forked from Snapchat/KeyDB
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdb.cpp
More file actions
2018 lines (1761 loc) · 67.7 KB
/
db.cpp
File metadata and controls
2018 lines (1761 loc) · 67.7 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (c) 2009-2012, Salvatore Sanfilippo <antirez at gmail dot com>
* 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.
*/
#include "server.h"
#include "cluster.h"
#include "atomicvar.h"
#include "aelocker.h"
#include <signal.h>
#include <ctype.h>
/*-----------------------------------------------------------------------------
* C-level DB API
*----------------------------------------------------------------------------*/
int keyIsExpired(redisDb *db, robj *key);
int expireIfNeeded(redisDb *db, robj *key, robj *o);
void dbOverwriteCore(redisDb *db, dictEntry *de, robj *key, robj *val, bool fUpdateMvcc, bool fRemoveExpire);
/* Update LFU when an object is accessed.
* Firstly, decrement the counter if the decrement time is reached.
* Then logarithmically increment the counter, and update the access time. */
void updateLFU(robj *val) {
unsigned long counter = LFUDecrAndReturn(val);
counter = LFULogIncr(counter);
val->lru = (LFUGetTimeInMinutes()<<8) | counter;
}
void updateExpire(redisDb *db, sds key, robj *valOld, robj *valNew)
{
serverAssert(valOld->FExpires());
serverAssert(!valNew->FExpires());
auto itr = db->setexpire->find(key);
serverAssert(itr != db->setexpire->end());
valNew->SetFExpires(true);
valOld->SetFExpires(false);
return;
}
void updateDbValAccess(dictEntry *de, int flags)
{
robj *val = (robj*)dictGetVal(de);
/* Update the access time for the ageing algorithm.
* Don't do it if we have a saving child, as this will trigger
* a copy on write madness. */
if (!hasActiveChildProcess() && !(flags & LOOKUP_NOTOUCH)){
if (g_pserver->maxmemory_policy & MAXMEMORY_FLAG_LFU) {
updateLFU(val);
} else {
val->lru = LRU_CLOCK();
}
}
}
/* Low level key lookup API, not actually called directly from commands
* implementations that should instead rely on lookupKeyRead(),
* lookupKeyWrite() and lookupKeyReadWithFlags(). */
static robj *lookupKey(redisDb *db, robj *key, int flags) {
dictEntry *de = dictFind(db->pdict,ptrFromObj(key));
if (de) {
robj *val = (robj*)dictGetVal(de);
updateDbValAccess(de, flags);
if (flags & LOOKUP_UPDATEMVCC) {
val->mvcc_tstamp = getMvccTstamp();
}
return val;
} else {
return NULL;
}
}
/* Lookup a key for read operations, or return NULL if the key is not found
* in the specified DB.
*
* As a side effect of calling this function:
* 1. A key gets expired if it reached it's TTL.
* 2. The key last access time is updated.
* 3. The global keys hits/misses stats are updated (reported in INFO).
* 4. If keyspace notifications are enabled, a "keymiss" notification is fired.
*
* This API should not be used when we write to the key after obtaining
* the object linked to the key, but only for read only operations.
*
* Flags change the behavior of this command:
*
* LOOKUP_NONE (or zero): no special flags are passed.
* LOOKUP_NOTOUCH: don't alter the last access time of the key.
*
* Note: this function also returns NULL if the key is logically expired
* but still existing, in case this is a replica, since this API is called only
* for read operations. Even if the key expiry is master-driven, we can
* correctly report a key is expired on slaves even if the master is lagging
* expiring our key via DELs in the replication link. */
robj_roptr lookupKeyReadWithFlags(redisDb *db, robj *key, int flags) {
robj *val;
serverAssert(GlobalLocksAcquired());
if (expireIfNeeded(db,key) == 1) {
/* Key expired. If we are in the context of a master, expireIfNeeded()
* returns 0 only when the key does not exist at all, so it's safe
* to return NULL ASAP. */
if (listLength(g_pserver->masters) == 0) {
g_pserver->stat_keyspace_misses++;
notifyKeyspaceEvent(NOTIFY_KEY_MISS, "keymiss", key, db->id);
return NULL;
}
/* However if we are in the context of a replica, expireIfNeeded() will
* not really try to expire the key, it only returns information
* about the "logical" status of the key: key expiring is up to the
* master in order to have a consistent view of master's data set.
