redict/src/dict.h

203 lines
7.5 KiB
C
Raw Normal View History

2009-03-22 05:30:00 -04:00
/* Hash Tables Implementation.
*
2012-10-03 00:58:36 -04:00
* This file implements in-memory hash tables with insert/del/replace/find/
* get-random-element operations. Hash tables will auto-resize if needed
2009-03-22 05:30:00 -04:00
* tables of power of two in size are used, collisions are handled by
* chaining. See the source code for more information... :)
*
2012-10-03 00:58:36 -04:00
* Copyright (c) 2006-2012, Salvatore Sanfilippo <antirez at gmail dot com>
2009-03-22 05:30:00 -04:00
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Redis nor the names of its contributors may be used
* to endorse or promote products derived from this software without
* specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef __DICT_H
#define __DICT_H
#include "mt19937-64.h"
#include <limits.h>
#include <stdint.h>
#include <stdlib.h>
2009-03-22 05:30:00 -04:00
#define DICT_OK 0
#define DICT_ERR 1
/* Unused arguments generate annoying warnings... */
#define DICT_NOTUSED(V) ((void) V)
typedef struct dictEntry {
void *key;
union {
void *val;
uint64_t u64;
int64_t s64;
double d;
} v;
2009-03-22 05:30:00 -04:00
struct dictEntry *next;
} dictEntry;
typedef struct dictType {
Use SipHash hash function to mitigate HashDos attempts. This change attempts to switch to an hash function which mitigates the effects of the HashDoS attack (denial of service attack trying to force data structures to worst case behavior) while at the same time providing Redis with an hash function that does not expect the input data to be word aligned, a condition no longer true now that sds.c strings have a varialbe length header. Note that it is possible sometimes that even using an hash function for which collisions cannot be generated without knowing the seed, special implementation details or the exposure of the seed in an indirect way (for example the ability to add elements to a Set and check the return in which Redis returns them with SMEMBERS) may make the attacker's life simpler in the process of trying to guess the correct seed, however the next step would be to switch to a log(N) data structure when too many items in a single bucket are detected: this seems like an overkill in the case of Redis. SPEED REGRESION TESTS: In order to verify that switching from MurmurHash to SipHash had no impact on speed, a set of benchmarks involving fast insertion of 5 million of keys were performed. The result shows Redis with SipHash in high pipelining conditions to be about 4% slower compared to using the previous hash function. However this could partially be related to the fact that the current implementation does not attempt to hash whole words at a time but reads single bytes, in order to have an output which is endian-netural and at the same time working on systems where unaligned memory accesses are a problem. Further X86 specific optimizations should be tested, the function may easily get at the same level of MurMurHash2 if a few optimizations are performed.
2017-02-20 10:09:54 -05:00
uint64_t (*hashFunction)(const void *key);
2009-03-22 05:30:00 -04:00
void *(*keyDup)(void *privdata, const void *key);
void *(*valDup)(void *privdata, const void *obj);
int (*keyCompare)(void *privdata, const void *key1, const void *key2);
void (*keyDestructor)(void *privdata, void *key);
void (*valDestructor)(void *privdata, void *obj);
Limit the main db and expires dictionaries to expand (#7954) As we know, redis may reject user's requests or evict some keys if used memory is over maxmemory. Dictionaries expanding may make things worse, some big dictionaries, such as main db and expires dict, may eat huge memory at once for allocating a new big hash table and be far more than maxmemory after expanding. There are related issues: #4213 #4583 More details, when expand dict in redis, we will allocate a new big ht[1] that generally is double of ht[0], The size of ht[1] will be very big if ht[0] already is big. For db dict, if we have more than 64 million keys, we need to cost 1GB for ht[1] when dict expands. If the sum of used memory and new hash table of dict needed exceeds maxmemory, we shouldn't allow the dict to expand. Because, if we enable keys eviction, we still couldn't add much more keys after eviction and rehashing, what's worse, redis will keep less keys when redis only remains a little memory for storing new hash table instead of users' data. Moreover users can't write data in redis if disable keys eviction. What this commit changed ? Add a new member function expandAllowed for dict type, it provide a way for caller to allow expand or not. We expose two parameters for this function: more memory needed for expanding and dict current load factor, users can implement a function to make a decision by them. For main db dict and expires dict type, these dictionaries may be very big and cost huge memory for expanding, so we implement a judgement function: we can stop dict to expand provisionally if used memory will be over maxmemory after dict expands, but to guarantee the performance of redis, we still allow dict to expand if dict load factor exceeds the safe load factor. Add test cases to verify we don't allow main db to expand when left memory is not enough, so that avoid keys eviction. Other changes: For new hash table size when expand. Before this commit, the size is that double used of dict and later _dictNextPower. Actually we aim to control a dict load factor between 0.5 and 1.0. Now we replace *2 with +1, since the first check is that used >= size, the outcome of before will usually be the same as _dictNextPower(used+1). The only case where it'll differ is when dict_can_resize is false during fork, so that later the _dictNextPower(used*2) will cause the dict to jump to *4 (i.e. _dictNextPower(1025*2) will return 4096). Fix rehash test cases due to changing algorithm of new hash table size when expand.
