开始之前,这里推荐一篇《大话程序员的恐怖之源-改需求》文章,作者:六月的雨在Tencent。
https://cloud.tencent.com/developer/article/2465509
程序员日常工作就是配合产品解析需求,然后制定开发计划进行后续的开发。文章分析了程序员为什么会害怕“改需求”?以及程序员害怕“改需求”大致上体现在哪几个方面。
跳表(多层级有序链表)结构用来实现有序集合。 鉴于 redis 需要实现 zrange 以及 zrevrange 功能;需要节点间最好能直接相连并且增删改操作后结构依然有序。 B+ 树时间复杂度为 h*O(log_2 n),但 B+ 数有复杂的节点分裂操作;有序数组通过二分查找能获得O(log_2 n)时间复杂度;平衡二叉树也能获得O(log_2 n) 时间复杂度。
每隔一个节点生成一个层级节点;模拟二叉树结构,以此达到搜索时间复杂度为 O(log_2 n) ;通过空间换时间的结构。 但是如果对理想跳表结构进行删除增加操作,很有可能改变跳表结构;如果重构理想结构,将是巨大的运算。
考虑用概率的方法来进行优化: 从每一个节点出发,每增加一个节点都有1/2的概率增加一个层级,1/4 的概率增加两个层级, 1/8的概率增加3 个层级,以此类推。 经过证明,当数据量足够大(256)时,通过概率构造的跳表趋向于理想跳表,并且此时如果删除节点,无需重构跳表结构,此时依然趋向于理想跳表。此时时间复杂度为:
从节约内存出发,redis 考虑牺牲一点时间复杂度让跳表结构更加变扁平,就像二叉堆改成四叉堆结构;并且 redis 还限制了跳表的最高层级为 32。 节点数量大于 128 或者有一个字符串长度大于 64,则使用跳表(skiplist)。
server.h
#define ZSKIPLIST_MAXLEVEL 32 /* Should be enough for 2^64 elements */
#define ZSKIPLIST_P 0.25 /* Skiplist P = 1/4 */
/* 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;// 用于zrank
} level[];
} zskiplistNode;
typedef struct zskiplist {
struct zskiplistNode *header, *tail;
unsigned long length;
int level;
} zskiplist;
typedef struct zset {
dict *dict;
zskiplist *zsl;
} zset;
要实现O(log_2 n)的时间复杂度,有很多方式,redis使用调表的原因是调表中的所有元素都在第一个层级(即level 0),如果要进行范围查询,只需要找到两个边界,(因为调表是有序的)第一层往下遍历就行了,这是其他数据结构时间复杂度不能达到的高效范围查询。
执行zadd命令时会执行如下的函数(t_zset.c):
int zsetAdd(robj *zobj, double score, sds ele, int *flags, double *newscore) {
/* Turn options into simple to check vars. */
int incr = (*flags & ZADD_INCR) != 0;
int nx = (*flags & ZADD_NX) != 0;
int xx = (*flags & ZADD_XX) != 0;
*flags = 0; /* We'll return our response flags. */
double curscore;
/* NaN as input is an error regardless of all the other parameters. */
if (isnan(score)) {
*flags = ZADD_NAN;
return 0;
}
/* Update the sorted set according to its encoding. */
if (zobj->encoding == OBJ_ENCODING_ZIPLIST) {
unsigned char *eptr;
if ((eptr = zzlFind(zobj->ptr,ele,&curscore)) != NULL) {
/* NX? Return, same element already exists. */
if (nx) {
*flags |= ZADD_NOP;
return 1;
}
/* Prepare the score for the increment if needed. */
if (incr) {
score += curscore;
if (isnan(score)) {
*flags |= ZADD_NAN;
return 0;
}
if (newscore) *newscore = score;
}
/* Remove and re-insert when score changed. */
if (score != curscore) {
zobj->ptr = zzlDelete(zobj->ptr,eptr);
zobj->ptr = zzlInsert(zobj->ptr,ele,score);
*flags |= ZADD_UPDATED;
}
return 1;
} else if (!xx) {
/* check if the element is too large or the list
* becomes too long *before* executing zzlInsert. */
if (zzlLength(zobj->ptr)+1 > server.zset_max_ziplist_entries ||
sdslen(ele) > server.zset_max_ziplist_value ||
!ziplistSafeToAdd(zobj->ptr, sdslen(ele)))
{
zsetConvert(zobj,OBJ_ENCODING_SKIPLIST);
} else {
zobj->ptr = zzlInsert(zobj->ptr,ele,score);
if (newscore) *newscore = score;
*flags |= ZADD_ADDED;
return 1;
}
} else {
*flags |= ZADD_NOP;
return 1;
}
}
/* Note that the above block handling ziplist would have either returned or
* converted the key to skiplist. */
if (zobj->encoding == OBJ_ENCODING_SKIPLIST) {
zset *zs = zobj->ptr;
zskiplistNode *znode;
dictEntry *de;
de = dictFind(zs->dict,ele);
if (de != NULL) {
/* NX? Return, same element already exists. */
if (nx) {
*flags |= ZADD_NOP;
return 1;
}
curscore = *(double*)dictGetVal(de);
/* Prepare the score for the increment if needed. */
if (incr) {
score += curscore;
if (isnan(score)) {
*flags |= ZADD_NAN;
return 0;
}
if (newscore) *newscore = score;
}
/* Remove and re-insert when score changes. */
if (score != curscore) {
znode = zslUpdateScore(zs->zsl,curscore,ele,score);
/* Note that we did not removed the original element from
* the hash table representing the sorted set, so we just
* update the score. */
dictGetVal(de) = &znode->score; /* Update score ptr. */
*flags |= ZADD_UPDATED;
}
return 1;
} else if (!xx) {
ele = sdsdup(ele);
znode = zslInsert(zs->zsl,score,ele);
serverAssert(dictAdd(zs->dict,ele,&znode->score) == DICT_OK);
*flags |= ZADD_ADDED;
if (newscore) *newscore = score;
return 1;
} else {
*flags |= ZADD_NOP;
return 1;
}
} else {
serverPanic("Unknown sorted set encoding");
}
return 0; /* Never reached. */
}
/*-----------------------------------------------------------------------------
