redis源码浅析-hash表实现

在redis中，除了前面说的ziplist和quicklist，还有hash结构，redis实现hash表也是基于拉链法来实现。而其对key进行hash是根据siphash算法来实现的。

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

typedef struct dictType {
    uint64_t (*hashFunction)(const void *key);
    void *(*keyDup)(void *privdata, const void *key);
    void *(*valDup)(void *privdata, const void *obj);
    int (*keyCompare)(void *privdata, const void *key1, const void *key2);
    void (*keyDestructor)(void *privdata, void *key);
    void (*valDestructor)(void *privdata, void *obj);
    int (*expandAllowed)(size_t moreMem, double usedRatio);
} dictType;

/* This is our hash table structure. Every dictionary has two of this as we
 * implement incremental rehashing, for the old to the new table. */
typedef struct dictht {
    dictEntry **table;
    unsigned long size;
    unsigned long sizemask;
    unsigned long used;
} dictht;

typedef struct dict {
    dictType *type;
    void *privdata;
    dictht ht[2];
    long rehashidx; /* rehashing not in progress if rehashidx == -1 */
    int16_t pauserehash; /* If >0 rehashing is paused (<0 indicates coding error) */
} dict;

上面的截个结构体是redis中hash表底层的几个结构。
hash表在初始创建的时候，就是建了一个空的dict ，在添加元素的时候，去进行实际节点的新增。

dict *dictCreate(dictType *type,
        void *privDataPtr)
{
    dict *d = zmalloc(sizeof(*d));

    _dictInit(d,type,privDataPtr);
    return d;
}

/* Initialize the hash table */
int _dictInit(dict *d, dictType *type,
        void *privDataPtr)
{
    _dictReset(&d->ht[0]);
    _dictReset(&d->ht[1]);
    d->type = type;
    d->privdata = privDataPtr;
    d->rehashidx = -1;
    d->pauserehash = 0;
    return DICT_OK;
}

通过dictAdd向hash表中添加元素

int dictAdd(dict *d, void *key, void *val)
{
    dictEntry *entry = dictAddRaw(d,key,NULL);

    if (!entry) return DICT_ERR;
    dictSetVal(d, entry, val);
    return DICT_OK;
}
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    long index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);

    /* Get the index of the new element, or -1 if
     * the element already exists. */
    if ((index = _dictKeyIndex(d, key, dictHashKey(d,key), existing)) == -1)
        return NULL;

    /* Allocate the memory and store the new entry.
     * Insert the element in top, with the assumption that in a database
     * system it is more likely that recently added entries are accessed
     * more frequently. */
    ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
    entry = zmalloc(sizeof(*entry));
    entry->next = ht->table[index];
    ht->table[index] = entry;
    ht->used++;

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

可以看到，在向hash桶中进行插入的时候，处于同一个hash桶上的链表，新插入的元素在在链表的头部进行插入的。

redis中的hash扩容采用的是一种渐进式hash的策略， 我们都知道，redis执行线程是单线程，如果一个hash表数据量比较大，那么扩容就比较耗费时间，redis采取是的一种渐进式hash策略，采用 dictht ht[2];两张表来进行，当ht[0]表满了的时候，会将元素分批多次移动到ht[1]上面来。当全部移动完之后，会将原来ht[0]释放掉，然后将ht[0]指向ht[1]，释放ht[1].redis在rehash时，是每次将一个桶全部移动完之后在移动下一个。

int dictRehash(dict *d, int n) {
    int empty_visits = n*10; /* Max number of empty buckets to visit. */
    if (dict_can_resize == DICT_RESIZE_FORBID || !dictIsRehashing(d)) return 0;
    if (dict_can_resize == DICT_RESIZE_AVOID && 
        (d->ht[1].size / d->ht[0].size < dict_force_resize_ratio))
    {
        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];
        /* Move all the keys in this bucket from the old to the new hash HT */
        while(de) {
            uint64_t 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;
}

hash表元素查找：

dictEntry *dictFind(dict *d, const void *key)
{
    dictEntry *he;
    uint64_t h, idx, table;

    if (dictSize(d) == 0) return NULL; /* dict is empty */
    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);
    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        he = d->ht[table].table[idx];
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key))
                return he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) return NULL;
    }
    return NULL;
}

hash表的查找相对来说比较简单，就是通过key的hash找到对应的桶上的链表，然后遍历即可