redis2.6.9源码学习---zipmap

在看此文件源码之前，先看到此文件头部的英文注释，以下是本人理解翻译版：</p>
该文件实现了一个数据结构映射到其他字符串的字符串，实施一个O(n)查找数据结构的设计是非常记忆高效的。 Redis的hase类型就是使用这种由小数量元素组成的数据结构，转换为一个哈希表。鉴于很多次Redis hase是用来表示对象组成的一些字段，这是一种在内存使用上很大的成功。
它的zipmap的格式为：
<zmlen><len>"foo"<len><free>"bar"<len>"hello"<len><free>"world"
<zmlen>是1字节长度,持有的当前zipmap的大小。当zipmap长度大于或等于254,这个值并不使用，zipmap需要遍历找出长度 。
<len>是下列字符串的长度(键或值)。<len>长度编码在一个单一的值或在一个5字节值。如果第一个字节值(作为一个unsigned 8位值)是介于0和252,这是一个单字节长度。如果它是253，接着后面会是一个四字节的无符号整数(在主机字节排序)。一个值255用于信号结束的散列。特殊值254是用来标记空空间,可用于添加新的键/值对。
<free>是修改key关联的value后string后的未使用的空闲的字节数。例如,如果“foo” 设置为“bar”,后“foo”将被设置为“hi”,它将有一个免费的字节，使用如果值将稍后再扩大,甚至添加一对适合的键/值。
<free>总是一个unsigned 8位,因为如果在一个更新操作有很多免费的字节,zipmap将重新分配,以确保它是尽可能小。

通过注释可以清楚此结构的最大优点就是内存使用。由此也基本知道了其结构的组成，下面分析源码也轻松很多。

/* Create a new empty zipmap. */
unsigned char *zipmapNew(void) {
    unsigned char *zm = zmalloc(2);

    zm[0] = 0; /* Length */
    zm[1] = ZIPMAP_END;
    return zm;
}

 

 

新建一个空的zipmap，其结构如图：

/* Decode the encoded length pointed by 'p' */
static unsigned int zipmapDecodeLength(unsigned char *p) {
    unsigned int len = *p;

    if (len < ZIPMAP_BIGLEN) return len;
    memcpy(&len,p+1,sizeof(unsigned int));
    memrev32ifbe(&len);//大小端转换
    return len;
}

/* Encode the length 'l' writing it in 'p'. If p is NULL it just returns
 * the amount of bytes required to encode such a length. */
static unsigned int zipmapEncodeLength(unsigned char *p, unsigned int len) {
    if (p == NULL) {
        return ZIPMAP_LEN_BYTES(len);
    } else {
        if (len < ZIPMAP_BIGLEN) {
            p[0] = len;
            return 1;
        } else {
            p[0] = ZIPMAP_BIGLEN;
            memcpy(p+1,&len,sizeof(len));
            memrev32ifbe(p+1);
            return 1+sizeof(len);
        }
    }
}

 //上为解码，下为编码(将key的长度转为char，返回所占的字节数)。主要是当key/value的长度大于等于ZIPMAP_BIGLEN(254)时，<len>的头字符就为ZIPMAP_BIGLEN，后将len转换为char型，存入len。（为了节省这四个字节）

 

/* Search for a matching key, returning a pointer to the entry inside the
 * zipmap. Returns NULL if the key is not found.
 *
 * If NULL is returned, and totlen is not NULL, it is set to the entire
 * size of the zimap, so that the calling function will be able to
 * reallocate the original zipmap to make room for more entries. */
static unsigned char *zipmapLookupRaw(unsigned char *zm, unsigned char *key, unsigned int klen, unsigned int *totlen) {
    unsigned char *p = zm+1, *k = NULL;//开始+1，跳过length
    unsigned int l,llen;

    while(*p != ZIPMAP_END) {
        unsigned char free;

        /* Match or skip the key */
        l = zipmapDecodeLength(p);//取得key的长度     
	llen = zipmapEncodeLength(NULL,l);//取得key占用的字节数        
	if (key != NULL && k == NULL && l == klen && !memcmp(p+llen,key,l)) {
            /* Only return when the user doesn't care
             * for the total length of the zipmap. */
            if (totlen != NULL) {
                k = p;
            } else {
                return p;
            }
        }
        p += llen+l;
        /* Skip the value as well */
        l = zipmapDecodeLength(p);//取得value的长度        
	p += zipmapEncodeLength(NULL,l);//取得value占用的字节数
        free = p[0];
        p += l+1+free; /* +1 to skip the free byte */
    }
    if (totlen != NULL) *totlen = (unsigned int)(p-zm)+1;
    return k;
}

 //查找key，注意totlen的值，如果没到key ，totlen将等于p的总长度,如果找到了，totlen等于key的下标

 

 

static unsigned long zipmapRequiredLength(unsigned int klen, unsigned int vlen) {
    unsigned int l;

    l = klen+vlen+3;//注意此处为何要加3？ (klen和vlen本身要占用1字节，还有1字节是留给free的)   
    if (klen >= ZIPMAP_BIGLEN) l += 4;//这里加4，是因为上面编码方法中所明    
    if (vlen >= ZIPMAP_BIGLEN) l += 4;
    return l;
}

