美文网首页
iOS类结构:cache_t分析

iOS类结构:cache_t分析

作者: 奉灬孝 | 来源:发表于2020-09-18 00:49 被阅读0次

    一、cache_t 内部结构分析

    1.1iOS类的结构分析中,我们已经分析过类(Class)的本质是一个结构体 ,结构体内部结构如下 :

    typedef struct objc_class *Class;
    typedef struct objc_object *id;
    
    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();
        }
        ...
    }
    
    • Class ISA :指向关联类 , 继承自 objc_object 。 参考 isa底层结构分析
    • Class superclass:父类指针 , 同样参考上述文章中有详细指向探索。
    • cache_t cache , 方法缓存存储数据结构。
    • class_data_bits_t bits , bit 中存储了属性,方法等类的源数据。

    1.2iOS类的结构分析中,我们已经分析过 cache_t 结构体,分为以下四个部分:

    struct cache_t {
        struct bucket_t * _buckets; // 缓存数组,即哈希桶
        mask_t _mask; // 缓存数组的容量临界值,实际上是为了 capacity 服务
        uint16_t _flags; // 位置标记
        uint16_t _occupied; // 缓存数组中已缓存方法数量
        ...省略
    }
    
    • _buckets:是 bucket_t 结构体的数组,bucket_t 是用来存放方法编号 SEL 和函数指针 IMP 的。
    struct bucket_t {
        explicit_atomic<uintptr_t> _imp;
        explicit_atomic<SEL> _sel;
    }
    
    • _mask: mask_t m = capacity - 1; (capacity = MAX_CACHE_SIZE;),用作掩码。因为这里缓存 Cache 的容量 Size 一直是2倍扩容的,所以 MAX_CACHE_SIZE 是2的整数次幂,所以 mask 的二进制位 000011, 000111, 001111 )刚好可以用作 Hash取余数的掩码。刚好保证相与后不超过缓存大小。
    capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;  // 扩容至两倍
    
    • _flags: 位置标记
    • _occupied是当前已缓存的方法数量。即数组中已使用了多少位置。

    二、方法缓存原理探索

    源码如下:

    @interface LGPerson : NSObject
    
    - (void)sayHello;
    
    - (void)sayCode;
    
    - (void)sayMaster;
    
    - (void)sayNB;
    
    + (void)sayHappy;
    
    @end
    #import "LGPerson.h"
    
    @implementation LGPerson
    - (void)sayHello{
        NSLog(@"LGPerson say : %s",__func__);
    }
    
    - (void)sayCode{
        NSLog(@"LGPerson say : %s",__func__);
    }
    
    - (void)sayMaster{
        NSLog(@"LGPerson say : %s",__func__);
    }
    
    - (void)sayNB{
        NSLog(@"LGPerson say : %s",__func__);
    }
    
    + (void)sayHappy{
        NSLog(@"LGPerson say : %s",__func__);
    }
    @end
    
    #import <Foundation/Foundation.h>
    #import "LGPerson.h"
    #import <objc/runtime.h>
    
    
    // cache_t
    int main(int argc, const char * argv[]) {
        @autoreleasepool {
            // insert code here...
            LGPerson *p  = [LGPerson alloc];
            Class pClass = [LGPerson class];
    
            [p sayHello];
            [p sayCode];
            [p sayMaster];
            [p sayNB];
    
            NSLog(@"%@",pClass);
        }
        return 0;
    }
    

    2.1 我们再sayHello方法前设置断点,LLDB调试 其中的 cache_t 的数据

    因为在类结构体中 cache_t 前面有 Class ISA指针Class superclass 父类指针 ,所以要偏移16位。

    (lldb) p/x pClass
    (Class) $0 = 0x00000001000022a0 LGPerson
    (lldb) p (cache_t *)0x00000001000022b0
    (cache_t *) $1 = 0x00000001000022b0
    (lldb) p *$1
    (cache_t) $2 = {
      _buckets = {
        std::__1::atomic<bucket_t *> = 0x000000010032e420 {
          _sel = {
            std::__1::atomic<objc_selector *> = (null)
          }
          _imp = {
            std::__1::atomic<unsigned long> = 0
          }
        }
      }
      _mask = {
        std::__1::atomic<unsigned int> = 0
      }
      _flags = 32804
      _occupied = 0
    }
    

