dict.c

/* Hash Tables Implementation.
 *
 * This file implements in memory hash tables with insert/del/replace/find/
 * get-random-element operations. Hash tables will auto resize if needed
 * tables of power of two in size are used, collisions are handled by
 * chaining. See the source code for more information... :)
 *
 * Copyright (c) 2006-2012, Salvatore Sanfilippo <antirez at gmail dot com>
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *   * Redistributions of source code must retain the above copyright notice,
 *     this list of conditions and the following disclaimer.
 *   * Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *   * Neither the name of Redis nor the names of its contributors may be used
 *     to endorse or promote products derived from this software without
 *     specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "fmacros.h"

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <stdarg.h>
#include <limits.h>
#include <sys/time.h>

#include "dict.h"
#include "zmalloc.h"
#include "redisassert.h"

/* Using dictEnableResize() / dictDisableResize() we make possible to
 * enable/disable resizing of the hash table as needed. This is very important
 * for Redis, as we use copy-on-write and don't want to move too much memory
 * around when there is a child performing saving operations.
 * 使用 dictEnableResize() / dictDisableResize() 方法可以让我们很容易去控制哈希表是否进行大小再分配
 * 使用了写时复制，当有子进程在进行 BGSAVE 或者 AOFRW 的时候，父进程对内存进行写操作（rehash）是很消耗性能的
 *
 * Note that even when dict_can_resize is set to 0, not all resizes are
 * prevented: a hash table is still allowed to grow if the ratio between
 * the number of elements and the buckets > dict_force_resize_ratio.
 */
/* 需要注意的是，即使 dict_can_resize 置为 0 时，也不意味着所有 resize 行为都被禁止了
 * 当哈希表元素与桶大小比值大于阈值 (dict_force_resize_ratio = 5), redis 还是会对哈希表进行 resize
 */
static int dict_can_resize = 1;
static unsigned int dict_force_resize_ratio = 5;

/* -------------------------- private prototypes ---------------------------- */

static int _dictExpandIfNeeded(dict *d);
static signed char _dictNextExp(unsigned long size);
static long _dictKeyIndex(dict *d, const void *key, uint64_t hash, dictEntry **existing);
static int _dictInit(dict *d, dictType *type);

/* -------------------------- hash functions -------------------------------- */

static uint8_t dict_hash_function_seed[16];

void dictSetHashFunctionSeed(uint8_t *seed) {
    memcpy(dict_hash_function_seed,seed,sizeof(dict_hash_function_seed));
}

uint8_t *dictGetHashFunctionSeed(void) {
    return dict_hash_function_seed;
}

/* The default hashing function uses SipHash implementation
 * in siphash.c. */

uint64_t siphash(const uint8_t *in, const size_t inlen, const uint8_t *k);
uint64_t siphash_nocase(const uint8_t *in, const size_t inlen, const uint8_t *k);

uint64_t dictGenHashFunction(const void *key, size_t len) {
    return siphash(key,len,dict_hash_function_seed);
}

uint64_t dictGenCaseHashFunction(const unsigned char *buf, size_t len) {
    return siphash_nocase(buf,len,dict_hash_function_seed);
}

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

/* Reset hash table parameters already initialized with _dictInit()*/
static void _dictReset(dict *d, int htidx)
{
    d->ht_table[htidx] = NULL;
    d->ht_size_exp[htidx] = -1;
    d->ht_used[htidx] = 0;
}

/* Create a new hash table */
dict *dictCreate(dictType *type)
{
    dict *d = zmalloc(sizeof(*d));

    _dictInit(d,type);
    return d;
}

/* Initialize the hash table */
int _dictInit(dict *d, dictType *type)
{
    _dictReset(d, 0);
    _dictReset(d, 1);
    d->type = type;
    d->rehashidx = -1;
    d->pauserehash = 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 */
/* 将哈希表大小重分配为最小所需大小
 * 但 已使用大小（元素数量）与桶大小（桶数量）比值 尽量接近或小于1 */
int dictResize(dict *d)
{
    unsigned long minimal;

    /* dictIsRehashing 用于判断当前哈希表是否处于重哈希中
     * 如果处于重哈希状态，不对其进行 resize */
    if (!dict_can_resize || dictIsRehashing(d)) return DICT_ERR;
    minimal = d->ht_used[0];
    if (minimal < DICT_HT_INITIAL_SIZE)
        minimal = DICT_HT_INITIAL_SIZE;
    return dictExpand(d, minimal);
}

/* Expand or create the hash table,
 * when malloc_failed is non-NULL, it'll avoid panic if malloc fails (in which case it'll be set to 1).
 * Returns DICT_OK if expand was performed, and DICT_ERR if skipped. */
int _dictExpand(dict *d, unsigned long size, int* malloc_failed)
{
    if (malloc_failed) *malloc_failed = 0;

    /* the size is invalid if it is smaller than the number of
     * elements already inside the hash table */
    /* 假如正处于重哈希过程中，或目前已使用大小大于目标大小，则跳过 */
    if (dictIsRehashing(d) || d->ht_used[0] > size)
        return DICT_ERR;

    /* the new hash table */
    dictEntry **new_ht_table;
    unsigned long new_ht_used;
    signed char new_ht_size_exp = _dictNextExp(size);

    /* Detect overflows */
    /* 如果目标大小小于原大小（一般为负），则可能是长度溢出了 */
    size_t newsize = 1ul<<new_ht_size_exp;
    if (newsize < size || newsize * sizeof(dictEntry*) < newsize)
        return DICT_ERR;

