Golang slice 通过growslice调用nextslicecap计算扩容

本文链接：https://blog.csdn.net/lucifer_qiao/article/details/132987088

先来看一段代码

code:	
    e := []int64{1, 2, 3}
	fmt.Println("cap of e before:", cap(e))
	e = append(e, 4, 5, 6, 7)
	fmt.Println("cap of e after:", cap(e))

output:

cap of e before: 3
cap of e after: 8

为什么容量是8？

append了的4个元素，如果是原来的2倍也才6个，小于长度7，所以容量赋值长度7

内存分配，为了高效使用需要对齐，找到合适的span对象

capmem = roundupsize(uintptr(newcap) * ptrSize) ptrSize 8字节

capmem = roundupsize(7*8)

capmem = 64

newcap = int(capmem / ptrSize)

newcap = 8

	_MaxSmallSize   = 32768
	smallSizeDiv    = 8
	smallSizeMax    = 1024
	largeSizeDiv    = 128
	_NumSizeClasses = 68
	_PageShift      = 13
	maxObjsPerSpan  = 1024
)

var class_to_size = [_NumSizeClasses]uint16{0, 8, 16, 24, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256, 288, 320, 352, 384, 416, 448, 480, 512, 576, 640, 704, 768, 896, 1024, 1152, 1280, 1408, 1536, 1792, 2048, 2304, 2688, 3072, 3200, 3456, 4096, 4864, 5376, 6144, 6528, 6784, 6912, 8192, 9472, 9728, 10240, 10880, 12288, 13568, 14336, 16384, 18432, 19072, 20480, 21760, 24576, 27264, 28672, 32768}
var class_to_allocnpages = [_NumSizeClasses]uint8{0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 1, 2, 1, 3, 2, 3, 1, 3, 2, 3, 4, 5, 6, 1, 7, 6, 5, 4, 3, 5, 7, 2, 9, 7, 5, 8, 3, 10, 7, 4}
var class_to_divmagic = [_NumSizeClasses]uint32{0, ^uint32(0)/8 + 1, ^uint32(0)/16 + 1, ^uint32(0)/24 + 1, ^uint32(0)/32 + 1, ^uint32(0)/48 + 1, ^uint32(0)/64 + 1, ^uint32(0)/80 + 1, ^uint32(0)/96 + 1, ^uint32(0)/112 + 1, ^uint32(0)/128 + 1, ^uint32(0)/144 + 1, ^uint32(0)/160 + 1, ^uint32(0)/176 + 1, ^uint32(0)/192 + 1, ^uint32(0)/208 + 1, ^uint32(0)/224 + 1, ^uint32(0)/240 + 1, ^uint32(0)/256 + 1, ^uint32(0)/288 + 1, ^uint32(0)/320 + 1, ^uint32(0)/352 + 1, ^uint32(0)/384 + 1, ^uint32(0)/416 + 1, ^uint32(0)/448 + 1, ^uint32(0)/480 + 1, ^uint32(0)/512 + 1, ^uint32(0)/576 + 1, ^uint32(0)/640 + 1, ^uint32(0)/704 + 1, ^uint32(0)/768 + 1, ^uint32(0)/896 + 1, ^uint32(0)/1024 + 1, ^uint32(0)/1152 + 1, ^uint32(0)/1280 + 1, ^uint32(0)/1408 + 1, ^uint32(0)/1536 + 1, ^uint32(0)/1792 + 1, ^uint32(0)/2048 + 1, ^uint32(0)/2304 + 1, ^uint32(0)/2688 + 1, ^uint32(0)/3072 + 1, ^uint32(0)/3200 + 1, ^uint32(0)/3456 + 1, ^uint32(0)/4096 + 1, ^uint32(0)/4864 + 1, ^uint32(0)/5376 + 1, ^uint32(0)/6144 + 1, ^uint32(0)/6528 + 1, ^uint32(0)/6784 + 1, ^uint32(0)/6912 + 1, ^uint32(0)/8192 + 1, ^uint32(0)/9472 + 1, ^uint32(0)/9728 + 1, ^uint32(0)/10240 + 1, ^uint32(0)/10880 + 1, ^uint32(0)/12288 + 1, ^uint32(0)/13568 + 1, ^uint32(0)/14336 + 1, ^uint32(0)/16384 + 1, ^uint32(0)/18432 + 1, ^uint32(0)/19072 + 1, ^uint32(0)/20480 + 1, ^uint32(0)/21760 + 1, ^uint32(0)/24576 + 1, ^uint32(0)/27264 + 1, ^uint32(0)/28672 + 1, ^uint32(0)/32768 + 1}
var size_to_class8 = [smallSizeMax/smallSizeDiv + 1]uint8{0, 1, 2, 3, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14, 15, 15, 16, 16, 17, 17, 18, 18, 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 23, 23, 23, 23, 24, 24, 24, 24, 25, 25, 25, 25, 26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27, 27, 28, 28, 28, 28, 28, 28, 28, 28, 29, 29, 29, 29, 29, 29, 29, 29, 30, 30, 30, 30, 30, 30, 30, 30, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32}
var size_to_class128 = [(_MaxSmallSize-smallSizeMax)/largeSizeDiv + 1]uint8{32, 33, 34, 35, 36, 37, 37, 38, 38, 39, 39, 40, 40, 40, 41, 41, 41, 42, 43, 43, 44, 44, 44, 44, 44, 45, 45, 45, 45, 45, 45, 46, 46, 46, 46, 47, 47, 47, 47, 47, 47, 48, 48, 48, 49, 49, 50, 51, 51, 51, 51, 51, 51, 51, 51, 51, 51, 52, 52, 52, 52, 52, 52, 52, 52, 52, 52, 53, 53, 54, 54, 54, 54, 55, 55, 55, 55, 55, 56, 56, 56, 56, 56, 56, 56, 56, 56, 56, 56, 57, 57, 57, 57, 57, 57, 57, 57, 57, 57, 58, 58, 58, 58, 58, 58, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 61, 61, 61, 61, 61, 62, 62, 62, 62, 62, 62, 62, 62, 62, 62, 62, 63, 63, 63, 63, 63, 63, 63, 63, 63, 63, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 66, 66, 66, 66, 66, 66, 66, 66, 66, 66, 66, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67}

