前言
在前面几篇文章中 我们分别探索了
objc_class中的isa,superClass,bits. 现在我们来看看 cache_t 中到底有什么作用
一 . cache_t 的结构
在这段类结构代码中，我们可以看到 类结构中存在一个cache_t
struct objc_class : objc_object {
// Class ISA;
Class superclass;
cache_t cache; // formerly cache pointer and vtable
class_data_bits_t bits; // class_rw_t * plus custom rr/alloc flags
class_rw_t *data() const {
return bits.data();
}
void setData(class_rw_t *newData) {
bits.setData(newData);
}
... 省略
}
下面是部分cache_t的结构
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_OUTLINED // macOS 模拟器
explicit_atomic _buckets;
explicit_atomic _mask;
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16 // 64 位真机
explicit_atomic _maskAndBuckets;
mask_t _mask_unused;
// How much the mask is shifted by.
static constexpr uintptr_t maskShift = 48;
// Additional bits after the mask which must be zero. msgSend
// takes advantage of these additional bits to construct the value
// `mask << 4` from `_maskAndBuckets` in a single instruction.
static constexpr uintptr_t maskZeroBits = 4;
// The largest mask value we can store. 可以存储的最大掩码值 2^16-1
static constexpr uintptr_t maxMask = ((uintptr_t)1 << (64 - maskShift)) - 1;
// The mask applied to `_maskAndBuckets` to retrieve the buckets pointer.
static constexpr uintptr_t bucketsMask = ((uintptr_t)1 << (maskShift - maskZeroBits)) - 1;
// Ensure we have enough bits for the buckets pointer.
static_assert(bucketsMask >= MACH_VM_MAX_ADDRESS, "Bucket field doesn't have enough bits for arbitrary pointers.");
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4 // 非64位真机
// _maskAndBuckets stores the mask shift in the low 4 bits, and
// the buckets pointer in the remainder of the value. The mask
// shift is the value where (0xffff >> shift) produces the correct
// mask. This is equal to 16 - log2(cache_size).
explicit_atomic _maskAndBuckets;
mask_t _mask_unused;
static constexpr uintptr_t maskBits = 4;
static constexpr uintptr_t maskMask = (1 << maskBits) - 1;
static constexpr uintptr_t bucketsMask = ~maskMask;
#else
#error Unknown cache mask storage type.
#endif
#if __LP64__
uint16_t _flags;
#endif
uint16_t _occupied;
由于 主要我们实在 Mac 上调试， 所以最终的 cache_t 的结构 具有四个参数
explicit_atomic _buckets; // 存储方法的 hash 表
explicit_atomic _mask; // 算法使用的掩码
uint16_t _occupied; // hash 表中占用的数量
其中主要是看 bucket_t 的结构
我们可以看到 真机和 模拟器的区别就是。 imp 和 sel 的顺序问题
看注释我们可以知道 这样调整顺序是在相应的架构下 有更好的优化
struct bucket_t {
private:
// IMP-first is better for arm64e ptrauth and no worse for arm64.
// SEL-first is better for armv7* and i386 and x86_64.
#if __arm64__ // 真机
explicit_atomic _imp; // 函数指针，指向方法的具体实现
explicit_atomic _sel; // 方法编号
#else // 模拟器
explicit_atomic _sel;
explicit_atomic _imp;
#endif
// Compute the ptrauth signing modifier from &_imp, newSel, and cls.
uintptr_t modifierForSEL(SEL newSel, Class cls) const {
return (uintptr_t)&_imp ^ (uintptr_t)newSel ^ (uintptr_t)cls;
}
// Sign newImp, with &_imp, newSel, and cls as modifiers.
uintptr_t encodeImp(IMP newImp, SEL newSel, Class cls) const {
if (!newImp) return 0;
#if CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_PTRAUTH
return (uintptr_t)
ptrauth_auth_and_resign(newImp,
ptrauth_key_function_pointer, 0,
ptrauth_key_process_dependent_code,
modifierForSEL(newSel, cls));
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_ISA_XOR
return (uintptr_t)newImp ^ (uintptr_t)cls;
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_NONE
return (uintptr_t)newImp;
#else
#error Unknown method cache IMP encoding.
#endif
}
二. cache_t 方法缓存的添加
- LLDB 调试准备 我们先建立一个测试类，其中添加一些实例方法
eg.
- (void)logCup;
- (void)logPen;
- (void)logKeyboard;
- (void)logMouse;
int main(int argc, const char * argv[]) {
@autoreleasepool {
// insert code here...
