Redis 源码分析-ziplist

发表于 | 分类于 ， | 阅读次数：

ziplist本质上就是字符串数组
当存储元素数量<UINT16_MAX时,可以直接读取长度
当存储元素数量>=UINT16_MAX时,需要遍历整个ziplist才能获取长度
采用了不同的编码来对数字,字符串存储进行了压缩

  • 结构
    <总字节数(4字节)><最后一个元素的偏移量(从头开始算)(4字节)><总元素个数(2字节)><数据(不定字节)>…<0xFF结尾标记(1字节)>
  • 数据的结构
    • 头
      • 前一个数据的编码类型和长度
        • 当长度小于0xFE时,是一个字节
        • 当长度大于等于0xFE时,是5个字节(第一个字节+4个字节的长度信息)
      • 当前数据的编码类型和长度
        第一个字节的前两位
        • 字符串
          • 00??????
            数据头总共占用一个字节
            后六位表示字符串长度
          • 01??????|????????
            数据头总共占用两个字节
            后14位表示字符串长度
          • 10______|????????|????????|????????|????????
            数据头总共占用5个字节
            后4个字节表示字符串长度
        • 数字
          • 11000000
            表示int16_t
            后面两个字节为具体数据
          • 11010000
            表示int32_t
            后面4个字节为具体数据
          • 11100000
            表示int64_t
            后面8个字节为具体数据
          • 11110000
            表示int24_t
            后面3个字节为具体数据
          • 11111110
            表示int8_t
            后面1个字节为具体数据
          • 11110001-11111101
            直接表示0-12的值
            后面没有数据
            值直接就在当前字节中
            其中
            11110001 0
            11110010 1
            …
            11111101 12
            就是字节后4位的值直接转化为整数
            然后-1所得的值
            结尾不是1110是因为1110为int8_t
            结尾不是1111是因为1111为ziplist结尾标记
    • 数据
      根据数据长度定义的连续字符串

相关文件

  • ziplist.h
  • ziplist.c

数据结构

1
2
3
4
5
6
7
typedef struct zlentry { // ziplist的单个entry元素结构体
    unsigned int prevrawlensize, prevrawlen; // 前一个元素的长度的编码长度,前一个元素的长度
    unsigned int lensize, len; // 当前元素的长度编码的长度,当前元素的长度
    unsigned int headersize; // prevrawlensize+lensize的值(就是从元素开始到该元素数据记录开始的字节数)(长度值是编码的数据)
    unsigned char encoding; // 当前元素所使用的编码类型
    unsigned char *p; // 数据(是头指针,不是数据指针,就是从前一个元素的长度那里开始的指针)
} zlentry;

主要宏

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
#define ZIP_END 255
#define ZIP_BIGLEN 254

/* Different encoding/length possibilities */
#define ZIP_STR_MASK 0xc0 // 就是11000000
#define ZIP_INT_MASK 0x30 // 就是00110000
#define ZIP_STR_06B (0 << 6) // 判断类型用
#define ZIP_STR_14B (1 << 6)
#define ZIP_STR_32B (2 << 6)
#define ZIP_INT_16B (0xc0 | 0<<4)
#define ZIP_INT_32B (0xc0 | 1<<4)
#define ZIP_INT_64B (0xc0 | 2<<4)
#define ZIP_INT_24B (0xc0 | 3<<4)
#define ZIP_INT_8B 0xfe
/* 4 bit integer immediate encoding */
#define ZIP_INT_IMM_MASK 0x0f
#define ZIP_INT_IMM_MIN 0xf1    /* 11110001 */
#define ZIP_INT_IMM_MAX 0xfd    /* 11111101 */
#define ZIP_INT_IMM_VAL(v) (v & ZIP_INT_IMM_MASK)

#define INT24_MAX 0x7fffff
#define INT24_MIN (-INT24_MAX - 1)

/* Macro to determine type */
#define ZIP_IS_STR(enc) (((enc) & ZIP_STR_MASK) < ZIP_STR_MASK) // 判断编码是否是字符串

/* Utility macros */
#define ZIPLIST_BYTES(zl)       (*((uint32_t*)(zl))) // 获取ziplist的字节数
#define ZIPLIST_TAIL_OFFSET(zl) (*((uint32_t*)((zl)+sizeof(uint32_t)))) // 获取ziplist的最后一个元素的偏移值
#define ZIPLIST_LENGTH(zl)      (*((uint16_t*)((zl)+sizeof(uint32_t)*2))) // 获取ziplist的元素个数
#define ZIPLIST_HEADER_SIZE     (sizeof(uint32_t)*2+sizeof(uint16_t)) // ziplist的头的字节数
#define ZIPLIST_END_SIZE        (sizeof(uint8_t)) // ziplist的结尾的字节数
#define ZIPLIST_ENTRY_HEAD(zl)  ((zl)+ZIPLIST_HEADER_SIZE) // 获取ziplist的第一个元素
#define ZIPLIST_ENTRY_TAIL(zl)  ((zl)+intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))) // 获取ziplist的最后一个元素
#define ZIPLIST_ENTRY_END(zl)   ((zl)+intrev32ifbe(ZIPLIST_BYTES(zl))-1) // 获取ziplist的结尾的指针

/* We know a positive increment can only be 1 because entries can only be
 * pushed one at a time. */
#define ZIPLIST_INCR_LENGTH(zl,incr) { \ // 增加ziplist的元素个数
    if (ZIPLIST_LENGTH(zl) < UINT16_MAX) \
        ZIPLIST_LENGTH(zl) = intrev16ifbe(intrev16ifbe(ZIPLIST_LENGTH(zl))+incr); \
}