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

    /* Allocate the new hash table and initialize all pointers to NULL */
    if (malloc_failed) {
        new_ht_table = ztrycalloc(newsize*sizeof(dictEntry*));
        *malloc_failed = new_ht_table == NULL;
        if (*malloc_failed)
            return DICT_ERR;
    } else
        new_ht_table = zcalloc(newsize*sizeof(dictEntry*));

    new_ht_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_table[0] == NULL) {
        d->ht_size_exp[0] = new_ht_size_exp;
        d->ht_used[0] = new_ht_used;
        d->ht_table[0] = new_ht_table;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    /* 从 dict.h 源码可以看出，ht_xxx 一般为大小为 2 的数组
     * 下标为 1 的元素用于在重哈希时临时存储新的哈希表
     * 因此这里将新哈希表的空间扩展指数，新哈希表已使用大小以及新哈希表指针赋值给下标为 1 的元素
     * 并且将 rehashidx 置为 0 (为 -1 时表示不处于重哈希过程中)，即可以让 redis 对哈希表进行再哈希 */
    d->ht_size_exp[1] = new_ht_size_exp;
    d->ht_used[1] = new_ht_used;
    d->ht_table[1] = new_ht_table;
    d->rehashidx = 0;
    return DICT_OK;
}

/* return DICT_ERR if expand was not performed */
/* 不设置 malloc_failed 变量的 resize 方法
 * 当无法 resize 时会中断程序 */
int dictExpand(dict *d, unsigned long size) {
    return _dictExpand(d, size, NULL);
}

/* return DICT_ERR if expand failed due to memory allocation failure */
/* 设置 malloc_failed 变量的 resize 方法
 * 当无法 resize 时会返回错误标识 */
int dictTryExpand(dict *d, unsigned long size) {
    int malloc_failed;
    _dictExpand(d, size, &malloc_failed);
    return malloc_failed? DICT_ERR : 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. */

/* 重哈希方法，如果返回 0 表示重哈希完成，返回 1 表示还有剩余未重哈希的元素
 * redis 采用渐进式重哈希，empty_visits 用于记录本次哈希允许遍历到为空值的元素
 * 当 empty_visits = 0 时，本次哈希结束，剩余元素的重哈希会在之后继续进行
 * rehashidx 记录上一次重哈希结束时遍历到哈希表元素的下标
 * */
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_used[0] != 0) {
        dictEntry *de, *nextde;

        /* Note that rehashidx can't overflow as we are sure there are more
         * elements because ht[0].used != 0 */
        /* 当 rehashidx 等于哈希表大小时，表明重哈希完成 */
        assert(DICTHT_SIZE(d->ht_size_exp[0]) > (unsigned long)d->rehashidx);
        while(d->ht_table[0][d->rehashidx] == NULL) {
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        de = d->ht_table[0][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) & DICTHT_SIZE_MASK(d->ht_size_exp[1]);
            de->next = d->ht_table[1][h];
            d->ht_table[1][h] = de;
            d->ht_used[0]--;
            d->ht_used[1]++;
            de = nextde;
        }
        d->ht_table[0][d->rehashidx] = NULL;
        d->rehashidx++;
    }

    /* Check if we already rehashed the whole table... */
    /* 当当前哈希表已使用大小为 0
     * 证明重哈希完成
     * 将下标为 1 的哈希表赋值到当前哈希表
     * 完成重哈希过程 */
    if (d->ht_used[0] == 0) {
        zfree(d->ht_table[0]);
        /* Copy the new ht onto the old one */
        d->ht_table[0] = d->ht_table[1];
        d->ht_used[0] = d->ht_used[1];
        d->ht_size_exp[0] = d->ht_size_exp[1];
        _dictReset(d, 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 in ms+"delta" milliseconds. The value of "delta" is larger 
 * than 0, and is smaller than 1 in most cases. The exact upper bound 
 * depends on the running time of dictRehash(d,100).*/
/* 此方法等于是用参数 ms 来控制 rehash 的时间
 * 目前观察来看 ms 一般设置为 1ms
 * 当重哈希时长超过 1ms 时， 结束本次重哈希，并返回本次重哈希元素的数量 */
int dictRehashMilliseconds(dict *d, int ms) {
    if (d->pauserehash > 0) return 0;

    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 hashing has
 * not been paused for our hash table. When we have iterators in the
 * middle of a rehashing we can't mess with the two hash tables otherwise
 * some elements 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. */
/* 此方法表示在对哈希表进行查找或者更新的时候
 * 动态地对哈希表进行重哈希
 * 这样做可以避免大规模对整个哈希表进行重哈希，导致阻塞 redis 进程 */
static void _dictRehashStep(dict *d) {
    if (d->pauserehash == 0) dictRehash(d,1);
}

/* Add an element to the target hash table */
/* 向字典（哈希表）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;
}

/* 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 they wish.
 *
 * 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.
 */
/* 此方法用与对所给定的 key ，在哈希表中添加一个实体（entry）
 * 此方法不会直接向实体中添加 value。相反，它会把该实体返回给调用者，让调用者按照自己的意愿来对这个实体进行操作
 *
 * 例子：
 * entry = dictAddRaw(dict,mykey,NULL);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * 假如 给定的 key 已经在哈希表中存在，则返回 NULL 并且将此 key 对应的实体赋值给 *existing
 * */
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    long index;
    dictEntry *entry;
    int htidx;

    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. */
    /* 如果哈希表处在重哈希状态，则对新表（ht_table[1]）进行操作 */
    htidx = dictIsRehashing(d) ? 1 : 0;
    size_t metasize = dictMetadataSize(d);
    entry = zmalloc(sizeof(*entry) + metasize);
    if (metasize > 0) {
        memset(dictMetadata(entry), 0, metasize);
    }
    entry->next = d->ht_table[htidx][index];
    d->ht_table[htidx][index] = entry;
    d->ht_used[htidx]++;

