Go语言中三种不同md5计算方式的性能比较

func md5sum1(file string) string {
 data, err := ioutil.ReadFile(file)
 if err != nil {
 return ""
 }

 return fmt.Sprintf("%x", md5.Sum(data))
}

var test_path = "/path/to/file"
func BenchmarkMd5Sum1(b *testing.B) {
 for i := 0; i < b.N; i++ {
 md5sum1(test_path)
 }
}

go test -test.run=none -test.bench="^BenchmarkMd5Sum1$" -benchtime=10s -benchmem

BenchmarkMd5Sum1-4 300 43704982 ns/op 19408224 B/op 14 allocs/op
PASS
ok tmp 17.446s

// ReadFile reads the file named by filename and returns the contents.
// A successful call returns err == nil, not err == EOF. Because ReadFile
// reads the whole file, it does not treat an EOF from Read as an error
// to be reported.
func ReadFile(filename string) ([]byte, error) {
 f, err := os.Open(filename)
 if err != nil {
 return nil, err
 }
 defer f.Close()
 // It's a good but not certain bet that FileInfo will tell us exactly how much to
 // read, so let's try it but be prepared for the answer to be wrong.
 var n int64

 if fi, err := f.Stat(); err == nil {
 // Don't preallocate a huge buffer, just in case.
 if size := fi.Size(); size < 1e9 {
 n = size
 }
 }
 // As initial capacity for readAll, use n + a little extra in case Size is zero,
 // and to avoid another allocation after Read has filled the buffer. The readAll
 // call will read into its allocated internal buffer cheaply. If the size was
 // wrong, we'll either waste some space off the end or reallocate as needed, but
 // in the overwhelmingly common case we'll get it just right.
 
 // readAll 第二个参数是即将创建的 buffer 大小
 return readAll(f, n+bytes.MinRead)
}

func readAll(r io.Reader, capacity int64) (b []byte, err error) {
 // 这个 buffer 的大小就是 file size + bytes.MinRead 

 buf := bytes.NewBuffer(make([]byte, 0, capacity))
 // If the buffer overflows, we will get bytes.ErrTooLarge.
 // Return that as an error. Any other panic remains.
 defer func() {
 e := recover()
 if e == nil {
 return
 }
 if panicErr, ok := e.(error); ok && panicErr == bytes.ErrTooLarge {
 err = panicErr
 } else {
 panic(e)
 }
 }()
 _, err = buf.ReadFrom(r)
 return buf.Bytes(), err
}

func md5sum2(file string) string {
 f, err := os.Open(file)
 if err != nil {
 return ""
 }
 defer f.Close()

 h := md5.New()

 _, err = io.Copy(h, f)
 if err != nil {
 return ""
 }

 return fmt.Sprintf("%x", h.Sum(nil))
}

func BenchmarkMd5Sum2(b *testing.B) {

 for i := 0; i < b.N; i++ {
 md5sum2(test_path)
 }
}

$ go test -test.run=none -test.bench="^BenchmarkMd5Sum2$" -benchtime=10s -benchmem

BenchmarkMd5Sum2-4 500 37538305 ns/op 33093 B/op 8 allocs/op
PASS
ok tmp 22.657s

func md5sum3(file string) string {
 f, err := os.Open(file)
 if err != nil {
 return ""
 }
 defer f.Close()
 r := bufio.NewReader(f)

 h := md5.New()

 _, err = io.Copy(h, r)
 if err != nil {
 return ""
 }

 return fmt.Sprintf("%x", h.Sum(nil))

}

func BenchmarkMd5Sum3(b *testing.B) {
 for i := 0; i < b.N; i++ {
 md5sum3(test_path)
 }
}

$ go test -test.run=none -test.bench="^BenchmarkMd5Sum3$" -benchtime=10s -benchmem
BenchmarkMd5Sum3-4 300 42589812 ns/op 4507 B/op 9 allocs/op
PASS
ok tmp 16.817s

func Copy(dst Writer, src Reader) (written int64, err error) {
 return copyBuffer(dst, src, nil)
}

// copyBuffer is the actual implementation of Copy and CopyBuffer.
// if buf is nil, one is allocated.
func copyBuffer(dst Writer, src Reader, buf []byte) (written int64, err error) {
 // If the reader has a WriteTo method, use it to do the copy.
 // Avoids an allocation and a copy.

 // hash.Hash 这个 Writer 并没有实现 WriteTo 方法，所以不会走这里
 if wt, ok := src.(WriterTo); ok {
 return wt.WriteTo(dst)
 }
 // Similarly, if the writer has a ReadFrom method, use it to do the copy.
 // 而 bufio.Reader 实现了 ReadFrom 方法，所以，会走这里
 if rt, ok := dst.(ReaderFrom); ok {
 return rt.ReadFrom(src)
 }
 
 if buf == nil {
 buf = make([]byte, 32*1024)
 }
 for {
 nr, er := src.Read(buf)
 if nr > 0 {
 nw, ew := dst.Write(buf[0:nr])
 if nw > 0 {
 written += int64(nw)
 }
 if ew != nil {
 err = ew
 break
 }
 if nr != nw {
 err = ErrShortWrite
 break
 }
 }
 if er == EOF {
 break
 }
 if er != nil {
 err = er
 break
 }
 }
 return written, err
}

// Md5Sum2 用 CopyBufer 重新实现，buf := make([]byte, 4096)
BenchmarkMd5Sum2-4  500 38484425 ns/op 4409 B/op  8 allocs/op
BenchmarkMd5Sum3-4  500 38671090 ns/op 4505 B/op  9 allocs/op

$ go test -test.run=none -test.bench="." -benchtime=10s -benchmem
testing: warning: no tests to run
BenchmarkMd5Sum1-4  300 42551920 ns/op 19408230 B/op  14 allocs/op
BenchmarkMd5Sum2-4  500 38445352 ns/op 33089 B/op  8 allocs/op
BenchmarkMd5Sum3-4  500 38809429 ns/op 4505 B/op  9 allocs/op
PASS
ok tmp 63.821s