redis-skip-list-impl.org

Redis跳表实现

Redis用跳表来实现什么数据结构：支持点查询和范围查询额有序集合。https://redisbook.readthedocs.io/en/latest/internal-datastruct/skiplist.html

理论上也可以使用平衡二叉树来实现，而且内存上应该是和跳表差不多，没有太明白跳表相比平衡二叉树的优势在哪里。

跳表原理还可以看这篇文章 https://juejin.im/post/57fa935b0e3dd90057c50fbc

下面跳表实现代码是我从redis-4.0.10里面分离出来的 code on github. 我只是在数据结构上增加了一下简单的注释。它的实现非常清晰，在头部也有很详细的注释。

#include <stdio.h>
#include <math.h>
#include <stdlib.h>
#include <string.h>

// ==================== server.h ====================
typedef char* sds; // 前缀表示长度的字符串
#define sdsfree free
#define sdscmp strcmp
#define zmalloc malloc // jemalloc实现
#define zfree free

#define ZSKIPLIST_MAXLEVEL 32 /* Should be enough for 2^32 elements */
// 控制跳表的高度
#define ZSKIPLIST_P 0.25      /* Skiplist P = 1/4 */

/* ZSETs use a specialized version of Skiplists */
typedef struct zskiplistNode {
    sds ele; // 元素值
    double score; // 元素权重
    struct zskiplistNode *backward; // 存储反向链表
    struct zskiplistLevel { // level上的数据
        struct zskiplistNode *forward; // 前向列表
        unsigned int span; // 从这个节点到forward覆盖多少元素
    } level[];
} zskiplistNode;

typedef struct zskiplist {
    struct zskiplistNode *header, *tail; // 为了实现方面增加了header和tail.
    unsigned long length; // 共有多少个节点
    int level; // 共有多少层
} zskiplist;


// ==================== t_zset.c ====================
/* Create a skiplist node with the specified number of levels.
 * The SDS string 'ele' is referenced by the node after the call. */
zskiplistNode *zslCreateNode(int level, double score, sds ele) {
    zskiplistNode *zn =
        zmalloc(sizeof(*zn)+level*sizeof(struct zskiplistLevel));
    zn->score = score;
    zn->ele = ele;
    return zn;
}

/* Create a new skiplist. */
zskiplist *zslCreate(void) {
    int j;
    zskiplist *zsl;

    zsl = zmalloc(sizeof(*zsl));
    zsl->level = 1;
    zsl->length = 0;
    zsl->header = zslCreateNode(ZSKIPLIST_MAXLEVEL,0,NULL);
    for (j = 0; j < ZSKIPLIST_MAXLEVEL; j++) {
        zsl->header->level[j].forward = NULL;
        zsl->header->level[j].span = 0;
    }
    zsl->header->backward = NULL;
    zsl->tail = NULL;
    return zsl;
}

/* Free the specified skiplist node. The referenced SDS string representation
 * of the element is freed too, unless node->ele is set to NULL before calling
 * this function. */
void zslFreeNode(zskiplistNode *node) {
    sdsfree(node->ele);
    zfree(node);
}

/* Free a whole skiplist. */
void zslFree(zskiplist *zsl) {
    zskiplistNode *node = zsl->header->level[0].forward, *next;

    zfree(zsl->header);
    while(node) {
        next = node->level[0].forward;
        zslFreeNode(node);
        node = next;
    }
    zfree(zsl);
}

/* 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;
}

/* 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;
}

/* Internal function used by zslDelete, zslDeleteByScore and zslDeleteByRank */
void zslDeleteNode(zskiplist *zsl, zskiplistNode *x, zskiplistNode **update) {
    int i;
    for (i = 0; i < zsl->level; i++) {
        if (update[i]->level[i].forward == x) {
            update[i]->level[i].span += x->level[i].span - 1;
            update[i]->level[i].forward = x->level[i].forward;
        } else {
            update[i]->level[i].span -= 1;
        }
    }
    if (x->level[0].forward) {
        x->level[0].forward->backward = x->backward;
    } else {
        zsl->tail = x->backward;
    }
    while(zsl->level > 1 && zsl->header->level[zsl->level-1].forward == NULL)
        zsl->level--;
    zsl->length--;
}

/* Delete an element with matching score/element from the skiplist.
 * The function returns 1 if the node was found and deleted, otherwise
 * 0 is returned.
 *
 * If 'node' is NULL the deleted node is freed by zslFreeNode(), otherwise
 * it is not freed (but just unlinked) and *node is set to the node pointer,
 * so that it is possible for the caller to reuse the node (including the
 * referenced SDS string at node->ele). */
int zslDelete(zskiplist *zsl, double score, sds ele, zskiplistNode **node) {
    zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
    int i;

    x = zsl->header;
    for (i = zsl->level-1; i >= 0; i--) {
        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)))
        {
            x = x->level[i].forward;
        }
        update[i] = x;
    }
    /* We may have multiple elements with the same score, what we need
     * is to find the element with both the right score and object. */
    x = x->level[0].forward;
    if (x && score == x->score && sdscmp(x->ele,ele) == 0) {
        zslDeleteNode(zsl, x, update);
        if (!node)
            zslFreeNode(x);
        else
            *node = x;
        return 1;
    }
    return 0; /* not found */
}