cache数据结构
我们先从objc源码查看一下，由于结构体里面内容太多，看一下简化版
struct cache_t {
private:
explicit_atomic<uintptr_t> _bucketsAndMaybeMask;
union {
struct {
explicit_atomic<mask_t> _maybeMask;
#if __LP64__
uint16_t _flags;
#endif
uint16_t _occupied;
};
explicit_atomic<preopt_cache_t *> _originalPreoptCache;
};
struct bucket_t *buckets() const;
void insert(SEL sel, IMP imp, id receiver);
...
}
1.cache_t里面保存了两个成员，_bucketsAndMaybeMask 和一个联合体，这两个成员都占有8字节，所有cache_t总共16字节，其他都是方法和常量
-
_bucketsAndMaybeMask，实际上是一块内存地址的首地址，这块内存存储的是方法的sel和imp，这个存储的结构式bucket_t。通过这个属性的名字其实我们不难看出有两层意思，一个是bucket，一个是mask（掩码）
mask:用于在哈希算法或者哈希冲突算法中哈希下标 _maybeMask = capacity -1
void cache_t::setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask)
{
uintptr_t buckets = (uintptr_t)newBuckets;
uintptr_t mask = (uintptr_t)newMask;
ASSERT(buckets <= bucketsMask);
ASSERT(mask <= maxMask);
_bucketsAndMaybeMask.store(((uintptr_t)newMask << maskShift) | (uintptr_t)newBuckets, memory_order_relaxed);
_occupied = 0;
}
static constexpr uintptr_t maskShift = 48;
为了节省空间，其中 mask 占用高16位，buckets占用48位
-
_occupied当前缓存占用的数量
void cache_t::insert(SEL sel, IMP imp, id receiver){
do {
if (fastpath(b[i].sel() == 0)) {
incrementOccupied();
b[i].set<Atomic, Encoded>(b, sel, imp, cls());
return;
}
if (b[i].sel() == sel) {
// 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 在整个类中结构
图一.png
lldb验证
验证代码：
@interface QHPerson : NSObject
- (void)say1;
- (void)say2;
+ (void)sayHello;
@end
int main(int argc, const char * argv[]) {
@autoreleasepool {
//0x00007ffffffffff8
QHPerson *p = [[QHPerson alloc] init];
NSLog(@"%p",p);
}
return 0;
}
类地址偏移16字节拿到cache_t地址：
地址偏移.png
尝试获取：
尝试获取.png
最后通过查找cache_t源码发现有一个buckets的方法：
buckets.png
调用
[p say1]方法，让后重新打印，发现occpued 和maskmaybe 又远了 1->2 3->7
数量变化.png
通过
bucket_t里面的sel(),获取方法编号imp()获取方法实现：
截屏2021-06-24 下午4.51.30.png
cache_t insert 流程分析
我们上面分析了如何获从cache_t获取方法，但是需要先插入，源码分析
第一步：如果缓存里面为空，先分配4个容量大小的空间，调用reallocate
if (slowpath(isConstantEmptyCache())) {
// Cache is read-only. Replace it.
if (!capacity) capacity = INIT_CACHE_SIZE;
reallocate(oldCapacity, capacity, /* freeOld */false);
}
调用reallocate->setBucketsAndMask
void cache_t::setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask)
{
...
//初始化bucketsAndMaybeMask的值
_bucketsAndMaybeMask.store((uintptr_t)newBuckets, memory_order_relaxed);
_maybeMask.store(newMask, memory_order_relaxed);
_occupied = 0;
}
跳出reallocate，继续往下有一个判断
else if (fastpath(newOccupied + CACHE_END_MARKER <= cache_fill_ratio(capacity))) {
// Cache is less than 3/4 or 7/8 full. Use it as-is.
}
#if CACHE_ALLOW_FULL_UTILIZATION
else if (capacity <= FULL_UTILIZATION_CACHE_SIZE && newOccupied + CACHE_END_MARKER <= capacity) {
// Allow 100% cache utilization for small buckets. Use it as-is.
}
#endif
else {
capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;
if (capacity > MAX_CACHE_SIZE) {
capacity = MAX_CACHE_SIZE;
}
reallocate(oldCapacity, capacity, true);
}
大致意思就是Occupied >0.75*capacity, 就会进行扩容，清理掉之前数据，从新分配 reallocate(oldCapacity, capacity, true)
继续下走：
bucket_t *b = buckets();
mask_t m = capacity - 1;
mask_t begin = cache_hash(sel, m);
mask_t i = begin;
do {
if (fastpath(b[i].sel() == 0)) {
incrementOccupied();
b[i].set<Atomic, Encoded>(b, sel, imp, cls());
return;
}
if (b[i].sel() == sel) {
// 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));
先通过hash算法，得到一个索引。然后通过这个索引找方法，如果不存在就保存，并且occupied+1，如果有hash冲突，重新计算。直到成功。
下面附上一张cache流程图：
cache_流程图.png
网友评论