Redis5.0.5源码解析 -- sds

redis源码地址
sds源码所在位置：src/sds.h src/sds.c
sds独立仓库地址
简介：sds (Simple Dynamic String)，即动态字符串管理库

why we need sds？
sds相比c的标准库优势：
1、相比于c标准库，获取字符串的len复杂读从O(N)降低到O(1)，sds结构中存储了字符串的长度，所以类似strlen(str)的操作不会成为redis的性能瓶颈。
2、在内存分配策略上，redis总是会尝试多分配一些空间，比如小于1MB的字符串，总是分配2倍内存空间，对于大于1MB的空间追加1MB冗余空间，这对于字符串操作（如strcat等）能减少重新内存分配的几率，提升运行性能。
3、SDS总是安全的，sds总是会自动追加字符串结尾符号’\0’，有效防止溢出发生。
4、惰性释放内存，改变原字符串时，标准库需要重新分配内存的复杂度为O(N)，SDS最大为O(N)，最优情况下无需重新分配内存空间。
5、二进制安全。（SDS以len的值判断结束，而不是’\0’）

在sds.h中，有如下定义

typedef char *sds;

/* Note: sdshdr5 is never used, we just access the flags byte directly.
 * However is here to document the layout of type 5 SDS strings. */
struct __attribute__ ((__packed__)) sdshdr5 {
    unsigned char flags; /* 3 lsb of type, and 5 msb of string length */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr8 {
    uint8_t len; /* used */
    uint8_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr16 {
    uint16_t len; /* used */
    uint16_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr32 {
    uint32_t len; /* used */
    uint32_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr64 {
    uint64_t len; /* used */
    uint64_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};

sds支持sdshdr5、sdshdr8、sdshdr16、sdshdr32、sdshdr64

sds structure layout
+--------+-------------------------------+-----------+
| Header | Binary safe C alike string... | Null term |
+--------+-------------------------------+-----------+
         |
         `-> Pointer returned to the user.

1、区别为字符串长度不同。
2、其中sdshdr5在源码中没有用到（即，如果用户申请的字符串长度满足sdshdr5则向上申请sdshdr8）
3、attribute ((packed))选项是告诉编译器，以1字节对齐。
4、len指已经使用的长度，alloc是申请的内存大小，flags低三位用于表示sds type
，源码如下：即（flags & SDS_TYPE_MASK）值就对应SDS_TYPE_xxx宏，比如flags = 0就代表SDS_TYPE_5， flags = 2就代表SDS_TYPE_16。

#define SDS_TYPE_5  0
#define SDS_TYPE_8  1
#define SDS_TYPE_16 2
#define SDS_TYPE_32 3
#define SDS_TYPE_64 4
#define SDS_TYPE_MASK 7
#define SDS_TYPE_BITS 3
#define SDS_HDR_VAR(T,s) struct sdshdr##T *sh = (void*)((s)-(sizeof(struct sdshdr##T)));
#define SDS_HDR(T,s) ((struct sdshdr##T *)((s)-(sizeof(struct sdshdr##T))))
#define SDS_TYPE_5_LEN(f) ((f)>>SDS_TYPE_BITS)

5、char buf[]用于存放真实的字符串。
5.1、注意这里的char buf[]是不占用空间的，怎么理解不占用空间呢，就是说用sizeof(sdshdr5)，获得的结果是1，而不是2。
5.2、这种用法在嵌入式中非常常用，也常用于网络协议包的信令结构定义中。
5.3、特别注意，char buf[]必须放在struct的最后。