#define ZIPLIST_ENTRY_ZERO(zle) { \ // 将元素置空
    (zle)->prevrawlensize = (zle)->prevrawlen = 0; \
    (zle)->lensize = (zle)->len = (zle)->headersize = 0; \
    (zle)->encoding = 0; \
    (zle)->p = NULL; \
}

/* Extract the encoding from the byte pointed by 'ptr' and set it into
 * 'encoding'. */
#define ZIP_ENTRY_ENCODING(ptr, encoding) do {  \ // 获取元素编码
    (encoding) = (ptr[0]); \
    if ((encoding) < ZIP_STR_MASK) (encoding) &= ZIP_STR_MASK; \
} while(0)

/* Decode the length encoded in 'ptr'. The 'encoding' variable will hold the
 * entries encoding, the 'lensize' variable will hold the number of bytes
 * required to encode the entries length, and the 'len' variable will hold the
 * entries length. */
#define ZIP_DECODE_LENGTH(ptr, encoding, lensize, len) do {                    \ // 根据编码获取到元素长度占用字节和元素长度
    ZIP_ENTRY_ENCODING((ptr), (encoding));                                     \
    if ((encoding) < ZIP_STR_MASK) {                                           \
        if ((encoding) == ZIP_STR_06B) {                                       \
            (lensize) = 1;                                                     \
            (len) = (ptr)[0] & 0x3f;                                           \
        } else if ((encoding) == ZIP_STR_14B) {                                \
            (lensize) = 2;                                                     \
            (len) = (((ptr)[0] & 0x3f) << 8) | (ptr)[1];                       \
        } else if (encoding == ZIP_STR_32B) {                                  \
            (lensize) = 5;                                                     \
            (len) = ((ptr)[1] << 24) |                                         \
                    ((ptr)[2] << 16) |                                         \
                    ((ptr)[3] <<  8) |                                         \
                    ((ptr)[4]);                                                \
        } else {                                                               \
            assert(NULL);                                                      \
        }                                                                      \
    } else {                                                                   \
        (lensize) = 1;                                                         \
        (len) = zipIntSize(encoding);                                          \
    }                                                                          \
} while(0);

/* Decode the number of bytes required to store the length of the previous
 * element, from the perspective of the entry pointed to by 'ptr'. */
#define ZIP_DECODE_PREVLENSIZE(ptr, prevlensize) do {                          \ // 获取前一个元素的长度记录的字节数
    if ((ptr)[0] < ZIP_BIGLEN) {                                               \
        (prevlensize) = 1;                                                     \
    } else {                                                                   \
        (prevlensize) = 5;                                                     \
    }                                                                          \
} while(0);

/* Decode the length of the previous element, from the perspective of the entry
 * pointed to by 'ptr'. */
#define ZIP_DECODE_PREVLEN(ptr, prevlensize, prevlen) do {                     \ // 获取前一个元素的长度记录的字节数和前一个元素的数据长度
    ZIP_DECODE_PREVLENSIZE(ptr, prevlensize);                                  \
    if ((prevlensize) == 1) {                                                  \
        (prevlen) = (ptr)[0];                                                  \
    } else if ((prevlensize) == 5) {                                           \
        assert(sizeof((prevlensize)) == 4);                                    \
        memcpy(&(prevlen), ((char*)(ptr)) + 1, 4);                             \
        memrev32ifbe(&prevlen);                                                \
    }                                                                          \
} while(0);

函数分析

unsigned int zipIntSize(unsigned char encoding);

功能

根据编码获取编码占用字节数

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
/* Return bytes needed to store integer encoded by 'encoding' */
unsigned int zipIntSize(unsigned char encoding) {
    switch(encoding) {
    case ZIP_INT_8B:  return 1;
    case ZIP_INT_16B: return 2;
    case ZIP_INT_24B: return 3;
    case ZIP_INT_32B: return 4;
    case ZIP_INT_64B: return 8;
    default: return 0; /* 4 bit immediate */
    }
    assert(NULL);
    return 0;
}

unsigned int zipEncodeLength(unsigned char *p, unsigned char encoding, unsigned int rawlen);

功能

设置编码,长度到ziplist中

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
/* Encode the length 'rawlen' writing it in 'p'. If p is NULL it just returns
 * the amount of bytes required to encode such a length. */
unsigned int zipEncodeLength(unsigned char *p, unsigned char encoding, unsigned int rawlen) {
    unsigned char len = 1, buf[5];

    if (ZIP_IS_STR(encoding)) {
        /* Although encoding is given it may not be set for strings,
         * so we determine it here using the raw length. */
        if (rawlen <= 0x3f) {
            if (!p) return len;
            buf[0] = ZIP_STR_06B | rawlen;
        } else if (rawlen <= 0x3fff) {
            len += 1;
            if (!p) return len;
            buf[0] = ZIP_STR_14B | ((rawlen >> 8) & 0x3f);
            buf[1] = rawlen & 0xff;
        } else {
            len += 4;
            if (!p) return len;
            buf[0] = ZIP_STR_32B;
            buf[1] = (rawlen >> 24) & 0xff;
            buf[2] = (rawlen >> 16) & 0xff;
            buf[3] = (rawlen >> 8) & 0xff;
            buf[4] = rawlen & 0xff;
        }
    } else {
        /* Implies integer encoding, so length is always 1. */
        if (!p) return len;
        buf[0] = encoding;
    }

