Redis 数据类型--字典 学习笔记

---

前言

本文是记录Redis字典数据类型的具体实现细节。Redis使用哈希表作为字典的底层实现，一个哈希表里可以有多个哈希表节点，每个哈希表节点保存一组键值对。我们可以通过Redis定义的数据结构及API，了解字典的具体实现原理。

---

一、字典是什么？

字典，又称符号表或映射（map）,是一个键值对（key-value）的集合。在字典中，每个键都是独一无二的，在程序中，我们可以通过key来操作对应的键值对，如查找值、修改值、或删除整个键值对等等。

二、Redis字典实现

1.哈希表

字典包含哈希表，哈希表用于存储键值对。代码位置：redis-3.2.1\src\dict.h

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

/* 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;

在哈希表结构dictht中各字段的解释：

table：哈希元素数组。

数组元素的类型为dictEntry；在dictEntry中保存键值对及一个后续元素的指针，这各指针其实是用来解决哈希索引冲突的。在元素节点中，值是联合类型，可以是void*/uint64_t/int64_t/double之一，因为有void的存在，所以字典几乎可以存储任意类型的数据。同理，键值对中的key的数据类型也是void，所以它也可以是任意类型的。

size：表示哈希表大小。

即哈希元素数组的大小（数组长度）。

sizemask：哈希表大小掩码。

用于计算哈希表的索引值，它的值总是等于size-1。这个值和哈希值一起决定一个键应该被放到table数组的哪个索引上。如果索引处已有dictEntry元素，则把新的dictEntry元素插到索引处，使用dictEntry的next指针连接原有的元素，这样就形成了一个列表（链地址法解决hash冲突）。之所以把新增的元素放在列表的首位，是为了提高操作效率，不然每次都要找到队尾再插入元素，效率非常低下。

used：哈希表中实际存储元素的个数。

就行Redis的列表、字符串设计一样，在定义中都有字段定义当前容器元素的个数，当需要获取容器中元素个数时，直接使用这个字段即可，可以提高操作效率，时间复杂度为O(1)。

2.字典

字典使用哈希表作为底层实现，代码位置：redis-3.2.1\src\dict.h

typedef struct dictType {
    unsigned int (*hashFunction)(const void *key);//计算哈希值
    void *(*keyDup)(void *privdata, const void *key);//复制键
    void *(*valDup)(void *privdata, const void *obj);//复制值
    int (*keyCompare)(void *privdata, const void *key1, const void *key2);//比较键
    void (*keyDestructor)(void *privdata, void *key);//销毁键
    void (*valDestructor)(void *privdata, void *obj);//销毁值
} dictType;

typedef struct dict {
    dictType *type;
    void *privdata;
    dictht ht[2];
    long rehashidx; /* rehashing not in progress if rehashidx == -1 */
    int iterators; /* number of iterators currently running */
} dict;

type：dictType指针。

每个dictType结构保存了一组用于操作特定类型键值对的函数，Redis会为不同的字典设置不同类型的特定函数。这有点类似面向对象的多态特性，当初始化字典对象时，指定一组对应的操作集合，即可实现对特定数据的处理，不同字典可以有不同的函数实现，类似虚函数。

privdata：特定函数的可选参数。

dictType结构中有些函数是需要用到privdata，这相当于上下文。

ht：两个哈希表的数组。

一般情况下只使用ht[0]这个哈希表，ht[1]哈希表只会在哈希表进行rehash的时候临时使用，一旦rehash结束，会交换ht[0]和ht[1]的值，然后ht[1]继续处于空闲状态，所有读写操作只针对ht[0]。

rehashidx：记录rehash目前的进度。

如果没有进行rehash，它的值为-1。

3.字典源码

/* ----------------------------- API implementation ------------------------- */

/* Reset a hash table already initialized with ht_init().
 * NOTE: This function should only be called by ht_destroy(). */
static void _dictReset(dictht *ht)
{
    ht->table = NULL;
    ht->size = 0;
    ht->sizemask = 0;
    ht->used = 0;
}

/* Create a new hash table */
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->iterators = 0;
    return DICT_OK;
}

/* Resize the table to the minimal size that contains all the elements,
 * but with the invariant of a USED/BUCKETS ratio near to <= 1 */
int dictResize(dict *d)
{
    int minimal;

    if (!dict_can_resize || dictIsRehashing(d)) return DICT_ERR;
    minimal = d->ht[0].used;
    if (minimal < DICT_HT_INITIAL_SIZE)
        minimal = DICT_HT_INITIAL_SIZE;
    return dictExpand(d, minimal);
}

/* Expand or create the hash table */
int dictExpand(dict *d, unsigned long size)
{
    dictht n; /* the new hash table */
    unsigned long realsize = _dictNextPower(size);

    /* 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;
    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) {
        d->ht[0] = n;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    d->ht[1] = n;
    d->rehashidx = 0;
    return DICT_OK;
}

/* Performs N steps of incremental rehashing. Returns 1 if there are still
 * keys to move from the old to the new hash table, otherwise 0 is returned.
 *
 * Note that a rehashing step consists in moving a bucket (that may have more
 * than one key as we use chaining) from the old to the new hash table, however
 * since part of the hash table may be composed of empty spaces, it is not
 * guaranteed that this function will rehash even a single bucket, since it
 * will visit at max N*10 empty buckets in total, otherwise the amount of
 * work it does would be unbound and the function may block for a long time. */
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];
        /* 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;
            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;
}

long long timeInMilliseconds(void) {
    struct timeval tv;

    gettimeofday(&tv,NULL);
    return (((long long)tv.tv_sec)*1000)+(tv.tv_usec/1000);
}