*
* However, if the command caller is not the master, and as additional
* safety measure, the command invoked is a read-only command, we can
* safely return NULL here, and provide a more consistent behavior
* to clients accessign expired values in a read-only fashion, that
* will say the key as non existing.
*
* Notably this covers GETs when slaves are used to scale reads. */
if (serverTL->current_client &&
!FActiveMaster(serverTL->current_client) &&
serverTL->current_client->cmd &&
serverTL->current_client->cmd->flags & CMD_READONLY)
{
g_pserver->stat_keyspace_misses++;
notifyKeyspaceEvent(NOTIFY_KEY_MISS, "keymiss", key, db->id);
return NULL;
}
}
val = lookupKey(db,key,flags);
if (val == NULL) {
g_pserver->stat_keyspace_misses++;
notifyKeyspaceEvent(NOTIFY_KEY_MISS, "keymiss", key, db->id);
}
else
g_pserver->stat_keyspace_hits++;
return val;
}
/* Like lookupKeyReadWithFlags(), but does not use any flag, which is the
* common case. */
robj_roptr lookupKeyRead(redisDb *db, robj *key) {
return lookupKeyReadWithFlags(db,key,LOOKUP_NONE);
}
/* Lookup a key for write operations, and as a side effect, if needed, expires
* the key if its TTL is reached.
*
* Returns the linked value object if the key exists or NULL if the key
* does not exist in the specified DB. */
robj *lookupKeyWriteWithFlags(redisDb *db, robj *key, int flags) {
expireIfNeeded(db,key);
robj *o = lookupKey(db,key,flags|LOOKUP_UPDATEMVCC);
return o;
}
robj *lookupKeyWrite(redisDb *db, robj *key) {
return lookupKeyWriteWithFlags(db, key, LOOKUP_NONE);
}
robj_roptr lookupKeyReadOrReply(client *c, robj *key, robj *reply) {
robj_roptr o = lookupKeyRead(c->db, key);
if (!o) addReply(c,reply);
return o;
}
robj *lookupKeyWriteOrReply(client *c, robj *key, robj *reply) {
robj *o = lookupKeyWrite(c->db, key);
if (!o) addReply(c,reply);
return o;
}
int dbAddCore(redisDb *db, robj *key, robj *val) {
serverAssert(!val->FExpires());
sds copy = sdsdup(szFromObj(key));
int retval = dictAdd(db->pdict, copy, val);
val->mvcc_tstamp = key->mvcc_tstamp = getMvccTstamp();
if (retval == DICT_OK)
{
if (val->type == OBJ_LIST ||
val->type == OBJ_ZSET ||
val->type == OBJ_STREAM)
signalKeyAsReady(db, key);
if (g_pserver->cluster_enabled) slotToKeyAdd(key);
}
else
{
sdsfree(copy);
}
return retval;
}
/* Add the key to the DB. It's up to the caller to increment the reference
* counter of the value if needed.
*
* The program is aborted if the key already exists. */
void dbAdd(redisDb *db, robj *key, robj *val)
{
int retval = dbAddCore(db, key, val);
serverAssertWithInfo(NULL,key,retval == DICT_OK);
}
void dbOverwriteCore(redisDb *db, dictEntry *de, robj *key, robj *val, bool fUpdateMvcc, bool fRemoveExpire)
{
dictEntry auxentry = *de;
robj *old = (robj*)dictGetVal(de);
if (old->FExpires()) {
if (fRemoveExpire) {
removeExpire(db, key);
}
else {
if (val->getrefcount(std::memory_order_relaxed) == OBJ_SHARED_REFCOUNT)
val = dupStringObject(val);
updateExpire(db, (sds)dictGetKey(de), old, val);
}
}
if (g_pserver->maxmemory_policy & MAXMEMORY_FLAG_LFU) {
val->lru = old->lru;
}
if (fUpdateMvcc) {
if (val->getrefcount(std::memory_order_relaxed) == OBJ_SHARED_REFCOUNT)
val = dupStringObject(val);
val->mvcc_tstamp = getMvccTstamp();
}
dictSetVal(db->pdict, de, val);
if (g_pserver->lazyfree_lazy_server_del) {
freeObjAsync(old);
dictSetVal(db->pdict, &auxentry, NULL);
}
dictFreeVal(db->pdict, &auxentry);
}
/* Overwrite an existing key with a new value. Incrementing the reference
* count of the new value is up to the caller.
