Redis源码阅读笔记（3）-Hash
在redis中，哈希表作为一个基础结构提供了kv存储查询的功能。
散列表（Hash table，也叫哈希表），是根据键（Key）而直接访问在内存储存位置的数据结构。也就是说，它通过计算出一个键值的函数，将所需查询的数据映射到表中一个位置来让人访问，这加快了查找速度。这个映射函数称做散列函数，存放记录的数组称做散列表。——Wikipedia
数据结构
我们还是先看哈希表的数据结构，在dict.h，dict.c这两个文件中，有对应定义：
typedef struct dictEntry {
void *key;
union {
void *val;
uint64_t u64;
int64_t s64;
double d;
} v;
struct dictEntry *next;
} dictEntry;
/* This is our hash table structure. Every dictionary has two of this as we
* implement incremental rehashing, for the old to the new table. */
typedef struct dictht {
dictEntry **table;
unsigned long size;
unsigned long sizemask;
unsigned long used;
} dictht;
typedef struct dict {
dictType *type;
void *privdata;
dictht ht[2];
long rehashidx; /* rehashing not in progress if rehashidx == -1 */
int16_t pauserehash; /* If >0 rehashing is paused (<0 indicates coding error) */
} dict;
可以看出，最顶层的结构是dict，每个dict中有两个dictht，在dictht中有dictEntry组成的table。
dictEntry中包含了同结构体的指针，通过链表来解决哈希表冲突。
这两个dictht是用来进行渐进式重哈希（incremental rehashing）的，减少因为rehash导致的性能下降。
API
dict结构对外提供了如下api：
/* API */
dict *dictCreate(dictType *type, void *privDataPtr);
int dictExpand(dict *d, unsigned long size);
int dictTryExpand(dict *d, unsigned long size);
int dictAdd(dict *d, void *key, void *val);
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing);
dictEntry *dictAddOrFind(dict *d, void *key);
int dictReplace(dict *d, void *key, void *val);
int dictDelete(dict *d, const void *key);
dictEntry *dictUnlink(dict *ht, const void *key);
void dictFreeUnlinkedEntry(dict *d, dictEntry *he);
void dictRelease(dict *d);
dictEntry * dictFind(dict *d, const void *key);
void *dictFetchValue(dict *d, const void *key);
int dictResize(dict *d);
dictIterator *dictGetIterator(dict *d);
dictIterator *dictGetSafeIterator(dict *d);
dictEntry *dictNext(dictIterator *iter);
void dictReleaseIterator(dictIterator *iter);
dictEntry *dictGetRandomKey(dict *d);
dictEntry *dictGetFairRandomKey(dict *d);
unsigned int dictGetSomeKeys(dict *d, dictEntry **des, unsigned int count);
void dictGetStats(char *buf, size_t bufsize, dict *d);
uint64_t dictGenHashFunction(const void *key, int len);
uint64_t dictGenCaseHashFunction(const unsigned char *buf, int len);
void dictEmpty(dict *d, void(callback)(void*));
void dictEnableResize(void);
void dictDisableResize(void);
int dictRehash(dict *d, int n);
int dictRehashMilliseconds(dict *d, int ms);
void dictSetHashFunctionSeed(uint8_t *seed);
uint8_t *dictGetHashFunctionSeed(void);
unsigned long dictScan(dict *d, unsigned long v, dictScanFunction *fn, dictScanBucketFunction *bucketfn, void *privdata);
uint64_t dictGetHash(dict *d, const void *key);
dictEntry **dictFindEntryRefByPtrAndHash(dict *d, const void *oldptr, uint64_t hash);
实现细节
dictExpand
我们先来看dict创建，扩容所使用的的函数：
/* Expand or create the hash table,
* when malloc_failed is non-NULL, it'll avoid panic if malloc fails (in which case it'll be set to 1).
* Returns DICT_OK if expand was performed, and DICT_ERR if skipped. */
int _dictExpand(dict *d, unsigned long size, int* malloc_failed)
{
if (malloc_failed) *malloc_failed = 0;
/* 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);
/* Detect overflows */
if (realsize < size || realsize * sizeof(dictEntry*) < realsize)
return DICT_ERR;
/* 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;
if (malloc_failed) {
n.table = ztrycalloc(realsize*sizeof(dictEntry*));
*malloc_failed = n.table == NULL;
if (*malloc_failed)
return DICT_ERR;
} else
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;
}
首先会判断是否在rehash，若不在，创建一个新的dictht。
根据传入的size，获取下一个2的次方大小，给新的dictht.table申请对应大小空间。
如果是初始化，则将第一张表设置为新申请的表。若不是，将其作为第二张表等待将第一张表rehash。
dictAddRaw
/* Low level add or find:
* This function adds the entry but instead of setting a value returns the
* dictEntry structure to the user, that will make sure to fill the value
* field as they wish.