    /* Store this length at p */
    memcpy(p,buf,len);
    return len;
}

unsigned int zipPrevEncodeLength(unsigned char *p, unsigned int len);

功能

设置前一个元素的长度到数据中
当p为NULL时直接返回需要存储该长度需要的字节数

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
/* Encode the length of the previous entry and write it to "p". Return the
 * number of bytes needed to encode this length if "p" is NULL. */
unsigned int zipPrevEncodeLength(unsigned char *p, unsigned int len) {
    if (p == NULL) {
        return (len < ZIP_BIGLEN) ? 1 : sizeof(len)+1;
    } else {
        if (len < ZIP_BIGLEN) {
            p[0] = len;
            return 1;
        } else {
            p[0] = ZIP_BIGLEN;
            memcpy(p+1,&len,sizeof(len));
            memrev32ifbe(p+1);
            return 1+sizeof(len);
        }
    }
}

void zipPrevEncodeLengthForceLarge(unsigned char *p, unsigned int len);

功能

强制使用5个字节的长度标记记录前一个字节的长度信息

源码

1
2
3
4
5
6
7
8
/* Encode the length of the previous entry and write it to "p". This only
 * uses the larger encoding (required in __ziplistCascadeUpdate). */
void zipPrevEncodeLengthForceLarge(unsigned char *p, unsigned int len) {
    if (p == NULL) return;
    p[0] = ZIP_BIGLEN;
    memcpy(p+1,&len,sizeof(len));
    memrev32ifbe(p+1);
}

int zipPrevLenByteDiff(unsigned char *p, unsigned int len);

功能

获取到要存储len长度的数据需要的字节数和前一个元素当前存储长度所用的字节数的差值

源码

1
2
3
4
5
6
7
/* Return the difference in number of bytes needed to store the length of the
 * previous element 'len', in the entry pointed to by 'p'. */
int zipPrevLenByteDiff(unsigned char *p, unsigned int len) {
    unsigned int prevlensize;
    ZIP_DECODE_PREVLENSIZE(p, prevlensize);
    return zipPrevEncodeLength(NULL, len) - prevlensize;
}

unsigned int zipRawEntryLength(unsigned char *p);

功能

获取到元素的整体长度
前一个元素的长度+当前元素的长度+当前元素的数据长度

源码

1
2
3
4
5
6
7
/* Return the total number of bytes used by the entry pointed to by 'p'. */
unsigned int zipRawEntryLength(unsigned char *p) {
    unsigned int prevlensize, encoding, lensize, len;
    ZIP_DECODE_PREVLENSIZE(p, prevlensize);
    ZIP_DECODE_LENGTH(p + prevlensize, encoding, lensize, len);
    return prevlensize + lensize + len;
}

int zipTryEncoding(unsigned char *entry, unsigned int entrylen, long long *v, unsigned char *encoding);

功能

将字符串转化为数字,并将可以存储该数字的编码格式返回

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
/* Check if string pointed to by 'entry' can be encoded as an integer.
 * Stores the integer value in 'v' and its encoding in 'encoding'. */
int zipTryEncoding(unsigned char *entry, unsigned int entrylen, long long *v, unsigned char *encoding) {
    long long value;

    if (entrylen >= 32 || entrylen == 0) return 0;
    if (string2ll((char*)entry,entrylen,&value)) {
        /* Great, the string can be encoded. Check what's the smallest
         * of our encoding types that can hold this value. */
        if (value >= 0 && value <= 12) {
            *encoding = ZIP_INT_IMM_MIN+value;
        } else if (value >= INT8_MIN && value <= INT8_MAX) {
            *encoding = ZIP_INT_8B;
        } else if (value >= INT16_MIN && value <= INT16_MAX) {
            *encoding = ZIP_INT_16B;
        } else if (value >= INT24_MIN && value <= INT24_MAX) {
            *encoding = ZIP_INT_24B;
        } else if (value >= INT32_MIN && value <= INT32_MAX) {
            *encoding = ZIP_INT_32B;
        } else {
            *encoding = ZIP_INT_64B;
        }
        *v = value;
        return 1;
    }
    return 0;
}

void zipSaveInteger(unsigned char *p, int64_t value, unsigned char encoding);

功能

根据编码格式将值存储在字符数组中

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
/* Store integer 'value' at 'p', encoded as 'encoding' */
void zipSaveInteger(unsigned char *p, int64_t value, unsigned char encoding) {
    int16_t i16;
    int32_t i32;
    int64_t i64;
    if (encoding == ZIP_INT_8B) {
        ((int8_t*)p)[0] = (int8_t)value;
    } else if (encoding == ZIP_INT_16B) {
        i16 = value;
        memcpy(p,&i16,sizeof(i16));
        memrev16ifbe(p);
    } else if (encoding == ZIP_INT_24B) {
        i32 = value<<8;
        memrev32ifbe(&i32);
        memcpy(p,((uint8_t*)&i32)+1,sizeof(i32)-sizeof(uint8_t));
    } else if (encoding == ZIP_INT_32B) {
        i32 = value;
        memcpy(p,&i32,sizeof(i32));
        memrev32ifbe(p);
    } else if (encoding == ZIP_INT_64B) {
        i64 = value;
        memcpy(p,&i64,sizeof(i64));
        memrev64ifbe(p);
    } else if (encoding >= ZIP_INT_IMM_MIN && encoding <= ZIP_INT_IMM_MAX) {
        /* Nothing to do, the value is stored in the encoding itself. */
    } else {
        assert(NULL);
    }
}

int64_t zipLoadInteger(unsigned char *p, unsigned char encoding);