    /* 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. */
/* 此方法可理解为哈希表的值更新
 * 假如表中不存在 key 所对应的实体，则当作添加操作处理
 * 假如已存在 key 对应实体，则更新对应的值 */
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 succeed. */
    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. */
    /* 此处先 set 后 free 这个顺序尤为重要
     * 主要是为了防止在新值与旧值相同的情况
     *
     * 假设 val 与 *existing 中 val 所指为同一个对象
     * 如果先释放了此val， 那么在 进行 dictSetVal 操作时，val 会为空 */
    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. */
/* 此方法可以看作 dictAddRaw 的另一个版本
 * 区别在于 dictAddOrFind 即使在哈希表存在 key 对应实体时，仍然会返回这个实体，而 dictAddRaw 在这种情况下返回 NULL */
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 a helper function for
 * dictDelete() and dictUnlink(), please check the top comment
 * of those functions. */
/* 此方法是 dictDelete() 和 dictUnlink() 的辅助方法
 * 值的注意的点是该方法接收的参数 nofree
 * 当 nofree = 1 时，该方法不会释放被 unlinked 的实体的内存，并且会把这个实体返回 */
static dictEntry *dictGenericDelete(dict *d, const void *key, int nofree) {
    uint64_t h, idx;
    dictEntry *he, *prevHe;
    int table;

    /* dict is empty */
    if (dictSize(d) == 0) return NULL;

    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);

    for (table = 0; table <= 1; table++) {
        idx = h & DICTHT_SIZE_MASK(d->ht_size_exp[table]);
        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) {
                    dictFreeUnlinkedEntry(d, he);
                }
                d->ht_used[table]--;
                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;
}

/* 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.
 */
/* 该方法调用 dictGenericDelete() 并传入 nofree = 1 ，并且返回被 unlinked 的实体
 * 这样做的好处是，如果该函数调用者在彻底释放被删除实体的内存前，需要使用到该实体做某些操作，可以直接使用 dictUnlink() 所返回的实体，并在
 * 使用完毕之后手动释放内存
 *
 * 否则，如果要完成上述的操作，需要对哈希表做两次查找操作：
 * entry = dictFind(...);
 * // Do something with entry
 * dictDelete(dictionary,entry);
 * */
dictEntry *dictUnlink(dict *d, const void *key) {
    return dictGenericDelete(d,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);
}

/* Destroy an entire dictionary */
/* 彻底释放整个哈希表，并重新初始化对应 htidx 位置上的哈希表 */
int _dictClear(dict *d, int htidx, void(callback)(dict*)) {
    unsigned long i;

    /* Free all the elements */
    for (i = 0; i < DICTHT_SIZE(d->ht_size_exp[htidx]) && d->ht_used[htidx] > 0; i++) {
        dictEntry *he, *nextHe;

        if (callback && (i & 65535) == 0) callback(d);

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

/* Clear & Release the hash table */
/* 清除整个字典的内容并释放内存 */
void dictRelease(dict *d)
{
    _dictClear(d,0,NULL);
    _dictClear(d,1,NULL);
    zfree(d);
}

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 & DICTHT_SIZE_MASK(d->ht_size_exp[table]);
        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;
}

/* 在哈希表中取 key 对应的值 */
void *dictFetchValue(dict *d, const void *key) {
    dictEntry *he;

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

/* A fingerprint is a 64 bit number that represents the state of the dictionary
 * at a given time, it's just a few dict properties xored together.
 * When an unsafe iterator is initialized, we get the dict fingerprint, and check
 * the fingerprint again when the iterator is released.
 * If the two fingerprints are different it means that the user of the iterator
 * performed forbidden operations against the dictionary while iterating. */
unsigned long long dictFingerprint(dict *d) {
    unsigned long long integers[6], hash = 0;
    int j;

    integers[0] = (long) d->ht_table[0];
    integers[1] = d->ht_size_exp[0];
    integers[2] = d->ht_used[0];
    integers[3] = (long) d->ht_table[1];
    integers[4] = d->ht_size_exp[1];
    integers[5] = d->ht_used[1];

    /* We hash N integers by summing every successive integer with the integer
     * hashing of the previous sum. Basically:
     *
     * Result = hash(hash(hash(int1)+int2)+int3) ...
     *
     * This way the same set of integers in a different order will (likely) hash
     * to a different number. */
    for (j = 0; j < 6; j++) {
        hash += integers[j];
        /* For the hashing step we use Tomas Wang's 64 bit integer hash. */
        hash = (~hash) + (hash << 21); // hash = (hash << 21) - hash - 1;
        hash = hash ^ (hash >> 24);
        hash = (hash + (hash << 3)) + (hash << 8); // hash * 265
        hash = hash ^ (hash >> 14);
        hash = (hash + (hash << 2)) + (hash << 4); // hash * 21
        hash = hash ^ (hash >> 28);
        hash = hash + (hash << 31);
    }
    return hash;
}

dictIterator *dictGetIterator(dict *d)
{
    dictIterator *iter = zmalloc(sizeof(*iter));

    iter->d = d;
    iter->table = 0;
    iter->index = -1;
    iter->safe = 0;
    iter->entry = NULL;
    iter->nextEntry = NULL;
    return iter;
}

dictIterator *dictGetSafeIterator(dict *d) {
    dictIterator *i = dictGetIterator(d);