    2.2 然后执行一步 sayHello 方法,再次进行 LLDB调试 ,查看 cache_t 的数据

    2020-09-17 22:37:33.187060+0800 KCObjc[34953:549295] LGPerson say : -[LGPerson sayHello]
    (lldb) p *$1
    (cache_t) $3 = {
      _buckets = {
        std::__1::atomic<bucket_t *> = 0x00000001006ad5f0 {
          _sel = {
            std::__1::atomic<objc_selector *> = ""
          }
          _imp = {
            std::__1::atomic<unsigned long> = 11936
          }
        }
      }
      _mask = {
        std::__1::atomic<unsigned int> = 3
      }
      _flags = 32804
      _occupied = 1
    }
    

    2.3 走到这里,大家应该发现 _buckets_mask_occupied 的变化了。其中_occupied 从0变为1,也证明了执行完 sayHello 方法 之后,缓存方法数量 + 1 。接下来我们查看一下哈希桶 _buckets 的变化,哈希桶数据类型 struct bucket_t 我们点进去查看如下:

    struct bucket_t {
    public:
        inline SEL sel() const { return _sel.load(memory_order::memory_order_relaxed); }
    
        inline IMP imp(Class cls) const {
            uintptr_t imp = _imp.load(memory_order::memory_order_relaxed);
            if (!imp) return nil;
    #if CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_PTRAUTH
            SEL sel = _sel.load(memory_order::memory_order_relaxed);
            return (IMP)
                ptrauth_auth_and_resign((const void *)imp,
                                        ptrauth_key_process_dependent_code,
                                        modifierForSEL(sel, cls),
                                        ptrauth_key_function_pointer, 0);
    #elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_ISA_XOR
            return (IMP)(imp ^ (uintptr_t)cls);
    #elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_NONE
            return (IMP)imp;
    #else
    #error Unknown method cache IMP encoding.
    #endif
        }
    }
    

    我们就可以查看 _bucketsSELIMP 信息。

    (lldb) p $3.buckets()
    (bucket_t *) $4 = 0x00000001006ad5f0
    (lldb) p *$4
    (bucket_t) $5 = {
      _sel = {
        std::__1::atomic<objc_selector *> = ""
      }
      _imp = {
        std::__1::atomic<unsigned long> = 11936
      }
    }
    (lldb) p $5.sel()
    (SEL) $6 = "sayHello"
    (lldb) p $5.imp(pClass)
    (IMP) $7 = 0x0000000100000c00 (KCObjc`-[LGPerson sayHello])
    

    然后我们也可以打开 MachOView 查看一下 sayHello 方法的 IMP 指针

    MachOView
    与我们 LLDB调试 结果不谋而合,完美~

    2.4 接下来我们继续执行 sayMaster 方法sayNB 方法 ,进行 LLDB调试 ,查看 cache_t 的数据

    2020-09-17 23:12:37.095330+0800 KCObjc[34953:549295] LGPerson say : -[LGPerson sayCode]
    (lldb) p *$1
    (cache_t) $8 = {
      _buckets = {
        std::__1::atomic<bucket_t *> = 0x00000001006ad5f0 {
          _sel = {
            std::__1::atomic<objc_selector *> = ""
          }
          _imp = {
            std::__1::atomic<unsigned long> = 11936
          }
        }
      }
      _mask = {
        std::__1::atomic<unsigned int> = 3
      }
      _flags = 32804
      _occupied = 2
    }
    2020-09-17 23:12:59.163825+0800 KCObjc[34953:549295] LGPerson say : -[LGPerson sayMaster]
    (lldb) p *$1
    (cache_t) $9 = {
      _buckets = {
        std::__1::atomic<bucket_t *> = 0x0000000103b4c7d0 {
          _sel = {
            std::__1::atomic<objc_selector *> = (null)
          }
          _imp = {
            std::__1::atomic<unsigned long> = 0
          }
        }
      }
      _mask = {
        std::__1::atomic<unsigned int> = 7
      }
      _flags = 32804
      _occupied = 1
    }
    