6、sdslen：获取len

static inline size_t sdslen(const sds s) {
    unsigned char flags = s[-1];  /* s[-1]这是trick的写法，s[-1]等价于s + (-1) */
    switch(flags&SDS_TYPE_MASK) { /* 通过flags 获取SDS_TYPE, 这在4中，已经讲过 */
        case SDS_TYPE_5:
            return SDS_TYPE_5_LEN(flags);
        case SDS_TYPE_8:
            return SDS_HDR(8,s)->len;
        case SDS_TYPE_16:
            return SDS_HDR(16,s)->len;
        case SDS_TYPE_32:
            return SDS_HDR(32,s)->len;
        case SDS_TYPE_64:
            return SDS_HDR(64,s)->len;
    }
    return 0;
}

7、sdsavail：获取空闲的内存空间，即alloc - len

static inline size_t sdsavail(const sds s) {
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5: {
            return 0;
        }
        case SDS_TYPE_8: {
            SDS_HDR_VAR(8,s);
            return sh->alloc - sh->len;
        }
        case SDS_TYPE_16: {
            SDS_HDR_VAR(16,s);
            return sh->alloc - sh->len;
        }
        case SDS_TYPE_32: {
            SDS_HDR_VAR(32,s);
            return sh->alloc - sh->len;
        }
        case SDS_TYPE_64: {
            SDS_HDR_VAR(64,s);
            return sh->alloc - sh->len;
        }
    }
    return 0;
}

8、sdssetlen：设置len

static inline void sdssetlen(sds s, size_t newlen) {
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            {
                unsigned char *fp = ((unsigned char*)s)-1;
                *fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS);
            }
            break;
        case SDS_TYPE_8:
            SDS_HDR(8,s)->len = newlen;
            break;
        case SDS_TYPE_16:
            SDS_HDR(16,s)->len = newlen;
            break;
        case SDS_TYPE_32:
            SDS_HDR(32,s)->len = newlen;
            break;
        case SDS_TYPE_64:
            SDS_HDR(64,s)->len = newlen;
            break;
    }
}

9、sdsinclen：increase len

static inline void sdsinclen(sds s, size_t inc) {
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            {
                unsigned char *fp = ((unsigned char*)s)-1;
                unsigned char newlen = SDS_TYPE_5_LEN(flags)+inc;
                *fp = SDS_TYPE_5 | (newlen << SDS_TYPE_BITS);
            }
            break;
        case SDS_TYPE_8:
            SDS_HDR(8,s)->len += inc;
            break;
        case SDS_TYPE_16:
            SDS_HDR(16,s)->len += inc;
            break;
        case SDS_TYPE_32:
            SDS_HDR(32,s)->len += inc;
            break;
        case SDS_TYPE_64:
            SDS_HDR(64,s)->len += inc;
            break;
    }
}

10、sdsalloc：获取alloc

/* sdsalloc() = sdsavail() + sdslen() */
static inline size_t sdsalloc(const sds s) {
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            return SDS_TYPE_5_LEN(flags);
        case SDS_TYPE_8:
            return SDS_HDR(8,s)->alloc;
        case SDS_TYPE_16:
            return SDS_HDR(16,s)->alloc;
        case SDS_TYPE_32:
            return SDS_HDR(32,s)->alloc;
        case SDS_TYPE_64:
            return SDS_HDR(64,s)->alloc;
    }
    return 0;
}

11、sdssetalloc：设置alloc

static inline void sdssetalloc(sds s, size_t newlen) {
    unsigned char flags = s[-1];
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5:
            /* Nothing to do, this type has no total allocation info. */
            break;
        case SDS_TYPE_8:
            SDS_HDR(8,s)->alloc = newlen;
            break;
        case SDS_TYPE_16:
            SDS_HDR(16,s)->alloc = newlen;
            break;
        case SDS_TYPE_32:
            SDS_HDR(32,s)->alloc = newlen;
            break;
        case SDS_TYPE_64:
            SDS_HDR(64,s)->alloc = newlen;
            break;
    }
}

12、sdsnew：创建sds

/* Create a new sds string starting from a null terminated C string. */
sds sdsnew(const char *init) {
    size_t initlen = (init == NULL) ? 0 : strlen(init);/*sds new主函数为sdsnewlen，本函数主要是做string len的计算*/
    return sdsnewlen(init, initlen);
}