* This function does not modify the expire time of the existing key.
*
* The program is aborted if the key was not already present. */
void dbOverwrite(redisDb *db, robj *key, robj *val) {
dictEntry *de = dictFind(db->pdict,ptrFromObj(key));
serverAssertWithInfo(NULL,key,de != NULL);
dbOverwriteCore(db, de, key, val, !!g_pserver->fActiveReplica, false);
}
/* Insert a key, handling duplicate keys according to fReplace */
int dbMerge(redisDb *db, robj *key, robj *val, int fReplace)
{
if (fReplace)
{
dictEntry *de = dictFind(db->pdict, ptrFromObj(key));
if (de == nullptr)
return (dbAddCore(db, key, val) == DICT_OK);
robj *old = (robj*)dictGetVal(de);
if (old->mvcc_tstamp <= val->mvcc_tstamp)
{
dbOverwriteCore(db, de, key, val, false, true);
return true;
}
return false;
}
else
{
return (dbAddCore(db, key, val) == DICT_OK);
}
}
/* High level Set operation. This function can be used in order to set
* a key, whatever it was existing or not, to a new object.
*
* 1) The ref count of the value object is incremented.
* 2) clients WATCHing for the destination key notified.
* 3) The expire time of the key is reset (the key is made persistent),
* unless 'keepttl' is true.
*
* All the new keys in the database should be created via this interface. */
void genericSetKey(redisDb *db, robj *key, robj *val, int keepttl) {
dictEntry *de = dictFind(db->pdict, ptrFromObj(key));
if (de == NULL) {
dbAdd(db,key,val);
} else {
updateDbValAccess(de, LOOKUP_NONE);
dbOverwriteCore(db,de,key,val,!!g_pserver->fActiveReplica,!keepttl);
}
incrRefCount(val);
signalModifiedKey(db,key);
}
/* Common case for genericSetKey() where the TTL is not retained. */
void setKey(redisDb *db, robj *key, robj *val) {
genericSetKey(db,key,val,0);
}
/* Return true if the specified key exists in the specified database.
* LRU/LFU info is not updated in any way. */
int dbExists(redisDb *db, robj *key) {
return dictFind(db->pdict,ptrFromObj(key)) != NULL;
}
/* Return a random key, in form of a Redis object.
* If there are no keys, NULL is returned.
*
* The function makes sure to return keys not already expired. */
robj *dbRandomKey(redisDb *db) {
dictEntry *de;
int maxtries = 100;
int allvolatile = dictSize(db->pdict) == db->setexpire->size();
while(1) {
sds key;
robj *keyobj;
de = dictGetRandomKey(db->pdict);
if (de == NULL) return NULL;
key = (sds)dictGetKey(de);
keyobj = createStringObject(key,sdslen(key));
if (((robj*)dictGetVal(de))->FExpires())
{
if (allvolatile && listLength(g_pserver->masters) && --maxtries == 0) {
/* If the DB is composed only of keys with an expire set,
* it could happen that all the keys are already logically
* expired in the replica, so the function cannot stop because
* expireIfNeeded() is false, nor it can stop because
* dictGetRandomKey() returns NULL (there are keys to return).
