sds
redis中使用sds来替换char *
源码中有几个sds的 sdshdr的定义。这些是sds实际的内存放的数据结构。
sds 只是这个结构体的 char[] buf
如果要获取 sds的其它字段，则通过内存位置 s[-n] 来获取
这样，既可以使用sds中新的api，又可以使用c 中的大部分的char *库函数
为了方便理解 拿以前版本的定义
typedef char *sds;
struct sdshdr {
int len;
int free;
char buf[];
};
通过对 buf 分配一些额外的空间， 并使用 free 记录未使用空间的大小， sdshdr 可以让执行追加操作所需的内存重分配次数大大减少
比较有意思的就是内存申请或者说扩容那里。
分配时会分配２倍所需的空间
但若大于 1M ，则只会分配多1M
下面是申请空间的源码
sds sdsMakeRoomFor(sds s, size_t addlen) {
void *sh, *newsh;
size_t avail = sdsavail(s);
size_t len, newlen;
char type, oldtype = s[-1] & SDS_TYPE_MASK;
int hdrlen;
/* Return ASAP if there is enough space left. */
if (avail >= addlen) return s;
len = sdslen(s);
sh = (char*)s-sdsHdrSize(oldtype);
newlen = (len+addlen);
if (newlen < SDS_MAX_PREALLOC)
newlen *= 2;
else
newlen += SDS_MAX_PREALLOC;
type = sdsReqType(newlen);
/* Don't use type 5: the user is appending to the string and type 5 is
* not able to remember empty space, so sdsMakeRoomFor() must be called
* at every appending operation. */
if (type == SDS_TYPE_5) type = SDS_TYPE_8;
hdrlen = sdsHdrSize(type);
if (oldtype==type) {
newsh = s_realloc(sh, hdrlen+newlen+1);
if (newsh == NULL) return NULL;
s = (char*)newsh+hdrlen;
} else {
/* Since the header size changes, need to move the string forward,
* and can't use realloc */
newsh = s_malloc(hdrlen+newlen+1);
if (newsh == NULL) return NULL;
memcpy((char*)newsh+hdrlen, s, len+1);
s_free(sh);
s = (char*)newsh+hdrlen;
s[-1] = type;
sdssetlen(s, len);
}
sdssetalloc(s, newlen);
return s;
}
adlist
双端列表
双端列表是一个非常有用的数据结构，因为很多数据结构的书都会介绍它。 所以这边也不说什么了。
redis的实现也很中规中矩，没什么特别亮点的。
所以这里只贴一下它的定义就好了：
typedef struct listNode {
struct listNode *prev;
struct listNode *next;
void *value;
} listNode;
typedef struct listIter {
listNode *next;
int direction;
} listIter;
typedef struct list {
listNode *head;
listNode *tail;
void *(*dup)(void *ptr);
void (*free)(void *ptr);
int (*match)(void *ptr, void *key);
unsigned long len;
} list;
dict
redis中的字典 dict 是用 hast实现的
dict的定义
typedef struct dict {
dictType *type;
void *privdata;
dictht ht[2];
long rehashidx; //==-1时表示现在不是rehash的进程中
unsigned long iterators; //当前有几个iterator在运行
} dict;
hast的定义
typedef struct dictht {
dictEntry **table;
unsigned long size;
unsigned long sizemask;
unsigned long used;
} dictht;
hast节点的定义
typedef struct dictEntry {
void *key;
union {
void *val;
uint64_t u64;
int64_t s64;
double d;
} v;
struct dictEntry *next;
} dictEntry;
使用链地址法来解决碰撞的
hast地址的算法是使用 SipHash算法
大部分非加密哈希算法的改良，都集中在让哈希速度更快更好上。SipHash 则是个异类，它的提出是为了解决一类安全问题：hash flooding。通过让输出随机化，SipHash 能够有效减缓 hash flooding 攻击。
源码
uint64_t siphash_nocase(const uint8_t *in, const size_t inlen, const uint8_t *k)
{
#ifndef UNALIGNED_LE_CPU
uint64_t hash;
uint8_t *out = (uint8_t*) &hash;
#endif
uint64_t v0 = 0x736f6d6570736575ULL;
uint64_t v1 = 0x646f72616e646f6dULL;
uint64_t v2 = 0x6c7967656e657261ULL;
uint64_t v3 = 0x7465646279746573ULL;
uint64_t k0 = U8TO64_LE(k);
uint64_t k1 = U8TO64_LE(k + 8);
uint64_t m;
const uint8_t *end = in + inlen - (inlen % sizeof(uint64_t));
