forked from redis/redis
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathreplication.c
1833 lines (1632 loc) · 71.2 KB
/
replication.c
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
/* Asynchronous replication implementation.
*
* 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 "redis.h"
#include <sys/time.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/socket.h>
#include <sys/stat.h>
void replicationDiscardCachedMaster(void);
void replicationResurrectCachedMaster(int newfd);
void replicationSendAck(void);
/* ---------------------------------- MASTER -------------------------------- */
void createReplicationBacklog(void) {
redisAssert(server.repl_backlog == NULL);
server.repl_backlog = zmalloc(server.repl_backlog_size);
server.repl_backlog_histlen = 0;
server.repl_backlog_idx = 0;
/* When a new backlog buffer is created, we increment the replication
* offset by one to make sure we'll not be able to PSYNC with any
* previous slave. This is needed because we avoid incrementing the
* master_repl_offset if no backlog exists nor slaves are attached. */
server.master_repl_offset++;
/* We don't have any data inside our buffer, but virtually the first
* byte we have is the next byte that will be generated for the
* replication stream. */
server.repl_backlog_off = server.master_repl_offset+1;
}
/* This function is called when the user modifies the replication backlog
* size at runtime. It is up to the function to both update the
* server.repl_backlog_size and to resize the buffer and setup it so that
* it contains the same data as the previous one (possibly less data, but
* the most recent bytes, or the same data and more free space in case the
* buffer is enlarged). */
void resizeReplicationBacklog(long long newsize) {
if (newsize < REDIS_REPL_BACKLOG_MIN_SIZE)
newsize = REDIS_REPL_BACKLOG_MIN_SIZE;
if (server.repl_backlog_size == newsize) return;
server.repl_backlog_size = newsize;
if (server.repl_backlog != NULL) {
/* What we actually do is to flush the old buffer and realloc a new
* empty one. It will refill with new data incrementally.
* The reason is that copying a few gigabytes adds latency and even
* worse often we need to alloc additional space before freeing the
* old buffer. */
zfree(server.repl_backlog);
server.repl_backlog = zmalloc(server.repl_backlog_size);
server.repl_backlog_histlen = 0;
server.repl_backlog_idx = 0;
/* Next byte we have is... the next since the buffer is emtpy. */
server.repl_backlog_off = server.master_repl_offset+1;
}
}
void freeReplicationBacklog(void) {
redisAssert(listLength(server.slaves) == 0);
zfree(server.repl_backlog);
server.repl_backlog = NULL;
}
/* Add data to the replication backlog.
* This function also increments the global replication offset stored at
* server.master_repl_offset, because there is no case where we want to feed
* the backlog without incrementing the buffer. */
void feedReplicationBacklog(void *ptr, size_t len) {
unsigned char *p = ptr;
server.master_repl_offset += len;
/* This is a circular buffer, so write as much data we can at every
* iteration and rewind the "idx" index if we reach the limit. */
while(len) {
size_t thislen = server.repl_backlog_size - server.repl_backlog_idx;
if (thislen > len) thislen = len;
memcpy(server.repl_backlog+server.repl_backlog_idx,p,thislen);
server.repl_backlog_idx += thislen;
if (server.repl_backlog_idx == server.repl_backlog_size)
server.repl_backlog_idx = 0;
len -= thislen;
p += thislen;
server.repl_backlog_histlen += thislen;
}
if (server.repl_backlog_histlen > server.repl_backlog_size)
server.repl_backlog_histlen = server.repl_backlog_size;
/* Set the offset of the first byte we have in the backlog. */
server.repl_backlog_off = server.master_repl_offset -
server.repl_backlog_histlen + 1;
}