* To prevent the infinite loop we do some tries, but if there
* are the conditions for an infinite loop, eventually we
* return a key name that may be already expired. */
return keyobj;
}
}
if (((robj*)dictGetVal(de))->FExpires())
{
if (expireIfNeeded(db,keyobj)) {
decrRefCount(keyobj);
continue; /* search for another key. This expired. */
}
}
return keyobj;
}
}
/* Delete a key, value, and associated expiration entry if any, from the DB */
int dbSyncDelete(redisDb *db, robj *key) {
/* Deleting an entry from the expires dict will not free the sds of
* the key, because it is shared with the main dictionary. */
dictEntry *de = dictFind(db->pdict, szFromObj(key));
if (de != nullptr && ((robj*)dictGetVal(de))->FExpires())
removeExpireCore(db, key, de);
if (dictDelete(db->pdict,ptrFromObj(key)) == DICT_OK) {
if (g_pserver->cluster_enabled) slotToKeyDel(key);
return 1;
} else {
return 0;
}
}
/* This is a wrapper whose behavior depends on the Redis lazy free
* configuration. Deletes the key synchronously or asynchronously. */
int dbDelete(redisDb *db, robj *key) {
return g_pserver->lazyfree_lazy_server_del ? dbAsyncDelete(db,key) :
dbSyncDelete(db,key);
}
/* Prepare the string object stored at 'key' to be modified destructively
* to implement commands like SETBIT or APPEND.
*
* An object is usually ready to be modified unless one of the two conditions
* are true:
*
* 1) The object 'o' is shared (refcount > 1), we don't want to affect
* other users.
* 2) The object encoding is not "RAW".
*
* If the object is found in one of the above conditions (or both) by the
* function, an unshared / not-encoded copy of the string object is stored
* at 'key' in the specified 'db'. Otherwise the object 'o' itself is
* returned.
*
* USAGE:
*
* The object 'o' is what the caller already obtained by looking up 'key'
* in 'db', the usage pattern looks like this:
*
* o = lookupKeyWrite(db,key);
* if (checkType(c,o,OBJ_STRING)) return;
* o = dbUnshareStringValue(db,key,o);
*
* At this point the caller is ready to modify the object, for example
* using an sdscat() call to append some data, or anything else.
*/
robj *dbUnshareStringValue(redisDb *db, robj *key, robj *o) {
serverAssert(o->type == OBJ_STRING);
if (o->getrefcount(std::memory_order_relaxed) != 1 || o->encoding != OBJ_ENCODING_RAW) {
robj *decoded = getDecodedObject(o);
o = createRawStringObject(szFromObj(decoded), sdslen(szFromObj(decoded)));
decrRefCount(decoded);
dbOverwrite(db,key,o);
}
return o;
}
/* Remove all keys from all the databases in a Redis g_pserver->
* If callback is given the function is called from time to time to
* signal that work is in progress.
*
* The dbnum can be -1 if all the DBs should be flushed, or the specified
* DB number if we want to flush only a single Redis database number.
*
* Flags are be EMPTYDB_NO_FLAGS if no special flags are specified or
* 1. EMPTYDB_ASYNC if we want the memory to be freed in a different thread.
* 2. EMPTYDB_BACKUP if we want to empty the backup dictionaries created by
* disklessLoadMakeBackups. In that case we only free memory and avoid
* firing module events.
* and the function to return ASAP.
*
* On success the fuction returns the number of keys removed from the
* database(s). Otherwise -1 is returned in the specific case the
* DB number is out of range, and errno is set to EINVAL. */
long long emptyDbGeneric(redisDb *dbarray, int dbnum, int flags, void(callback)(void*)) {
int async = (flags & EMPTYDB_ASYNC);
int backup = (flags & EMPTYDB_BACKUP); /* Just free the memory, nothing else */
RedisModuleFlushInfoV1 fi = {REDISMODULE_FLUSHINFO_VERSION,!async,dbnum};
long long removed = 0;
if (dbnum < -1 || dbnum >= cserver.dbnum) {
errno = EINVAL;
return -1;
}
/* Pre-flush actions */
if (!backup) {
/* Fire the flushdb modules event. */
moduleFireServerEvent(REDISMODULE_EVENT_FLUSHDB,
REDISMODULE_SUBEVENT_FLUSHDB_START,
&fi);
/* Make sure the WATCHed keys are affected by the FLUSH* commands.