const int left = inlen & 7;
uint64_t b = ((uint64_t)inlen) << 56;
v3 ^= k1;
v2 ^= k0;
v1 ^= k1;
v0 ^= k0;
for (; in != end; in += 8) {
m = U8TO64_LE_NOCASE(in);
v3 ^= m;
SIPROUND;
v0 ^= m;
}
switch (left) {
case 7: b |= ((uint64_t)siptlw(in[6])) << 48; /* fall-thru */
case 6: b |= ((uint64_t)siptlw(in[5])) << 40; /* fall-thru */
case 5: b |= ((uint64_t)siptlw(in[4])) << 32; /* fall-thru */
case 4: b |= ((uint64_t)siptlw(in[3])) << 24; /* fall-thru */
case 3: b |= ((uint64_t)siptlw(in[2])) << 16; /* fall-thru */
case 2: b |= ((uint64_t)siptlw(in[1])) << 8; /* fall-thru */
case 1: b |= ((uint64_t)siptlw(in[0])); break;
case 0: break;
}
v3 ^= b;
SIPROUND;
v0 ^= b;
v2 ^= 0xff;
SIPROUND;
SIPROUND;
b = v0 ^ v1 ^ v2 ^ v3;
#ifndef UNALIGNED_LE_CPU
U64TO8_LE(out, b);
return hash;
#else
return b;
#endif
}
- 创建新字典（并没有为table分配空间）
dict *dictCreate(dictType *type, void *privDataPtr) {
dict *d = zmalloc(sizeof(*d));
_dictInit(d,type,privDataPtr);
return d;
}
//初始化
int _dictInit(dict *d, dictType *type, void *privDataPtr) {
_dictReset(&d->ht[0]);
_dictReset(&d->ht[1]);
d->type = type;
d->privdata = privDataPtr;
d->rehashidx = -1;
d->iterators = 0;
return DICT_OK;
}
static void _dictReset(dictht *ht) {
ht->table = NULL;
ht->size = 0;
ht->sizemask = 0;
ht->used = 0;
}
- 添加键值到字典
- if key Is exist return
- if ht[0] is nil init it
- if rehash -> ht[1]
else -> ht[0] - calc idx
- create dictEntry
- set dictEntry to index
int dictAdd(dict *d, void *key, void *val) {
dictEntry *entry = dictAddRaw(d,key,NULL);
if (!entry) return DICT_ERR;
dictSetVal(d, entry, val);
return DICT_OK;
}
/* 比较低级的add/find
* 这个函数增加一个节点,并返回这个节点, 会保证把那个节点加进去
*
* 这个函数也是为用户实现存储一个值，而不是一个节点，example:
*
* entry = dictAddRaw(dict,mykey,NULL);
* if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
*
* Return values:
*
* 如果key已经存在，则返回空
and "*existing" is populated
* with the existing entry if existing is not NULL.
*
* 如果key被加进去了。返回的entry是调用者去控制生命周期的
*/
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing) {
long index;
dictEntry *entry;
dictht *ht;
if (dictIsRehashing(d)) _dictRehashStep(d);
/* Get the index of the new element, or -1 if
* the element already exists. */
if ((index = _dictKeyIndex(d, key, dictHashKey(d,key), existing)) == -1)
return NULL;
/* Allocate the memory and store the new entry.
* Insert the element in top, with the assumption that in a database
* system it is more likely that recently added entries are accessed
* more frequently. */
ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
entry = zmalloc(sizeof(*entry));
entry->next = ht->table[index]; //发生碰撞就放原来的放到新的尾部
ht->table[index] = entry;
ht->used++;
/* Set the hash entry fields. */
dictSetKey(d, entry, key);
return entry;
}
- 添加新键值时触发了rehash
static void _dictRehashStep(dict *d) {
if (d->iterators == 0) dictRehash(d,1);
}
- rehash
/* Performs N steps of incremental rehashing. Returns 1 if there are still
* keys to move from the old to the new hash table, otherwise 0 is returned.