    i->safe = 1;
    return i;
}

dictEntry *dictNext(dictIterator *iter)
{
    /* 1) 找到下一个不为 NULL 的 entry，直接返回
     * 2) 或者已经查找完字典所有的 bucket，退出循环，方法返回 NULL */
    while (1) {
        /* 1) 如果 entry 为 NULL，index++，切换到下一个 bucket
         * 2) 否则 entry = entry->next，若新 entry 不为 NULL，直接返回，否则循环重复这段逻辑 */
        if (iter->entry == NULL) {
            if (iter->index == -1 && iter->table == 0) {
                /* 迭代器第一次执行时，1)标记 dict 暂停 rehash。2)或计算并记录 dict 指纹 */
                if (iter->safe)
                    dictPauseRehashing(iter->d);
                else
                    iter->fingerprint = dictFingerprint(iter->d);
            }
            iter->index++;
            if (iter->index >= (long) DICTHT_SIZE(iter->d->ht_size_exp[iter->table])) {
                /* 在字典的 ht[0] 查找完毕的情况下
                 *   若字典正在 rehash 的中间状态，则切换到 ht[1] 继续查找下一个 entry
                 *   否则结束查找，方法返回 NULL，表示迭代器到达终点 */
                if (dictIsRehashing(iter->d) && iter->table == 0) {
                    iter->table++;
                    iter->index = 0;
                } else {
                    break;
                }
            }
            iter->entry = iter->d->ht_table[iter->table][iter->index];
        } else {
            iter->entry = iter->nextEntry;
        }
        if (iter->entry) {
            /* We need to save the 'next' here, the iterator user
             * may delete the entry we are returning. */
            iter->nextEntry = iter->entry->next;
            return iter->entry;
        }
    }
    return NULL;
}

void dictReleaseIterator(dictIterator *iter)
{
    if (!(iter->index == -1 && iter->table == 0)) {
        if (iter->safe)
            dictResumeRehashing(iter->d);
        else
            assert(iter->fingerprint == dictFingerprint(iter->d));
    }
    zfree(iter);
}

/* Return a random entry from the hash table. Useful to
 * implement randomized algorithms */
dictEntry *dictGetRandomKey(dict *d)
{
    dictEntry *he, *orighe;
    unsigned long h;
    int listlen, listele;

    if (dictSize(d) == 0) return NULL;
    if (dictIsRehashing(d)) _dictRehashStep(d);
    if (dictIsRehashing(d)) {
        unsigned long s0 = DICTHT_SIZE(d->ht_size_exp[0]);
        do {
            /* We are sure there are no elements in indexes from 0
             * to rehashidx-1 */
            h = d->rehashidx + (randomULong() % (dictSlots(d) - d->rehashidx));
            he = (h >= s0) ? d->ht_table[1][h - s0] : d->ht_table[0][h];
        } while(he == NULL);
    } else {
        unsigned long m = DICTHT_SIZE_MASK(d->ht_size_exp[0]);
        do {
            h = randomULong() & m;
            he = d->ht_table[0][h];
        } while(he == NULL);
    }

    /* Now we found a non empty bucket, but it is a linked
     * list and we need to get a random element from the list.
     * The only sane way to do so is counting the elements and
     * select a random index. */
    /* 由于在桶中采用了链地址法解决哈希冲突
     * 因此在随机找到一个非空桶之后，需要在链表中随机找到一个实体 */
    listlen = 0;
    orighe = he;
    while(he) {
        he = he->next;
        listlen++;
    }
    listele = random() % listlen;
    he = orighe;
    while(listele--) he = he->next;
    return he;
}

/* This function samples the dictionary to return a few keys from random
 * locations.
 *
 * It does not guarantee to return all the keys specified in 'count', nor
 * it does guarantee to return non-duplicated elements, however it will make
 * some effort to do both things.
 *
 * Returned pointers to hash table entries are stored into 'des' that
 * points to an array of dictEntry pointers. The array must have room for
 * at least 'count' elements, that is the argument we pass to the function
 * to tell how many random elements we need.
 *
 * The function returns the number of items stored into 'des', that may
 * be less than 'count' if the hash table has less than 'count' elements
 * inside, or if not enough elements were found in a reasonable amount of
 * steps.
 *
 * Note that this function is not suitable when you need a good distribution
 * of the returned items, but only when you need to "sample" a given number
 * of continuous elements to run some kind of algorithm or to produce
 * statistics. However the function is much faster than dictGetRandomKey()
 * at producing N elements. */
/* 此方法用于随机在字典中取出 N 个元素
 * 此方法接收的参数 count 指明了 des 数组所需要最少空间，但是此方法执行完成后 des 中实体的数量并不一定等于 count
 *
 * 这个方法并不适合需要在字典中得到比较均匀分布的实体的场景，它更适合用于获取 N 个连续的实体用于某些算法或统计 */
unsigned int dictGetSomeKeys(dict *d, dictEntry **des, unsigned int count) {
    unsigned long j; /* internal hash table id, 0 or 1. */
    unsigned long tables; /* 1 or 2 tables? */
    unsigned long stored = 0, maxsizemask;
    unsigned long maxsteps;

    if (dictSize(d) < count) count = dictSize(d);
    maxsteps = count*10;

    /* Try to do a rehashing work proportional to 'count'. */
    for (j = 0; j < count; j++) {
        if (dictIsRehashing(d))
            _dictRehashStep(d);
        else
            break;
    }

    tables = dictIsRehashing(d) ? 2 : 1;
    maxsizemask = DICTHT_SIZE_MASK(d->ht_size_exp[0]);
    if (tables > 1 && maxsizemask < DICTHT_SIZE_MASK(d->ht_size_exp[1]))
        maxsizemask = DICTHT_SIZE_MASK(d->ht_size_exp[1]);