功能

根据编码读取数字数据

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
/* Read integer encoded as 'encoding' from 'p' */
int64_t zipLoadInteger(unsigned char *p, unsigned char encoding) {
    int16_t i16;
    int32_t i32;
    int64_t i64, ret = 0;
    if (encoding == ZIP_INT_8B) {
        ret = ((int8_t*)p)[0];
    } else if (encoding == ZIP_INT_16B) {
        memcpy(&i16,p,sizeof(i16));
        memrev16ifbe(&i16);
        ret = i16;
    } else if (encoding == ZIP_INT_32B) {
        memcpy(&i32,p,sizeof(i32));
        memrev32ifbe(&i32);
        ret = i32;
    } else if (encoding == ZIP_INT_24B) {
        i32 = 0;
        memcpy(((uint8_t*)&i32)+1,p,sizeof(i32)-sizeof(uint8_t));
        memrev32ifbe(&i32);
        ret = i32>>8;
    } else if (encoding == ZIP_INT_64B) {
        memcpy(&i64,p,sizeof(i64));
        memrev64ifbe(&i64);
        ret = i64;
    } else if (encoding >= ZIP_INT_IMM_MIN && encoding <= ZIP_INT_IMM_MAX) {
        ret = (encoding & ZIP_INT_IMM_MASK)-1;
    } else {
        assert(NULL);
    }
    return ret;
}

void zipEntry(unsigned char *p, zlentry *e);

功能

读取一个完整的zlentry

源码

1
2
3
4
5
6
7
8
/* Return a struct with all information about an entry. */
void zipEntry(unsigned char *p, zlentry *e) {

    ZIP_DECODE_PREVLEN(p, e->prevrawlensize, e->prevrawlen);
    ZIP_DECODE_LENGTH(p + e->prevrawlensize, e->encoding, e->lensize, e->len);
    e->headersize = e->prevrawlensize + e->lensize;
    e->p = p;
}

unsigned char *ziplistNew(void);

功能

创建一个新的ziplist

源码

1
2
3
4
5
6
7
8
9
10
/* Create a new empty ziplist. */
unsigned char *ziplistNew(void) {
    unsigned int bytes = ZIPLIST_HEADER_SIZE+1;
    unsigned char *zl = zmalloc(bytes);
    ZIPLIST_BYTES(zl) = intrev32ifbe(bytes);
    ZIPLIST_TAIL_OFFSET(zl) = intrev32ifbe(ZIPLIST_HEADER_SIZE);
    ZIPLIST_LENGTH(zl) = 0;
    zl[bytes-1] = ZIP_END;
    return zl;
}

unsigned char *ziplistResize(unsigned char *zl, unsigned int len);

功能

ziplist重新分配内存大小

源码

1
2
3
4
5
6
7
/* Resize the ziplist. */
unsigned char *ziplistResize(unsigned char *zl, unsigned int len) {
    zl = zrealloc(zl,len);
    ZIPLIST_BYTES(zl) = intrev32ifbe(len);
    zl[len-1] = ZIP_END;
    return zl;
}

unsigned char *__ziplistCascadeUpdate(unsigned char *zl, unsigned char *p);

功能

插入新元素后,维护后续元素的前一个元素的尺寸接口

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
/* When an entry is inserted, we need to set the prevlen field of the next
 * entry to equal the length of the inserted entry. It can occur that this
 * length cannot be encoded in 1 byte and the next entry needs to be grow
 * a bit larger to hold the 5-byte encoded prevlen. This can be done for free,
 * because this only happens when an entry is already being inserted (which
 * causes a realloc and memmove). However, encoding the prevlen may require
 * that this entry is grown as well. This effect may cascade throughout
 * the ziplist when there are consecutive entries with a size close to
 * ZIP_BIGLEN, so we need to check that the prevlen can be encoded in every
 * consecutive entry.
 *
 * Note that this effect can also happen in reverse, where the bytes required
 * to encode the prevlen field can shrink. This effect is deliberately ignored,
 * because it can cause a "flapping" effect where a chain prevlen fields is
 * first grown and then shrunk again after consecutive inserts. Rather, the
 * field is allowed to stay larger than necessary, because a large prevlen
 * field implies the ziplist is holding large entries anyway.
 *
 * The pointer "p" points to the first entry that does NOT need to be
 * updated, i.e. consecutive fields MAY need an update. */
unsigned char *__ziplistCascadeUpdate(unsigned char *zl, unsigned char *p) {
    size_t curlen = intrev32ifbe(ZIPLIST_BYTES(zl)), rawlen, rawlensize;
    size_t offset, noffset, extra;
    unsigned char *np;
    zlentry cur, next;

    while (p[0] != ZIP_END) {
        zipEntry(p, &cur);
        rawlen = cur.headersize + cur.len;
        rawlensize = zipPrevEncodeLength(NULL,rawlen);

        /* Abort if there is no next entry. */
        if (p[rawlen] == ZIP_END) break;
        zipEntry(p+rawlen, &next);

        /* Abort when "prevlen" has not changed. */
        if (next.prevrawlen == rawlen) break;

        if (next.prevrawlensize < rawlensize) {
            /* The "prevlen" field of "next" needs more bytes to hold
             * the raw length of "cur". */
            offset = p-zl;
            extra = rawlensize-next.prevrawlensize;
            zl = ziplistResize(zl,curlen+extra);
            p = zl+offset;

            /* Current pointer and offset for next element. */
            np = p+rawlen;
            noffset = np-zl;