*
* Note that a rehashing step consists in moving a bucket (that may have more
* than one key as we use chaining) from the old to the new hash table, however
* since part of the hash table may be composed of empty spaces, it is not
* guaranteed that this function will rehash even a single bucket, since it
* will visit at max N*10 empty buckets in total, otherwise the amount of
* work it does would be unbound and the function may block for a long time. */
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;
}
intset
整数集合
就是用一个数组以有序的形式保存，来表示整数集合。
有一个前提：数量不多。
因为如果数量比较多的话，增加和删除都会比较慢。
增：如果需要升级就升级。然后扩容，移数据，插入正确的位置
删：找位置,移数据,减容
查：使用二分查找
定义
typedef struct intset {
uint32_t encoding;
uint32_t length;
int8_t contents[];
} intset;
增：
static void intsetMoveTail(intset *is, uint32_t from, uint32_t to) {
void *src, *dst;
uint32_t bytes = intrev32ifbe(is->length)-from;
uint32_t encoding = intrev32ifbe(is->encoding);
if (encoding == INTSET_ENC_INT64) {
src = (int64_t*)is->contents+from;
dst = (int64_t*)is->contents+to;
bytes *= sizeof(int64_t);
} else if (encoding == INTSET_ENC_INT32) {
src = (int32_t*)is->contents+from;
dst = (int32_t*)is->contents+to;
bytes *= sizeof(int32_t);
} else {
src = (int16_t*)is->contents+from;
dst = (int16_t*)is->contents+to;
bytes *= sizeof(int16_t);
}
memmove(dst,src,bytes);
}
/* Insert an integer in the intset */
intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
uint8_t valenc = _intsetValueEncoding(value);
uint32_t pos;
if (success) *success = 1;
/* Upgrade encoding if necessary. If we need to upgrade, we know that
* this value should be either appended (if > 0) or prepended (if < 0),
* because it lies outside the range of existing values. */
if (valenc > intrev32ifbe(is->encoding)) {
/* This always succeeds, so we don't need to curry *success. */
return intsetUpgradeAndAdd(is,value);
} else {
/* Abort if the value is already present in the set.
* This call will populate "pos" with the right position to insert
* the value when it cannot be found. */
if (intsetSearch(is,value,&pos)) {
if (success) *success = 0;
return is;
}
is = intsetResize(is,intrev32ifbe(is->length)+1);
if (pos < intrev32ifbe(is->length)) intsetMoveTail(is,pos,pos+1);
}
_intsetSet(is,pos,value);
is->length = intrev32ifbe(intrev32ifbe(is->length)+1);
return is;
}
删：
/* Delete integer from intset */
intset *intsetRemove(intset *is, int64_t value, int *success) {
uint8_t valenc = _intsetValueEncoding(value);
uint32_t pos;
if (success) *success = 0;
if (valenc <= intrev32ifbe(is->encoding) && intsetSearch(is,value,&pos)) {
uint32_t len = intrev32ifbe(is->length);
/* We know we can delete */
if (success) *success = 1;
/* Overwrite value with tail and update length */
if (pos < (len-1)) intsetMoveTail(is,pos+1,pos);
is = intsetResize(is,len-1);
is->length = intrev32ifbe(len-1);
}
return is;
}
查：
/* Determine whether a value belongs to this set */
uint8_t intsetFind(intset *is, int64_t value) {
uint8_t valenc = _intsetValueEncoding(value);
return valenc <= intrev32ifbe(is->encoding) && intsetSearch(is,value,NULL);
}
/* Search for the position of "value". Return 1 when the value was found and
* sets "pos" to the position of the value within the intset. Return 0 when
* the value is not present in the intset and sets "pos" to the position
* where "value" can be inserted. */
static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
int min = 0, max = intrev32ifbe(is->length)-1, mid = -1;
int64_t cur = -1;
/* The value can never be found when the set is empty */
if (intrev32ifbe(is->length) == 0) {
if (pos) *pos = 0;
return 0;
} else {
/* Check for the case where we know we cannot find the value,
* but do know the insert position. */
if (value > _intsetGet(is,max)) {
if (pos) *pos = intrev32ifbe(is->length);
return 0;
} else if (value < _intsetGet(is,0)) {
if (pos) *pos = 0;
return 0;
}
}
while(max >= min) {
mid = ((unsigned int)min + (unsigned int)max) >> 1;
cur = _intsetGet(is,mid);
if (value > cur) {
min = mid+1;
} else if (value < cur) {
max = mid-1;
} else {
break;
}
}
if (value == cur) {
if (pos) *pos = mid;
return 1;
} else {
if (pos) *pos = min;
return 0;
}
}
ziplist
压缩列表 (跟intset中差不多，只不过保存的是char*)
ziplist并没有明确的定义，在内存中数据分布为：
/* ... */
各字段意义
uint32_t zlbytes : 整个ziplist
uint32_t zltail: 是列表中最后一个条目的偏移量。 这允许在列表的远端进行弹出操作，而无需完全遍历。
uint16_t zllen: entries的个数，最多只能是2^16-2 个,当大于时，通过遍历去获取有多个个
uint8_t zlend: ziplist结束的标志 = 255(0xFF)
entry 的定义
typedef struct zlentry {
unsigned int prevrawlensize; /* Bytes used to encode the previous entry len*/
unsigned int prevrawlen; /* Previous entry len. */
unsigned int lensize; /* Bytes used to encode this entry type/len.