    /* Pick a random point inside the larger table. */
    unsigned long i = randomULong() & maxsizemask;
    unsigned long emptylen = 0; /* Continuous empty entries so far. */
    while(stored < count && maxsteps--) {
        for (j = 0; j < tables; j++) {
            /* Invariant of the dict.c rehashing: up to the indexes already
             * visited in ht[0] during the rehashing, there are no populated
             * buckets, so we can skip ht[0] for indexes between 0 and idx-1. */
            /* 当处于重哈希时，本方法会对两个哈希表都进行操作
             * 当当前所查找的表为 ht_table[0] 时，已经被 rehash 的位置不会被添加到 des 中 */
            if (tables == 2 && j == 0 && i < (unsigned long) d->rehashidx) {
                /* Moreover, if we are currently out of range in the second
                 * table, there will be no elements in both tables up to
                 * the current rehashing index, so we jump if possible.
                 * (this happens when going from big to small table). */
                if (i >= DICTHT_SIZE(d->ht_size_exp[1]))
                    i = d->rehashidx;
                else
                    continue;
            }
            if (i >= DICTHT_SIZE(d->ht_size_exp[j])) continue; /* Out of range for this table. */
            dictEntry *he = d->ht_table[j][i];

            /* Count contiguous empty buckets, and jump to other
             * locations if they reach 'count' (with a minimum of 5). */
            if (he == NULL) {
                emptylen++;
                if (emptylen >= 5 && emptylen > count) {
                    i = randomULong() & maxsizemask;
                    emptylen = 0;
                }
            } else {
                emptylen = 0;
                while (he) {
                    /* Collect all the elements of the buckets found non
                     * empty while iterating. */
                    *des = he;
                    des++;
                    he = he->next;
                    stored++;
                    if (stored == count) return stored;
                }
            }
        }
        i = (i+1) & maxsizemask;
    }
    return stored;
}

/* This is like dictGetRandomKey() from the POV of the API, but will do more
 * work to ensure a better distribution of the returned element.
 *
 * This function improves the distribution because the dictGetRandomKey()
 * problem is that it selects a random bucket, then it selects a random
 * element from the chain in the bucket. However elements being in different
 * chain lengths will have different probabilities of being reported. With
 * this function instead what we do is to consider a "linear" range of the table
 * that may be constituted of N buckets with chains of different lengths
 * appearing one after the other. Then we report a random element in the range.
 * In this way we smooth away the problem of different chain lengths. */
/* 此方法和 dictGetRandomKey() 相似
 * 不同之处在于此方法能产生更离散的随机结果
 *
 * 在 dictGetRandomKey() 方法中，随机选取元素的粒度精确到桶
 * 由于 redis dict 采用链地址法，每个桶所含有的实体数量不一致，这样会导致在随机选取元素时并不能得到非常离散的结果
 *
 * 因此在此方法中，先采用随机粒度为实体的 dictGetSomeKeys() 方法获取实体列表
 * 通过再次在此列表中再次随机选取一个元素，达到更好的随机效果
 * */
#define GETFAIR_NUM_ENTRIES 15
dictEntry *dictGetFairRandomKey(dict *d) {
    dictEntry *entries[GETFAIR_NUM_ENTRIES];
    unsigned int count = dictGetSomeKeys(d,entries,GETFAIR_NUM_ENTRIES);
    /* Note that dictGetSomeKeys() may return zero elements in an unlucky
     * run() even if there are actually elements inside the hash table. So
     * when we get zero, we call the true dictGetRandomKey() that will always
     * yield the element if the hash table has at least one. */
    if (count == 0) return dictGetRandomKey(d);
    unsigned int idx = rand() % count;
    return entries[idx];
}

/* Function to reverse bits. Algorithm from:
 * http://graphics.stanford.edu/~seander/bithacks.html#ReverseParallel */
static unsigned long rev(unsigned long v) {
    unsigned long s = CHAR_BIT * sizeof(v); // bit size; must be power of 2
    unsigned long mask = ~0UL;
    while ((s >>= 1) > 0) {
        mask ^= (mask << s);
        v = ((v >> s) & mask) | ((v << s) & ~mask);
    }
    return v;
}