2020-12-06 04:53:04 -05:00
int (*expandAllowed)(size_t moreMem, double usedRatio);
2009-03-22 05:30:00 -04:00
} dictType;
/* 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 {
2009-03-22 05:30:00 -04:00
dictEntry **table;
unsigned long size;
unsigned long sizemask;
unsigned long used;
} dictht;
typedef struct dict {
dictType *type;
2009-03-22 05:30:00 -04:00
void *privdata;
dictht ht[2];
long rehashidx; /* rehashing not in progress if rehashidx == -1 */
unsigned long iterators; /* number of iterators currently running */
2009-03-22 05:30:00 -04:00
} dict;
2012-10-03 00:58:36 -04:00
/* If safe is set to 1 this is a safe iterator, that means, you can call
* dictAdd, dictFind, and other functions against the dictionary even while
* iterating. Otherwise it is a non safe iterator, and only dictNext()
* should be called while iterating. */
2009-03-22 05:30:00 -04:00
typedef struct dictIterator {
dict *d;
long index;
int table, safe;
2009-03-22 05:30:00 -04:00
dictEntry *entry, *nextEntry;
/* unsafe iterator fingerprint for misuse detection. */
long long fingerprint;
2009-03-22 05:30:00 -04:00
} dictIterator;
2012-07-09 04:00:26 -04:00
typedef void (dictScanFunction)(void *privdata, const dictEntry *de);
2016-12-29 20:37:52 -05:00
typedef void (dictScanBucketFunction)(void *privdata, dictEntry **bucketref);
2012-07-09 04:00:26 -04:00
2009-03-22 05:30:00 -04:00
/* This is the initial size of every hash table */
#define DICT_HT_INITIAL_SIZE 4
2009-03-22 05:30:00 -04:00
/* ------------------------------- Macros ------------------------------------*/
#define dictFreeVal(d, entry) \
if ((d)->type->valDestructor) \
(d)->type->valDestructor((d)->privdata, (entry)->v.val)
2009-03-22 05:30:00 -04:00
#define dictSetVal(d, entry, _val_) do { \
if ((d)->type->valDup) \
(entry)->v.val = (d)->type->valDup((d)->privdata, _val_); \
2009-03-22 05:30:00 -04:00
else \
(entry)->v.val = (_val_); \
2009-03-22 05:30:00 -04:00
} while(0)
#define dictSetSignedIntegerVal(entry, _val_) \
do { (entry)->v.s64 = _val_; } while(0)
#define dictSetUnsignedIntegerVal(entry, _val_) \
do { (entry)->v.u64 = _val_; } while(0)
#define dictSetDoubleVal(entry, _val_) \
do { (entry)->v.d = _val_; } while(0)
#define dictFreeKey(d, entry) \
if ((d)->type->keyDestructor) \
(d)->type->keyDestructor((d)->privdata, (entry)->key)
2009-03-22 05:30:00 -04:00
#define dictSetKey(d, entry, _key_) do { \
if ((d)->type->keyDup) \
(entry)->key = (d)->type->keyDup((d)->privdata, _key_); \
2009-03-22 05:30:00 -04:00
else \
(entry)->key = (_key_); \
2009-03-22 05:30:00 -04:00
} while(0)
#define dictCompareKeys(d, key1, key2) \
(((d)->type->keyCompare) ? \
(d)->type->keyCompare((d)->privdata, key1, key2) : \
2009-03-22 05:30:00 -04:00
(key1) == (key2))
#define dictHashKey(d, key) (d)->type->hashFunction(key)
#define dictGetKey(he) ((he)->key)
#define dictGetVal(he) ((he)->v.val)
#define dictGetSignedIntegerVal(he) ((he)->v.s64)
#define dictGetUnsignedIntegerVal(he) ((he)->v.u64)
#define dictGetDoubleVal(he) ((he)->v.d)
#define dictSlots(d) ((d)->ht[0].size+(d)->ht[1].size)
#define dictSize(d) ((d)->ht[0].used+(d)->ht[1].used)
#define dictIsRehashing(d) ((d)->rehashidx != -1)
2009-03-22 05:30:00 -04:00
/* If our unsigned long type can store a 64 bit number, use a 64 bit PRNG. */
#if ULONG_MAX >= 0xffffffffffffffff
#define randomULong() ((unsigned long) genrand64_int64())
#else
#define randomULong() random()
#endif
2009-03-22 05:30:00 -04:00
/* API */
dict *dictCreate(dictType *type, void *privDataPtr);
2010-04-15 12:07:57 -04:00
int dictExpand(dict *d, unsigned long size);
int dictTryExpand(dict *d, unsigned long size);
2010-04-15 12:07:57 -04:00
int dictAdd(dict *d, void *key, void *val);
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing);
dictEntry *dictAddOrFind(dict *d, void *key);
2010-04-15 12:07:57 -04:00
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);
2010-04-15 12:07:57 -04:00
void dictRelease(dict *d);
dictEntry * dictFind(dict *d, const void *key);
void *dictFetchValue(dict *d, const void *key);
2010-04-15 12:07:57 -04:00
int dictResize(dict *d);
dictIterator *dictGetIterator(dict *d);
dictIterator *dictGetSafeIterator(dict *d);
2009-03-22 05:30:00 -04:00
dictEntry *dictNext(dictIterator *iter);
void dictReleaseIterator(dictIterator *iter);
2010-04-15 12:07:57 -04:00
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);