For example strings have a 1, 2 or 5 bytes
header. Integers always use a single byte.*/
unsigned int len; /* Bytes used to represent the actual entry.
For strings this is just the string length
while for integers it is 1, 2, 3, 4, 8 or
0 (for 4 bit immediate) depending on the
number range. */
unsigned int headersize; /* prevrawlensize + lensize. */
unsigned char encoding; /* Set to ZIP_STR_* or ZIP_INT_* depending on
the entry encoding. However for 4 bits
immediate integers this can assume a range
of values and must be range-checked. */
unsigned char *p; /* Pointer to the very start of the entry, that
is, this points to prev-entry-len field. */
} zlentry;
增删查的逻辑都跟 intset的逻辑差不多，只不过因为存储的是char* 所以更加复杂
增:
/* Insert item at "p". */
unsigned char *__ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen) {
size_t curlen = intrev32ifbe(ZIPLIST_BYTES(zl)), reqlen;
unsigned int prevlensize, prevlen = 0;
size_t offset;
int nextdiff = 0;
unsigned char encoding = 0;
long long value = 123456789; /* initialized to avoid warning. Using a value
that is easy to see if for some reason
we use it uninitialized. */
zlentry tail;
/* Find out prevlen for the entry that is inserted. */
if (p[0] != ZIP_END) {
ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
} else {
unsigned char *ptail = ZIPLIST_ENTRY_TAIL(zl);
if (ptail[0] != ZIP_END) {
prevlen = zipRawEntryLength(ptail);
}
}
/* See if the entry can be encoded */
if (zipTryEncoding(s,slen,&value,&encoding)) {
/* 'encoding' is set to the appropriate integer encoding */
reqlen = zipIntSize(encoding);
} else {
/* 'encoding' is untouched, however zipStoreEntryEncoding will use the
* string length to figure out how to encode it. */
reqlen = slen;
}
/* We need space for both the length of the previous entry and
* the length of the payload. */
reqlen += zipStorePrevEntryLength(NULL,prevlen);
reqlen += zipStoreEntryEncoding(NULL,encoding,slen);
/* When the insert position is not equal to the tail, we need to
* make sure that the next entry can hold this entry's length in
* its prevlen field. */
int forcelarge = 0;
nextdiff = (p[0] != ZIP_END) ? zipPrevLenByteDiff(p,reqlen) : 0;
if (nextdiff == -4 && reqlen < 4) {
nextdiff = 0;
forcelarge = 1;
}
/* Store offset because a realloc may change the address of zl. */
offset = p-zl;
zl = ziplistResize(zl,curlen+reqlen+nextdiff);
p = zl+offset;
/* Apply memory move when necessary and update tail offset. */
if (p[0] != ZIP_END) {
/* Subtract one because of the ZIP_END bytes */
memmove(p+reqlen,p-nextdiff,curlen-offset-1+nextdiff);
/* Encode this entry's raw length in the next entry. */
if (forcelarge)
zipStorePrevEntryLengthLarge(p+reqlen,reqlen);
else
zipStorePrevEntryLength(p+reqlen,reqlen);
/* Update offset for tail */
ZIPLIST_TAIL_OFFSET(zl) =
intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+reqlen);
/* When the tail contains more than one entry, we need to take
* "nextdiff" in account as well. Otherwise, a change in the
* size of prevlen doesn't have an effect on the *tail* offset. */
zipEntry(p+reqlen, &tail);
if (p[reqlen+tail.headersize+tail.len] != ZIP_END) {
ZIPLIST_TAIL_OFFSET(zl) =
intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+nextdiff);
}
} else {
