Redis深度历险记(六)源码

Simple Dynamic String

书中的SDS的代码应该是示意用的,居然有泛型.实际上官方代码是根据平台有不同的.结构如下

结构体

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[];
};

embstr vs raw

Redis的字符串有两种存储方式,在长度特别短时,使用embstr形式存储,而当长度超过44字节时,使用raw形式存储

上面两种存储方式的差别如下

44

下面解释下44的由来
先附上redisObject的源代码,在server.h里

typedef struct redisObject {
    unsigned type:4;
    unsigned encoding:4;
    unsigned lru:LRU_BITS; /* LRU time (relative to global lru_clock) or
                            * LFU data (least significant 8 bits frequency
                            * and most significant 16 bits access time). */
    int refcount;
    void *ptr;
} robj;

由于一般一次申请内存是64byte,然后,减掉占用的19byte和一个NULL结尾(为了复用glibc)

扩容策略

在1MB以下是倍增,超过后每次加1M,需要说明的是默认情况下len和alloc是相等的,因为大多数情况下不需要扩容.

dict

以下是server.h里对Redis数据库的声明

/* Redis database representation. There are multiple databases identified
 * by integers from 0 (the default database) up to the max configured
 * database. The database number is the 'id' field in the structure. */
typedef struct redisDb {
    dict *dict;                 /* The keyspace for this DB */
    dict *expires;              /* Timeout of keys with a timeout set */
    dict *blocking_keys;        /* Keys with clients waiting for data (BLPOP)*/
    dict *ready_keys;           /* Blocked keys that received a PUSH */
    dict *watched_keys;         /* WATCHED keys for MULTI/EXEC CAS */
    int id;                     /* Database ID */
    long long avg_ttl;          /* Average TTL, just for stats */
    unsigned long expires_cursor; /* Cursor of the active expire cycle. */
    list *defrag_later;         /* List of key names to attempt to defrag one by one, gradually. */
} redisDb;

中间使用的dict如下

typedef struct dict {
    dictType *type;
    void *privdata;
    dictht ht[2];
    long rehashidx; /* rehashing not in progress if rehashidx == -1 */
    unsigned long iterators; /* number of iterators currently running */
} dict;

rehash

有两处地方调用,一处是在dictAddRaw里调用dictRehash,另一个是在databaseCron里调用.

static int _dictExpandIfNeeded(dict *d)
{
    /* Incremental rehashing already in progress. Return. */
    if (dictIsRehashing(d)) return DICT_OK;

    /* If the hash table is empty expand it to the initial size. */
    if (d->ht[0].size == 0) return dictExpand(d, DICT_HT_INITIAL_SIZE);

    /* If we reached the 1:1 ratio, and we are allowed to resize the hash
     * table (global setting) or we should avoid it but the ratio between
     * elements/buckets is over the "safe" threshold, we resize doubling
     * the number of buckets. */
    if (d->ht[0].used >= d->ht[0].size &&
        (dict_can_resize ||
         d->ht[0].used/d->ht[0].size > dict_force_resize_ratio))
    {
        return dictExpand(d, d->ht[0].used*2);
    }
    return DICT_OK;
}


/* Expand or create the hash table */
int dictExpand(dict *d, unsigned long size)
{
    /* the size is invalid if it is smaller than the number of
     * elements already inside the hash table */
    if (dictIsRehashing(d) || d->ht[0].used > size)
        return DICT_ERR;

    dictht n; /* the new hash table */
    unsigned long realsize = _dictNextPower(size);

    /* Rehashing to the same table size is not useful. */
    if (realsize == d->ht[0].size) return DICT_ERR;

    /* Allocate the new hash table and initialize all pointers to NULL */
    n.size = realsize;
    n.sizemask = realsize-1;
    n.table = zcalloc(realsize*sizeof(dictEntry*));
    n.used = 0;

    /* Is this the first initialization? If so it's not really a rehashing
     * we just set the first hash table so that it can accept keys. */
    if (d->ht[0].table == NULL) {
        d->ht[0] = n;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    d->ht[1] = n;
    d->rehashidx = 0;
    return DICT_OK;
}

整个流程可以简化成下面的图,需要注意的是C语言相对于Java而言喜欢把返回值的指针作为参数传给被调用函数

注意上面并没有遵循OO设计的画法,只是为了说明各个方法的相互关系

incrementallyRehash

/* Our hash table implementation performs rehashing incrementally while
 * we write/read from the hash table. Still if the server is idle, the hash
 * table will use two tables for a long time. So we try to use 1 millisecond
 * of CPU time at every call of this function to perform some rehahsing.
 *
 * The function returns 1 if some rehashing was performed, otherwise 0
 * is returned. */
int incrementallyRehash(int dbid) {
    /* Keys dictionary */
    if (dictIsRehashing(server.db[dbid].dict)) {
        dictRehashMilliseconds(server.db[dbid].dict,1);
        return 1; /* already used our millisecond for this loop... */
    }
    /* Expires */
    if (dictIsRehashing(server.db[dbid].expires)) {
        dictRehashMilliseconds(server.db[dbid].expires,1);
        return 1; /* already used our millisecond for this loop... */
    }
    return 0;
}