13、sdsnewlen

/* Create a new sds string with the content specified by the 'init' pointer
 * and 'initlen'.
 * If NULL is used for 'init' the string is initialized with zero bytes.
 * If SDS_NOINIT is used, the buffer is left uninitialized;
 *
 * The string is always null-termined (all the sds strings are, always) so
 * even if you create an sds string with:
 *
 * mystring = sdsnewlen("abc",3);
 *
 * You can print the string with printf() as there is an implicit \0 at the
 * end of the string. However the string is binary safe and can contain
 * \0 characters in the middle, as the length is stored in the sds header. */
sds sdsnewlen(const void *init, size_t initlen) {
    void *sh;
    sds s;
    char type = sdsReqType(initlen); /* 通过initlen得到SDS_TYPE */
    /* Empty strings are usually created in order to append. Use type 8
     * since type 5 is not good at this. */
    if (type == SDS_TYPE_5 && initlen == 0) type = SDS_TYPE_8;/* SDS_TYPE_5永远不会使用，即使用户申请的string长度为0，也使用SDS_TYPE_8 */
    int hdrlen = sdsHdrSize(type); /* 这里是获取header的长度，即类似sizeof(sdshdr8) */
    unsigned char *fp; /* flags pointer. */

    sh = s_malloc(hdrlen+initlen+1);/* 实际申请的空间大小为header + string len + '\0' */
    if (init==SDS_NOINIT)
        init = NULL;
    else if (!init)
        memset(sh, 0, hdrlen+initlen+1);
    if (sh == NULL) return NULL;   /* 这里空指针检查代码需要和memset调换顺序，源码有点小问题，已经给redis提交pull request */
    s = (char*)sh+hdrlen;   /* s指向char buf[]，即返回的sds指针 */
    fp = ((unsigned char*)s)-1;
    switch(type) {
        case SDS_TYPE_5: {
            *fp = type | (initlen << SDS_TYPE_BITS);
            break;
        }
        case SDS_TYPE_8: {
            SDS_HDR_VAR(8,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_16: {
            SDS_HDR_VAR(16,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_32: {
            SDS_HDR_VAR(32,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
        case SDS_TYPE_64: {
            SDS_HDR_VAR(64,s);
            sh->len = initlen;
            sh->alloc = initlen;
            *fp = type;
            break;
        }
    }
    if (initlen && init)
        memcpy(s, init, initlen);
    s[initlen] = '\0'; /* 默认补全'\0' */
    return s;
}

14、sdsdup：复制sds

/* Duplicate an sds string. */
sds sdsdup(const sds s) {
    /* 这个比较简单，和新建一个一样 */
    return sdsnewlen(s, sdslen(s));
}

15、sdsfree：释放sds

/* Free an sds string. No operation is performed if 's' is NULL. */
void sdsfree(sds s) {
    if (s == NULL) return;
    s_free((char*)s-sdsHdrSize(s[-1])); /* s[-1]获取到flags，通过flags得到SDS_TYPE_XX， 通过SDS_TYPE_XX获得到header的长度，将s往前移动header的长度，即为 sdshdrXX的结构指针 */
}

16、sdsupdatelen：更新len的值

/* Set the sds string length to the length as obtained with strlen(), so
 * considering as content only up to the first null term character.
 *
 * This function is useful when the sds string is hacked manually in some
 * way, like in the following example:
 *
 * s = sdsnew("foobar");
 * s[2] = '\0';
 * sdsupdatelen(s);
 * printf("%d\n", sdslen(s));
 *
 * The output will be "2", but if we comment out the call to sdsupdatelen()
 * the output will be "6" as the string was modified but the logical length
 * remains 6 bytes. */
void sdsupdatelen(sds s) {
    size_t reallen = strlen(s); /* 该接口的使用场景，上面的英文例子已经写得很清楚了，这是一种trick的玩法 */
    sdssetlen(s, reallen);
}