/* Wrapper for feedReplicationBacklog() that takes Redis string objects
* as input. */
void feedReplicationBacklogWithObject(robj *o) {
char llstr[REDIS_LONGSTR_SIZE];
void *p;
size_t len;
if (o->encoding == REDIS_ENCODING_INT) {
len = ll2string(llstr,sizeof(llstr),(long)o->ptr);
p = llstr;
} else {
len = sdslen(o->ptr);
p = o->ptr;
}
feedReplicationBacklog(p,len);
}
void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc) {
listNode *ln;
listIter li;
int j, len;
char llstr[REDIS_LONGSTR_SIZE];
/* If there aren't slaves, and there is no backlog buffer to populate,
* we can return ASAP. */
if (server.repl_backlog == NULL && listLength(slaves) == 0) return;
/* We can't have slaves attached and no backlog. */
redisAssert(!(listLength(slaves) != 0 && server.repl_backlog == NULL));
/* Send SELECT command to every slave if needed. */
if (server.slaveseldb != dictid) {
robj *selectcmd;
/* For a few DBs we have pre-computed SELECT command. */
if (dictid >= 0 && dictid < REDIS_SHARED_SELECT_CMDS) {
selectcmd = shared.select[dictid];
} else {
int dictid_len;
dictid_len = ll2string(llstr,sizeof(llstr),dictid);
selectcmd = createObject(REDIS_STRING,
sdscatprintf(sdsempty(),
"*2\r\n$6\r\nSELECT\r\n$%d\r\n%s\r\n",
dictid_len, llstr));
}
/* Add the SELECT command into the backlog. */
if (server.repl_backlog) feedReplicationBacklogWithObject(selectcmd);
/* Send it to slaves. */
listRewind(slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
addReply(slave,selectcmd);
}
if (dictid < 0 || dictid >= REDIS_SHARED_SELECT_CMDS)
decrRefCount(selectcmd);
}
server.slaveseldb = dictid;
/* Write the command to the replication backlog if any. */
if (server.repl_backlog) {
char aux[REDIS_LONGSTR_SIZE+3];
/* Add the multi bulk reply length. */
aux[0] = '*';
len = ll2string(aux+1,sizeof(aux)-1,argc);
aux[len+1] = '\r';
aux[len+2] = '\n';
feedReplicationBacklog(aux,len+3);
for (j = 0; j < argc; j++) {
long objlen = stringObjectLen(argv[j]);
/* We need to feed the buffer with the object as a bulk reply
* not just as a plain string, so create the $..CRLF payload len
* ad add the final CRLF */
aux[0] = '$';
len = ll2string(aux+1,sizeof(aux)-1,objlen);
aux[len+1] = '\r';
aux[len+2] = '\n';
feedReplicationBacklog(aux,len+3);
feedReplicationBacklogWithObject(argv[j]);
feedReplicationBacklog(aux+len+1,2);
}
}
/* Write the command to every slave. */
listRewind(slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
/* Don't feed slaves that are still waiting for BGSAVE to start */
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) continue;
/* Feed slaves that are waiting for the initial SYNC (so these commands
* are queued in the output buffer until the initial SYNC completes),
* or are already in sync with the master. */
/* Add the multi bulk length. */
addReplyMultiBulkLen(slave,argc);
/* Finally any additional argument that was not stored inside the
* static buffer if any (from j to argc). */
for (j = 0; j < argc; j++)
addReplyBulk(slave,argv[j]);
}
}
void replicationFeedMonitors(redisClient *c, list *monitors, int dictid, robj **argv, int argc) {
listNode *ln;
listIter li;
int j;
sds cmdrepr = sdsnew("+");
robj *cmdobj;
struct timeval tv;
gettimeofday(&tv,NULL);
cmdrepr = sdscatprintf(cmdrepr,"%ld.%06ld ",(long)tv.tv_sec,(long)tv.tv_usec);
if (c->flags & REDIS_LUA_CLIENT) {
cmdrepr = sdscatprintf(cmdrepr,"[%d lua] ",dictid);
} else if (c->flags & REDIS_UNIX_SOCKET) {
cmdrepr = sdscatprintf(cmdrepr,"[%d unix:%s] ",dictid,server.unixsocket);
} else {
cmdrepr = sdscatprintf(cmdrepr,"[%d %s] ",dictid,getClientPeerId(c));
}
for (j = 0; j < argc; j++) {
if (argv[j]->encoding == REDIS_ENCODING_INT) {
cmdrepr = sdscatprintf(cmdrepr, "\"%ld\"", (long)argv[j]->ptr);
} else {
cmdrepr = sdscatrepr(cmdrepr,(char*)argv[j]->ptr,
sdslen(argv[j]->ptr));
}
