【redis源码】（三）Zipmap

更科学的分析见这篇文章，小弟看了之后才明白一点点的

http://www.open-open.com/bbs/view/1321697543077

下面几句是我自己对zipmap的理解

1. zipmap是一个简单的使用字符串实现的hash表，按照作者的本意，只会包含254以内的的key-value对

2. 整个redis来看，redis是一个巨大地hash表【key-value对】，只不过这个大hash表的value不只支持字符串，而是redisObject，redisObject中的void * ptr指针可以指向任何数据结构~~~【强悍的扩展性，咱可以自己添加】

3. dict乃是redis实现hash表的数据结构，这是个复杂的东西【如果entry量很小，用起来效率很低】，作者为了节省内存，当redisobject为一个hashmap并且entry数量很小【<254】，value会使用轻量级的zipmap作为map的承载体. zip本身的操作复杂度是O(n)【n为key-value对的数量】

哦了~ 贴代码，只是加了一些本人的注释，没啥特别的，供自己做个记录用~

Ziphash.h

#ifndef _ZIMMAP_H
#define _ZIPMAP_H

unsigned char *zipmapNew(void);
unsigned char *zipmapSet(unsigned char *zm, unsigned char *key, unsigned int klen, unsigned char *val, unsigned int vlen, int *update);
unsigned char *zipmapDel(unsigned char *zm, unsigned char *key, unsigned int klen, int *deleted);
unsigned char *zipmapRewind(unsigned char *zm);
unsigned char *zipmapNext(unsigned char *zm, unsigned char **key, unsigned int *klen, unsigned char **value, unsigned int *vlen);
int zipmapGet(unsigned char *zm, unsigned char *key, unsigned int klen, unsigned char **value, unsigned int *vlen);
int zipmapExists(unsigned char *zm, unsigned char *key, unsigned int klen);
unsigned int zipmapLen(unsigned char *zm);
void zipmapRepr(unsigned char *p);

#endif

Ziphash.c

#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "zmalloc.h"

//如果len字段为254，则后4个字节表示真正长度
#define ZIPMAP_BIGLEN 254
//zipmap串最后一个byte的值
#define ZIPMAP_END 255

/* The following defines the max value for the <free> field described in the
 * comments above, that is, the max number of trailing bytes in a value. */
//如果free字段大于此值，则进行压缩操作，节省空间
#define ZIPMAP_VALUE_MAX_FREE 4

/* The following macro returns the number of bytes needed to encode the length
 * for the integer value _l, that is, 1 byte for lengths < ZIPMAP_BIGLEN and
 * 5 bytes for all the other lengths. */
//这个宏用来计算表达len的真实长度，如果小于254，则len占用1个字节，否则占用4+1个字节
#define ZIPMAP_LEN_BYTES(_l) (((_l) < ZIPMAP_BIGLEN) ? 1 : sizeof(unsigned int)+1)

//创建一个新的zipmap，这个空zipmap占用2个byte的内存空间
/* Create a new empty zipmap. */
unsigned char *zipmapNew(void) {
    unsigned char *zm = zmalloc(2);

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


//如果长度p所在的unsigned char的小于254，即使后边跟随的string的长度，如果大于等于254，即后边的4个bytes为真实长度
/* 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));
    return len;
}


//输入value或者key的长度len，将zipmap自有的长度表示方法的字符串放到p开头的字符串中，如果p为NULL直接返回占用的byte字节数
/* 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));
            return 1+sizeof(len);
        }
    }
}

//在zm中寻找长度为klen的key，如果找到，返回其所为key的<len>字段的指针，如果没找到返回NULL.
//如果totlen字段不为NULL，则使其为整个zm所占的bytes数
/* 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;
    unsigned int l,llen;

    while(*p != ZIPMAP_END) { //如果未到结尾
        unsigned char free;

        /* Match or skip the key */
        l = zipmapDecodeLength(p); //得到value或者key长度大小
        llen = zipmapEncodeLength(NULL,l); // 得到len本身占的byte数
        //如果长度和cmp结果为0(相同)
        if (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 { //如果totlen为NULL直接返回指针p
                return p;
            }
        }
        p += llen+l;
        /* Skip the value as well */
        l = zipmapDecodeLength(p);
        p += zipmapEncodeLength(NULL,l);
        free = p[0];
        p += l+1+free; /* +1 to skip the free byte */
    }
    if (totlen != NULL) *totlen = (unsigned int)(p-zm)+1;
    return k;
}


