Redis源码分析：字典实现(二)

本文分析的是Redis的版本为4.0.11。

接口实现

本文继续分析字典的接口实现。

添加

在分析键值对添加接口实现前，先来分析一下_dictKeyIndex()函数实现。该函数根据提供key、哈希值来获取哈希表的插入位置。如果该key在哈希表中已存在，可以通过existing参数返回dictEntry地址，并将返回值设置为-1，表示key已存在。如果dict正在进行重新哈希的过程，需要在新旧两个哈希表查找。

/* Returns the index of a free slot that can be populated with
 * a hash entry for the given 'key'.
 * If the key already exists, -1 is returned
 * and the optional output parameter may be filled.
 *
 * Note that if we are in the process of rehashing the hash table, the
 * index is always returned in the context of the second (new) hash table. */
static long _dictKeyIndex(dict *d, const void *key, uint64_t hash, dictEntry **existing)
{
    unsigned long idx, table;
    dictEntry *he;
    if (existing) *existing = NULL;

    /* Expand the hash table if needed */
    if (_dictExpandIfNeeded(d) == DICT_ERR)
        return -1;
    for (table = 0; table <= 1; table++) {
        idx = hash & d->ht[table].sizemask;
        /* Search if this slot does not already contain the given key */
        he = d->ht[table].table[idx];
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                if (existing) *existing = he;
                return -1;
            }
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return idx;
}

接下来，介绍另外一个底层函数dictAddRaw(), 该函数会调用_dictKeyIndex()获取添加key的哈希表索引位置，如果key已经存在，则直接返回NULL，可以从existing获取已经存在key的dictEntry。如果不存在，则分配新的内存空间，并将其加入指定的索引位置，并设置key值。该用户可以通过相关的接口很方便的设置函数返回的dictEntry的value值。

/* 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)
{
    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;
}

添加接口依赖上面的函数实现。dictAdd()函数实现比较简单，通过dictAddRaw()底层函数创建dictEntry，若已存在，则返回错误。通过dictSetVal宏设置value值。

/* 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;
}

dictAddOrFind()是dictAddRaw()的简化版，它总是返回指定key的dictEntry结构。

/* 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;
}

覆写

dictReplace()提供了添加和覆写的功能。其底层也是调用了dictAddRaw(), 如果key不存在，则直接设置范围的dictEntry的value属性值；否则的话，则采取覆写的功能，同时释放value占用的资源。

/* 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;
}

删除

删除的底层函数为dictGenericDelete()，实现了在哈希表中查找key所在的索引位置，并从链表中摘除，是否需要释放dictEntry资源，取决与nofree的值。

/* 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) {
    uint64_t 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);
    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 */
}

dictDelete()函数会删除key及占用的资源，而dictUnlink()仅将Key的dictEntry从哈希表中摘除，并不释放资源，这样用户有机会可以获取对应的其value值，如果要释放相应的资源的话，需要调用dictFreeUnlinkedEntry()函数。

/* 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;
}

/* Remove an element from the table, but without actually releasing
 * the key, value and dictionary entry. The dictionary entry is returned
 * if the element was found (and unlinked from the table), and the user
 * should later call `dictFreeUnlinkedEntry()` with it in order to release it.
 * Otherwise if the key is not found, NULL is returned.
 *
 * This function is useful when we want to remove something from the hash
 * table but want to use its value before actually deleting the entry.
 * Without this function the pattern would require two lookups:
 *
 *  entry = dictFind(...);
 *  // Do something with entry
 *  dictDelete(dictionary,entry);
 *
 * Thanks to this function it is possible to avoid this, and use
 * instead:
 *
 * entry = dictUnlink(dictionary,entry);
 * // Do something with entry
 * dictFreeUnlinkedEntry(entry); // <- This does not need to lookup again.
 */
dictEntry *dictUnlink(dict *ht, const void *key) {
    return dictGenericDelete(ht,key,1);
}

/* You need to call this function to really free the entry after a call
 * to dictUnlink(). It's safe to call this function with 'he' = NULL. */
void dictFreeUnlinkedEntry(dict *d, dictEntry *he) {
    if (he == NULL) return;
    dictFreeKey(d, he);
    dictFreeVal(d, he);
    zfree(he);
}

查找

查找接口的实现，提供了两个接口，dictFind()用于查找指定的key对应的dictEntry项，dictFetchValue()函数用于取值。

dictEntry *dictFind(dict *d, const void *key)
{
    dictEntry *he;
    uint64_t 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;
}