func divRoundUp(n, a uintptr) uintptr {
	// a is generally a power of two. This will get inlined and
	// the compiler will optimize the division.
	return (n + a - 1) / a
}

func roundupsize(size uintptr) uintptr {
 if size < _MaxSmallSize {
  if size <= smallSizeMax-8 {
   return uintptr(class_to_size[size_to_class8[divRoundUp(size, smallSizeDiv)]])
  } else {
   return uintptr(class_to_size[size_to_class128[divRoundUp(size-smallSizeMax, largeSizeDiv)]])
  }
 }
 if size+_PageSize < size {
  return size
 }
 return alignUp(size, _PageSize)
}

计算容量

< 256 容量*2,反之

容量 += 容量+3*256 >> 2 (二进制中右移n位，相当于除以2的n次方_

举例512扩容

512 += (512 + 256 * 3)>>2

cap = 512 + 320 = 832

func nextslicecap(newLen, oldCap int) int {
	newcap := oldCap
	doublecap := newcap + newcap
	if newLen > doublecap {
		return newLen
	}

	const threshold = 256
	if oldCap < threshold {
		return doublecap
	}
	for {
		// Transition from growing 2x for small slices
		// to growing 1.25x for large slices. This formula
		// gives a smooth-ish transition between the two.
		newcap += (newcap + 3*threshold) >> 2

		// We need to check `newcap >= newLen` and whether `newcap` overflowed.
		// newLen is guaranteed to be larger than zero, hence
		// when newcap overflows then `uint(newcap) > uint(newLen)`.
		// This allows to check for both with the same comparison.
		if uint(newcap) >= uint(newLen) {
			break
		}
	}

	// Set newcap to the requested cap when
	// the newcap calculation overflowed.
	if newcap <= 0 {
		return newLen
	}
	return newcap
}


func growslice(oldPtr unsafe.Pointer, newLen, oldCap, num int, et *_type) slice {
    ...

	newcap := nextslicecap(newLen, oldCap)

	var overflow bool
	var lenmem, newlenmem, capmem uintptr
	// Specialize for common values of et.Size.
	// For 1 we don't need any division/multiplication.
	// For goarch.PtrSize, compiler will optimize division/multiplication into a shift by a constant.
	// For powers of 2, use a variable shift.
	switch {
	case et.Size_ == 1:
		lenmem = uintptr(oldLen)
		newlenmem = uintptr(newLen)
		capmem = roundupsize(uintptr(newcap))
		overflow = uintptr(newcap) > maxAlloc
		newcap = int(capmem)
	case et.Size_ == goarch.PtrSize:
		lenmem = uintptr(oldLen) * goarch.PtrSize
		newlenmem = uintptr(newLen) * goarch.PtrSize
		capmem = roundupsize(uintptr(newcap) * goarch.PtrSize)
		overflow = uintptr(newcap) > maxAlloc/goarch.PtrSize
		newcap = int(capmem / goarch.PtrSize)
	case isPowerOfTwo(et.Size_):
		var shift uintptr
		if goarch.PtrSize == 8 {
			// Mask shift for better code generation.
			shift = uintptr(sys.TrailingZeros64(uint64(et.Size_))) & 63
		} else {
			shift = uintptr(sys.TrailingZeros32(uint32(et.Size_))) & 31
		}
		lenmem = uintptr(oldLen) << shift
		newlenmem = uintptr(newLen) << shift
		capmem = roundupsize(uintptr(newcap) << shift)
		overflow = uintptr(newcap) > (maxAlloc >> shift)
		newcap = int(capmem >> shift)
		capmem = uintptr(newcap) << shift
	default:
		lenmem = uintptr(oldLen) * et.Size_
		newlenmem = uintptr(newLen) * et.Size_
		capmem, overflow = math.MulUintptr(et.Size_, uintptr(newcap))
		capmem = roundupsize(capmem)
		newcap = int(capmem / et.Size_)
		capmem = uintptr(newcap) * et.Size_
	}

...
	memmove(p, oldPtr, lenmem)

	return slice{p, newLen, newcap}
}