if (j != argc-1)
cmdrepr = sdscatlen(cmdrepr," ",1);
}
cmdrepr = sdscatlen(cmdrepr,"\r\n",2);
cmdobj = createObject(REDIS_STRING,cmdrepr);
listRewind(monitors,&li);
while((ln = listNext(&li))) {
redisClient *monitor = ln->value;
addReply(monitor,cmdobj);
}
decrRefCount(cmdobj);
}
/* Feed the slave 'c' with the replication backlog starting from the
* specified 'offset' up to the end of the backlog. */
long long addReplyReplicationBacklog(redisClient *c, long long offset) {
long long j, skip, len;
redisLog(REDIS_DEBUG, "[PSYNC] Slave request offset: %lld", offset);
if (server.repl_backlog_histlen == 0) {
redisLog(REDIS_DEBUG, "[PSYNC] Backlog history len is zero");
return 0;
}
redisLog(REDIS_DEBUG, "[PSYNC] Backlog size: %lld",
server.repl_backlog_size);
redisLog(REDIS_DEBUG, "[PSYNC] First byte: %lld",
server.repl_backlog_off);
redisLog(REDIS_DEBUG, "[PSYNC] History len: %lld",
server.repl_backlog_histlen);
redisLog(REDIS_DEBUG, "[PSYNC] Current index: %lld",
server.repl_backlog_idx);
/* Compute the amount of bytes we need to discard. */
skip = offset - server.repl_backlog_off;
redisLog(REDIS_DEBUG, "[PSYNC] Skipping: %lld", skip);
/* Point j to the oldest byte, that is actaully our
* server.repl_backlog_off byte. */
j = (server.repl_backlog_idx +
(server.repl_backlog_size-server.repl_backlog_histlen)) %
server.repl_backlog_size;
redisLog(REDIS_DEBUG, "[PSYNC] Index of first byte: %lld", j);
/* Discard the amount of data to seek to the specified 'offset'. */
j = (j + skip) % server.repl_backlog_size;
/* Feed slave with data. Since it is a circular buffer we have to
* split the reply in two parts if we are cross-boundary. */
len = server.repl_backlog_histlen - skip;
redisLog(REDIS_DEBUG, "[PSYNC] Reply total length: %lld", len);
while(len) {
long long thislen =
((server.repl_backlog_size - j) < len) ?
(server.repl_backlog_size - j) : len;
redisLog(REDIS_DEBUG, "[PSYNC] addReply() length: %lld", thislen);
addReplySds(c,sdsnewlen(server.repl_backlog + j, thislen));
len -= thislen;
j = 0;
}
return server.repl_backlog_histlen - skip;
}
/* This function handles the PSYNC command from the point of view of a
* master receiving a request for partial resynchronization.
*
* On success return REDIS_OK, otherwise REDIS_ERR is returned and we proceed
* with the usual full resync. */
int masterTryPartialResynchronization(redisClient *c) {
long long psync_offset, psync_len;
char *master_runid = c->argv[1]->ptr;
char buf[128];
int buflen;
/* Is the runid of this master the same advertised by the wannabe slave
* via PSYNC? If runid changed this master is a different instance and
* there is no way to continue. */
if (strcasecmp(master_runid, server.runid)) {
/* Run id "?" is used by slaves that want to force a full resync. */
if (master_runid[0] != '?') {
redisLog(REDIS_NOTICE,"Partial resynchronization not accepted: "
"Runid mismatch (Client asked for runid '%s', my runid is '%s')",
master_runid, server.runid);
} else {
redisLog(REDIS_NOTICE,"Full resync requested by slave.");
}
goto need_full_resync;
}
/* We still have the data our slave is asking for? */
if (getLongLongFromObjectOrReply(c,c->argv[2],&psync_offset,NULL) !=
REDIS_OK) goto need_full_resync;
if (!server.repl_backlog ||
psync_offset < server.repl_backlog_off ||
psync_offset > (server.repl_backlog_off + server.repl_backlog_histlen))
{
redisLog(REDIS_NOTICE,
"Unable to partial resync with the slave for lack of backlog (Slave request was: %lld).", psync_offset);
if (psync_offset > server.master_repl_offset) {
redisLog(REDIS_WARNING,
"Warning: slave tried to PSYNC with an offset that is greater than the master replication offset.");
}
goto need_full_resync;
}
/* If we reached this point, we are able to perform a partial resync:
* 1) Set client state to make it a slave.
