Go并发编程：select与default陷阱及调度器行为分析

package main

import (
    "fmt"
    "os"
    "time" // Added for demonstration of busy-waiting
)

type Fetcher interface {
    Fetch(url string) (body string, urls []string, err error)
}

func crawl(todo Todo, fetcher Fetcher,
    todoList chan Todo, done chan bool) {
    body, urls, err := fetcher.Fetch(todo.url)
    if err != nil {
        fmt.Println(err)
    } else {
        fmt.Printf("found: %s %q\n", todo.url, body)
        for _, u := range urls {
            todoList <- Todo{u, todo.depth - 1}
        }
    }
    done <- true // 发送完成信号
    return
}

type Todo struct {
    url   string
    depth int
}

func Crawl(url string, depth int, fetcher Fetcher) {
    visited := make(map[string]bool)
    doneCrawling := make(chan bool, 100) // 缓冲通道，用于接收爬取完成信号
    toDoList := make(chan Todo, 100)     // 缓冲通道，用于发送待爬取任务
    toDoList <- Todo{url, depth}         // 初始任务

    crawling := 0 // 正在进行的爬取任务计数器
    for {
        select {
        case todo := <-toDoList: // 接收待爬取任务
            if todo.depth > 0 && !visited[todo.url] {
                crawling++
                visited[todo.url] = true
                go crawl(todo, fetcher, toDoList, doneCrawling)
            }
        case <-doneCrawling: // 接收爬取完成信号
            crawling--
        default: // 无其他通道操作时执行
            if os.Args[1] == "ok" {
                fmt.Print("") // 关键差异点
            }
            if crawling == 0 { // 所有任务完成
                goto END
            }
            // time.Sleep(time.Millisecond) // 可用于缓解忙等待，但不是根本解决方案
        }
    }
END:
    return
}

func main() {
    // 模拟的Fetcher实现
    var fetcher = &fakeFetcher{
        "http://golang.org/": &fakeResult{
            "The Go Programming Language",
            []string{"http://golang.org/pkg/", "http://golang.org/cmd/"},
        },
        "http://golang.org/pkg/": &fakeResult{
            "Packages",
            []string{"http://golang.org/", "http://golang.org/cmd/", "http://golang.org/pkg/fmt/", "http://golang.org/pkg/os/"},
        },
        "http://golang.org/pkg/fmt/": &fakeResult{
            "Package fmt",
            []string{"http://golang.org/", "http://golang.org/pkg/"},
        },
        "http://golang.org/pkg/os/": &fakeResult{
            "Package os",
            []string{"http://golang.org/", "http://golang.org/pkg/"},
        },
    }
    Crawl("http://golang.org/", 4, fetcher)
    fmt.Println("Crawling finished.")
}

type fakeFetcher map[string]*fakeResult
type fakeResult struct {
    body string
    urls []string
}

func (f *fakeFetcher) Fetch(url string) (string, []string, error) {
    if res, ok := (*f)[url]; ok {
        return res.body, res.urls, nil
    }
    return "", nil, fmt.Errorf("not found: %s", url)
}

func Crawl(url string, depth int, fetcher Fetcher) {
    visited := make(map[string]bool)
    doneCrawling := make(chan bool, 100)
    toDoList := make(chan Todo, 100)
    toDoList <- Todo{url, depth}

    crawling := 0
    for {
        select {
        case todo := <-toDoList:
            if todo.depth > 0 && !visited[todo.url] {
                crawling++
                visited[todo.url] = true
                go crawl(todo, fetcher, toDoList, doneCrawling)
            }
        case <-doneCrawling:
            crawling--
        }
        // 将终止条件检查移到select外部
        if crawling == 0 {
            break // 退出循环
        }
    }
    fmt.Println("所有爬取任务已完成。") // 确认退出
    return
}