* Note that we need to call the function while the keys are still
* there. */
signalFlushedDb(dbnum);
}
int startdb, enddb;
if (dbnum == -1) {
startdb = 0;
enddb = cserver.dbnum-1;
} else {
startdb = enddb = dbnum;
}
for (int j = startdb; j <= enddb; j++) {
removed += dictSize(dbarray[j].pdict);
if (async) {
emptyDbAsync(&dbarray[j]);
} else {
dictEmpty(dbarray[j].pdict,callback);
dbarray[j].setexpire->clear();
}
}
/* Post-flush actions */
if (!backup) {
if (g_pserver->cluster_enabled) {
if (async) {
slotToKeyFlushAsync();
} else {
slotToKeyFlush();
}
}
if (dbnum == -1) flushSlaveKeysWithExpireList();
/* Also fire the end event. Note that this event will fire almost
* immediately after the start event if the flush is asynchronous. */
moduleFireServerEvent(REDISMODULE_EVENT_FLUSHDB,
REDISMODULE_SUBEVENT_FLUSHDB_END,
&fi);
}
return removed;
}
long long emptyDb(int dbnum, int flags, void(callback)(void*)) {
return emptyDbGeneric(g_pserver->db, dbnum, flags, callback);
}
int selectDb(client *c, int id) {
if (id < 0 || id >= cserver.dbnum)
return C_ERR;
c->db = &g_pserver->db[id];
return C_OK;
}
long long dbTotalServerKeyCount() {
long long total = 0;
int j;
for (j = 0; j < cserver.dbnum; j++) {
total += dictSize(g_pserver->db[j].pdict);
}
return total;
}
/*-----------------------------------------------------------------------------
* Hooks for key space changes.
*
* Every time a key in the database is modified the function
* signalModifiedKey() is called.
*
* Every time a DB is flushed the function signalFlushDb() is called.
*----------------------------------------------------------------------------*/
void signalModifiedKey(redisDb *db, robj *key) {
touchWatchedKey(db,key);
trackingInvalidateKey(key);
}
void signalFlushedDb(int dbid) {
touchWatchedKeysOnFlush(dbid);
trackingInvalidateKeysOnFlush(dbid);
}
/*-----------------------------------------------------------------------------
* Type agnostic commands operating on the key space
*----------------------------------------------------------------------------*/
/* Return the set of flags to use for the emptyDb() call for FLUSHALL
* and FLUSHDB commands.
*
* Currently the command just attempts to parse the "ASYNC" option. It
* also checks if the command arity is wrong.
*
* On success C_OK is returned and the flags are stored in *flags, otherwise
* C_ERR is returned and the function sends an error to the client. */
int getFlushCommandFlags(client *c, int *flags) {
/* Parse the optional ASYNC option. */
if (c->argc > 1) {
if (c->argc > 2 || strcasecmp(szFromObj(c->argv[1]),"async")) {
addReply(c,shared.syntaxerr);
return C_ERR;
}
*flags = EMPTYDB_ASYNC;
} else {
*flags = EMPTYDB_NO_FLAGS;
}
return C_OK;
}
/* Flushes the whole server data set. */
void flushAllDataAndResetRDB(int flags) {
g_pserver->dirty += emptyDb(-1,flags,NULL);
if (g_pserver->rdb_child_pid != -1) killRDBChild();
if (g_pserver->saveparamslen > 0) {
/* Normally rdbSave() will reset dirty, but we don't want this here
* as otherwise FLUSHALL will not be replicated nor put into the AOF. */
int saved_dirty = g_pserver->dirty;
rdbSaveInfo rsi, *rsiptr;
rsiptr = rdbPopulateSaveInfo(&rsi);
rdbSave(rsiptr);
g_pserver->dirty = saved_dirty;
}
g_pserver->dirty++;
#if defined(USE_JEMALLOC)
/* jemalloc 5 doesn't release pages back to the OS when there's no traffic.
* for large databases, flushdb blocks for long anyway, so a bit more won't
* harm and this way the flush and purge will be synchroneus. */
if (!(flags & EMPTYDB_ASYNC))
jemalloc_purge();
#endif
}
/* FLUSHDB [ASYNC]
*
* Flushes the currently SELECTed Redis DB. */
void flushdbCommand(client *c) {
int flags;
if (getFlushCommandFlags(c,&flags) == C_ERR) return;
g_pserver->dirty += emptyDb(c->db->id,flags,NULL);
addReply(c,shared.ok);
#if defined(USE_JEMALLOC)
/* jemalloc 5 doesn't release pages back to the OS when there's no traffic.