* 2) Inform the client we can continue with +CONTINUE
* 3) Send the backlog data (from the offset to the end) to the slave. */
c->flags |= REDIS_SLAVE;
c->replstate = REDIS_REPL_ONLINE;
c->repl_ack_time = server.unixtime;
listAddNodeTail(server.slaves,c);
/* We can't use the connection buffers since they are used to accumulate
* new commands at this stage. But we are sure the socket send buffer is
* emtpy so this write will never fail actually. */
buflen = snprintf(buf,sizeof(buf),"+CONTINUE\r\n");
if (write(c->fd,buf,buflen) != buflen) {
freeClientAsync(c);
return REDIS_OK;
}
psync_len = addReplyReplicationBacklog(c,psync_offset);
redisLog(REDIS_NOTICE,
"Partial resynchronization request accepted. Sending %lld bytes of backlog starting from offset %lld.", psync_len, psync_offset);
/* Note that we don't need to set the selected DB at server.slaveseldb
* to -1 to force the master to emit SELECT, since the slave already
* has this state from the previous connection with the master. */
refreshGoodSlavesCount();
return REDIS_OK; /* The caller can return, no full resync needed. */
need_full_resync:
/* We need a full resync for some reason... notify the client. */
psync_offset = server.master_repl_offset;
/* Add 1 to psync_offset if it the replication backlog does not exists
* as when it will be created later we'll increment the offset by one. */
if (server.repl_backlog == NULL) psync_offset++;
/* Again, we can't use the connection buffers (see above). */
buflen = snprintf(buf,sizeof(buf),"+FULLRESYNC %s %lld\r\n",
server.runid,psync_offset);
if (write(c->fd,buf,buflen) != buflen) {
freeClientAsync(c);
return REDIS_OK;
}
return REDIS_ERR;
}
/* SYNC ad PSYNC command implemenation. */
void syncCommand(redisClient *c) {
/* ignore SYNC if already slave or in monitor mode */
if (c->flags & REDIS_SLAVE) return;
/* Refuse SYNC requests if we are a slave but the link with our master
* is not ok... */
if (server.masterhost && server.repl_state != REDIS_REPL_CONNECTED) {
addReplyError(c,"Can't SYNC while not connected with my master");
return;
}
/* SYNC can't be issued when the server has pending data to send to
* the client about already issued commands. We need a fresh reply
* buffer registering the differences between the BGSAVE and the current
* dataset, so that we can copy to other slaves if needed. */
if (listLength(c->reply) != 0 || c->bufpos != 0) {
addReplyError(c,"SYNC and PSYNC are invalid with pending output");
return;
}
redisLog(REDIS_NOTICE,"Slave asks for synchronization");
/* Try a partial resynchronization if this is a PSYNC command.
* If it fails, we continue with usual full resynchronization, however
* when this happens masterTryPartialResynchronization() already
* replied with:
*
* +FULLRESYNC <runid> <offset>
*
* So the slave knows the new runid and offset to try a PSYNC later
* if the connection with the master is lost. */
if (!strcasecmp(c->argv[0]->ptr,"psync")) {
if (masterTryPartialResynchronization(c) == REDIS_OK) {
server.stat_sync_partial_ok++;
return; /* No full resync needed, return. */
} else {
char *master_runid = c->argv[1]->ptr;
/* Increment stats for failed PSYNCs, but only if the
* runid is not "?", as this is used by slaves to force a full
* resync on purpose when they are not albe to partially
* resync. */
if (master_runid[0] != '?') server.stat_sync_partial_err++;
}
} else {
/* If a slave uses SYNC, we are dealing with an old implementation
* of the replication protocol (like redis-cli --slave). Flag the client
* so that we don't expect to receive REPLCONF ACK feedbacks. */
c->flags |= REDIS_PRE_PSYNC;
}
/* Full resynchronization. */
server.stat_sync_full++;
/* Here we need to check if there is a background saving operation
* in progress, or if it is required to start one */
if (server.rdb_child_pid != -1) {
/* Ok a background save is in progress. Let's check if it is a good
* one for replication, i.e. if there is another slave that is
* registering differences since the server forked to save */