            /* Update tail offset when next element is not the tail element. */
            if ((zl+intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))) != np) {
                ZIPLIST_TAIL_OFFSET(zl) =
                    intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+extra);
            }

            /* Move the tail to the back. */
            memmove(np+rawlensize,
                np+next.prevrawlensize,
                curlen-noffset-next.prevrawlensize-1);
            zipPrevEncodeLength(np,rawlen);

            /* Advance the cursor */
            p += rawlen;
            curlen += extra;
        } else {
            if (next.prevrawlensize > rawlensize) {
                /* This would result in shrinking, which we want to avoid.
                 * So, set "rawlen" in the available bytes. */
                zipPrevEncodeLengthForceLarge(p+rawlen,rawlen);
            } else {
                zipPrevEncodeLength(p+rawlen,rawlen);
            }

            /* Stop here, as the raw length of "next" has not changed. */
            break;
        }
    }
    return zl;
}

unsigned char *__ziplistDelete(unsigned char *zl, unsigned char *p, unsigned int num);

功能

从p开始删除num个元素

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
/* Delete "num" entries, starting at "p". Returns pointer to the ziplist. */
unsigned char *__ziplistDelete(unsigned char *zl, unsigned char *p, unsigned int num) {
    unsigned int i, totlen, deleted = 0;
    size_t offset;
    int nextdiff = 0;
    zlentry first, tail;

    zipEntry(p, &first);
    for (i = 0; p[0] != ZIP_END && i < num; i++) {
        p += zipRawEntryLength(p);
        deleted++;
    }

    totlen = p-first.p;
    if (totlen > 0) {
        if (p[0] != ZIP_END) {
            /* Storing `prevrawlen` in this entry may increase or decrease the
             * number of bytes required compare to the current `prevrawlen`.
             * There always is room to store this, because it was previously
             * stored by an entry that is now being deleted. */
            nextdiff = zipPrevLenByteDiff(p,first.prevrawlen);
            p -= nextdiff;
            zipPrevEncodeLength(p,first.prevrawlen);

            /* Update offset for tail */
            ZIPLIST_TAIL_OFFSET(zl) =
                intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))-totlen);

            /* When the tail contains more than one entry, we need to take
             * "nextdiff" in account as well. Otherwise, a change in the
             * size of prevlen doesn't have an effect on the *tail* offset. */
            zipEntry(p, &tail);
            if (p[tail.headersize+tail.len] != ZIP_END) {
                ZIPLIST_TAIL_OFFSET(zl) =
                   intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+nextdiff);
            }

            /* Move tail to the front of the ziplist */
            memmove(first.p,p,
                intrev32ifbe(ZIPLIST_BYTES(zl))-(p-zl)-1);
        } else {
            /* The entire tail was deleted. No need to move memory. */
            ZIPLIST_TAIL_OFFSET(zl) =
                intrev32ifbe((first.p-zl)-first.prevrawlen);
        }

        /* Resize and update length */
        offset = first.p-zl;
        zl = ziplistResize(zl, intrev32ifbe(ZIPLIST_BYTES(zl))-totlen+nextdiff);
        ZIPLIST_INCR_LENGTH(zl,-deleted);
        p = zl+offset;

        /* When nextdiff != 0, the raw length of the next entry has changed, so
         * we need to cascade the update throughout the ziplist */
        if (nextdiff != 0)
            zl = __ziplistCascadeUpdate(zl,p);
    }
    return zl;
}

unsigned char *__ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen);

功能

在p的位置插入元素

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
/* Insert item at "p". */
unsigned char *__ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen) {
    size_t curlen = intrev32ifbe(ZIPLIST_BYTES(zl)), reqlen;
    unsigned int prevlensize, prevlen = 0;
    size_t offset;
    int nextdiff = 0;
    unsigned char encoding = 0;
    long long value = 123456789; /* initialized to avoid warning. Using a value
                                    that is easy to see if for some reason
                                    we use it uninitialized. */
    zlentry tail;

    /* Find out prevlen for the entry that is inserted. */
    if (p[0] != ZIP_END) {
        ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
    } else {
        unsigned char *ptail = ZIPLIST_ENTRY_TAIL(zl);
        if (ptail[0] != ZIP_END) {
            prevlen = zipRawEntryLength(ptail);
        }
    }

    /* See if the entry can be encoded */
    if (zipTryEncoding(s,slen,&value,&encoding)) {
        /* 'encoding' is set to the appropriate integer encoding */
        reqlen = zipIntSize(encoding);
    } else {
        /* 'encoding' is untouched, however zipEncodeLength will use the
         * string length to figure out how to encode it. */
        reqlen = slen;
    }
    /* We need space for both the length of the previous entry and
     * the length of the payload. */
    reqlen += zipPrevEncodeLength(NULL,prevlen);
    reqlen += zipEncodeLength(NULL,encoding,slen);

    /* When the insert position is not equal to the tail, we need to
     * make sure that the next entry can hold this entry's length in
     * its prevlen field. */
    int forcelarge = 0;
    nextdiff = (p[0] != ZIP_END) ? zipPrevLenByteDiff(p,reqlen) : 0;
    if (nextdiff == -4 && reqlen < 4) {
        nextdiff = 0;
        forcelarge = 1;
    }

    /* Store offset because a realloc may change the address of zl. */
    offset = p-zl;
    zl = ziplistResize(zl,curlen+reqlen+nextdiff);
    p = zl+offset;

    /* Apply memory move when necessary and update tail offset. */
    if (p[0] != ZIP_END) {
        /* Subtract one because of the ZIP_END bytes */
        memmove(p+reqlen,p-nextdiff,curlen-offset-1+nextdiff);

