OC中类的结构探索之cache

2021-06-28  本文已影响0人  Eli_app

在前面的文章里面我们已经探索过类的结构《OC中类的结构探索》本篇文章我们重点分析一下cache

cache的结构

我们先看下cache的源码结构,本次继续使用objc4-818.2,下面代码精简一下

typedef unsigned long           uintptr_t; //8
#if __LP64__
typedef uint32_t mask_t;  // x86_64 & arm64 asm are less efficient with 16-bits
#else
typedef uint16_t mask_t;
#endif
struct cache_t {
private:
    explicit_atomic<uintptr_t> _bucketsAndMaybeMask;//8
    union {
        struct {
            explicit_atomic<mask_t>    _maybeMask;  //4
#if __LP64__
            uint16_t                   _flags;      //2
#endif
            uint16_t                   _occupied;   //2
        };
        explicit_atomic<preopt_cache_t *> _originalPreoptCache;//8(结构体指针)
    };
   
    /*
     #if defined(__arm64__) && __LP64__
     #if TARGET_OS_OSX || TARGET_OS_SIMULATOR
     // __arm64__的模拟器
     #define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_HIGH_16_BIG_ADDRS
     #else
     //__arm64__的真机
     #define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_HIGH_16
     #endif
     #elif defined(__arm64__) && !__LP64__
     //32位 真机
     #define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_LOW_4
     #else
     //macOS 模拟器
     #define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_OUTLINED
     #endif
     ******  中间是不同的架构之间的判断 主要是用来不同类型 mask 和 buckets 的掩码
    */
    
    public:
    void incrementOccupied();
    void setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask);
    void reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld);
    unsigned capacity() const;
    struct bucket_t *buckets() const;
    Class cls() const;
    void insert(SEL sel, IMP imp, id receiver);
    //省略。。。
 
};

我们在源码里面发现有bucket_t还有insert()方法。跟进去看一下insert()的实现,也有bucket_t我们猜测cache里面存储的内容,实际上就是在bucket_t里面存储。我们先看下bucket_t的源码实现

struct bucket_t {

private:

#if __arm64__

  explicit_atomic<uintptr_t> _imp;

  explicit_atomic<SEL> _sel;

#else

  explicit_atomic<SEL> _sel;

  explicit_atomic<uintptr_t> _imp;

