Redis 设计与实现（第四章） -- 字典dict 概述

Hash表结构
typedef struct dictht {
    dictEntry **table;  //哈希表数组
    unsigned long size;  //hash表大小
    unsigned long sizemask;  //hash表大小掩码，总是等于size-1，用于计算哈希索引
    unsigned long used;  //已使用大小
} dictht;

typedef struct dictEntry {
    void *key;  //键
    union {  //值
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next;  //指向下个哈希表节点，形成链表（在hash冲突时使用）
} dictEntry;

typedef struct dict {
    dictType *type;  //类型特定函数
    void *privdata;  //私有数据
    dictht ht[2];  //hash表
    long rehashidx; /* rehashing not in progress if rehashidx == -1 */
    int iterators; /* number of iterators currently running */
} dict;

/* Add an element to the target hash table */
int dictAdd(dict *d, void *key, void *val)
{
    dictEntry *entry = dictAddRaw(d,key);  //添加一个哈希节点

    if (!entry) return DICT_ERR;
    dictSetVal(d, entry, val);  //设置value
    return DICT_OK;
}

/* Low level add. This function adds the entry but instead of setting
 * a value returns the dictEntry structure to the user, that will make
 * sure to fill the value field as he wishes.
 *
 * This function is also directly exposed to the user API to be called
 * mainly in order to store non-pointers inside the hash value, example:
 *
 * entry = dictAddRaw(dict,mykey);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * Return values:
 *
 * If key already exists NULL is returned.
 * If key was added, the hash entry is returned to be manipulated by the caller.
 */
dictEntry *dictAddRaw(dict *d, void *key)
{
    int index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);  //如果正则rehash，进行rehash操作

    /* Get the index of the new element, or -1 if
     * the element already exists. */
    if ((index = _dictKeyIndex(d, key)) == -1)  //如果存在，则返回
        return NULL;

    /* Allocate the memory and store the new entry */
    ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0]; //正在rehash，取ht[1]，ht为ht[0]，也验证了上面问题3的答案。
    entry = zmalloc(sizeof(*entry));  //分配内存空间
    entry->next = ht->table[index];  //新元素加入头节点
    ht->table[index] = entry;
    ht->used++;

    /* Set the hash entry fields. */
    dictSetKey(d, entry, key);  //设置key
    return entry;
}

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

    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);
        while(d->ht[0].table[d->rehashidx] == NULL) {
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        de = d->ht[0].table[d->rehashidx]; //正则rehash的哈希节点
        /* Move all the keys in this bucket from the old to the new hash HT */
        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; //新hash表中的索引值
            de->next = d->ht[1].table[h];  //插入
            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) { //ht[0]中的used为0，说明rehash完成了
        zfree(d->ht[0].table);  //释放ht[0]
        d->ht[0] = d->ht[1];  //ht[1]变为ht[0]
        _dictReset(&d->ht[1]);  //重置ht[1]
        d->rehashidx = -1;
        return 0;
    }

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

/* Expand or create the hash table */
int dictExpand(dict *d, unsigned long size)
{
    dictht n; /* the new hash table */
    unsigned long realsize = _dictNextPower(size);  //为ht[1]计算分配的空间大小

    /* the size is invalid if it is smaller than the number of
     * elements already inside the hash table */
    if (dictIsRehashing(d) || d->ht[0].used > size)
        return DICT_ERR;

    /* Rehashing to the same table size is not useful. */
    if (realsize == d->ht[0].size) return DICT_ERR;

    /* Allocate the new hash table and initialize all pointers to NULL */
    n.size = realsize; //新的哈希表大小
    n.sizemask = realsize-1;
    n.table = zcalloc(realsize*sizeof(dictEntry*));
    n.used = 0;

    /* Is this the first initialization? If so it's not really a rehashing
     * we just set the first hash table so that it can accept keys. */
    if (d->ht[0].table == NULL) {  //第一次加入元素时，创建hash表
        d->ht[0] = n;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    d->ht[1] = n; //rehash，将新的hash表赋值给ht[1]
    d->rehashidx = 0;
    return DICT_OK;
}

/* Our hash table capability is a power of two */
static unsigned long _dictNextPower(unsigned long size)
{
    unsigned long i = DICT_HT_INITIAL_SIZE;

    if (size >= LONG_MAX) return LONG_MAX;
    while(1) {   
        if (i >= size)  //size为第一个大于等于size的2的幂次方
            return i;
        i *= 2;
    }
}