        /* Encode this entry's raw length in the next entry. */
        if (forcelarge)
            zipPrevEncodeLengthForceLarge(p+reqlen,reqlen);
        else
            zipPrevEncodeLength(p+reqlen,reqlen);

        /* Update offset for tail */
        ZIPLIST_TAIL_OFFSET(zl) =
            intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+reqlen);

        /* When the tail contains more than one entry, we need to take
         * "nextdiff" in account as well. Otherwise, a change in the
         * size of prevlen doesn't have an effect on the *tail* offset. */
        zipEntry(p+reqlen, &tail);
        if (p[reqlen+tail.headersize+tail.len] != ZIP_END) {
            ZIPLIST_TAIL_OFFSET(zl) =
                intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+nextdiff);
        }
    } else {
        /* This element will be the new tail. */
        ZIPLIST_TAIL_OFFSET(zl) = intrev32ifbe(p-zl);
    }

    /* When nextdiff != 0, the raw length of the next entry has changed, so
     * we need to cascade the update throughout the ziplist */
    if (nextdiff != 0) {
        offset = p-zl;
        zl = __ziplistCascadeUpdate(zl,p+reqlen);
        p = zl+offset;
    }

    /* Write the entry */
    p += zipPrevEncodeLength(p,prevlen);
    p += zipEncodeLength(p,encoding,slen);
    if (ZIP_IS_STR(encoding)) {
        memcpy(p,s,slen);
    } else {
        zipSaveInteger(p,value,encoding);
    }
    ZIPLIST_INCR_LENGTH(zl,1);
    return zl;
}

unsigned char *ziplistMerge(unsigned char **first, unsigned char **second);

功能

合并两个ziplist,返回新的ziplist

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
/* Merge ziplists 'first' and 'second' by appending 'second' to 'first'.
 *
 * NOTE: The larger ziplist is reallocated to contain the new merged ziplist.
 * Either 'first' or 'second' can be used for the result.  The parameter not
 * used will be free'd and set to NULL.
 *
 * After calling this function, the input parameters are no longer valid since
 * they are changed and free'd in-place.
 *
 * The result ziplist is the contents of 'first' followed by 'second'.
 *
 * On failure: returns NULL if the merge is impossible.
 * On success: returns the merged ziplist (which is expanded version of either
 * 'first' or 'second', also frees the other unused input ziplist, and sets the
 * input ziplist argument equal to newly reallocated ziplist return value. */
unsigned char *ziplistMerge(unsigned char **first, unsigned char **second) {
    /* If any params are null, we can't merge, so NULL. */
    if (first == NULL || *first == NULL || second == NULL || *second == NULL)
        return NULL;

    /* Can't merge same list into itself. */
    if (*first == *second)
        return NULL;

    size_t first_bytes = intrev32ifbe(ZIPLIST_BYTES(*first));
    size_t first_len = intrev16ifbe(ZIPLIST_LENGTH(*first));

    size_t second_bytes = intrev32ifbe(ZIPLIST_BYTES(*second));
    size_t second_len = intrev16ifbe(ZIPLIST_LENGTH(*second));

    int append;
    unsigned char *source, *target;
    size_t target_bytes, source_bytes;
    /* Pick the largest ziplist so we can resize easily in-place.
     * We must also track if we are now appending or prepending to
     * the target ziplist. */
    if (first_len >= second_len) {
        /* retain first, append second to first. */
        target = *first;
        target_bytes = first_bytes;
        source = *second;
        source_bytes = second_bytes;
        append = 1;
    } else {
        /* else, retain second, prepend first to second. */
        target = *second;
        target_bytes = second_bytes;
        source = *first;
        source_bytes = first_bytes;
        append = 0;
    }

    /* Calculate final bytes (subtract one pair of metadata) */
    size_t zlbytes = first_bytes + second_bytes -
                     ZIPLIST_HEADER_SIZE - ZIPLIST_END_SIZE;
    size_t zllength = first_len + second_len;

    /* Combined zl length should be limited within UINT16_MAX */
    zllength = zllength < UINT16_MAX ? zllength : UINT16_MAX;

    /* Save offset positions before we start ripping memory apart. */
    size_t first_offset = intrev32ifbe(ZIPLIST_TAIL_OFFSET(*first));
    size_t second_offset = intrev32ifbe(ZIPLIST_TAIL_OFFSET(*second));

    /* Extend target to new zlbytes then append or prepend source. */
    target = zrealloc(target, zlbytes);
    if (append) {
        /* append == appending to target */
        /* Copy source after target (copying over original [END]):
         *   [TARGET - END, SOURCE - HEADER] */
        memcpy(target + target_bytes - ZIPLIST_END_SIZE,
               source + ZIPLIST_HEADER_SIZE,
               source_bytes - ZIPLIST_HEADER_SIZE);
    } else {
        /* !append == prepending to target */
        /* Move target *contents* exactly size of (source - [END]),
         * then copy source into vacataed space (source - [END]):
         *   [SOURCE - END, TARGET - HEADER] */
        memmove(target + source_bytes - ZIPLIST_END_SIZE,
                target + ZIPLIST_HEADER_SIZE,
                target_bytes - ZIPLIST_HEADER_SIZE);
        memcpy(target, source, source_bytes - ZIPLIST_END_SIZE);
    }