    走到这里,我们发现:
    问题①. _occupied 由 2 变为了 1 ,缓存方法数量 _occupied 为什么会减少呢?
    问题②. _mask 由 3 变为了 7 ,至于 _mask 的变化,大家可以能想到,前面我们讲过, _mask 是受缓存容量 CACHE SIZE 2 倍扩容的影响。缓存容量 CACHE SIZE 由 4 变为了 8 。
    问题③. _buckets 里面的 SELIMP 消失了。

    2.5 接下来,我们来一探究竟。在 void incrementOccupied(); 方法中我们看到了 _occupied++;

    void cache_t::incrementOccupied() 
    {
        _occupied++;
    }
    

    2.6 然后我们在源码中找一下,什么地方执行了 incrementOccupied(); 这个方法。惊喜来了,cache_t::insert() 方法中执行了 incrementOccupied(); 这个方法。从名称我们就可以发现,这是向缓存插入的方法。

    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.
            if (!capacity) capacity = INIT_CACHE_SIZE;
            reallocate(oldCapacity, capacity, /* freeOld */false);
        }
        else if (fastpath(newOccupied + CACHE_END_MARKER <= capacity / 4 * 3)) { // 4  3 + 1 bucket cache_t
            // Cache is less than 3/4 full. Use it as-is.
        }
        else {
            capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;  // 扩容两倍 4
            if (capacity > MAX_CACHE_SIZE) {
                capacity = MAX_CACHE_SIZE;
            }
            reallocate(oldCapacity, capacity, true);  // 内存 库容完毕
        }
    
        bucket_t *b = buckets();
        mask_t m = capacity - 1;
        mask_t begin = cache_hash(sel, m);
        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.
        do {
            if (fastpath(b[i].sel() == 0)) {
                incrementOccupied();
                b[i].set<Atomic, Encoded>(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::bad_cache(receiver, (SEL)sel, cls);
    }
    

    2.6.1 接下来我们分析一下这个小概率事件 -> 初始化方法:
    如果缓存为空,则开辟缓存 INIT_CACHE_SIZE :4。然后利用 reallocate() 方法 开辟空间。

    enum {
        INIT_CACHE_SIZE_LOG2 = 2,
        INIT_CACHE_SIZE      = (1 << INIT_CACHE_SIZE_LOG2),
        MAX_CACHE_SIZE_LOG2  = 16,
        MAX_CACHE_SIZE       = (1 << MAX_CACHE_SIZE_LOG2),
    };
    
    if (slowpath(isConstantEmptyCache())) { // 小概率事件 -> 初始化方法
        // Cache is read-only. Replace it.
        if (!capacity) capacity = INIT_CACHE_SIZE; // 4 (枚举定义:1 左移 2 位)
        reallocate(oldCapacity, capacity, /* freeOld */false);
    }
    

    reallocate() 方法

    1. 申请 newCapacity 大小的地址
    2. 调用 setBucketsAndMask() 方法 初始化 bucket
    void cache_t::reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld)
    {
        bucket_t *oldBuckets = buckets();
        bucket_t *newBuckets = allocateBuckets(newCapacity);
    
        // Cache's old contents are not propagated. 
        // This is thought to save cache memory at the cost of extra cache fills.
        // fixme re-measure this
    