/* Rehash for an amount of time between ms milliseconds and ms+1 milliseconds */
int dictRehashMilliseconds(dict *d, int ms) {
    long long start = timeInMilliseconds();
    int rehashes = 0;

    while(dictRehash(d,100)) {
        rehashes += 100;
        if (timeInMilliseconds()-start > ms) break;
    }
    return rehashes;
}

int dictRehash(dict *d, int n) {
    int empty_visits = n*10; /* Max number of empty buckets to visit. */
    if (!dictIsRehashing(d)) return 0;

    while(n-- && d->ht[0].used != 0) {
        dictEntry *de, *nextde;

        /* Note that rehashidx can't overflow as we are sure there are more
         * elements because ht[0].used != 0 */
        assert(d->ht[0].size > (unsigned long)d->rehashidx);
        while(d->ht[0].table[d->rehashidx] == NULL) {
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        de = d->ht[0].table[d->rehashidx];
        /* Move all the keys in this bucket from the old to the new hash HT */
        while(de) {
            uint64_t h;

            nextde = de->next;
            /* Get the index in the new hash table */
            h = dictHashKey(d, de->key) & d->ht[1].sizemask;
            de->next = d->ht[1].table[h];
            d->ht[1].table[h] = de;
            d->ht[0].used--;
            d->ht[1].used++;
            de = nextde;
        }
        d->ht[0].table[d->rehashidx] = NULL;
        d->rehashidx++;
    }

    /* Check if we already rehashed the whole table... */
    if (d->ht[0].used == 0) {
        zfree(d->ht[0].table);
        d->ht[0] = d->ht[1];
        _dictReset(&d->ht[1]);
        d->rehashidx = -1;
        return 0;
    }

    /* More to rehash... */
    return 1;
}

整的看来和hash差不多,区别就是一次搬100个,然后看下时间过了没,如果过了就停下来

ziplist

根据zoplist.h可以看出ziplist都是被视为unsigned char *,根据ziplist.c的说明ziplist内部结构如下

<zlbytes> <zltail> <zllen> <entry> <entry> ... <entry> <zlend>

而entry的内部结构如下

<prevlen> <encoding> <entry-data>

其中prevlen又分为小于254和大于253两种情况,第一种情况比较简单,第二种情况是用0xFE开头来标识.不过反过来未必成立,即使使用了0xFE开头,后面的数据也有可能是小于254的,这种情况是由于shrink引起的

<prevlen from 0 to 253> <encoding> <entry>
0xFE <4 bytes unsigned little endian prevlen> <encoding> <entry>

至于encoding比较复杂,感觉使用了哈夫曼编码

quicklist

listpack

intset

根据intset.hintset结构如下

typedef struct intset {
    uint32_t encoding;
    uint32_t length;
    int8_t contents[];
} intset;

书中提出了一个观点,认为encoding和length都可以不用32位的,我翻了下源代码,除了反复处理encoding比较诡异外,我也认同书中作者观点.

zskiplist

zset内部其实是由dict和zskiplist组成

typedef struct zset {
    dict *dict;
    zskiplist *zsl;
} zset;

typedef struct zskiplist {
    struct zskiplistNode *header, *tail;
    unsigned long length;
    int level;
} zskiplist;


/* ZSETs use a specialized version of Skiplists */
typedef struct zskiplistNode {
    sds ele;
    double score;
    struct zskiplistNode *backward;
    struct zskiplistLevel {
        struct zskiplistNode *forward;
        unsigned long span;
    } level[];
} zskiplistNode;

新增node放入那一层是随机的,代码如下

/* Returns a random level for the new skiplist node we are going to create.
 * The return value of this function is between 1 and ZSKIPLIST_MAXLEVEL
 * (both inclusive), with a powerlaw-alike distribution where higher
 * levels are less likely to be returned. */
int zslRandomLevel(void) {
    int level = 1;
    while ((random()&0xFFFF) < (ZSKIPLIST_P * 0xFFFF))
        level += 1;
    return (level<ZSKIPLIST_MAXLEVEL) ? level : ZSKIPLIST_MAXLEVEL;
}

