entity GetAwaiter() {
        return this;
    }

    public Entity GetResult() {
        return this;
    }

    public bool IsCompleted { get { return true; } }

    public void Execute() {
        if (i > 0) Console.WriteLine("What");
    }
}

然后我写了一个测试工具。测试工具通过 TestA 和 TestB 迭代 1600 次，仅测量后者 1500 次(以允许 JIT“预热”)。 set 是 Entity 对象的集合(但实现无关)。该集合中有 50,000 个实体。测试工具使用 Stopwatch 类进行测试。

private static void DoTestA() {
    Entity[] objects = set.GetElements();
    Parallel.For(0, objects.Length, async i => {
        Entity e = objects[i];
        if (e == null) return;

        (await e).Execute();
    });
}

private static void DoTestB() {
    Entity[] objects = set.GetElements();
    Parallel.For(0, objects.Length, i => {
        Entity e = objects[i];
        if (e == null) return;

        e.Execute();
    });
}

这两个例程是相同的，除了一个在调用 Execute() 之前等待实体(Execute() 没有做任何有用的事情，它只是一些愚蠢的代码来确保处理器真的在为每个实体)。

---

在针对 AnyCPU 的release 模式下执行我的测试后，我得到以下输出:

>>> 1500 repetitions >>> IN NANOSECONDS (1000ns = 0.001ms)
Method   Avg.         Min.         Max.         Jitter       Total
A        1,301,465ns  1,232,200ns  2,869,000ns  1,567,534ns  ! 1952.199ms
B        130,053ns    116,000ns    711,200ns    581,146ns    ! 195.081ms

如您所见，带有 await 的方法大约慢了 10 倍。

事实是，据我所知，没有什么可等待的 - GetResult 始终为真。这是否意味着即使等待的“事物”已经准备好，状态机也会执行？

如果是这样，有什么办法解决这个问题吗？我想使用 async/await 的语义，但这种开销对我的应用程序来说太高了......

---

编辑:请求后添加完整的基准测试代码:

程序.cs

using System;
using System.Collections.Concurrent;
using System.Collections.Generic;
using System.Collections.Specialized;
using System.Diagnostics;
using System.Linq;
using System.Reflection;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
using System.Text;
using System.Threading;
using System.Threading.Tasks;

namespace CSharpPerfTest {
    public class Entity : INotifyCompletion {
        private Action continuation;
        private int i;

        public void OnCompleted(Action continuation) {
            this.continuation = continuation;
        }

        public Entity GetAwaiter() {
            return this;
        }

        public Entity GetResult() {
            return this;
        }

        public bool IsCompleted { get { return true; } }

        public void Execute() {
            if (i > 0) Console.WriteLine("What");
        }
    }

    static class Program {
        static ConcurrentSet<Entity> set;
        const int MAX_ELEMENTS = 50000;

        // Called once before all testing begins
        private static void OnceBefore() {
            set = new ConcurrentSet<Entity>();

            Parallel.For(0, MAX_ELEMENTS, i => {
                set.Add(new Entity());
            });
        }

        // Called twice each repetition, once before DoTestA and once before DoTestB
        private static void PreTest() {

        }

        private static void DoTestA() {
            Entity[] objects = set.GetElements();
            Parallel.For(0, objects.Length, async i => {
                Entity e = objects[i];
                if (e == null) return;
                (await e).Execute();
            });
        }

        private static void DoTestB() {
            Entity[] objects = set.GetElements();
            Parallel.For(0, objects.Length, i => {
                Entity e = objects[i];
                if (e == null) return;
                e.Execute();
            });
        }

        private const int REPETITIONS = 1500;
        private const int JIT_WARMUPS = 10;

        #region Test Harness
        private static double[] aTimes = new double[REPETITIONS];
        private static double[] bTimes = new double[REPETITIONS];

        private static void Main(string[] args) {
            Stopwatch stopwatch = new Stopwatch();

            OnceBefore();

            for (int i = JIT_WARMUPS * -1; i < REPETITIONS; ++i) {
                Console.WriteLine("Starting repetition " + i);

                PreTest();
                stopwatch.Restart();
                DoTestA();
                stopwatch.Stop();
                if (i >= 0) aTimes[i] = stopwatch.Elapsed.TotalMilliseconds;

                PreTest();
                stopwatch.Restart();
                DoTestB();
                stopwatch.Stop();
                if (i >= 0) bTimes[i] = stopwatch.Elapsed.TotalMilliseconds;
            }

            DisplayScores();
        }

        private static void DisplayScores() {
            Console.WriteLine();
            Console.WriteLine();

            bool inNanos = false;
            if (aTimes.Average() < 10 || bTimes.Average() < 10) {
                inNanos = true;
                for (int i = 0; i < aTimes.Length; ++i) aTimes[i] *= 1000000;
                for (int i = 0; i < bTimes.Length; ++i) bTimes[i] *= 1000000;
            }

            Console.WriteLine(">>> " + REPETITIONS + " repetitions >>> " + (inNanos ? "IN NANOSECONDS (1000ns = 0.001ms)" : "IN MILLISECONDS (1000ms = 1s)"));
            Console.WriteLine("Method   Avg.         Min.         Max.         Jitter       Total");

            Console.WriteLine(
            "A        "
            + (String.Format("{0:N0}", (long) aTimes.Average()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) aTimes.Min()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) aTimes.Max()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) Math.Max(aTimes.Average() - aTimes.Min(), aTimes.Max() - aTimes.Average())) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + ((long) aTimes.Sum() >= 10000 && inNanos ? "! " + String.Format("{0:f3}", aTimes.Sum() / 1000000) + "ms" : (long) aTimes.Sum() + (inNanos ? "ns" : "ms"))
            );
            Console.WriteLine(
            "B        "
            + (String.Format("{0:N0}", (long) bTimes.Average()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) bTimes.Min()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) bTimes.Max()) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + (String.Format("{0:N0}", (long) Math.Max(bTimes.Average() - bTimes.Min(), bTimes.Max() - bTimes.Average())) + (inNanos ? "ns" : "ms")).PadRight(13, ' ')
            + ((long) bTimes.Sum() >= 10000 && inNanos ? "! " + String.Format("{0:f3}", bTimes.Sum() / 1000000) + "ms" : (long) bTimes.Sum() + (inNanos ? "ns" : "ms"))
            );

            Console.ReadKey();
        }
        #endregion

    }
}

Answer 1

如果你的函数has a response time that 1ms for 50,000 calls is considered significant您不应该等待该代码，而应该同步运行它。

使用异步代码的开销很小，它必须为内部驱动它的状态机添加一个函数调用。如果与运行状态机的开销成本相比，您进行异步的工作也很小，那么您应该编写需要重新考虑代码是否应该异步的代码。