Redis源码解读 -简单动态字符串 SDS

  简单动态字符串（Simple Dynamic Strings, SDS）是Redis的基本数据结构之一，用于存储字符串和整型数据。SDS兼容C语言标准字符串处理函数，且在此基础上保证了二进制安全。

  SDS如何实现二进制安全，同时兼容C语言标准字符串处理？先来看下它的定义：

typedef char *sds;

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是char类型的指针，以'\0'为字符串结束标志，而后面的一系列sdshdr结构体则是数据存储的真实格式；为什么要这样做？

   __attribute__ ((__packed__)) 关键字的作用是取消字节对齐，使得结构体后面的 char buf[] （实际存储字符串内容的数组）成为了一个柔性数组成员，sds就是指向这个数组的首地址。

   这样一来，C语言中就可以直接对sds使用标准字符串函数处理。

   那么它如何实现二进制安全？

   结构体中的 unsigned char flags 是固定长度，因此只需要对sds进行-1操作，也就是 buf-1 就可以很方便的得到flags的内容：

#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)

static inline size_t sdslen(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)->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;
}

  以上代码可以看出，flags的低三位固定存储sds类型，sdshdr5的flags高5位还存储了字符串长度

  对于其他结构体，其头部还存储字符串长度len和申请的内存大小alloc，这两个成员的类型可以通过flags的低三位判断。

  由于结构体中存储了字符串真实长度len，因此可以实现二进制安全。

 

　　附：sds的创建：

/* 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);
    return sdsnewlen(init, initlen);
}

sds sdsnewlen(const void *init, size_t initlen) {
    void *sh;
    sds s;
    char type = sdsReqType(initlen);
    /* 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;
    int hdrlen = sdsHdrSize(type);
    unsigned char *fp; /* flags pointer. */

    sh = s_malloc(hdrlen+initlen+1);
    if (init==SDS_NOINIT)
        init = NULL;
    else if (!init)
        memset(sh, 0, hdrlen+initlen+1);
    if (sh == NULL) return NULL;
    s = (char*)sh+hdrlen;
    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';
    return s;
}

　 附：sds扩容：

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)
        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 {
        /* 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;
}

 

 附：sds缩容：redis会对有大量闲置空间的sds进行缩容处理：

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);
    sh = (char*)s-oldhdrlen;

    /* 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;
}