也就是默认第1层,运气好(25%)则会触发level+=1
复杂的数据结构带来复杂的操作,下面是insert的情况

/* Insert a new node in the skiplist. Assumes the element does not already
 * exist (up to the caller to enforce that). The skiplist takes ownership
 * of the passed SDS string 'ele'. */
zskiplistNode *zslInsert(zskiplist *zsl, double score, sds ele) {
    zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
    unsigned int rank[ZSKIPLIST_MAXLEVEL];
    int i, level;

    serverAssert(!isnan(score));
    x = zsl->header;
    for (i = zsl->level-1; i >= 0; i--) {
        /* store rank that is crossed to reach the insert position */
        rank[i] = i == (zsl->level-1) ? 0 : rank[i+1];
        while (x->level[i].forward &&
                (x->level[i].forward->score < score ||
                    (x->level[i].forward->score == score &&
                    sdscmp(x->level[i].forward->ele,ele) < 0)))
        {
            rank[i] += x->level[i].span;
            x = x->level[i].forward;
        }
        update[i] = x;
    }
    /* we assume the element is not already inside, since we allow duplicated
     * scores, reinserting the same element should never happen since the
     * caller of zslInsert() should test in the hash table if the element is
     * already inside or not. */
    level = zslRandomLevel();
    if (level > zsl->level) {
        for (i = zsl->level; i < level; i++) {
            rank[i] = 0;
            update[i] = zsl->header;
            update[i]->level[i].span = zsl->length;
        }
        zsl->level = level;
    }
    x = zslCreateNode(level,score,ele);
    for (i = 0; i < level; i++) {
        x->level[i].forward = update[i]->level[i].forward;
        update[i]->level[i].forward = x;

        /* update span covered by update[i] as x is inserted here */
        x->level[i].span = update[i]->level[i].span - (rank[0] - rank[i]);
        update[i]->level[i].span = (rank[0] - rank[i]) + 1;
    }

    /* increment span for untouched levels */
    for (i = level; i < zsl->level; i++) {
        update[i]->level[i].span++;
    }

    x->backward = (update[0] == zsl->header) ? NULL : update[0];
    if (x->level[0].forward)
        x->level[0].forward->backward = x;
    else
        zsl->tail = x;
    zsl->length++;
    return x;
}

至于文中说到zslUpdateScore过于简单粗暴,然后作者给了优化建议,我看到最新的代码是redis作者采纳了书中作者的建议

/* Update the score of an elmenent inside the sorted set skiplist.
 * Note that the element must exist and must match 'score'.
 * This function does not update the score in the hash table side, the
 * caller should take care of it.
 *
 * Note that this function attempts to just update the node, in case after
 * the score update, the node would be exactly at the same position.
 * Otherwise the skiplist is modified by removing and re-adding a new
 * element, which is more costly.
 *
 * The function returns the updated element skiplist node pointer. */
zskiplistNode *zslUpdateScore(zskiplist *zsl, double curscore, sds ele, double newscore) {
    zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
    int i;

    /* We need to seek to element to update to start: this is useful anyway,
     * we'll have to update or remove it. */
    x = zsl->header;
    for (i = zsl->level-1; i >= 0; i--) {
        while (x->level[i].forward &&
                (x->level[i].forward->score < curscore ||
                    (x->level[i].forward->score == curscore &&
                     sdscmp(x->level[i].forward->ele,ele) < 0)))
        {
            x = x->level[i].forward;
        }
        update[i] = x;
    }

    /* Jump to our element: note that this function assumes that the
     * element with the matching score exists. */
    x = x->level[0].forward;
    serverAssert(x && curscore == x->score && sdscmp(x->ele,ele) == 0);

    /* If the node, after the score update, would be still exactly
     * at the same position, we can just update the score without
     * actually removing and re-inserting the element in the skiplist. */
    if ((x->backward == NULL || x->backward->score < newscore) &&
        (x->level[0].forward == NULL || x->level[0].forward->score > newscore))
    {
        x->score = newscore;
        return x;
    }

    /* No way to reuse the old node: we need to remove and insert a new
     * one at a different place. */
    zslDeleteNode(zsl, x, update);
    zskiplistNode *newnode = zslInsert(zsl,newscore,x->ele);
    /* We reused the old node x->ele SDS string, free the node now
     * since zslInsert created a new one. */
    x->ele = NULL;
    zslFreeNode(x);
    return newnode;
}

rax

下面代码来自rax.h

typedef struct raxNode {
    uint32_t iskey:1;     /* Does this node contain a key? */
    uint32_t isnull:1;    /* Associated value is NULL (don't store it). */
    uint32_t iscompr:1;   /* Node is compressed. */
    uint32_t size:29;     /* Number of children, or compressed string len. */
    unsigned char data[];
} raxNode;

压缩节点就是只有一个子节点的节点,如图所示深蓝色节点(看上去是为了缩短路径)