    /* Update header metadata. */
    ZIPLIST_BYTES(target) = intrev32ifbe(zlbytes);
    ZIPLIST_LENGTH(target) = intrev16ifbe(zllength);
    /* New tail offset is:
     *   + N bytes of first ziplist
     *   - 1 byte for [END] of first ziplist
     *   + M bytes for the offset of the original tail of the second ziplist
     *   - J bytes for HEADER because second_offset keeps no header. */
    ZIPLIST_TAIL_OFFSET(target) = intrev32ifbe(
                                   (first_bytes - ZIPLIST_END_SIZE) +
                                   (second_offset - ZIPLIST_HEADER_SIZE));

    /* __ziplistCascadeUpdate just fixes the prev length values until it finds a
     * correct prev length value (then it assumes the rest of the list is okay).
     * We tell CascadeUpdate to start at the first ziplist's tail element to fix
     * the merge seam. */
    target = __ziplistCascadeUpdate(target, target+first_offset);

    /* Now free and NULL out what we didn't realloc */
    if (append) {
        zfree(*second);
        *second = NULL;
        *first = target;
    } else {
        zfree(*first);
        *first = NULL;
        *second = target;
    }
    return target;
}

unsigned char *ziplistPush(unsigned char *zl, unsigned char *s, unsigned int slen, int where);

功能

向ziplist添加数据
where表示在前面或者后面添加数据

源码

1
2
3
4
5
6
7
8
#define ZIPLIST_HEAD 0
#define ZIPLIST_TAIL 1

unsigned char *ziplistPush(unsigned char *zl, unsigned char *s, unsigned int slen, int where) {
    unsigned char *p;
    p = (where == ZIPLIST_HEAD) ? ZIPLIST_ENTRY_HEAD(zl) : ZIPLIST_ENTRY_END(zl);
    return __ziplistInsert(zl,p,s,slen);
}

unsigned char *ziplistIndex(unsigned char *zl, int index);

功能

根据索引获取元素

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
/* Returns an offset to use for iterating with ziplistNext. When the given
 * index is negative, the list is traversed back to front. When the list
 * doesn't contain an element at the provided index, NULL is returned. */
unsigned char *ziplistIndex(unsigned char *zl, int index) {
    unsigned char *p;
    unsigned int prevlensize, prevlen = 0;
    if (index < 0) {
        index = (-index)-1;
        p = ZIPLIST_ENTRY_TAIL(zl);
        if (p[0] != ZIP_END) {
            ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
            while (prevlen > 0 && index--) {
                p -= prevlen;
                ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
            }
        }
    } else {
        p = ZIPLIST_ENTRY_HEAD(zl);
        while (p[0] != ZIP_END && index--) {
            p += zipRawEntryLength(p);
        }
    }
    return (p[0] == ZIP_END || index > 0) ? NULL : p;
}

unsigned char *ziplistNext(unsigned char *zl, unsigned char *p);

功能

获取ziplist的下一个元素

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
/* Return pointer to next entry in ziplist.
 *
 * zl is the pointer to the ziplist
 * p is the pointer to the current element
 *
 * The element after 'p' is returned, otherwise NULL if we are at the end. */
unsigned char *ziplistNext(unsigned char *zl, unsigned char *p) {
    ((void) zl);

    /* "p" could be equal to ZIP_END, caused by ziplistDelete,
     * and we should return NULL. Otherwise, we should return NULL
     * when the *next* element is ZIP_END (there is no next entry). */
    if (p[0] == ZIP_END) {
        return NULL;
    }

    p += zipRawEntryLength(p);
    if (p[0] == ZIP_END) {
        return NULL;
    }

    return p;
}

unsigned char *ziplistPrev(unsigned char *zl, unsigned char *p);

功能

获取ziplist的前一个元素

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
/* Return pointer to previous entry in ziplist. */
unsigned char *ziplistPrev(unsigned char *zl, unsigned char *p) {
    unsigned int prevlensize, prevlen = 0;

    /* Iterating backwards from ZIP_END should return the tail. When "p" is
     * equal to the first element of the list, we're already at the head,
     * and should return NULL. */
    if (p[0] == ZIP_END) {
        p = ZIPLIST_ENTRY_TAIL(zl);
        return (p[0] == ZIP_END) ? NULL : p;
    } else if (p == ZIPLIST_ENTRY_HEAD(zl)) {
        return NULL;
    } else {
        ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
        assert(prevlen > 0);
        return p-prevlen;
    }
}

unsigned int ziplistGet(unsigned char *p, unsigned char **sstr, unsigned int *slen, long long *sval);

功能

p为ziplist的一个entry的起始位置
获取这个p指向的entry的字符串或这值

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
/* Get entry pointed to by 'p' and store in either '*sstr' or 'sval' depending
 * on the encoding of the entry. '*sstr' is always set to NULL to be able
 * to find out whether the string pointer or the integer value was set.
 * Return 0 if 'p' points to the end of the ziplist, 1 otherwise. */
unsigned int ziplistGet(unsigned char *p, unsigned char **sstr, unsigned int *slen, long long *sval) {
    zlentry entry;
    if (p == NULL || p[0] == ZIP_END) return 0;
    if (sstr) *sstr = NULL;

    zipEntry(p, &entry);
    if (ZIP_IS_STR(entry.encoding)) {
        if (sstr) {
            *slen = entry.len;
            *sstr = p+entry.headersize;
        }
    } else {
        if (sval) {
            *sval = zipLoadInteger(p+entry.headersize,entry.encoding);
        }
    }
    return 1;
}

unsigned char *ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen);

功能

在ziplist的p位置插入新的元素

源码

1
2
3
4
/* Insert an entry at "p". */
unsigned char *ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen) {
    return __ziplistInsert(zl,p,s,slen);
}

unsigned char *ziplistDelete(unsigned char *zl, unsigned char **p)