/* dictScan() is used to iterate over the elements of a dictionary.
 *
 * Iterating works the following way:
 *
 * 1) Initially you call the function using a cursor (v) value of 0.
 * 2) The function performs one step of the iteration, and returns the
 *    new cursor value you must use in the next call.
 * 3) When the returned cursor is 0, the iteration is complete.
 *
 * The function guarantees all elements present in the
 * dictionary get returned between the start and end of the iteration.
 * However it is possible some elements get returned multiple times.
 *
 * For every element returned, the callback argument 'fn' is
 * called with 'privdata' as first argument and the dictionary entry
 * 'de' as second argument.
 *
 * HOW IT WORKS.
 *
 * The iteration algorithm was designed by Pieter Noordhuis.
 * The main idea is to increment a cursor starting from the higher order
 * bits. That is, instead of incrementing the cursor normally, the bits
 * of the cursor are reversed, then the cursor is incremented, and finally
 * the bits are reversed again.
 *
 * This strategy is needed because the hash table may be resized between
 * iteration calls.
 *
 * dict.c hash tables are always power of two in size, and they
 * use chaining, so the position of an element in a given table is given
 * by computing the bitwise AND between Hash(key) and SIZE-1
 * (where SIZE-1 is always the mask that is equivalent to taking the rest
 *  of the division between the Hash of the key and SIZE).
 *
 * For example if the current hash table size is 16, the mask is
 * (in binary) 1111. The position of a key in the hash table will always be
 * the last four bits of the hash output, and so forth.
 *
 * WHAT HAPPENS IF THE TABLE CHANGES IN SIZE?
 *
 * If the hash table grows, elements can go anywhere in one multiple of
 * the old bucket: for example let's say we already iterated with
 * a 4 bit cursor 1100 (the mask is 1111 because hash table size = 16).
 *
 * If the hash table will be resized to 64 elements, then the new mask will
 * be 111111. The new buckets you obtain by substituting in ??1100
 * with either 0 or 1 can be targeted only by keys we already visited
 * when scanning the bucket 1100 in the smaller hash table.
 *
 * By iterating the higher bits first, because of the inverted counter, the
 * cursor does not need to restart if the table size gets bigger. It will
 * continue iterating using cursors without '1100' at the end, and also
 * without any other combination of the final 4 bits already explored.
 *
 * Similarly when the table size shrinks over time, for example going from
 * 16 to 8, if a combination of the lower three bits (the mask for size 8
 * is 111) were already completely explored, it would not be visited again
 * because we are sure we tried, for example, both 0111 and 1111 (all the
 * variations of the higher bit) so we don't need to test it again.
 *
 * WAIT... YOU HAVE *TWO* TABLES DURING REHASHING!
 *
 * Yes, this is true, but we always iterate the smaller table first, then
 * we test all the expansions of the current cursor into the larger
 * table. For example if the current cursor is 101 and we also have a
 * larger table of size 16, we also test (0)101 and (1)101 inside the larger
 * table. This reduces the problem back to having only one table, where
 * the larger one, if it exists, is just an expansion of the smaller one.
 *
 * LIMITATIONS
 *
 * This iterator is completely stateless, and this is a huge advantage,
 * including no additional memory used.
 *
 * The disadvantages resulting from this design are:
 *
 * 1) It is possible we return elements more than once. However this is usually
 *    easy to deal with in the application level.
 * 2) The iterator must return multiple elements per call, as it needs to always
 *    return all the keys chained in a given bucket, and all the expansions, so
 *    we are sure we don't miss keys moving during rehashing.
 * 3) The reverse cursor is somewhat hard to understand at first, but this
 *    comment is supposed to help.
 */
unsigned long dictScan(dict *d,
                       unsigned long v,
                       dictScanFunction *fn,
                       dictScanBucketFunction* bucketfn,
                       void *privdata)
{
    int htidx0, htidx1;
    const dictEntry *de, *next;
    unsigned long m0, m1;

    if (dictSize(d) == 0) return 0;

    /* This is needed in case the scan callback tries to do dictFind or alike. */
    dictPauseRehashing(d);

    if (!dictIsRehashing(d)) {
        htidx0 = 0;
        m0 = DICTHT_SIZE_MASK(d->ht_size_exp[htidx0]);

        /* Emit entries at cursor */
        if (bucketfn) bucketfn(d, &d->ht_table[htidx0][v & m0]);
        de = d->ht_table[htidx0][v & m0];
        while (de) {
            next = de->next;
            fn(privdata, de);
            de = next;
        }

        /* Set unmasked bits so incrementing the reversed cursor
         * operates on the masked bits */
        v |= ~m0;

        /* Increment the reverse cursor */
        v = rev(v);
        v++;
        v = rev(v);

    } else {
        htidx0 = 0;
        htidx1 = 1;

        /* Make sure t0 is the smaller and t1 is the bigger table */
        if (DICTHT_SIZE(d->ht_size_exp[htidx0]) > DICTHT_SIZE(d->ht_size_exp[htidx1])) {
            htidx0 = 1;
            htidx1 = 0;
        }

        m0 = DICTHT_SIZE_MASK(d->ht_size_exp[htidx0]);
        m1 = DICTHT_SIZE_MASK(d->ht_size_exp[htidx1]);

        /* Emit entries at cursor */
        if (bucketfn) bucketfn(d, &d->ht_table[htidx0][v & m0]);
        de = d->ht_table[htidx0][v & m0];
        while (de) {
            next = de->next;
            fn(privdata, de);
            de = next;
        }

        /* Iterate over indices in larger table that are the expansion
         * of the index pointed to by the cursor in the smaller table */
        do {
            /* Emit entries at cursor */
            if (bucketfn) bucketfn(d, &d->ht_table[htidx1][v & m1]);
            de = d->ht_table[htidx1][v & m1];
            while (de) {
                next = de->next;
                fn(privdata, de);
                de = next;
            }

            /* Increment the reverse cursor not covered by the smaller mask.*/
            v |= ~m1;
            v = rev(v);
            v++;
            v = rev(v);

            /* Continue while bits covered by mask difference is non-zero */
        } while (v & (m0 ^ m1));
    }

    dictResumeRehashing(d);

    return v;
}

/* ------------------------- private functions ------------------------------ */

/* Because we may need to allocate huge memory chunk at once when dict
 * expands, we will check this allocation is allowed or not if the dict
 * type has expandAllowed member function. */
static int dictTypeExpandAllowed(dict *d) {
    if (d->type->expandAllowed == NULL) return 1;
    return d->type->expandAllowed(
                    DICTHT_SIZE(_dictNextExp(d->ht_used[0] + 1)) * sizeof(dictEntry*),
                    (double)d->ht_used[0] / DICTHT_SIZE(d->ht_size_exp[0]));
}