/* This element will be the new tail. */
ZIPLIST_TAIL_OFFSET(zl) = intrev32ifbe(p-zl);
}
/* When nextdiff != 0, the raw length of the next entry has changed, so
* we need to cascade the update throughout the ziplist */
if (nextdiff != 0) {
offset = p-zl;
zl = __ziplistCascadeUpdate(zl,p+reqlen);
p = zl+offset;
}
/* Write the entry */
p += zipStorePrevEntryLength(p,prevlen);
p += zipStoreEntryEncoding(p,encoding,slen);
if (ZIP_IS_STR(encoding)) {
memcpy(p,s,slen);
} else {
zipSaveInteger(p,value,encoding);
}
ZIPLIST_INCR_LENGTH(zl,1);
return zl;
}
删:
/* Delete "num" entries, starting at "p". Returns pointer to the ziplist. */
unsigned char *__ziplistDelete(unsigned char *zl, unsigned char *p, unsigned int num) {
unsigned int i, totlen, deleted = 0;
size_t offset;
int nextdiff = 0;
zlentry first, tail;
zipEntry(p, &first);
for (i = 0; p[0] != ZIP_END && i < num; i++) {
p += zipRawEntryLength(p);
deleted++;
}
totlen = p-first.p; /* Bytes taken by the element(s) to delete. */
if (totlen > 0) {
if (p[0] != ZIP_END) {
/* Storing `prevrawlen` in this entry may increase or decrease the
* number of bytes required compare to the current `prevrawlen`.
* There always is room to store this, because it was previously
* stored by an entry that is now being deleted. */
nextdiff = zipPrevLenByteDiff(p,first.prevrawlen);
/* Note that there is always space when p jumps backward: if
* the new previous entry is large, one of the deleted elements
* had a 5 bytes prevlen header, so there is for sure at least
* 5 bytes free and we need just 4. */
p -= nextdiff;
zipStorePrevEntryLength(p,first.prevrawlen);
/* Update offset for tail */
ZIPLIST_TAIL_OFFSET(zl) =
intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))-totlen);
/* When the tail contains more than one entry, we need to take
* "nextdiff" in account as well. Otherwise, a change in the
* size of prevlen doesn't have an effect on the *tail* offset. */
zipEntry(p, &tail);
if (p[tail.headersize+tail.len] != ZIP_END) {
ZIPLIST_TAIL_OFFSET(zl) =
intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+nextdiff);
}
/* Move tail to the front of the ziplist */
memmove(first.p,p,
intrev32ifbe(ZIPLIST_BYTES(zl))-(p-zl)-1);
} else {
/* The entire tail was deleted. No need to move memory. */
ZIPLIST_TAIL_OFFSET(zl) =
intrev32ifbe((first.p-zl)-first.prevrawlen);
}
/* Resize and update length */
offset = first.p-zl;
zl = ziplistResize(zl, intrev32ifbe(ZIPLIST_BYTES(zl))-totlen+nextdiff);
ZIPLIST_INCR_LENGTH(zl,-deleted);
p = zl+offset;
/* When nextdiff != 0, the raw length of the next entry has changed, so
* we need to cascade the update throughout the ziplist */
if (nextdiff != 0)
zl = __ziplistCascadeUpdate(zl,p);
}
return zl;
}
查：
/* Find pointer to the entry equal to the specified entry. Skip 'skip' entries
* between every comparison. Returns NULL when the field could not be found. */
unsigned char *ziplistFind(unsigned char *p, unsigned char *vstr, unsigned int vlen, unsigned int skip) {
int skipcnt = 0;
unsigned char vencoding = 0;
long long vll = 0;
while (p[0] != ZIP_END) {
unsigned int prevlensize, encoding, lensize, len;
unsigned char *q;
ZIP_DECODE_PREVLENSIZE(p, prevlensize);
ZIP_DECODE_LENGTH(p + prevlensize, encoding, lensize, len);