功能

删除ziplist元素,返回新的ziplist

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
/* Delete a single entry from the ziplist, pointed to by *p.
 * Also update *p in place, to be able to iterate over the
 * ziplist, while deleting entries. */
unsigned char *ziplistDelete(unsigned char *zl, unsigned char **p) {
    size_t offset = *p-zl;
    zl = __ziplistDelete(zl,*p,1);

    /* Store pointer to current element in p, because ziplistDelete will
     * do a realloc which might result in a different "zl"-pointer.
     * When the delete direction is back to front, we might delete the last
     * entry and end up with "p" pointing to ZIP_END, so check this. */
    *p = zl+offset;
    return zl;
}

unsigned char *ziplistDeleteRange(unsigned char *zl, int index, unsigned int num);

功能

从index开始连续删除num个元素

源码

1
2
3
4
5
/* Delete a range of entries from the ziplist. */
unsigned char *ziplistDeleteRange(unsigned char *zl, int index, unsigned int num) {
    unsigned char *p = ziplistIndex(zl,index);
    return (p == NULL) ? zl : __ziplistDelete(zl,p,num);
}

unsigned int ziplistCompare(unsigned char *p, unsigned char *sstr, unsigned int slen);

功能

判断传入的数据是否与p对应的元素的值相同

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
/* Compare entry pointer to by 'p' with 'sstr' of length 'slen'. */
/* Return 1 if equal. */
unsigned int ziplistCompare(unsigned char *p, unsigned char *sstr, unsigned int slen) {
    zlentry entry;
    unsigned char sencoding;
    long long zval, sval;
    if (p[0] == ZIP_END) return 0;

    zipEntry(p, &entry);
    if (ZIP_IS_STR(entry.encoding)) {
        /* Raw compare */
        if (entry.len == slen) {
            return memcmp(p+entry.headersize,sstr,slen) == 0;
        } else {
            return 0;
        }
    } else {
        /* Try to compare encoded values. Don't compare encoding because
         * different implementations may encoded integers differently. */
        if (zipTryEncoding(sstr,slen,&sval,&sencoding)) {
          zval = zipLoadInteger(p+entry.headersize,entry.encoding);
          return zval == sval;
        }
    }
    return 0;
}

unsigned char *ziplistFind(unsigned char *p, unsigned char *vstr, unsigned int vlen, unsigned int skip);

功能

查找指定元素
skip:需要跳过的元素的个数

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
/* Find pointer to the entry equal to the specified entry. Skip 'skip' entries
 * between every comparison. Returns NULL when the field could not be found. */
unsigned char *ziplistFind(unsigned char *p, unsigned char *vstr, unsigned int vlen, unsigned int skip) {
    int skipcnt = 0;
    unsigned char vencoding = 0;
    long long vll = 0;

    while (p[0] != ZIP_END) {
        unsigned int prevlensize, encoding, lensize, len;
        unsigned char *q;

        ZIP_DECODE_PREVLENSIZE(p, prevlensize);
        ZIP_DECODE_LENGTH(p + prevlensize, encoding, lensize, len);
        q = p + prevlensize + lensize;

        if (skipcnt == 0) {
            /* Compare current entry with specified entry */
            if (ZIP_IS_STR(encoding)) {
                if (len == vlen && memcmp(q, vstr, vlen) == 0) {
                    return p;
                }
            } else {
                /* Find out if the searched field can be encoded. Note that
                 * we do it only the first time, once done vencoding is set
                 * to non-zero and vll is set to the integer value. */
                if (vencoding == 0) {
                    if (!zipTryEncoding(vstr, vlen, &vll, &vencoding)) {
                        /* If the entry can't be encoded we set it to
                         * UCHAR_MAX so that we don't retry again the next
                         * time. */
                        vencoding = UCHAR_MAX;
                    }
                    /* Must be non-zero by now */
                    assert(vencoding);
                }

                /* Compare current entry with specified entry, do it only
                 * if vencoding != UCHAR_MAX because if there is no encoding
                 * possible for the field it can't be a valid integer. */
                if (vencoding != UCHAR_MAX) {
                    long long ll = zipLoadInteger(q, encoding);
                    if (ll == vll) {
                        return p;
                    }
                }
            }

            /* Reset skip count */
            skipcnt = skip;
        } else {
            /* Skip entry */
            skipcnt--;
        }

        /* Move to next entry */
        p = q + len;
    }

    return NULL;
}

unsigned int ziplistLen(unsigned char *zl);

功能

获取ziplist的长度

源码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
/* Return length of ziplist. */
unsigned int ziplistLen(unsigned char *zl) {
    unsigned int len = 0;
    if (intrev16ifbe(ZIPLIST_LENGTH(zl)) < UINT16_MAX) {
        len = intrev16ifbe(ZIPLIST_LENGTH(zl));
    } else {
        unsigned char *p = zl+ZIPLIST_HEADER_SIZE;
        while (*p != ZIP_END) {
            p += zipRawEntryLength(p);
            len++;
        }

        /* Re-store length if small enough */
        if (len < UINT16_MAX) ZIPLIST_LENGTH(zl) = intrev16ifbe(len);
    }
    return len;
}

size_t ziplistBlobLen(unsigned char *zl);

功能

获取ziplist的总占用字节数

源码

1
2
3
4
/* Return ziplist blob size in bytes. */
size_t ziplistBlobLen(unsigned char *zl) {
    return intrev32ifbe(ZIPLIST_BYTES(zl));
}