17、sdsclear：设置为空字符串，但是不会free空间

/* Modify an sds string in-place to make it empty (zero length).
 * However all the existing buffer is not discarded but set as free space
 * so that next append operations will not require allocations up to the
 * number of bytes previously available. */
void sdsclear(sds s) {
    sdssetlen(s, 0);
    s[0] = '\0'; /* 仅仅把字符串设置为“”，但s指向的内存依然有效 */
}

18、sdsRemoveFreeSpace：remove空闲的内存，如果s重新分配了内存，那么 sds所有引用到的地方都需要修改，因为以前的指针已经失效，这个算是sds的一个弱点吧。

/* Reallocate the sds string so that it has no free space at the end. The
 * contained string remains not altered, but next concatenation operations
 * will require a reallocation.
 *
 * After the call, the passed sds string is no longer valid and all the
 * references must be substituted with the new pointer returned by the call. */
sds sdsRemoveFreeSpace(sds s) {
    void *sh, *newsh;
    char type, oldtype = s[-1] & SDS_TYPE_MASK;
    int hdrlen, oldhdrlen = sdsHdrSize(oldtype);
    size_t len = sdslen(s);
    size_t avail = sdsavail(s);
    sh = (char*)s-oldhdrlen;

    /* Return ASAP if there is no space left. */
    if (avail == 0) return s;

    /* Check what would be the minimum SDS header that is just good enough to
     * fit this string. */
    type = sdsReqType(len);
    hdrlen = sdsHdrSize(type);

    /* If the type is the same, or at least a large enough type is still
     * required, we just realloc(), letting the allocator to do the copy
     * only if really needed. Otherwise if the change is huge, we manually
     * reallocate the string to use the different header type. */
    if (oldtype==type || type > SDS_TYPE_8) {
        newsh = s_realloc(sh, oldhdrlen+len+1);
        if (newsh == NULL) return NULL;
        s = (char*)newsh+oldhdrlen;
    } else {
        newsh = s_malloc(hdrlen+len+1);
        if (newsh == NULL) return NULL;
        memcpy((char*)newsh+hdrlen, s, len+1);
        s_free(sh);
        s = (char*)newsh+hdrlen;
        s[-1] = type;
        sdssetlen(s, len);
    }
    sdssetalloc(s, len);
    return s;
}

19、sdsAllocSize：返回sds真实分配的内存大小。

/* Return the total size of the allocation of the specified sds string,
 * including:
 * 1) The sds header before the pointer.
 * 2) The string.
 * 3) The free buffer at the end if any.
 * 4) The implicit null term.
 */
size_t sdsAllocSize(sds s) {
    size_t alloc = sdsalloc(s);
    return sdsHdrSize(s[-1])+alloc+1;
}

20、sdsAllocPtr：获取sds对应的sdshdrXX头指针。

/* Return the pointer of the actual SDS allocation (normally SDS strings
 * are referenced by the start of the string buffer). */
void *sdsAllocPtr(sds s) {
    return (void*) (s-sdsHdrSize(s[-1]));
}

21、sdsMakeRoomFor：增加内存空间，调用该接口后，如果sds返回指针发送变化，所以原sds的指针引用都将失效，需更新到新的sds

/* Enlarge the free space at the end of the sds string so that the caller
 * is sure that after calling this function can overwrite up to addlen
 * bytes after the end of the string, plus one more byte for nul term.
 *
 * Note: this does not change the *length* of the sds string as returned
 * by sdslen(), but only the free buffer space we have. */
sds sdsMakeRoomFor(sds s, size_t addlen) {
    void *sh, *newsh;
    size_t avail = sdsavail(s);
    size_t len, newlen;
    char type, oldtype = s[-1] & SDS_TYPE_MASK;
    int hdrlen;