Use SipHash hash function to mitigate HashDos attempts. This change attempts to switch to an hash function which mitigates the effects of the HashDoS attack (denial of service attack trying to force data structures to worst case behavior) while at the same time providing Redis with an hash function that does not expect the input data to be word aligned, a condition no longer true now that sds.c strings have a varialbe length header. Note that it is possible sometimes that even using an hash function for which collisions cannot be generated without knowing the seed, special implementation details or the exposure of the seed in an indirect way (for example the ability to add elements to a Set and check the return in which Redis returns them with SMEMBERS) may make the attacker's life simpler in the process of trying to guess the correct seed, however the next step would be to switch to a log(N) data structure when too many items in a single bucket are detected: this seems like an overkill in the case of Redis. SPEED REGRESION TESTS: In order to verify that switching from MurmurHash to SipHash had no impact on speed, a set of benchmarks involving fast insertion of 5 million of keys were performed. The result shows Redis with SipHash in high pipelining conditions to be about 4% slower compared to using the previous hash function. However this could partially be related to the fact that the current implementation does not attempt to hash whole words at a time but reads single bytes, in order to have an output which is endian-netural and at the same time working on systems where unaligned memory accesses are a problem. Further X86 specific optimizations should be tested, the function may easily get at the same level of MurMurHash2 if a few optimizations are performed.
2017-02-20 10:09:54 -05:00
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);
2010-04-15 12:07:57 -04:00
int dictRehashMilliseconds(dict *d, int ms);
Use SipHash hash function to mitigate HashDos attempts. This change attempts to switch to an hash function which mitigates the effects of the HashDoS attack (denial of service attack trying to force data structures to worst case behavior) while at the same time providing Redis with an hash function that does not expect the input data to be word aligned, a condition no longer true now that sds.c strings have a varialbe length header. Note that it is possible sometimes that even using an hash function for which collisions cannot be generated without knowing the seed, special implementation details or the exposure of the seed in an indirect way (for example the ability to add elements to a Set and check the return in which Redis returns them with SMEMBERS) may make the attacker's life simpler in the process of trying to guess the correct seed, however the next step would be to switch to a log(N) data structure when too many items in a single bucket are detected: this seems like an overkill in the case of Redis. SPEED REGRESION TESTS: In order to verify that switching from MurmurHash to SipHash had no impact on speed, a set of benchmarks involving fast insertion of 5 million of keys were performed. The result shows Redis with SipHash in high pipelining conditions to be about 4% slower compared to using the previous hash function. However this could partially be related to the fact that the current implementation does not attempt to hash whole words at a time but reads single bytes, in order to have an output which is endian-netural and at the same time working on systems where unaligned memory accesses are a problem. Further X86 specific optimizations should be tested, the function may easily get at the same level of MurMurHash2 if a few optimizations are performed.
2017-02-20 10:09:54 -05:00
void dictSetHashFunctionSeed(uint8_t *seed);
uint8_t *dictGetHashFunctionSeed(void);
2016-12-29 20:37:52 -05:00
unsigned long dictScan(dict *d, unsigned long v, dictScanFunction *fn, dictScanBucketFunction *bucketfn, void *privdata);
2017-11-29 22:34:37 -05:00
uint64_t dictGetHash(dict *d, const void *key);
dictEntry **dictFindEntryRefByPtrAndHash(dict *d, const void *oldptr, uint64_t hash);
2009-03-22 05:30:00 -04:00
/* Hash table types */
extern dictType dictTypeHeapStringCopyKey;
extern dictType dictTypeHeapStrings;
extern dictType dictTypeHeapStringCopyKeyValue;
#endif /* __DICT_H */