/* Return the total amount used by a key (encoded length + payload) */
static unsigned int zipmapRawKeyLength(unsigned char *p) {
    unsigned int l = zipmapDecodeLength(p);
    return zipmapEncodeLength(NULL,l) + l;
}
//返回key总字节数

/* Return the total amount used by a value
 * (encoded length + single byte free count + payload) */
static unsigned int zipmapRawValueLength(unsigned char *p) {
    unsigned int l = zipmapDecodeLength(p);
    unsigned int used;
    
    used = zipmapEncodeLength(NULL,l);
    used += p[used] + 1 + l;
    return used;
}
//返回value总字节数，包含free字节
/* If 'p' points to a key, this function returns the total amount of
 * bytes used to store this entry (entry = key + associated value + trailing
 * free space if any). */
static unsigned int zipmapRawEntryLength(unsigned char *p) {
    unsigned int l = zipmapRawKeyLength(p);
    return l + zipmapRawValueLength(p+l);
}
//返回key和value总共所占的字节
static inline unsigned char *zipmapResize(unsigned char *zm, unsigned int len) {
    zm = zrealloc(zm, len);
    zm[len-1] = ZIPMAP_END;
    return zm;
}
//重置zm

 

 

 

/* Set key to value, creating the key if it does not already exist.
 * If 'update' is not NULL, *update is set to 1 if the key was
 * already preset, otherwise to 0. */
unsigned char *zipmapSet(unsigned char *zm, unsigned char *key, unsigned int klen, unsigned char *val, unsigned int vlen, int *update) {
    unsigned int zmlen, offset;
    unsigned int freelen, reqlen = zipmapRequiredLength(klen,vlen);
    unsigned int empty, vempty;
    unsigned char *p;
   
    freelen = reqlen;
    if (update) *update = 0;
    p = zipmapLookupRaw(zm,key,klen,&zmlen);
    if (p == NULL) {
        /* Key not found: enlarge */
        zm = zipmapResize(zm, zmlen+reqlen);
        p = zm+zmlen-1;
        zmlen = zmlen+reqlen;

        /* Increase zipmap length (this is an insert) */
        if (zm[0] < ZIPMAP_BIGLEN) zm[0]++;
    } else {
        /* Key found. Is there enough space for the new value? */
        /* Compute the total length: */
        if (update) *update = 1;
        freelen = zipmapRawEntryLength(p);
        if (freelen < reqlen) {
            /* Store the offset of this key within the current zipmap, so
             * it can be resized. Then, move the tail backwards so this
             * pair fits at the current position. */
            offset = p-zm;
            zm = zipmapResize(zm, zmlen-freelen+reqlen);
            p = zm+offset;

            /* The +1 in the number of bytes to be moved is caused by the
             * end-of-zipmap byte. Note: the *original* zmlen is used. */
            memmove(p+reqlen, p+freelen, zmlen-(offset+freelen+1));
            zmlen = zmlen-freelen+reqlen;
            freelen = reqlen;
        }
    }

    /* We now have a suitable block where the key/value entry can
     * be written. If there is too much free space, move the tail
     * of the zipmap a few bytes to the front and shrink the zipmap,
     * as we want zipmaps to be very space efficient. */
    empty = freelen-reqlen;
    if (empty >= ZIPMAP_VALUE_MAX_FREE) {
        /* First, move the tail <empty> bytes to the front, then resize
         * the zipmap to be <empty> bytes smaller. */
        offset = p-zm;
        memmove(p+reqlen, p+freelen, zmlen-(offset+freelen+1));
        zmlen -= empty;
        zm = zipmapResize(zm, zmlen);
        p = zm+offset;
        vempty = 0;
    } else {
        vempty = empty;
    }

    /* Just write the key + value and we are done. */
    /* Key: */
    p += zipmapEncodeLength(p,klen);
    memcpy(p,key,klen);
    p += klen;
    /* Value: */
    p += zipmapEncodeLength(p,vlen);
    *p++ = vempty;
    memcpy(p,val,vlen);
    return zm;
}

 此方法图解如下：


 
 文件中还有几个方法如zipmapGet，zipmapNext等，如果zipmapSet搞懂，其它方法便无障碍。

 

/* Return the number of entries inside a zipmap */
unsigned int zipmapLen(unsigned char *zm) {
    unsigned int len = 0;
    if (zm[0] < ZIPMAP_BIGLEN) {
//早在注释时就说过，如果size大小超过了ZIPMAP_BIGLEN，那么zipmap的第一个字节将不会记录size,size需要遍历才能得出
        len = zm[0];
    } else {
        unsigned char *p = zipmapRewind(zm);
        while((p = zipmapNext(p,NULL,NULL,NULL,NULL)) != NULL) len++;

        /* Re-store length if small enough */
        if (len < ZIPMAP_BIGLEN) zm[0] = len;
    }
    return len;
}

 //为什么在记录zipmap长度时不效仿记录key/value长度的方法，以至于如果取个数都需要遍历一遍？

不过根据我的实际应用经验，很少会直接去取hase的size.