redis源代码学习-哈希表的实现

  在redis中有专门的文件定义自己的数据结构，这篇我学习的时其中的哈希列表的实现，包括insert/delete/find/replace/get-random-element等操作。dict结构的主要目的是解决Redis中的数据查找问题。它利用哈希函数确定key值的位置，并且拥有两张数据表，在数据容量不够时自动实现扩容，并对当前哈希表中的数据rehash，但这个rehash操作不是一次完成的，而是分散到不同的操作中逐步完成，避免一次操作花费太多时间，加快操作的响应速度。

      1.基本的结构体

            哈希列表的基本节点是dictEntry，它是一个key-value的结构体，由于value类型是不确定的，因而采用union结构体定义，它还包含指向下一个节点的指针。

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

 哈希列表定义了一个类型包含一些字典集合操作，采用函数指针的方法，它主要定义了针对key和value值得各种操作。

typedef struct dictType {

//哈希计算方法，返回整形变量 
    uint64_t (*hashFunction)(const void *key);

 //复制key函数 
    void *(*keyDup)(void *privdata, const void *key);

    void *(*valDup)(void *privdata, const void *obj);

//key值比较方法
    int (*keyCompare)(void *privdata, const void *key1, const void *key2);

//key的析构函数  
    void (*keyDestructor)(void *privdata, void *key);
    void (*valDestructor)(void *privdata, void *obj);
} dictType;

哈希表的结构体如下，通常一个字典中有两个表，用于实现rehash(即原有哈希表容量不够需要扩容重新对每个元素分配位置)。dict是哈希字典，包含两个哈希表和字典类型以及私有数据指针。私有数据是执行某些操作时返回调用者。dictIterator是字典迭代器，包含一个字典，是否安全，节点，下一个节点。

typedef struct dictht {
    dictEntry **table;
    unsigned long size;//哈希表的大小
    unsigned long sizemask;
    unsigned long used;//使用节点数
} dictht;

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

typedef struct dictIterator {
    dict *d;
    long index;
    int table, safe;
    dictEntry *entry, *nextEntry;
    /* unsafe iterator fingerprint for misuse detection. */
    long long fingerprint;
} dictIterator;

接着以宏的方式定义了字典中的一些基本操作，如复制值，析构值，设置等操作，关于这些宏定义函数的方法值得学习。

#define dictFreeVal(d, entry) \
    if ((d)->type->valDestructor) \
        (d)->type->valDestructor((d)->privdata, (entry)->v.val)
//设置void*数据的方法，若有自定义dup方法，则调用，否则指针赋值
#define dictSetVal(d, entry, _val_) do { \
    if ((d)->type->valDup) \
        (entry)->v.val = (d)->type->valDup((d)->privdata, _val_); \
    else \
        (entry)->v.val = (_val_); \
} while(0)

#define dictSetSignedIntegerVal(entry, _val_) \
    do { (entry)->v.s64 = _val_; } while(0)

#define dictSetUnsignedIntegerVal(entry, _val_) \
    do { (entry)->v.u64 = _val_; } while(0)

#define dictSetDoubleVal(entry, _val_) \
    do { (entry)->v.d = _val_; } while(0)

接着定义了一些基本的插入、删除、查找操作，可以看到在每个操作中都会先判断是否处于rehash过程中，若是，则将rehash向前推进，通过这样分散rehash操作。

/* Add an element to the target hash table */
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;
}

/* Low level add or find:
 * 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,NULL);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * Return values:
 *
 * If key already exists NULL is returned, and "*existing" is populated
 * with the existing entry if existing is not NULL.
 *
 * If key was added, the hash entry is returned to be manipulated by the caller.
 */
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    int index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);//每次添加数据时，若是需要rehash，则执行一步rehash操作

    /* 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;//将新添加的值加入链表头，假设新加入的数据会被频繁访问
    ht->used++;

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

/* Add or Overwrite:
 * Add an element, discarding the old value 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, *existing, auxentry;

    /* Try to add the element. If the key
     * does not exists dictAdd will suceed. */
    entry = dictAddRaw(d,key,&existing);
    if (entry) {
        dictSetVal(d, entry, val);
        return 1;
    }

    /* 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 = *existing;
    dictSetVal(d, existing, val);
    dictFreeVal(d, &auxentry);
    return 0;
}

/* Add or Find:
 * dictAddOrFind() 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 *dictAddOrFind(dict *d, void *key) {
    dictEntry *entry, *existing;
    entry = dictAddRaw(d,key,&existing);
    return entry ? entry : existing;
}

/* Search and remove an element. This is an helper function for
 * dictDelete() and dictUnlink(), please check the top comment
 * of those functions. */
static dictEntry *dictGenericDelete(dict *d, const void *key, int nofree) {
    unsigned int h, idx;
    dictEntry *he, *prevHe;
    int table;

    if (d->ht[0].used == 0 && d->ht[1].used == 0) return NULL;

    if (dictIsRehashing(d)) _dictRehashStep(d);//TODO:有什么作用澹?
    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 he;
            }
            prevHe = he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return NULL; /* not found */
}

/* Remove an element, returning DICT_OK on success or DICT_ERR if the
 * element was not found. */
int dictDelete(dict *ht, const void *key) {
    return dictGenericDelete(ht,key,0) ? DICT_OK : DICT_ERR;
}

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;
}
//找到key值对应的val值指针，若找不到，返回NULL
void *dictFetchValue(dict *d, const void *key) {
    dictEntry *he;

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