TObject *t = [TObject alloc];
NSLog(@"%p", t);
[t logCup];
[t logPen];
[t logMouse];
[t logKeyboard];
}
return 0;
}
- 我们在初始化之前先下个断点 进行
lldb调试 ,由下面的调试我们可以知道 缓存 内都是空的，并没有任何方法的痕迹
(lldb) p/x TObject.class // 获取 class 类对象地址
(Class) $0 = 0x0000000100002318 TObject
(lldb) p (cache_t*)0x0000000100002328 // 通过地址偏移16字节，强转 cache_t 类型
(cache_t *) $1 = 0x0000000100002328
(lldb) p *$1
(cache_t) $2 = {
_buckets = {
std::__1::atomic = 0x000000010032d420 {
_sel = {
std::__1::atomic = (null)
}
_imp = {
std::__1::atomic = 0
}
}
}
_mask = {
std::__1::atomic = 0
}
_flags = 32804
_occupied = 0
}
- 接下来 我们在调用
alloc之后下一个断点 继续调试
我们可以看到_buckets缓存数据发生了改变
(lldb) p/x t.class
(Class) $6 = 0x0000000100002318 TObject
(lldb) p (cache_t*) 0x0000000100002328
(cache_t *) $7 = 0x0000000100002328
(lldb) p *$7
(cache_t) $8 = {
_buckets = {
std::__1::atomic = 0x0000000101004bf0 {
_sel = {
std::__1::atomic = ""
}
_imp = {
std::__1::atomic = 3274184
}
}
}
_mask = {
std::__1::atomic = 3
}
_flags = 32804
_occupied = 2
}
(lldb)
- 我们在每个方法都打个断点,当调用完第一个方法之后我们进行调试， 我们看到
_occupied又变成1了，那这到底做了什么呢？
2020-12-21 23:54:11.872707+0800 Objc_m [2835:50950] -[TObject logCup]
(lldb) p *$1
(cache_t) $3 = {
_buckets = {
std::__1::atomic = 0x00000001007117a0 {
_sel = {
std::__1::atomic = (null)
}
_imp = {
std::__1::atomic = 0
}
}
}
_mask = {
std::__1::atomic = 7
}
_flags = 32804
_occupied = 1
}
- 我们在第二个方法调用完下个断点，继续调试,我们可以看到
_occupied又加了1
2020-12-21 23:56:51.210222+0800 Objc_m[2835:50950] -[TObject logPen]
(lldb) p *$1
(cache_t) $4 = {
_buckets = {
std::__1::atomic = 0x00000001007117a0 {
_sel = {
std::__1::atomic = (null)
}
_imp = {
std::__1::atomic = 0
}
}
}
_mask = {
std::__1::atomic = 7
}
_flags = 32804
_occupied = 2
}
- 我们在第三个方法调用完下个断点，继续调试,我们可以看到
_occupied又加了1， 这是我们可以猜测_occupied和方法的个数有关
2020-12-21 23:59:32.413929+0800 Objc_m[2835:50950] -[TObject logMouse]
(lldb) p *$1
(cache_t) $5 = {
_buckets = {
std::__1::atomic = 0x00000001007117a0 {
_sel = {
std::__1::atomic = ""
}
_imp = {
std::__1::atomic = 12264
}
}
}
_mask = {
std::__1::atomic = 7
}
_flags = 32804
_occupied = 3
}
此时我们就可以通过 源码进行调试，搜索_occupied,观察其变化，也就有了下面的代码
void cache_t::incrementOccupied()
{
_occupied++;
}
void cache_t::insert(Class cls, SEL sel, IMP imp, id receiver)
{
#if CONFIG_USE_CACHE_LOCK
cacheUpdateLock.assertLocked();
#else
runtimeLock.assertLocked();
#endif
ASSERT(sel != 0 && cls->isInitialized());
// Use the cache as-is if it is less than 3/4 full
mask_t newOccupied = occupied() + 1;
unsigned oldCapacity = capacity(), capacity = oldCapacity;
if (slowpath(isConstantEmptyCache())) {
// Cache is read-only. Replace it.
// 假如之前没有分配过缓存空间的，分配一个初始容量为4的空间，并在其中将_occupied置为0
// INIT_CACHE_SIZE 1<<2
if (!capacity) capacity = INIT_CACHE_SIZE;
reallocate(oldCapacity, capacity, /* freeOld */false);
}
else if (fastpath(newOccupied + CACHE_END_MARKER <= capacity / 4 * 3)) {
// Cache is less than 3/4 full. Use it as-is.
// 缓存不超过3/4就会维持缓存空间不变
}
else {
// 缓存超过3/4则分配一个容量为当前两倍的新空间
capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;
// MAX_CACHE_SIZE 1<<16
if (capacity > MAX_CACHE_SIZE) {
capacity = MAX_CACHE_SIZE;
}
reallocate(oldCapacity, capacity, true);
}
bucket_t *b = buckets();
mask_t m = capacity - 1;
mask_t begin = cache_hash(sel, m); // 通过掩码获取方法的缓存的次序
mask_t i = begin;
// Scan for the first unused slot and insert there.
// There is guaranteed to be an empty slot because the
// minimum size is 4 and we resized at 3/4 full.
// 最小是4，当充满3/4 就会 重新分配
do {
if (fastpath(b[i].sel() == 0)) {
incrementOccupied(); // 自增 _occupied
b[i].set(sel, imp, cls); // 方法写入缓存
return;
}
if (b[i].sel() == sel) { // 已经加入了缓存
// The entry was added to the cache by some other thread
// before we grabbed the cacheUpdateLock.
return;
}
} while (fastpath((i = cache_next(i, m)) != begin));
cache_t::bad_cache(receiver, (SEL)sel, cls);
}
void cache_fill(Class cls, SEL sel, IMP imp, id receiver)
{
runtimeLock.assertLocked();
#if !DEBUG_TASK_THREADS
// Never cache before +initialize is done
if (cls->isInitialized()) {
cache_t *cache = getCache(cls);
#if CONFIG_USE_CACHE_LOCK
mutex_locker_t lock(cacheUpdateLock);
#endif
cache->insert(cls, sel, imp, receiver);
}
#else
_collecting_in_critical();
#endif
}
我们下断点 观察一下 alloc 到底做了什么
可以看到 调用了 alloc 方法, 接着 开辟了4 字节的空间，接着调用 return 方法，添加引用技术，所以 _occupied 变成了2
image.png
image.png
通过断点 我们发现 之前 的 2 都是针对于 NSObject 类对象产生的
而之后的方法的 Tobject 调用方法 使用的是 Tobject 的类对象中的 cache_t
三. 总结
- OC 中的实例方法混存在类中，类方法缓存在元类上
- 缓存最小是4字节，缓存充满 3/4时，会扩容至当前的2倍
- 扩容并不是在原来的基础上添加，而是重新开辟新的
allocateBuckets，释放旧的cache_collect_free,把最近一次临界的imp和key缓存进来，经典的LRU算法。