*
* This function is also directly exposed to the user API to be called
* mainly in order to store non-pointers inside the hash value, example:
*
* entry = dictAddRaw(dict,mykey,NULL);
* if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
*
* Return values:
*
* If key already exists NULL is returned, and "*existing" is populated
* with the existing entry if existing is not NULL.
*
* If key was added, the hash entry is returned to be manipulated by the caller.
*/
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];
ht->table[index] = entry;
ht->used++;
/* Set the hash entry fields. */
dictSetKey(d, entry, key);
return entry;
}
如果dict需要rehash，则会进行一步_dictRehashStep操作。
通过_dictKeyIndex函数获取插入key的位置。
/* Returns the index of a free slot that can be populated with
* a hash entry for the given 'key'.
* If the key already exists, -1 is returned
* and the optional output parameter may be filled.
*
* Note that if we are in the process of rehashing the hash table, the
* index is always returned in the context of the second (new) hash table. */
static long _dictKeyIndex(dict *d, const void *key, uint64_t hash, dictEntry **existing)
{
unsigned long idx, table;
dictEntry *he;
if (existing) *existing = NULL;
/* Expand the hash table if needed */
if (_dictExpandIfNeeded(d) == DICT_ERR)
return -1;
for (table = 0; table <= 1; table++) {
idx = hash & d->ht[table].sizemask;
/* Search if this slot does not already contain the given key */
he = d->ht[table].table[idx];
while(he) {
if (key==he->key || dictCompareKeys(d, key, he->key)) {
if (existing) *existing = he;
return -1;
}
he = he->next;
}
if (!dictIsRehashing(d)) break;
}
return idx;
}
dictRehash
上面提到的rehash步骤，是通过_dictRehashStep调用dictRehash(d,1)完成的。
可以看到，_dictRehashStep在dictAddRaw, dictGenericDelete, dictFind, dictGetRandomKey, dictGetSomeKeys中被调用。
其中，调用dictGetSomeKeys是，会按照dict的大小n来调用n次单步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;
}
上面这段就是rehash实际的实现代码，每一步会将rehashidx对应的所有元素移动到新的表中，最后检查是否完成了整个表的rehash。
dictFind
hash表中查找一个key实现
dictEntry *dictFind(dict *d, const void *key)
{
dictEntry *he;
uint64_t h, idx, table;
if (dictSize(d) == 0) return NULL; /* dict is empty */
if (dictIsRehashing(d)) _dictRehashStep(d);
h = dictHashKey(d, key);
for (table = 0; table <= 1; table++) {
idx = h & d->ht[table].sizemask;
he = d->ht[table].table[idx];
while(he) {
if (key==he->key || dictCompareKeys(d, key, he->key))
return he;
he = he->next;
}
if (!dictIsRehashing(d)) return NULL;
}
return NULL;
}
dictEntry *dictFind(dict *d, const void *key)
{
dictEntry *he;
uint64_t h, idx, table;
if (dictSize(d) == 0) return NULL; /* dict is empty */
if (dictIsRehashing(d)) _dictRehashStep(d);
h = dictHashKey(d, key);
for (table = 0; table <= 1; table++) {
idx = h & d->ht[table].sizemask;
he = d->ht[table].table[idx];
while(he) {
if (key==he->key || dictCompareKeys(d, key, he->key))
return he;
he = he->next;
}
if (!dictIsRehashing(d)) return NULL;
}
return NULL;
}
- 如果在rehash，从两个表中查找
- 找到
h后，链式查找 - 会进行一步rehash操作
- sizemap会控制住
h的范围，如果超过了当前hash的大小，则会使用bucket 0
dictGenericDelete
通用的删除函数
/* Search and remove an element. This is an helper function for
* dictDelete() and dictUnlink(), please check the top comment
* of those functions. */
static dictEntry *dictGenericDelete(dict *d, const void *key, int nofree) {
uint64_t h, idx;
dictEntry *he, *prevHe;
int table;
if (d->ht[0].used == 0 && d->ht[1].used == 0) return NULL;
if (dictIsRehashing(d)) _dictRehashStep(d);
h = dictHashKey(d, key);
for (table = 0; table <= 1; table++) {
idx = h & d->ht[table].sizemask;
he = d->ht[table].table[idx];
prevHe = NULL;
while(he) {
if (key==he->key || dictCompareKeys(d, key, he->key)) {
/* Unlink the element from the list */
if (prevHe)
prevHe->next = he->next;
else
d->ht[table].table[idx] = he->next;
if (!nofree) {
dictFreeKey(d, he);
dictFreeVal(d, he);
zfree(he);
}
d->ht[table].used--;
return he;
}
prevHe = he;
he = he->next;
}
if (!dictIsRehashing(d)) break;
}
return NULL; /* not found */
}
- 查找key的节点
- 删除链表中的节点
- 释放内存（
!nofree）