/* Rehash for an amount of time between ms milliseconds and ms+1 milliseconds */
int dictRehashMilliseconds(dict *d, int ms) {
    long long start = timeInMilliseconds();
    int rehashes = 0;

    while(dictRehash(d,100)) {
        rehashes += 100;
        if (timeInMilliseconds()-start > ms) break;
    }
    return rehashes;
}

/* This function performs just a step of rehashing, and only if there are
 * no safe iterators bound to our hash table. When we have iterators in the
 * middle of a rehashing we can't mess with the two hash tables otherwise
 * some element can be missed or duplicated.
 *
 * This function is called by common lookup or update operations in the
 * dictionary so that the hash table automatically migrates from H1 to H2
 * while it is actively used. */
static void _dictRehashStep(dict *d) {
    if (d->iterators == 0) dictRehash(d,1);
}

/* Add an element to the target hash table */
int dictAdd(dict *d, void *key, void *val)
{
    dictEntry *entry = dictAddRaw(d,key);

    if (!entry) return DICT_ERR;
    dictSetVal(d, entry, val);
    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);

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

/* Add an element, discarding the old if the key already exists.
 * Return 1 if the key was added from scratch, 0 if there was already an
 * element with such key and dictReplace() just performed a value update
 * operation. */
int dictReplace(dict *d, void *key, void *val)
{
    dictEntry *entry, auxentry;

    /* Try to add the element. If the key
     * does not exists dictAdd will suceed. */
    if (dictAdd(d, key, val) == DICT_OK)
        return 1;
    /* It already exists, get the entry */
    entry = dictFind(d, key);
    /* Set the new value and free the old one. Note that it is important
     * to do that in this order, as the value may just be exactly the same
     * as the previous one. In this context, think to reference counting,
     * you want to increment (set), and then decrement (free), and not the
     * reverse. */
    auxentry = *entry;
    dictSetVal(d, entry, val);
    dictFreeVal(d, &auxentry);
    return 0;
}

/* dictReplaceRaw() is simply a version of dictAddRaw() that always
 * returns the hash entry of the specified key, even if the key already
 * exists and can't be added (in that case the entry of the already
 * existing key is returned.)
 *
 * See dictAddRaw() for more information. */
dictEntry *dictReplaceRaw(dict *d, void *key) {
    dictEntry *entry = dictFind(d,key);

    return entry ? entry : dictAddRaw(d,key);
}

/* Search and remove an element */
static int dictGenericDelete(dict *d, const void *key, int nofree)
{
    unsigned int h, idx;
    dictEntry *he, *prevHe;
    int table;

    if (d->ht[0].size == 0) return DICT_ERR; /* d->ht[0].table is NULL */
    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];
        prevHe = NULL;
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                /* Unlink the element from the list */
                if (prevHe)
                    prevHe->next = he->next;
                else
                    d->ht[table].table[idx] = he->next;
                if (!nofree) {
                    dictFreeKey(d, he);
                    dictFreeVal(d, he);
                }
                zfree(he);
                d->ht[table].used--;
                return DICT_OK;
            }
            prevHe = he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return DICT_ERR; /* not found */
}

int dictDelete(dict *ht, const void *key) {
    return dictGenericDelete(ht,key,0);
}

int dictDeleteNoFree(dict *ht, const void *key) {
    return dictGenericDelete(ht,key,1);
}

/* Destroy an entire dictionary */
int _dictClear(dict *d, dictht *ht, void(callback)(void *)) {
    unsigned long i;

    /* Free all the elements */
    for (i = 0; i < ht->size && ht->used > 0; i++) {
        dictEntry *he, *nextHe;

        if (callback && (i & 65535) == 0) callback(d->privdata);

        if ((he = ht->table[i]) == NULL) continue;
        while(he) {
            nextHe = he->next;
            dictFreeKey(d, he);
            dictFreeVal(d, he);
            zfree(he);
            ht->used--;
            he = nextHe;
        }
    }
    /* Free the table and the allocated cache structure */
    zfree(ht->table);
    /* Re-initialize the table */
    _dictReset(ht);
    return DICT_OK; /* never fails */
}

/* Clear & Release the hash table */
void dictRelease(dict *d)
{
    _dictClear(d,&d->ht[0],NULL);
    _dictClear(d,&d->ht[1],NULL);
    zfree(d);
}

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

    if (d->ht[0].used + d->ht[1].used == 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;
}

void *dictFetchValue(dict *d, const void *key) {
    dictEntry *he;

    he = dictFind(d,key);
    return he ? dictGetVal(he) : NULL;
}

---

总结

rehash

字典可以储存大量的数据，随着字典操作的不断执行，哈希表保存的键值对会逐渐的增加或减少，为了让哈希表的负载因子维持在一个合理的范围内，当哈希表保存的键值对太多或太少时，字典需要对哈希表进行扩展或收缩。字典通过执行rehash（重新散列）来达到扩展和收缩的目的。