//得到一个只保存一个keyvalue对的zipmap所需要的bytes数
static unsigned long zipmapRequiredLength(unsigned int klen, unsigned int vlen) {
    unsigned int l;

    l = klen+vlen+3; //key_len+value_len+value_free
    if (klen >= ZIPMAP_BIGLEN) l += 4; 
    if (vlen >= ZIPMAP_BIGLEN) l += 4;
    return l;
}

//得到一个key所需要的内存大小
/* 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;
}

//p为value的首地址，计算value段占用的内存bytes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; //p[used] free的字节数+ free本身一个字节+len长度(1 or 5)
    return used;
}

//返回整个p指向的key-value对所占用的内存空间大小
/* 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);
}


//realloc 内存for zm
static inline unsigned char *zipmapResize(unsigned char *zm, unsigned int len) {
    zm = zrealloc(zm, len);
    zm[len-1] = ZIPMAP_END;
    return zm;
}

//插入一个key-value对，如果key不存在，则直接resize zm，加到最后边的位置
//如果key存在，并且空间够用，则直接在原位置对value进行替换，更新free,如果free小于ZIPMAP_VALUE_MAX_FREE，则保留free，如果大于等于ZIPMAP_VALUE_MAX_FREE，则需要尽心memmove
/* 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;
}


//删除指定key，并用deleted来indicated执行结果
/* Remove the specified key. If 'deleted' is not NULL the pointed integer is
 * set to 0 if the key was not found, to 1 if it was found and deleted. */
unsigned char *zipmapDel(unsigned char *zm, unsigned char *key, unsigned int klen, int *deleted) {
    unsigned int zmlen, freelen;
    unsigned char *p = zipmapLookupRaw(zm,key,klen,&zmlen);
    if (p) {
        freelen = zipmapRawEntryLength(p);
        memmove(p, p+freelen, zmlen-((p-zm)+freelen+1));
        zm = zipmapResize(zm, zmlen-freelen);

        /* Decrease zipmap length */
        if (zm[0] < ZIPMAP_BIGLEN) zm[0]--;

        if (deleted) *deleted = 1;
    } else {
        if (deleted) *deleted = 0;
    }
    return zm;
}

/* Call it before to iterate trought elements via zipmapNext() */
unsigned char *zipmapRewind(unsigned char *zm) {
    return zm+1;
}

/* This function is used to iterate through all the zipmap elements.
 * In the first call the first argument is the pointer to the zipmap + 1.
 * In the next calls what zipmapNext returns is used as first argument.
 * Example:
 *
 * unsigned char *i = zipmapRewind(my_zipmap);
 * while((i = zipmapNext(i,&key,&klen,&value,&vlen)) != NULL) {
 *     printf("%d bytes key at $p\n", klen, key);
 *     printf("%d bytes value at $p\n", vlen, value);
 * }
 */
unsigned char *zipmapNext(unsigned char *zm, unsigned char **key, unsigned int *klen, unsigned char **value, unsigned int *vlen) {
    if (zm[0] == ZIPMAP_END) return NULL;
    if (key) {
        *key = zm;
        *klen = zipmapDecodeLength(zm);
        *key += ZIPMAP_LEN_BYTES(*klen);
    }
    zm += zipmapRawKeyLength(zm);
    if (value) {
        *value = zm+1;
        *vlen = zipmapDecodeLength(zm);
        *value += ZIPMAP_LEN_BYTES(*vlen);
    }
    zm += zipmapRawValueLength(zm);
    return zm;
}

//取得一个key对应的value，如果找到key，返回1，否则返回0
/* Search a key and retrieve the pointer and len of the associated value.
 * If the key is found the function returns 1, otherwise 0. */
int zipmapGet(unsigned char *zm, unsigned char *key, unsigned int klen, unsigned char **value, unsigned int *vlen) {
    unsigned char *p;

    if ((p = zipmapLookupRaw(zm,key,klen,NULL)) == NULL) return 0;
    p += zipmapRawKeyLength(p);
    *vlen = zipmapDecodeLength(p);
    *value = p + ZIPMAP_LEN_BYTES(*vlen) + 1;
    return 1;
}