/* Expand the hash table if needed */
static int _dictExpandIfNeeded(dict *d)
{
    /* Incremental rehashing already in progress. Return. */
    if (dictIsRehashing(d)) return DICT_OK;

    /* If the hash table is empty expand it to the initial size. */
    if (DICTHT_SIZE(d->ht_size_exp[0]) == 0) return dictExpand(d, DICT_HT_INITIAL_SIZE);

    /* If we reached the 1:1 ratio, and we are allowed to resize the hash
     * table (global setting) or we should avoid it but the ratio between
     * elements/buckets is over the "safe" threshold, we resize doubling
     * the number of buckets. */
    if (d->ht_used[0] >= DICTHT_SIZE(d->ht_size_exp[0]) &&
        (dict_can_resize ||
         d->ht_used[0]/ DICTHT_SIZE(d->ht_size_exp[0]) > dict_force_resize_ratio) &&
        dictTypeExpandAllowed(d))
    {
        return dictExpand(d, d->ht_used[0] + 1);
    }
    return DICT_OK;
}

/* TODO: clz optimization */
/* Our hash table capability is a power of two */
static signed char _dictNextExp(unsigned long size)
{
    unsigned char e = DICT_HT_INITIAL_EXP;

    if (size >= LONG_MAX) return (8*sizeof(long)-1);
    while(1) {
        if (((unsigned long)1<<e) >= size)
            return e;
        e++;
    }
}

/* 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. */
/* 此方法用于返回给定的 key 所在哈希表中的位置
 * 假如所给定的 key 在哈希表中并没有对应的实体，则返回一个可被插入键值对实体的 index，否则返回 -1
 *
 * 需要注意的是，如果在执行此方法时哈希表正处于重哈希的过程中，那么所返回的下标位置永远为新哈希表（ht_table[1]）中的位置
 * */
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 & DICTHT_SIZE_MASK(d->ht_size_exp[table]);
        /* Search if this slot does not already contain the given key */
        /* 此处用于检查 idx 所对应的桶不包含给定的 key */
        he = d->ht_table[table][idx];
        while(he) {
            /* 假如所找到的桶位置中实体 he 并不为空，则先对比此位置中的 key 是否与所给定的 key 相同
             * 如果相同，则将此位置赋值给 existing 并返回 -1*/
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                if (existing) *existing = he;
                return -1;
            }
            /* 如果不相同，则根据链地址法，继续在此桶中寻找到下一个可插入实体的位置
             * 此处的做法主要为了解决哈希冲突 */
            he = he->next;
        }
        /* 如果哈希表并不处于重哈希过程中，则结束寻找 idx 过程
         * 否则在新哈希表 （ht_table[1]）中重新寻找 idx，以达到在重哈希过程中只返回新表中 idx 的目的 */
        if (!dictIsRehashing(d)) break;
    }
    return idx;
}

void dictEmpty(dict *d, void(callback)(dict*)) {
    _dictClear(d,0,callback);
    _dictClear(d,1,callback);
    d->rehashidx = -1;
    d->pauserehash = 0;
}

void dictEnableResize(void) {
    dict_can_resize = 1;
}

void dictDisableResize(void) {
    dict_can_resize = 0;
}

uint64_t dictGetHash(dict *d, const void *key) {
    return dictHashKey(d, key);
}

/* Finds the dictEntry reference by using pointer and pre-calculated hash.
 * oldkey is a dead pointer and should not be accessed.
 * the hash value should be provided using dictGetHash.
 * no string / key comparison is performed.
 * return value is the reference to the dictEntry if found, or NULL if not found. */
dictEntry **dictFindEntryRefByPtrAndHash(dict *d, const void *oldptr, uint64_t hash) {
    dictEntry *he, **heref;
    unsigned long idx, table;

    if (dictSize(d) == 0) return NULL; /* dict is empty */
    for (table = 0; table <= 1; table++) {
        idx = hash & DICTHT_SIZE_MASK(d->ht_size_exp[table]);
        heref = &d->ht_table[table][idx];
        he = *heref;
        while(he) {
            if (oldptr==he->key)
                return heref;
            heref = &he->next;
            he = *heref;
        }
        if (!dictIsRehashing(d)) return NULL;
    }
    return NULL;
}

/* ------------------------------- Debugging ---------------------------------*/

#define DICT_STATS_VECTLEN 50
size_t _dictGetStatsHt(char *buf, size_t bufsize, dict *d, int htidx) {
    unsigned long i, slots = 0, chainlen, maxchainlen = 0;
    unsigned long totchainlen = 0;
    unsigned long clvector[DICT_STATS_VECTLEN];
    size_t l = 0;

    if (d->ht_used[htidx] == 0) {
        return snprintf(buf,bufsize,
            "No stats available for empty dictionaries\n");
    }

    /* Compute stats. */
    for (i = 0; i < DICT_STATS_VECTLEN; i++) clvector[i] = 0;
    for (i = 0; i < DICTHT_SIZE(d->ht_size_exp[htidx]); i++) {
        dictEntry *he;

        if (d->ht_table[htidx][i] == NULL) {
            clvector[0]++;
            continue;
        }
        slots++;
        /* For each hash entry on this slot... */
        chainlen = 0;
        he = d->ht_table[htidx][i];
        while(he) {
            chainlen++;
            he = he->next;
        }
        clvector[(chainlen < DICT_STATS_VECTLEN) ? chainlen : (DICT_STATS_VECTLEN-1)]++;
        if (chainlen > maxchainlen) maxchainlen = chainlen;
        totchainlen += chainlen;
    }

