[redis 源碼走讀] 整數集合(inset)

整數集合

整數集合，是一個有序的數值數組對象，存儲的數值不允許重複。源碼在 intset.c

---

數據結構

/* Note that these encodings are ordered, so:
 * INTSET_ENC_INT16 < INTSET_ENC_INT32 < INTSET_ENC_INT64. */
#define INTSET_ENC_INT16 (sizeof(int16_t))
#define INTSET_ENC_INT32 (sizeof(int32_t))
#define INTSET_ENC_INT64 (sizeof(int64_t))

typedef struct intset {
    uint32_t encoding; // 編碼。
    uint32_t length;   // 數組長度。
    int8_t contents[]; // 整數值數值。
} intset;

根據插入數值大小，決定 contents 數組的encoding格式。編碼格式分別有 int16_t，int32_t，int64_t。以最大的數值爲準，如果最大的數值是 int64_t 那麼數組的每個 item 都是 int64_t，優點是統一簡單，提高數組查找效率——源碼實現是通過二分法查找。如果數組不同數值用不同的編碼存儲，就很難用二分法查找了。
但是這樣做一方面提高了查找效率，另一方面也會導致內存浪費，如果所有數據中，只有一個數據是 int64_t，其它數據都是 int16_t，整個數組 item 都以 int64_t 存儲，顯然會造成內存浪費。
當然 redis 的數據結構是豐富的，連續內存上的數據管理有：字符串對象（sds），壓縮列表（ziplist），這裏有整數集合（intset），都分別針對不同的應用場景進行應用。

---

接口

數值編碼

#define INT8_MAX         127
#define INT16_MAX        32767
#define INT32_MAX        2147483647
#define INT64_MAX        9223372036854775807LL

#define INT8_MIN          -128
#define INT16_MIN         -32768

/* Return the required encoding for the provided value. */
static uint8_t _intsetValueEncoding(int64_t v) {
    if (v < INT32_MIN || v > INT32_MAX)
        return INTSET_ENC_INT64;
    else if (v < INT16_MIN || v > INT16_MAX)
        return INTSET_ENC_INT32;
    else
        return INTSET_ENC_INT16;
}

插入數據

檢查插入數據是否大於當前編碼格式，決定是否需要升級

/* Insert an integer in the intset */
intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
    uint8_t valenc = _intsetValueEncoding(value);
    uint32_t pos;
    if (success) *success = 1;

    /* Upgrade encoding if necessary. If we need to upgrade, we know that
     * this value should be either appended (if > 0) or prepended (if < 0),
     * because it lies outside the range of existing values. */
    // 如果插入數值大於當前編碼，那麼需要升級數組
    if (valenc > intrev32ifbe(is->encoding)) {
        /* This always succeeds, so we don't need to curry *success. */
        return intsetUpgradeAndAdd(is,value);
    } else {
        /* Abort if the value is already present in the set.
         * This call will populate "pos" with the right position to insert
         * the value when it cannot be found. */
        // 如果數值已經存在，就不需要插入數據了。*success = 0;
        if (intsetSearch(is,value,&pos)) {
            if (success) *success = 0;
            return is;
        }

        // 數據增長，重新申請內存。
        is = intsetResize(is,intrev32ifbe(is->length)+1);
        if (pos < intrev32ifbe(is->length)) intsetMoveTail(is,pos,pos+1);
    }

    _intsetSet(is,pos,value);
    is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
    return is;
}

升級

/* Upgrades the intset to a larger encoding and inserts the given integer. */
static intset *intsetUpgradeAndAdd(intset *is, int64_t value) {
    uint8_t curenc = intrev32ifbe(is->encoding);
    uint8_t newenc = _intsetValueEncoding(value);
    int length = intrev32ifbe(is->length);

    // 因爲插入新的數據，而且數據超出了當前數組所有數值的範圍纔會升級。
    // 超出了負數，或者超出了正數。正數在數組末添加，負數在數組前面添加。
    int prepend = value < 0 ? 1 : 0;

    /* First set new encoding and resize */
    is->encoding = intrev32ifbe(newenc);
    is = intsetResize(is,intrev32ifbe(is->length)+1);

    /* Upgrade back-to-front so we don't overwrite values.
     * Note that the "prepend" variable is used to make sure we have an empty
     * space at either the beginning or the end of the intset. */
    // 擴充內存後，遷移數據。
    while(length--)
        _intsetSet(is,length+prepend,_intsetGetEncoded(is,length,curenc));

    /* Set the value at the beginning or the end. */
    if (prepend)
        _intsetSet(is,0,value);
    else
        _intsetSet(is,intrev32ifbe(is->length),value);
    is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
    return is;
}

搜索

二分法搜索數組數據。

/* Search for the position of "value". Return 1 when the value was found and
 * sets "pos" to the position of the value within the intset. Return 0 when
 * the value is not present in the intset and sets "pos" to the position
 * where "value" can be inserted. */
static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
    int min = 0, max = intrev32ifbe(is->length)-1, mid = -1;
    int64_t cur = -1;

    /* The value can never be found when the set is empty */
    if (intrev32ifbe(is->length) == 0) {
        if (pos) *pos = 0;
        return 0;
    } else {
        // 檢查數值是否大於或小於數組裏的所有數值。
        /* Check for the case where we know we cannot find the value,
         * but do know the insert position. */
        if (value > _intsetGet(is,max)) {
            if (pos) *pos = intrev32ifbe(is->length);
            return 0;
        } else if (value < _intsetGet(is,0)) {
            if (pos) *pos = 0;
            return 0;
        }
    }

    // 數值如果在存儲的數據中間，用二分法查找。
    while(max >= min) {
        mid = ((unsigned int)min + (unsigned int)max) >> 1;
        cur = _intsetGet(is,mid);
        if (value > cur) {
            min = mid+1;
        } else if (value < cur) {
            max = mid-1;
        } else {
            break;
        }
    }

    if (value == cur) {
        if (pos) *pos = mid;
        return 1;
    } else {
        if (pos) *pos = min;
        return 0;
    }
}