#endif

}

这个一看我们太熟悉了,里面就是selimp,我们用lldb动态调试一下,看看能不能打印出我们想要的内容

(lldb) x/4gx ELPerson.class

0x100008258: 0x0000000100008230 0x0000000100357140

0x100008268: 0x000000010034f390 0x0000802c00000000

(lldb) p (cache_t \*)0x100008268   //0x100008258+0x16=0x100008268内存偏移

(cache_t *) $1 = 0x0000000100008268

(lldb) p *$1

(cache_t) $2 = {

 _bucketsAndMaybeMask = {

  std::__1::atomic<unsigned long> = {

   Value = 4298437520

  }

 }

  = {

   = {

   _maybeMask = {

    std::__1::atomic<unsigned int> = {

     Value = 0

    }

   }

   _flags = 32812

   _occupied = 0     

  }

  _originalPreoptCache = {

   std::__1::atomic<preopt_cache_t *> = {

    Value = 0x0000802c00000000

   }
  }

 }

}

可以看到_maybeMask_occupied的值都是0,我们调用一下方法,看看是不是会有变化

p [per sayNB]
2021-06-24 17:31:51.447839+0800 KCObjcBuild[79832:1703897] NB
(lldb) p *$1
(cache_t) $3 = {
  _bucketsAndMaybeMask = {
    std::__1::atomic<unsigned long> = {
      Value = 4311894672
    }
  }
   = {
     = {
      _maybeMask = {
        std::__1::atomic<unsigned int> = {
          Value = 7
        }
      }
      _flags = 32812
      _occupied = 1
    }
    _originalPreoptCache = {
      std::__1::atomic<preopt_cache_t *> = {
        Value = 0x0001802c00000007
      }
    }
  }
}
(lldb) p $3->buckets()
(bucket_t *) $4 = 0x0000000101024a90
  Fix-it applied, fixed expression was: 
    $3.buckets()
(lldb) p *$4
(bucket_t) $5 = {
  _sel = {
    std::__1::atomic<objc_selector *> = "" {
      Value = ""
    }
  }
  _imp = {
    std::__1::atomic<unsigned long> = {
      Value = 48968
    }
  }
}
(lldb) p $5.sel()
(SEL) $6 = "sayNB"
(lldb) p $5.imp(nil,ELPerson.class)
(IMP) $7 = 0x0000000100003d10 (KCObjcBuild`-[ELPerson sayNB])

我们发现方法被调用之后_maybeMask_occupied都有值了,并且我们打印出来了缓存的方法。

cache_t::insert(SEL sel, IMP imp, id receiver)

1、获取已缓存的容量并且+1,第一次为0

2、获取缓存容量,不存在时,需要先开辟容量,第一次开辟1<<2=4。将bucket_t *首地址存入_bucketsAndMaybeMask,将newCapacity - 1mask存入_maybeMask_occupied设置为0。

3、容量情况判断,当容量用完3/4或者7/8时(具体分架构),需要按照2倍的大小扩容。扩容过程开辟新的容量,同时回收旧的容量。

3.1、这个容量是因为负载因子问题,超过这个限制的时候,哈希冲突将会大大增加

3.2、扩容时要清除旧的容量,开辟新的容量。第一、已经开辟出来的内存无法更改,所以不是原内存简单的增加。第二、旧的内存里面的东西如果全部移动到新的内存中耗费性能,并且旧的内存中被调用过的方法,继续调用的概率比较低,全部移动到新内存不划算。如果再次调用,会再新的内存中缓存的。

4、通过哈希算法查找存储的位置,do...while循环查找,没有就存,不能存再哈希,一直找下去。最后不成功,调用bad_cache

4.1在arm64中cache_next会向前插入i ? i-1 : mask,其他架构中,向后插入(i+1) & mask

void cache_t::insert(SEL sel, IMP imp, id receiver)

{


  mask_t newOccupied = occupied() + 1; // 1+1

  unsigned oldCapacity = capacity(), capacity = oldCapacity;

  if (slowpath(isConstantEmptyCache())) {//第一次进来为空

    if (!capacity) capacity = INIT_CACHE_SIZE;//capacity = 1 << 2 = 4

   reallocate(oldCapacity, capacity, /* freeOld */false);

  }

  else if (fastpath(newOccupied + CACHE_END_MARKER <= cache_fill_ratio(capacity))) {

    // 不超过3/4或者7/8,正常使用。用哪个分架构

  }

\#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 {// 超过3/4或者7/8,会2倍扩容

    capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;

    if (capacity > MAX_CACHE_SIZE) {

     capacity = MAX_CACHE_SIZE;

    }
    // 重新开辟一块capacity * sizeof(bucket_t)大小的内存空间,
    // 将`bucket_t *`首地址存入`_bucketsAndMaybeMask`,
    // 将`newCapacity - 1`的`mask`存入`_maybeMask`,
    // _occupied设置为0,回收旧内存

    reallocate(oldCapacity, capacity, true);

  }


 //创建bucket_t
  bucket_t *b = buckets();

  mask_t m = capacity - 1; // 4-1=3
 //哈希算法,存储
  mask_t begin = cache_hash(sel, m);

  mask_t i = begin;


  do {
 //找到为空的地方插入,do...while循环查找
    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));
 //无论如何都找不到,就bad_cache()
  bad_cache(receiver, (SEL)sel);

#endif // !DEBUG_TASK_THREADS

}

cache流程图:

image
上一篇下一篇

猜你喜欢

热点阅读