    /* Generate human readable stats. */
    l += snprintf(buf+l,bufsize-l,
        "Hash table %d stats (%s):\n"
        " table size: %lu\n"
        " number of elements: %lu\n"
        " different slots: %lu\n"
        " max chain length: %lu\n"
        " avg chain length (counted): %.02f\n"
        " avg chain length (computed): %.02f\n"
        " Chain length distribution:\n",
        htidx, (htidx == 0) ? "main hash table" : "rehashing target",
        DICTHT_SIZE(d->ht_size_exp[htidx]), d->ht_used[htidx], slots, maxchainlen,
        (float)totchainlen/slots, (float)d->ht_used[htidx]/slots);

    for (i = 0; i < DICT_STATS_VECTLEN-1; i++) {
        if (clvector[i] == 0) continue;
        if (l >= bufsize) break;
        l += snprintf(buf+l,bufsize-l,
            "   %ld: %ld (%.02f%%)\n",
            i, clvector[i], ((float)clvector[i]/DICTHT_SIZE(d->ht_size_exp[htidx]))*100);
    }

    /* Unlike snprintf(), return the number of characters actually written. */
    if (bufsize) buf[bufsize-1] = '\0';
    return strlen(buf);
}

void dictGetStats(char *buf, size_t bufsize, dict *d) {
    size_t l;
    char *orig_buf = buf;
    size_t orig_bufsize = bufsize;

    l = _dictGetStatsHt(buf,bufsize,d,0);
    buf += l;
    bufsize -= l;
    if (dictIsRehashing(d) && bufsize > 0) {
        _dictGetStatsHt(buf,bufsize,d,1);
    }
    /* Make sure there is a NULL term at the end. */
    if (orig_bufsize) orig_buf[orig_bufsize-1] = '\0';
}

/* ------------------------------- Benchmark ---------------------------------*/

#ifdef REDIS_TEST
#include "testhelp.h"

#define UNUSED(V) ((void) V)

uint64_t hashCallback(const void *key) {
    return dictGenHashFunction((unsigned char*)key, strlen((char*)key));
}

int compareCallback(dict *d, const void *key1, const void *key2) {
    int l1,l2;
    UNUSED(d);

    l1 = strlen((char*)key1);
    l2 = strlen((char*)key2);
    if (l1 != l2) return 0;
    return memcmp(key1, key2, l1) == 0;
}

void freeCallback(dict *d, void *val) {
    UNUSED(d);

    zfree(val);
}

char *stringFromLongLong(long long value) {
    char buf[32];
    int len;
    char *s;

    len = sprintf(buf,"%lld",value);
    s = zmalloc(len+1);
    memcpy(s, buf, len);
    s[len] = '\0';
    return s;
}

dictType BenchmarkDictType = {
    hashCallback,
    NULL,
    NULL,
    compareCallback,
    freeCallback,
    NULL,
    NULL
};

#define start_benchmark() start = timeInMilliseconds()
#define end_benchmark(msg) do { \
    elapsed = timeInMilliseconds()-start; \
    printf(msg ": %ld items in %lld ms\n", count, elapsed); \
} while(0)

/* ./redis-server test dict [<count> | --accurate] */
int dictTest(int argc, char **argv, int flags) {
    long j;
    long long start, elapsed;
    dict *dict = dictCreate(&BenchmarkDictType);
    long count = 0;
    int accurate = (flags & REDIS_TEST_ACCURATE);

    if (argc == 4) {
        if (accurate) {
            count = 5000000;
        } else {
            count = strtol(argv[3],NULL,10);
        }
    } else {
        count = 5000;
    }

    start_benchmark();
    for (j = 0; j < count; j++) {
        int retval = dictAdd(dict,stringFromLongLong(j),(void*)j);
        assert(retval == DICT_OK);
    }
    end_benchmark("Inserting");
    assert((long)dictSize(dict) == count);

    /* Wait for rehashing. */
    while (dictIsRehashing(dict)) {
        dictRehashMilliseconds(dict,100);
    }

    start_benchmark();
    for (j = 0; j < count; j++) {
        char *key = stringFromLongLong(j);
        dictEntry *de = dictFind(dict,key);
        assert(de != NULL);
        zfree(key);
    }
    end_benchmark("Linear access of existing elements");

    start_benchmark();
    for (j = 0; j < count; j++) {
        char *key = stringFromLongLong(j);
        dictEntry *de = dictFind(dict,key);
        assert(de != NULL);
        zfree(key);
    }
    end_benchmark("Linear access of existing elements (2nd round)");

    start_benchmark();
    for (j = 0; j < count; j++) {
        char *key = stringFromLongLong(rand() % count);
        dictEntry *de = dictFind(dict,key);
        assert(de != NULL);
        zfree(key);
    }
    end_benchmark("Random access of existing elements");

    start_benchmark();
    for (j = 0; j < count; j++) {
        dictEntry *de = dictGetRandomKey(dict);
        assert(de != NULL);
    }
    end_benchmark("Accessing random keys");

    start_benchmark();
    for (j = 0; j < count; j++) {
        char *key = stringFromLongLong(rand() % count);
        key[0] = 'X';
        dictEntry *de = dictFind(dict,key);
        assert(de == NULL);
        zfree(key);
    }
    end_benchmark("Accessing missing");

    start_benchmark();
    for (j = 0; j < count; j++) {
        char *key = stringFromLongLong(j);
        int retval = dictDelete(dict,key);
        assert(retval == DICT_OK);
        key[0] += 17; /* Change first number to letter. */
        retval = dictAdd(dict,key,(void*)j);
        assert(retval == DICT_OK);
    }
    end_benchmark("Removing and adding");
    dictRelease(dict);
    return 0;
}
#endif