* for large databases, flushdb blocks for long anyway, so a bit more won't
* harm and this way the flush and purge will be synchroneus. */
if (!(flags & EMPTYDB_ASYNC))
jemalloc_purge();
#endif
}
/* FLUSHALL [ASYNC]
*
* Flushes the whole server data set. */
void flushallCommand(client *c) {
int flags;
if (getFlushCommandFlags(c,&flags) == C_ERR) return;
flushAllDataAndResetRDB(flags);
addReply(c,shared.ok);
}
/* This command implements DEL and LAZYDEL. */
void delGenericCommand(client *c, int lazy) {
int numdel = 0, j;
for (j = 1; j < c->argc; j++) {
expireIfNeeded(c->db,c->argv[j]);
int deleted = lazy ? dbAsyncDelete(c->db,c->argv[j]) :
dbSyncDelete(c->db,c->argv[j]);
if (deleted) {
signalModifiedKey(c->db,c->argv[j]);
notifyKeyspaceEvent(NOTIFY_GENERIC,
"del",c->argv[j],c->db->id);
g_pserver->dirty++;
numdel++;
}
}
addReplyLongLong(c,numdel);
}
void delCommand(client *c) {
delGenericCommand(c,0);
}
void unlinkCommand(client *c) {
delGenericCommand(c,1);
}
/* EXISTS key1 key2 ... key_N.
* Return value is the number of keys existing. */
void existsCommand(client *c) {
long long count = 0;
int j;
for (j = 1; j < c->argc; j++) {
if (lookupKeyRead(c->db,c->argv[j])) count++;
}
addReplyLongLong(c,count);
}
void selectCommand(client *c) {
long id;
if (getLongFromObjectOrReply(c, c->argv[1], &id,
"invalid DB index") != C_OK)
return;
if (g_pserver->cluster_enabled && id != 0) {
addReplyError(c,"SELECT is not allowed in cluster mode");
return;
}
if (selectDb(c,id) == C_ERR) {
addReplyError(c,"DB index is out of range");
} else {
addReply(c,shared.ok);
}
}
void randomkeyCommand(client *c) {
robj *key;
if ((key = dbRandomKey(c->db)) == NULL) {
addReplyNull(c);
return;
}
addReplyBulk(c,key);
decrRefCount(key);
}
void keysCommand(client *c) {
dictIterator *di;
dictEntry *de;
sds pattern = szFromObj(c->argv[1]);
int plen = sdslen(pattern), allkeys;
unsigned long numkeys = 0;
void *replylen = addReplyDeferredLen(c);
di = dictGetSafeIterator(c->db->pdict);
allkeys = (pattern[0] == '*' && plen == 1);
while((de = dictNext(di)) != NULL) {
sds key = (sds)dictGetKey(de);
robj *keyobj;
if (allkeys || stringmatchlen(pattern,plen,key,sdslen(key),0)) {
keyobj = createStringObject(key,sdslen(key));
if (!keyIsExpired(c->db,keyobj)) {
addReplyBulk(c,keyobj);
numkeys++;
}
decrRefCount(keyobj);
}
}
dictReleaseIterator(di);
setDeferredArrayLen(c,replylen,numkeys);
}
/* This callback is used by scanGenericCommand in order to collect elements
* returned by the dictionary iterator into a list. */
void scanCallback(void *privdata, const dictEntry *de) {
void **pd = (void**) privdata;
list *keys = (list*)pd[0];
robj *o = (robj*)pd[1];
robj *key, *val = NULL;
if (o == NULL) {
sds sdskey = (sds)dictGetKey(de);
key = createStringObject(sdskey, sdslen(sdskey));
} else if (o->type == OBJ_SET) {
sds keysds = (sds)dictGetKey(de);
key = createStringObject(keysds,sdslen(keysds));
} else if (o->type == OBJ_HASH) {
sds sdskey = (sds)dictGetKey(de);
sds sdsval = (sds)dictGetVal(de);
key = createStringObject(sdskey,sdslen(sdskey));
val = createStringObject(sdsval,sdslen(sdsval));
} else if (o->type == OBJ_ZSET) {
sds sdskey = (sds)dictGetKey(de);
key = createStringObject(sdskey,sdslen(sdskey));
val = createStringObjectFromLongDouble(*(double*)dictGetVal(de),0);
} else {
serverPanic("Type not handled in SCAN callback.");
}
listAddNodeTail(keys, key);
if (val) listAddNodeTail(keys, val);
}
/* Try to parse a SCAN cursor stored at object 'o':
* if the cursor is valid, store it as unsigned integer into *cursor and
* returns C_OK. Otherwise return C_ERR and send an error to the
* client. */
int parseScanCursorOrReply(client *c, robj *o, unsigned long *cursor) {
char *eptr;
/* Use strtoul() because we need an *unsigned* long, so
* getLongLongFromObject() does not cover the whole cursor space. */
errno = 0;
*cursor = strtoul(szFromObj(o), &eptr, 10);
if (isspace(((char*)ptrFromObj(o))[0]) || eptr[0] != '\0' || errno == ERANGE)
{
addReplyError(c, "invalid cursor");
return C_ERR;
}
return C_OK;
}
/* This command implements SCAN, HSCAN and SSCAN commands.