    /* Return ASAP if there is enough space left. */
    if (avail >= addlen) return s;

    len = sdslen(s);
    sh = (char*)s-sdsHdrSize(oldtype);
    newlen = (len+addlen);
    if (newlen < SDS_MAX_PREALLOC) /* 为了减少malloc，用户申请分配的大小在小于1M时实际分配2倍用户申请空间，如果申请超过1M则追加1M */
        newlen *= 2;
    else
        newlen += SDS_MAX_PREALLOC;

    type = sdsReqType(newlen);

    /* Don't use type 5: the user is appending to the string and type 5 is
     * not able to remember empty space, so sdsMakeRoomFor() must be called
     * at every appending operation. */
    if (type == SDS_TYPE_5) type = SDS_TYPE_8;

    hdrlen = sdsHdrSize(type);
    if (oldtype==type) {
        newsh = s_realloc(sh, hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        s = (char*)newsh+hdrlen;
    } else {/* 如果type不同，因为header的长度是不一样的，所以目前用的策略是重新分配一块新地址 */
        /* Since the header size changes, need to move the string forward,
         * and can't use realloc */
        newsh = s_malloc(hdrlen+newlen+1);
        if (newsh == NULL) return NULL;
        memcpy((char*)newsh+hdrlen, s, len+1);
        s_free(sh);
        s = (char*)newsh+hdrlen;
        s[-1] = type;
        sdssetlen(s, len);
    }
    sdssetalloc(s, newlen);
    return s;
}

22、sdsIncrLen：增加len

/* Increment the sds length and decrements the left free space at the
 * end of the string according to 'incr'. Also set the null term
 * in the new end of the string.
 *
 * This function is used in order to fix the string length after the
 * user calls sdsMakeRoomFor(), writes something after the end of
 * the current string, and finally needs to set the new length.
 *
 * Note: it is possible to use a negative increment in order to
 * right-trim the string.
 *
 * Usage example:
 *
 * Using sdsIncrLen() and sdsMakeRoomFor() it is possible to mount the
 * following schema, to cat bytes coming from the kernel to the end of an
 * sds string without copying into an intermediate buffer:
 *
 * oldlen = sdslen(s);
 * s = sdsMakeRoomFor(s, BUFFER_SIZE);
 * nread = read(fd, s+oldlen, BUFFER_SIZE);
 * ... check for nread <= 0 and handle it ...
 * sdsIncrLen(s, nread);
 */
void sdsIncrLen(sds s, ssize_t incr) {
    unsigned char flags = s[-1];
    size_t len;
    switch(flags&SDS_TYPE_MASK) {
        case SDS_TYPE_5: {
            unsigned char *fp = ((unsigned char*)s)-1;
            unsigned char oldlen = SDS_TYPE_5_LEN(flags);
            assert((incr > 0 && oldlen+incr < 32) || (incr < 0 && oldlen >= (unsigned int)(-incr)));
            *fp = SDS_TYPE_5 | ((oldlen+incr) << SDS_TYPE_BITS);
            len = oldlen+incr;
            break;
        }
        case SDS_TYPE_8: {
            SDS_HDR_VAR(8,s);
            assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_16: {
            SDS_HDR_VAR(16,s);
            assert((incr >= 0 && sh->alloc-sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_32: {
            SDS_HDR_VAR(32,s);
            assert((incr >= 0 && sh->alloc-sh->len >= (unsigned int)incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
            len = (sh->len += incr);
            break;
        }
        case SDS_TYPE_64: {
            SDS_HDR_VAR(64,s);
            assert((incr >= 0 && sh->alloc-sh->len >= (uint64_t)incr) || (incr < 0 && sh->len >= (uint64_t)(-incr)));
            len = (sh->len += incr);
            break;
        }
        default: len = 0; /* Just to avoid compilation warnings. */
    }
    s[len] = '\0';
}