* Sorted set commands
*----------------------------------------------------------------------------*/
/* This generic command implements both ZADD and ZINCRBY. */
void zaddGenericCommand(client *c, int flags) {
static char *nanerr = "resulting score is not a number (NaN)";
robj *key = c->argv[1];
robj *zobj;
sds ele;
double score = 0, *scores = NULL;
int j, elements;
int scoreidx = 0;
/* The following vars are used in order to track what the command actually
* did during the execution, to reply to the client and to trigger the
* notification of keyspace change. */
int added = 0; /* Number of new elements added. */
int updated = 0; /* Number of elements with updated score. */
int processed = 0; /* Number of elements processed, may remain zero with
options like XX. */
/* Parse options. At the end 'scoreidx' is set to the argument position
* of the score of the first score-element pair. */
scoreidx = 2;
while(scoreidx < c->argc) {
char *opt = c->argv[scoreidx]->ptr;
if (!strcasecmp(opt,"nx")) flags |= ZADD_NX;
else if (!strcasecmp(opt,"xx")) flags |= ZADD_XX;
else if (!strcasecmp(opt,"ch")) flags |= ZADD_CH;
else if (!strcasecmp(opt,"incr")) flags |= ZADD_INCR;
else break;
scoreidx++;
}
/* Turn options into simple to check vars. */
int incr = (flags & ZADD_INCR) != 0;
int nx = (flags & ZADD_NX) != 0;
int xx = (flags & ZADD_XX) != 0;
int ch = (flags & ZADD_CH) != 0;
/* After the options, we expect to have an even number of args, since
* we expect any number of score-element pairs. */
elements = c->argc-scoreidx;
if (elements % 2 || !elements) {
addReply(c,shared.syntaxerr);
return;
}
elements /= 2; /* Now this holds the number of score-element pairs. */
/* Check for incompatible options. */
if (nx && xx) {
addReplyError(c,
"XX and NX options at the same time are not compatible");
return;
}
if (incr && elements > 1) {
addReplyError(c,
"INCR option supports a single increment-element pair");
return;
}
/* Start parsing all the scores, we need to emit any syntax error
* before executing additions to the sorted set, as the command should
* either execute fully or nothing at all. */
scores = zmalloc(sizeof(double)*elements);
for (j = 0; j < elements; j++) {
if (getDoubleFromObjectOrReply(c,c->argv[scoreidx+j*2],&scores[j],NULL)
!= C_OK) goto cleanup;
}
/* Lookup the key and create the sorted set if does not exist. */
zobj = lookupKeyWrite(c->db,key);
if (zobj == NULL) {
if (xx) goto reply_to_client; /* No key + XX option: nothing to do. */
if (server.zset_max_ziplist_entries == 0 ||
server.zset_max_ziplist_value < sdslen(c->argv[scoreidx+1]->ptr))
{
zobj = createZsetObject();
} else {
zobj = createZsetZiplistObject();
}
dbAdd(c->db,key,zobj);
} else {
if (zobj->type != OBJ_ZSET) {
addReply(c,shared.wrongtypeerr);
goto cleanup;
}
}
for (j = 0; j < elements; j++) {
double newscore;
score = scores[j];
int retflags = flags;
ele = c->argv[scoreidx+1+j*2]->ptr;
int retval = zsetAdd(zobj, score, ele, &retflags, &newscore);
if (retval == 0) {
addReplyError(c,nanerr);
goto cleanup;
}
if (retflags & ZADD_ADDED) added++;
if (retflags & ZADD_UPDATED) updated++;
if (!(retflags & ZADD_NOP)) processed++;
score = newscore;
}
server.dirty += (added+updated);
reply_to_client:
if (incr) { /* ZINCRBY or INCR option. */
if (processed)
addReplyDouble(c,score);
else
addReplyNull(c);
} else { /* ZADD. */
addReplyLongLong(c,ch ? added+updated : added);
}
cleanup:
zfree(scores);
if (added || updated) {
signalModifiedKey(c,c->db,key);
notifyKeyspaceEvent(NOTIFY_ZSET,
incr ? "zincr" : "zadd", key, c->db->id);
}
}
void zaddCommand(client *c) {
zaddGenericCommand(c,ZADD_NONE);
}
lookupKeyWrite(c->db,key)检查key是否存在。 createZsetObject()是创建跳表。
createZsetZiplistObject()是创建ziplist。 zsetConvert(zobj,OBJ_ENCODING_SKIPLIST)转换存储类型。
创建调表的条件由zset_max_ziplist_entries和zset_max_ziplist_value两个参数决定。调试时可以在redis.conf文件中修改这两个参数。
# Similarly to hashes and lists, sorted sets are also specially encoded in
# order to save a lot of space. This encoding is only used when the length and
# elements of a sorted set are below the following limits:
zset-max-ziplist-entries 2
zset-max-ziplist-value 64
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。