Redis의 SCAN은 어떻게 동작하는가?

void scanGenericCommand(redisClient *c, robj *o, unsigned long cursor) {
    ......
    ht = NULL;
    if (o == NULL) {
        ht = c->db->dict;
    } else if (o->type == REDIS_SET && o->encoding == REDIS_ENCODING_HT) {
        ht = o->ptr;
    } else if (o->type == REDIS_HASH && o->encoding == REDIS_ENCODING_HT) {
        ht = o->ptr;
        count *= 2; /* We return key / value for this type. */
    } else if (o->type == REDIS_ZSET && o->encoding == REDIS_ENCODING_SKIPLIST) {
        zset *zs = o->ptr;
        ht = zs->dict;
        count *= 2; /* We return key / value for this type. */
    }

    if (ht) {
        void *privdata[2];

        /* We pass two pointers to the callback: the list to which it will
         * add new elements, and the object containing the dictionary so that
         * it is possible to fetch more data in a type-dependent way. */
        privdata[0] = keys;
        privdata[1] = o;
        do {
            cursor = dictScan(ht, cursor, scanCallback, privdata);
        } while (cursor && listLength(keys) < count);
    } else if (o->type == REDIS_SET) {
        int pos = 0;
        int64_t ll;

        while(intsetGet(o->ptr,pos++,&ll))
            listAddNodeTail(keys,createStringObjectFromLongLong(ll));
        cursor = 0;
    } else if (o->type == REDIS_HASH || o->type == REDIS_ZSET) {
        unsigned char *p = ziplistIndex(o->ptr,0);
        unsigned char *vstr;
        unsigned int vlen;
        long long vll;

        while(p) {
            ziplistGet(p,&vstr,&vlen,&vll);
            listAddNodeTail(keys,
                (vstr != NULL) ? createStringObject((char*)vstr,vlen) :
                                 createStringObjectFromLongLong(vll));
            p = ziplistNext(o->ptr,p);
        }
        cursor = 0;
    } else {
        redisPanic("Not handled encoding in SCAN.");
    }

    ......

/* MurmurHash2, by Austin Appleby
 * Note - This code makes a few assumptions about how your machine behaves -
 * 1. We can read a 4-byte value from any address without crashing
 * 2. sizeof(int) == 4
 *
 * And it has a few limitations -
 *
 * 1. It will not work incrementally.
 * 2. It will not produce the same results on little-endian and big-endian
 *    machines.
 */
unsigned int dictGenHashFunction(const void *key, int len) {
    /* 'm' and 'r' are mixing constants generated offline.
     They're not really 'magic', they just happen to work well.  */
    uint32_t seed = dict_hash_function_seed;
    const uint32_t m = 0x5bd1e995;
    const int r = 24;

    /* Initialize the hash to a 'random' value */
    uint32_t h = seed ^ len;

    /* Mix 4 bytes at a time into the hash */
    const unsigned char *data = (const unsigned char *)key;

    while(len >= 4) {
        uint32_t k = *(uint32_t*)data;

        k *= m;
        k ^= k >> r;
        k *= m;

        h *= m;
        h ^= k;

        data += 4;
        len -= 4;
    }

    /* Handle the last few bytes of the input array  */
    switch(len) {
    case 3: h ^= data[2] << 16;
    case 2: h ^= data[1] << 8;
    case 1: h ^= data[0]; h *= m;
    };

    /* Do a few final mixes of the hash to ensure the last few
     * bytes are well-incorporated. */
    h ^= h >> 13;
    h *= m;
    h ^= h >> 15;

    return (unsigned int)h;
}

/* 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.
 *
 * 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 int _dictKeyIndex(dict *d, const void *key)
{
    ......
    h = dictHashKey(d, key);
    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        ......
    }
    return idx;
}

t0 = &(d->ht[0]);
m0 = t0->sizemask;

/* Emit entries at cursor */
de = t0->table[v & m0];
while (de) {
    fn(privdata, de);
    de = de->next;
}

/* 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 (d->ht[0].size == 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[0].used >= d->ht[0].size &&
        (dict_can_resize ||
         d->ht[0].used/d->ht[0].size > dict_force_resize_ratio))
    {
        return dictExpand(d, d->ht[0].used*2);
    }
    return DICT_OK;
}

#define dictIsRehashing(d) ((d)->rehashidx != -1)

/* 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;

    /* 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;
}

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 */
    int iterators; /* number of iterators currently running */
} dict;

/* 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. */
int dictRehash(dict *d, int n) {
    if (!dictIsRehashing(d)) return 0;

    while(n--) {
        dictEntry *de, *nextde;

        /* 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;
        }

        /* 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++;
        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++;
    }
    return 1;
}

} else {
    t0 = &d->ht[0];
    t1 = &d->ht[1];

    /* Make sure t0 is the smaller and t1 is the bigger table */
    if (t0->size > t1->size) {
        t0 = &d->ht[1];
        t1 = &d->ht[0];
    }

    m0 = t0->sizemask;
    m1 = t1->sizemask;

    /* Emit entries at cursor */
    de = t0->table[v & m0];
    while (de) {
        fn(privdata, de);
        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 */
        de = t1->table[v & m1];
        while (de) {
            fn(privdata, de);
            de = de->next;
        }

        /* Increment bits not covered by the smaller mask */
        v = (((v | m0) + 1) & ~m0) | (v & m0);

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

v = (((v | m0) + 1) & ~m0) | (v & m0);

unsigned long dictScan(dict *d,
                       unsigned long v,
                       dictScanFunction *fn,
                       void *privdata)
{
    dictht *t0, *t1;
    const dictEntry *de;
    unsigned long m0, m1;

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

    if (!dictIsRehashing(d)) {
        t0 = &(d->ht[0]);
        m0 = t0->sizemask;

        /* Emit entries at cursor */
        de = t0->table[v & m0];
        while (de) {
            fn(privdata, de);
            de = de->next;
        }

    } else {
      ......
    }

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

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

    return v;
}

/* Function to reverse bits. Algorithm from:
 * http://graphics.stanford.edu/~seander/bithacks.html#ReverseParallel */
static unsigned long rev(unsigned long v) {
    unsigned long s = 8 * sizeof(v); // bit size; must be power of 2
    unsigned long mask = ~0;
    while ((s >>= 1) > 0) {
        mask ^= (mask << s);
        v = ((v >> s) & mask) | ((v << s) & ~mask);
    }
    return v;
}