q = p + prevlensize + lensize;
if (skipcnt == 0) {
/* Compare current entry with specified entry */
if (ZIP_IS_STR(encoding)) {
if (len == vlen && memcmp(q, vstr, vlen) == 0) {
return p;
}
} else {
/* Find out if the searched field can be encoded. Note that
* we do it only the first time, once done vencoding is set
* to non-zero and vll is set to the integer value. */
if (vencoding == 0) {
if (!zipTryEncoding(vstr, vlen, &vll, &vencoding)) {
/* If the entry can't be encoded we set it to
* UCHAR_MAX so that we don't retry again the next
* time. */
vencoding = UCHAR_MAX;
}
/* Must be non-zero by now */
assert(vencoding);
}
/* Compare current entry with specified entry, do it only
* if vencoding != UCHAR_MAX because if there is no encoding
* possible for the field it can't be a valid integer. */
if (vencoding != UCHAR_MAX) {
long long ll = zipLoadInteger(q, encoding);
if (ll == vll) {
return p;
}
}
}
/* Reset skip count */
skipcnt = skip;
} else {
/* Skip entry */
skipcnt--;
}
/* Move to next entry */
p = q + len;
}
return NULL;
}
skiplist
跳跃表以有序的方式在层次化的链表中保存元素， 效率和平衡树媲美 .查找,删除,添加等操作都可以在对数期望时间下完成， 并且比起平衡树来说， 跳跃表的实现要简单直观得多。
跳表的insert：简单来讲就是，找到所有level的前置。然后将那个node插进去。
跳表的查找：从高的level往下找。
跳表的删除：找到所有的前置，更新前置，删除节点。
跳表的更新：删除旧的，然后插入新的。不过做了一个优化，如果新值并不影响排位，那么则不需要删除也不需要插入, 只更新值即可。
跳表图示
skiplist.png
跳表的定义
typedef struct zskiplistNode {
sds ele;
double score;
struct zskiplistNode *backward;
struct zskiplistLevel {
struct zskiplistNode *forward;
unsigned long span;
} level[];
} zskiplistNode;
typedef struct zskiplist {
struct zskiplistNode *header, *tail;
unsigned long length;
int level;
} zskiplist;
跳表的insert
/* 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;
}
跳表的查找
/* 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, sds ele) {
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 &&
sdscmp(x->level[i].forward->ele,ele) <= 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->ele && sdscmp(x->ele,ele) == 0) {
return rank;
}
}
return 0;
}
跳表的删除
/* 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 */
}
/* 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--;
}
跳表的更新
/* 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;
}
redisObject
redis中使用 redisObject来表示 string list set zset 和 hash
#define OBJ_STRING 0 /* String object. */
#define OBJ_LIST 1 /* List object. */
#define OBJ_SET 2 /* Set object. */
#define OBJ_ZSET 3 /* Sorted set object. */
#define OBJ_HASH 4 /* Hash object. */
encoding的类型:
#define OBJ_ENCODING_RAW 0 /* Raw representation */
#define OBJ_ENCODING_INT 1 /* Encoded as integer */
#define OBJ_ENCODING_HT 2 /* Encoded as hash table */
#define OBJ_ENCODING_ZIPMAP 3 /* Encoded as zipmap */
#define OBJ_ENCODING_LINKEDLIST 4 /* No longer used: old list encoding. */
#define OBJ_ENCODING_ZIPLIST 5 /* Encoded as ziplist */
#define OBJ_ENCODING_INTSET 6 /* Encoded as intset */
#define OBJ_ENCODING_SKIPLIST 7 /* Encoded as skiplist */
#define OBJ_ENCODING_EMBSTR 8 /* Embedded sds string encoding */
#define OBJ_ENCODING_QUICKLIST 9 /* Encoded as linked list of ziplists */
#define OBJ_ENCODING_STREAM 10 /* Encoded as a radix tree of listpacks */
redisObject的定义
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;
一个robj先是根据type，后根据encoding来获取
void *ptr是什么数据类型。然后再进行操作