结合redis设计与实现的redis源码学习-5-skiplist（跳跃表）

跳跃表示一种有序的数据结构他通过在每个节点中维持多个指向其他节点的指针，从而达到快速访问节点的目的，平均访问速度O(logN)，最坏O(N)复杂度的节点查找，还可以通过顺序性操作类批量处理节点。

在redis中，在实现有序集合键和在集群节点中用作内部数据结构时用到了跳跃表。

跳跃表的特点：1、redis中的跳跃表实现由zskiplist和zskiplistNode两个结构组成，其中zskiplist保存跳跃表的信息，zskiplistNode表示跳跃表的节点；

2、每个跳跃表的节点的层高都是1-32之间的随机数；

3、在同一个跳跃表中，多个节点可以包含相同的分值，但每个节点的成员对象必须是唯一的；

4、跳跃表中的节点按照分值大小进行排序，当分值相同时，节点按照成员对象的大小进行排序；

跳跃表利用接近双倍的空间创造了一个类似二叉搜索树的数据结构，不过效果看天，理想期望值相近。

redis3.2中，跳跃表的声明在server.h，实现在T_zset.c中，这两个文件包含的内容比较多，所以在此我挑选出了一部分跳跃表用到的代码来学习，代码：

//跳跃标节点
typedef struct zskiplistNode {
robj *obj;//成员对象
double score;//分值
struct zskiplistNode *backward;//后退指针
struct zskiplistLevel {//层
struct zskiplistNode *forward;//前进指针
unsigned int span;//跨度
} level[];
} zskiplistNode;
//跳跃表
typedef struct
f73b
zskiplist {
struct zskiplistNode *header, *tail;//头尾指针
unsigned long length;//长度
int level;//层数
} zskiplist;

实现代码，挑选了一些必须的函数：

//创建一个跳跃表的节点
zskiplistNode *zslCreateNode(int level, double score, robj *obj) {
zskiplistNode *zn = zmalloc(sizeof(*zn)+level*sizeof(struct zskiplistLevel));
zn->score = score;
zn->obj = obj;
return zn;
}

//创建一个新的跳跃表
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++) {//初始化每层的头和跨度
zsl->header->level[j].forward = NULL;
zsl->header->level[j].span = 0;
}
zsl->header->backward = NULL;
zsl->tail = NULL;
return zsl;
}
//这个函数用来释放多种数据结构，根据跳跃表保存的数据类型选择
void decrRefCount(robj *o) {
if (o->refcount <= 0) serverPanic("decrRefCount against refcount <= 0");
if (o->refcount == 1) {
switch(o->type) {
case OBJ_STRING: freeStringObject(o); break;
case OBJ_LIST: freeListObject(o); break;
case OBJ_SET: freeSetObject(o); break;
case OBJ_ZSET: freeZsetObject(o); break;
case OBJ_HASH: freeHashObject(o); break;
default: serverPanic("Unknown object type"); break;
}
zfree(o);
} else {
o->refcount--;
}
}

//释放一个节点
void zslFreeNode(zskiplistNode *node) {
decrRefCount(node->obj);
zfree(node);
}
//释放整个跳跃表
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);
}
//随机新节点层数，小于最大层数，我看书还以为虚幻随机32次，为1加1层呢
int zslRandomLevel(void) {
int level = 1;
while ((random()&0xFFFF) < (ZSKIPLIST_P * 0xFFFF))
level += 1;
return (level<ZSKIPLIST_MAXLEVEL) ? level : ZSKIPLIST_MAXLEVEL;
}
//跳跃表插入对象
zskiplistNode *zslInsert(zskiplist *zsl, double score, robj *obj) {
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 寻找插入位置，真长*/
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 &&
compareStringObjects(x->level[i].forward->obj,obj) < 0))) {
rank[i] += x->level[i].span;
x = x->level[i].forward;
}
update[i] = x;
}
/* we assume the key is not already inside, since we allow duplicated
* scores, and the re-insertion of score and redis object 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,obj);
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;
}
//删除一个节点
/* 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--;
}
//删除跳跃表中包含给定成员和分值的节点
/* Delete an element with matching score/object from the skiplist. */
int zslDelete(zskiplist *zsl, double score, robj *obj) {
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 &&
compareStringObjects(x->level[i].forward->obj,obj) < 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 && equalStringObjects(x->obj,obj)) {
zslDeleteNode(zsl, x, update);
zslFreeNode(x);
return 1;
}
return 0; /* not found */
}
//获取最大最小值
static int zslValueGteMin(double value, zrangespec *spec) {
return spec->minex ? (value > spec->min) : (value >= spec->min);
}
int zslValueLteMax(double value, zrangespec *spec) {
return spec->maxex ? (value < spec->max) : (value <= spec->max);
}
//给定一个分值返回，判断是否在跳跃表的范围内返回1，没有返回0
/* Returns if there is a part of the zset is in range. */
int zslIsInRange(zskiplist *zsl, zrangespec *range) {
zskiplistNode *x;

/* Test for ranges that will always be empty. */
if (range->min > range->max ||
(range->min == range->max && (range->minex || range->maxex)))
return 0;
x = zsl->tail;
if (x == NULL || !zslValueGteMin(x->score,range))
return 0;
x = zsl->header->level[0].forward;
if (x == NULL || !zslValueLteMax(x->score,range))
return 0;
return 1;
}
//给定一个分值范围，返回跳跃表中第一个符合这个范围的节点
/* Find the first node that is contained in the specified range.
* Returns NULL when no element is contained in the range. */
zskiplistNode *zslFirstInRange(zskiplist *zsl, zrangespec *range) {
zskiplistNode *x;
int i;