* If object 'o' is passed, then it must be a Hash, Set or Zset object, otherwise
* if 'o' is NULL the command will operate on the dictionary associated with
* the current database.
*
* When 'o' is not NULL the function assumes that the first argument in
* the client arguments vector is a key so it skips it before iterating
* in order to parse options.
*
* In the case of a Hash object the function returns both the field and value
* of every element on the Hash. */
void scanGenericCommand(client *c, robj_roptr o, unsigned long cursor) {
int i, j;
list *keys = listCreate();
listNode *node, *nextnode;
long count = 10;
sds pat = NULL;
sds type = NULL;
int patlen = 0, use_pattern = 0;
dict *ht;
/* Object must be NULL (to iterate keys names), or the type of the object
* must be Set, Sorted Set, or Hash. */
serverAssert(o == nullptr || o->type == OBJ_SET || o->type == OBJ_HASH ||
o->type == OBJ_ZSET);
/* Set i to the first option argument. The previous one is the cursor. */
i = (o == nullptr) ? 2 : 3; /* Skip the key argument if needed. */
/* Step 1: Parse options. */
while (i < c->argc) {
j = c->argc - i;
if (!strcasecmp(szFromObj(c->argv[i]), "count") && j >= 2) {
if (getLongFromObjectOrReply(c, c->argv[i+1], &count, NULL)
!= C_OK)
{
goto cleanup;
}
if (count < 1) {
addReply(c,shared.syntaxerr);
goto cleanup;
}
i += 2;
} else if (!strcasecmp(szFromObj(c->argv[i]), "match") && j >= 2) {
pat = szFromObj(c->argv[i+1]);
patlen = sdslen(pat);
/* The pattern always matches if it is exactly "*", so it is
* equivalent to disabling it. */
use_pattern = !(pat[0] == '*' && patlen == 1);
i += 2;
} else if (!strcasecmp(szFromObj(c->argv[i]), "type") && o == nullptr && j >= 2) {
/* SCAN for a particular type only applies to the db dict */
type = szFromObj(c->argv[i+1]);
i+= 2;
} else {
addReply(c,shared.syntaxerr);
goto cleanup;
}
}
/* Step 2: Iterate the collection.
