• 1.字典相關的幾個結構體

 dict由hash table存儲key-value， hash table數組每一個元素存放dictEntry鏈接的鏈表頭結點，dictEntry節點存放key-value

typedef struct dictEntry {
    void *key;
    union {
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next;
} dictEntry;

typedef struct
 
 dictht {
    dictEntry **table;  // 指向dictEntry數組的指針
    unsigned long size; //哈希表table的大小，初始化大小為4
    unsigned long sizemask;  // size - 1 ,用來對hash值求與計算獲得index
    unsigned long used;   // 已經賦值了的數量
} dictht;

typedef struct dict {
    dictType *type; // 方法
    void *privdata;  // 保存key和value
    dictht ht[2];   //
 
  hash table
    long rehashidx; // 如果rehashidx=-1表示沒有進行rehash,如果如果rehashidx>-1，則表示正在進行rehash,搬運的位置是rehashidx
    int iterators; /* number of iterators currently running */
} dict;

• 2.動態擴容方法 int dictRehash(dict *d, int n)

　　　為了對dictht進行動態擴容，rehash方法將ht[0]中的值搬n個到ht[1]中， 分批次進行搬運，直到ht[0]中的值都搬到ht[1]上，再將ht[1]指針交給ht[0]，rehashidx=-1，完成此次rehash過程

int dictRehash(dict *d, int n) {
    int empty_visits = n * 10; /* Max number of empty buckets to visit. */
    if (!dictIsRehashing(d)) return 0;

    // 從ht[0]中搬n個鏈表到ht[1]中
    while (n-- && d->ht[0].used != 0) {
        dictEntry *de, *nextde;

        /* Note that rehashidx can‘t overflow as we are sure there are more
         * elements because ht[0].used != 0 */
        assert(d->ht[0].size > (unsigned long) d->rehashidx);
        // 通過rehashidx可以接著從上一次搬完的位置開始搬
        while (d->ht[0].table[d->rehashidx] == NULL) {
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        de = d->ht[0].table[d->rehashidx];
        /* Move all the keys in this bucket from the old to the new hash HT */

        // 把ht[0]上的一個鏈表搬到ht[1]上
        while (de) {
            unsigned int h;

            nextde = de->next;
            /* Get the index in the new hash table */
            h = dictHashKey(d, de->key) & d->ht[1].sizemask;
            de->next = d->ht[1].table[h];
            d->ht[1].table[h] = de;
            d->ht[0].used--;
            d->ht[1].used++;
            de = nextde;
        }
        d->ht[0].table[d->rehashidx] = NULL;
        d->rehashidx++;
    }

    /* Check if we already rehashed the whole table... */
    if (d->ht[0].used == 0) {
        zfree(d->ht[0].table);
        d->ht[0] = d->ht[1];
        _dictReset(&d->ht[1]);
        d->rehashidx = -1;
        return 0;
    }

    /* More to rehash... */
    return 1;
}

• 3.使用到的幾個hash算法

  1. 針對int的hash函數

      unsigned int dictIntHashFunction(unsigned int key) {
           key += ~(key << 15);
           key ^= (key >> 10);
           key += (key << 3);
           key ^= (key >> 6);
           key += ~(key << 11);
           key ^= (key >> 16);
           return key;
       }

  2. MurmurHash2算法

       unsigned int dictGenHashFunction(const void *key, int len) {
           /* ‘m‘ and ‘r‘ are mixing constants generated offline.
            They‘re not really ‘magic‘, they just happen to work well.  */
           uint32_t seed = dict_hash_function_seed;
           const uint32_t m = 0x5bd1e995;
           const int r = 24;
     
           /* Initialize the hash to a ‘random‘ value */
           uint32_t h = seed ^len;
     
           /* Mix 4 bytes at a time into the hash */
           const unsigned char *data = (const unsigned char *) key;
     
           // 長度大於等於4的情況
           while (len >= 4) {
               uint32_t k = *(uint32_t *) data;   // 4*8=32, 取4個字節當作uint32
     
               k *= m;
               k ^= k >> r;
               k *= m;
     
               h *= m;
               h ^= k;
     
               data += 4;
               len -= 4;
           }
     
           /* Handle the last few bytes of the input array  */
           // 剩下的長度小於4
           switch (len) {
               case 3:
                   h ^= data[2] << 16;
               case 2:
                   h ^= data[1] << 8;
               case 1:
                   h ^= data[0];
                   h *= m;
           };
     
           /* Do a few final mixes of the hash to ensure the last few
            * bytes are well-incorporated. */
           h ^= h >> 13;
           h *= m;
           h ^= h >> 15;
     
           return (unsigned int) h;
       }

  3. djb hash算法

  unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len) {

      unsigned int hash = (unsigned int) dict_hash_function_seed;
      while (len--)
          hash = ((hash << 5) + hash) + (tolower(*buf++)); /* hash * 33 + c */
      return hash;
  } 　　

細節前往

    (https://github.com/fangwendong/redis-learning/tree/master/struct/dict)

redis源碼學習-dict