//判断一个key是否存在于zm中
/* Return 1 if the key exists, otherwise 0 is returned. */
int zipmapExists(unsigned char *zm, unsigned char *key, unsigned int klen) {
    return zipmapLookupRaw(zm,key,klen,NULL) != NULL;
}

/* Return the number of entries inside a zipmap */
unsigned int zipmapLen(unsigned char *zm) {
    unsigned int len = 0;
    if (zm[0] < ZIPMAP_BIGLEN) {
        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;
}

//打印p开头的kye-value对
void zipmapRepr(unsigned char *p) {
    unsigned int l;

    printf("{status %u}",*p++);
    while(1) {
        if (p[0] == ZIPMAP_END) {
            printf("{end}");
            break;
        } else {
            unsigned char e;

            l = zipmapDecodeLength(p);
            printf("{key %u}",l);
            p += zipmapEncodeLength(NULL,l);
            if (l != 0 && fwrite(p,l,1,stdout) == 0) perror("fwrite");
            p += l;

            l = zipmapDecodeLength(p);
            printf("{value %u}",l);
            p += zipmapEncodeLength(NULL,l);
            e = *p++;
            if (l != 0 && fwrite(p,l,1,stdout) == 0) perror("fwrite");
            p += l+e;
            if (e) {
                printf("[");
                while(e--) printf(".");
                printf("]");
            }
        }
    }
    printf("\n");
}

#ifdef ZIPMAP_TEST_MAIN
int main(void) {
    unsigned char *zm;

    zm = zipmapNew();

    zm = zipmapSet(zm,(unsigned char*) "name",4, (unsigned char*) "foo",3,NULL);
    zm = zipmapSet(zm,(unsigned char*) "surname",7, (unsigned char*) "foo",3,NULL);
    zm = zipmapSet(zm,(unsigned char*) "age",3, (unsigned char*) "foo",3,NULL);
    zipmapRepr(zm);

    zm = zipmapSet(zm,(unsigned char*) "hello",5, (unsigned char*) "world!",6,NULL);
    zm = zipmapSet(zm,(unsigned char*) "foo",3, (unsigned char*) "bar",3,NULL);
    zm = zipmapSet(zm,(unsigned char*) "foo",3, (unsigned char*) "!",1,NULL);
    zipmapRepr(zm);
    zm = zipmapSet(zm,(unsigned char*) "foo",3, (unsigned char*) "12345",5,NULL);
    zipmapRepr(zm);
    zm = zipmapSet(zm,(unsigned char*) "new",3, (unsigned char*) "xx",2,NULL);
    zm = zipmapSet(zm,(unsigned char*) "noval",5, (unsigned char*) "",0,NULL);
    zipmapRepr(zm);
    zm = zipmapDel(zm,(unsigned char*) "new",3,NULL);
    zipmapRepr(zm);

    printf("\nLook up large key:\n");
    {
        unsigned char buf[512];
        unsigned char *value;
        unsigned int vlen, i;
        for (i = 0; i < 512; i++) buf[i] = 'a';

        zm = zipmapSet(zm,buf,512,(unsigned char*) "long",4,NULL);
        if (zipmapGet(zm,buf,512,&value,&vlen)) {
            printf("  <long key> is associated to the %d bytes value: %.*s\n",
                vlen, vlen, value);
        }
    }

    printf("\nPerform a direct lookup:\n");
    {
        unsigned char *value;
        unsigned int vlen;

        if (zipmapGet(zm,(unsigned char*) "foo",3,&value,&vlen)) {
            printf("  foo is associated to the %d bytes value: %.*s\n",
                vlen, vlen, value);
        }
    }
    printf("\nIterate trought elements:\n");
    {
        unsigned char *i = zipmapRewind(zm);
        unsigned char *key, *value;
        unsigned int klen, vlen;

        while((i = zipmapNext(i,&key,&klen,&value,&vlen)) != NULL) {
            printf("  %d:%.*s => %d:%.*s\n", klen, klen, key, vlen, vlen, value);
        }
    }
    return 0;
}
#endif

下一篇将介绍ziplist~~