*
* Note that if the object is encoded with a ziplist, intset, or any other
* representation that is not a hash table, we are sure that it is also
* composed of a small number of elements. So to avoid taking state we
* just return everything inside the object in a single call, setting the
* cursor to zero to signal the end of the iteration. */
/* Handle the case of a hash table. */
ht = NULL;
if (o == nullptr) {
ht = c->db->pdict;
} else if (o->type == OBJ_SET && o->encoding == OBJ_ENCODING_HT) {
ht = (dict*)ptrFromObj(o);
} else if (o->type == OBJ_HASH && o->encoding == OBJ_ENCODING_HT) {
ht = (dict*)ptrFromObj(o);
count *= 2; /* We return key / value for this type. */
} else if (o->type == OBJ_ZSET && o->encoding == OBJ_ENCODING_SKIPLIST) {
zset *zs = (zset*)ptrFromObj(o);
ht = zs->pdict;
count *= 2; /* We return key / value for this type. */
}
if (ht) {
void *privdata[2];
/* We set the max number of iterations to ten times the specified
* COUNT, so if the hash table is in a pathological state (very
* sparsely populated) we avoid to block too much time at the cost
* of returning no or very few elements. */
long maxiterations = count*10;
/* We pass two pointers to the callback: the list to which it will
* add new elements, and the object containing the dictionary so that
* it is possible to fetch more data in a type-dependent way. */
privdata[0] = keys;
privdata[1] = o.unsafe_robjcast();
do {
cursor = dictScan(ht, cursor, scanCallback, NULL, privdata);
} while (cursor &&
maxiterations-- &&
listLength(keys) < (unsigned long)count);
} else if (o->type == OBJ_SET) {
int pos = 0;
int64_t ll;
while(intsetGet((intset*)ptrFromObj(o),pos++,&ll))
listAddNodeTail(keys,createStringObjectFromLongLong(ll));
cursor = 0;
} else if (o->type == OBJ_HASH || o->type == OBJ_ZSET) {
unsigned char *p = ziplistIndex((unsigned char*)ptrFromObj(o),0);
unsigned char *vstr;
unsigned int vlen;
long long vll;
while(p) {
ziplistGet(p,&vstr,&vlen,&vll);
listAddNodeTail(keys,
(vstr != NULL) ? createStringObject((char*)vstr,vlen) :
createStringObjectFromLongLong(vll));
p = ziplistNext((unsigned char*)ptrFromObj(o),p);
}
cursor = 0;
} else {
serverPanic("Not handled encoding in SCAN.");
}
/* Step 3: Filter elements. */
node = listFirst(keys);
while (node) {
robj *kobj = (robj*)listNodeValue(node);
nextnode = listNextNode(node);
int filter = 0;
/* Filter element if it does not match the pattern. */
if (!filter && use_pattern) {
if (sdsEncodedObject(kobj)) {
if (!stringmatchlen(pat, patlen, szFromObj(kobj), sdslen(szFromObj(kobj)), 0))
filter = 1;
} else {
char buf[LONG_STR_SIZE];
int len;
serverAssert(kobj->encoding == OBJ_ENCODING_INT);
len = ll2string(buf,sizeof(buf),(long)ptrFromObj(kobj));
if (!stringmatchlen(pat, patlen, buf, len, 0)) filter = 1;
}
}
/* Filter an element if it isn't the type we want. */
if (!filter && o == nullptr && type){
robj_roptr typecheck = lookupKeyReadWithFlags(c->db, kobj, LOOKUP_NOTOUCH);
const char* typeT = getObjectTypeName(typecheck);
if (strcasecmp((char*) type, typeT)) filter = 1;
}
/* Filter element if it is an expired key. */
if (!filter && o == nullptr && expireIfNeeded(c->db, kobj)) filter = 1;
/* Remove the element and its associted value if needed. */
if (filter) {
decrRefCount(kobj);
listDelNode(keys, node);
}
/* If this is a hash or a sorted set, we have a flat list of
* key-value elements, so if this element was filtered, remove the
* value, or skip it if it was not filtered: we only match keys. */
if (o && (o->type == OBJ_ZSET || o->type == OBJ_HASH)) {
node = nextnode;
nextnode = listNextNode(node);
if (filter) {
kobj = (robj*)listNodeValue(node);
decrRefCount(kobj);
listDelNode(keys, node);
}
}
node = nextnode;
}
/* Step 4: Reply to the client. */
addReplyArrayLen(c, 2);
addReplyBulkLongLong(c,cursor);
addReplyArrayLen(c, listLength(keys));
while ((node = listFirst(keys)) != NULL) {
robj *kobj = (robj*)listNodeValue(node);
addReplyBulk(c, kobj);
decrRefCount(kobj);
listDelNode(keys, node);
}
cleanup:
listSetFreeMethod(keys,decrRefCountVoid);
listRelease(keys);
}
/* The SCAN command completely relies on scanGenericCommand. */
void scanCommand(client *c) {
unsigned long cursor;
if (parseScanCursorOrReply(c,c->argv[1],&cursor) == C_ERR) return;
scanGenericCommand(c,nullptr,cursor);
}
void dbsizeCommand(client *c) {
addReplyLongLong(c,dictSize(c->db->pdict));
}
void lastsaveCommand(client *c) {