        ASSERT(newCapacity > 0);
        ASSERT((uintptr_t)(mask_t)(newCapacity-1) == newCapacity-1);
    
        setBucketsAndMask(newBuckets, newCapacity - 1);
        
        if (freeOld) {
            cache_collect_free(oldBuckets, oldCapacity);
        }
    }
    

    setBucketsAndMask() 方法

    1. 旧bucket 存入 新bucket
    2. _occupied = 0,这里我们留意到了 reallocate() 方法 会将 _occupied = 0
    void cache_t::setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask)
    {
        // objc_msgSend uses mask and buckets with no locks.
        // It is safe for objc_msgSend to see new buckets but old mask.
        // (It will get a cache miss but not overrun the buckets' bounds).
        // It is unsafe for objc_msgSend to see old buckets and new mask.
        // Therefore we write new buckets, wait a lot, then write new mask.
        // objc_msgSend reads mask first, then buckets.
    
    #ifdef __arm__
        // ensure other threads see buckets contents before buckets pointer
        mega_barrier();
    
        _buckets.store(newBuckets, memory_order::memory_order_relaxed);
        
        // ensure other threads see new buckets before new mask
        mega_barrier();
        
        _mask.store(newMask, memory_order::memory_order_relaxed);
        _occupied = 0;
    #elif __x86_64__ || i386
        // ensure other threads see buckets contents before buckets pointer
        _buckets.store(newBuckets, memory_order::memory_order_release);
        
        // ensure other threads see new buckets before new mask
        _mask.store(newMask, memory_order::memory_order_release);
        _occupied = 0;
    #else
    #error Don't know how to do setBucketsAndMask on this architecture.
    #endif
    }
    

    2.6.2 接下来就是大概率事件方法

    如果缓存 newOccupied + CACHE_END_MARKER(1) < capacity / 4 * 3,则什么都不需要做。

    #define CACHE_END_MARKER 1
    
    else if (fastpath(newOccupied + CACHE_END_MARKER <= capacity / 4 * 3)) { // 4  3 + 1 bucket cache_t
        // Cache is less than 3/4 full. Use it as-is.
    }
    

    2.6.3 接下来就是扩容方法

    • 如果大于总容量的 3 / 4 的时候,就需要扩容了(扩容至2倍)。
    • 扩容之后仍然需要利用 reallocate() 方法 开辟空间,在 2.6.1
      setBucketsAndMask() 方法 中我们讲过, reallocate() 方法 会将 _occupied = 0。到这,我们终于理解了2.4 当中的 问题② ,为什么 _occupied 会减少,因为扩容之后 _occupied 会初始化至 0,重新计算。
    else {
        capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;  // 扩容至两倍 4
        if (capacity > MAX_CACHE_SIZE) {
            capacity = MAX_CACHE_SIZE;
        }
        reallocate(oldCapacity, capacity, true);  // 内存 扩容完毕
    }
    

    2.6.4 reallocate() 方法

    • 调用 setBucketsAndMask() 方法 初始化 bucket ,因为 bucket 受扩容影响重新初始化了,所以2.4 当中的 问题③ 的原因就在这里。
    void cache_t::reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld)
    {
        bucket_t *oldBuckets = buckets();
        bucket_t *newBuckets = allocateBuckets(newCapacity);
    
        // Cache's old contents are not propagated. 
        // This is thought to save cache memory at the cost of extra cache fills.
        // fixme re-measure this
    
        ASSERT(newCapacity > 0);
        ASSERT((uintptr_t)(mask_t)(newCapacity-1) == newCapacity-1);
    
        setBucketsAndMask(newBuckets, newCapacity - 1);
        
        if (freeOld) {
            cache_collect_free(oldBuckets, oldCapacity);
        }
    }
    

    2.6.5 接下来就是 _mask 变化的方法,在2.6.3 中我们知道容量扩容到 2 倍,那么 mask 的值就是 2 的 n次幂 - 1 , 所以 2.4 当中的 问题① 便迎刃而解了。

    mask_t m = capacity - 1;
    

    相关文章

      网友评论

          本文标题:iOS类结构:cache_t分析

          本文链接:https://www.haomeiwen.com/subject/hykryktx.html