如何高效利用多个Goroutine实现大文件的高速读写？

package main

import (
    "bufio"
    "fmt"
    "io"
    "log"
    "os"
    "runtime"
    "sync"
)

const (
    chunkSize = 10 * 1024 * 1024 // 10MB chunk
)

func main() {
    // 获取CPU核心数，作为Goroutine数量的参考
    numCPU := runtime.NumCPU()
    numGoroutines := numCPU * 2 //  根据实际情况调整

    srcFile, err := os.Open("F:/src.txt")
    if err != nil {
        log.Fatal(err)
    }
    defer srcFile.Close()

    dstFile, err := os.OpenFile("F:/dst.txt", os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0666)
    if err != nil {
        log.Fatal(err)
    }
    defer dstFile.Close()

    fileInfo, err := srcFile.Stat()
    if err != nil {
        log.Fatal(err)
    }
    fileSize := fileInfo.Size()

    var wg sync.WaitGroup
    chunkChan := make(chan []byte, numGoroutines) // Buffered channel

    // 读取文件
    for i := 0; i < numGoroutines; i++ {
        wg.Add(1)
        go func() {
            defer wg.Done()
            for chunk := range chunkChan {
                // 处理chunk
                _, err := dstFile.Write(chunk)
                if err != nil {
                    log.Fatal(err)
                }
            }
        }()
    }

    // 将文件分割成块，发送到channel
    buffer := make([]byte, chunkSize)
    for {
        n, err := srcFile.Read(buffer)
        if n > 0 {
            chunkChan <- buffer[:n]
        }
        if err == io.EOF {
            break
        }
        if err != nil {
            log.Fatal(err)
        }
    }
    close(chunkChan)
    wg.Wait()
}