/* If everything is out of range, return early. */
if (!zslIsInRange(zsl,range)) return NULL;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
/* Go forward while *OUT* of range. */
while (x->level[i].forward &&
!zslValueGteMin(x->level[i].forward->score,range))
x = x->level[i].forward;
}

/* This is an inner range, so the next node cannot be NULL. */
x = x->level[0].forward;
serverAssert(x != NULL);

/* Check if score <= max. */
if (!zslValueLteMax(x->score,range)) return NULL;
return x;
}
//给定一个分值范围，返回跳跃表中最后一个符合这个范围的节点
/* Find the last node that is contained in the specified range.
* Returns NULL when no element is contained in the range. */
zskiplistNode *zslLastInRange(zskiplist *zsl, zrangespec *range) {
zskiplistNode *x;
int i;

/* If everything is out of range, return early. */
if (!zslIsInRange(zsl,range)) return NULL;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
/* Go forward while *IN* range. */
while (x->level[i].forward &&
zslValueLteMax(x->level[i].forward->score,range))
x = x->level[i].forward;
}

/* This is an inner range, so this node cannot be NULL. */
serverAssert(x != NULL);

/* Check if score >= min. */
if (!zslValueGteMin(x->score,range)) return NULL;
return x;
}
//给定一个分值范围，删除所有在这个分值范围内的节点
/* Delete all the elements with score between min and max from the skiplist.
* Min and max are inclusive, so a score >= min || score <= max is deleted.
* Note that this function takes the reference to the hash table view of the
* sorted set, in order to remove the elements from the hash table too. */
unsigned long zslDeleteRangeByScore(zskiplist *zsl, zrangespec *range, dict *dict) {
zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
unsigned long removed = 0;
int i;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
while (x->level[i].forward && (range->minex ?
x->level[i].forward->score <= range->min :
x->level[i].forward->score < range->min))
x = x->level[i].forward;
update[i] = x;
}

/* Current node is the last with score < or <= min. */
x = x->level[0].forward;

/* Delete nodes while in range. */
while (x &&
(range->maxex ? x->score < range->max : x->score <= range->max))
{
zskiplistNode *next = x->level[0].forward;
zslDeleteNode(zsl,x,update);
dictDelete(dict,x->obj);
zslFreeNode(x);
removed++;
x = next;
}
return removed;
}
//
unsigned long zslDeleteRangeByLex(zskiplist *zsl, zlexrangespec *range, dict *dict) {
zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
unsigned long removed = 0;
int i;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
while (x->level[i].forward &&
!zslLexValueGteMin(x->level[i].forward->obj,range))
x = x->level[i].forward;
update[i] = x;
}

/* Current node is the last with score < or <= min. */
x = x->level[0].forward;

/* Delete nodes while in range. */
while (x && zslLexValueLteMax(x->obj,range)) {
zskiplistNode *next = x->level[0].forward;
zslDeleteNode(zsl,x,update);
dictDelete(dict,x->obj);
zslFreeNode(x);
removed++;
x = next;
}
return removed;
}
//给定一个排位范围，杀出跳跃表中所有在这个范围内的节点
/* Delete all the elements with rank between start and end from the skiplist.
* Start and end are inclusive. Note that start and end need to be 1-based */
unsigned long zslDeleteRangeByRank(zskiplist *zsl, unsigned int start, unsigned int end, dict *dict) {
zskiplistNode *update[ZSKIPLIST_MAXLEVEL], *x;
unsigned long traversed = 0, removed = 0;
int i;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
while (x->level[i].forward && (traversed + x->level[i].span) < start) {
traversed += x->level[i].span;
x = x->level[i].forward;
}
update[i] = x;
}

traversed++;
x = x->level[0].forward;
while (x && traversed <= end) {
zskiplistNode *next = x->level[0].forward;
zslDeleteNode(zsl,x,update);
dictDelete(dict,x->obj);
zslFreeNode(x);
removed++;
traversed++;
x = next;
}
return removed;
}
//返回包含给定成员和分值的节点在跳跃表中的排位
/* Find the rank for an element by both score and key.
* Returns 0 when the element cannot be found, rank otherwise.
* Note that the rank is 1-based due to the span of zsl->header to the
* first element. */
unsigned long zslGetRank(zskiplist *zsl, double score, robj *o) {
zskiplistNode *x;
unsigned long rank = 0;
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 &&
compareStringObjects(x->level[i].forward->obj,o) <= 0))) {
rank += x->level[i].span;
x = x->level[i].forward;
}

/* x might be equal to zsl->header, so test if obj is non-NULL */
if (x->obj && equalStringObjects(x->obj,o)) {
return rank;
}
}
return 0;
}
//返回跳跃表在给定排位上的节点
/* Finds an element by its rank. The rank argument needs to be 1-based. */
zskiplistNode* zslGetElementByRank(zskiplist *zsl, unsigned long rank) {
zskiplistNode *x;
unsigned long traversed = 0;
int i;

x = zsl->header;
for (i = zsl->level-1; i >= 0; i--) {
while (x->level[i].forward && (traversed + x->level[i].span) <= rank)
{
traversed += x->level[i].span;
x = x->level[i].forward;
}
if (traversed == rank) {
return x;
}
}
return NULL;
}