redisClient *slave;
listNode *ln;
listIter li;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) break;
}
if (ln) {
/* Perfect, the server is already registering differences for
* another slave. Set the right state, and copy the buffer. */
copyClientOutputBuffer(c,slave);
c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
redisLog(REDIS_NOTICE,"Waiting for end of BGSAVE for SYNC");
} else {
/* No way, we need to wait for the next BGSAVE in order to
* register differences */
c->replstate = REDIS_REPL_WAIT_BGSAVE_START;
redisLog(REDIS_NOTICE,"Waiting for next BGSAVE for SYNC");
}
} else {
/* Ok we don't have a BGSAVE in progress, let's start one */
redisLog(REDIS_NOTICE,"Starting BGSAVE for SYNC");
if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
redisLog(REDIS_NOTICE,"Replication failed, can't BGSAVE");
addReplyError(c,"Unable to perform background save");
return;
}
c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
/* Flush the script cache for the new slave. */
replicationScriptCacheFlush();
}
if (server.repl_disable_tcp_nodelay)
anetDisableTcpNoDelay(NULL, c->fd); /* Non critical if it fails. */
c->repldbfd = -1;
c->flags |= REDIS_SLAVE;
server.slaveseldb = -1; /* Force to re-emit the SELECT command. */
listAddNodeTail(server.slaves,c);
if (listLength(server.slaves) == 1 && server.repl_backlog == NULL)
createReplicationBacklog();
return;
}
/* REPLCONF <option> <value> <option> <value> ...
* This command is used by a slave in order to configure the replication
* process before starting it with the SYNC command.
*
* Currently the only use of this command is to communicate to the master
* what is the listening port of the Slave redis instance, so that the
* master can accurately list slaves and their listening ports in
* the INFO output.
*
* In the future the same command can be used in order to configure
* the replication to initiate an incremental replication instead of a
* full resync. */
void replconfCommand(redisClient *c) {
int j;
if ((c->argc % 2) == 0) {
/* Number of arguments must be odd to make sure that every
* option has a corresponding value. */
addReply(c,shared.syntaxerr);
return;
}
/* Process every option-value pair. */
for (j = 1; j < c->argc; j+=2) {
if (!strcasecmp(c->argv[j]->ptr,"listening-port")) {
long port;
if ((getLongFromObjectOrReply(c,c->argv[j+1],
&port,NULL) != REDIS_OK))
return;
c->slave_listening_port = port;
} else if (!strcasecmp(c->argv[j]->ptr,"ack")) {
/* REPLCONF ACK is used by slave to inform the master the amount
* of replication stream that it processed so far. It is an
* internal only command that normal clients should never use. */
long long offset;
if (!(c->flags & REDIS_SLAVE)) return;
if ((getLongLongFromObject(c->argv[j+1], &offset) != REDIS_OK))
return;
if (offset > c->repl_ack_off)
c->repl_ack_off = offset;
c->repl_ack_time = server.unixtime;
/* Note: this command does not reply anything! */
return;
} else if (!strcasecmp(c->argv[j]->ptr,"getack")) {
/* REPLCONF GETACK is used in order to request an ACK ASAP
* to the slave. */
if (server.masterhost && server.master) replicationSendAck();
/* Note: this command does not reply anything! */
} else {
addReplyErrorFormat(c,"Unrecognized REPLCONF option: %s",
(char*)c->argv[j]->ptr);
return;
}
}
addReply(c,shared.ok);
}
void sendBulkToSlave(aeEventLoop *el, int fd, void *privdata, int mask) {
redisClient *slave = privdata;
REDIS_NOTUSED(el);
REDIS_NOTUSED(mask);
char buf[REDIS_IOBUF_LEN];
ssize_t nwritten, buflen;
/* Before sending the RDB file, we send the preamble as configured by the
* replication process. Currently the preamble is just the bulk count of
* the file in the form "$<length>\r\n". */
if (slave->replpreamble) {
nwritten = write(fd,slave->replpreamble,sdslen(slave->replpreamble));
if (nwritten == -1) {
redisLog(REDIS_VERBOSE,"Write error sending RDB preamble to slave: %s",
strerror(errno));
freeClient(slave);
return;
}
sdsrange(slave->replpreamble,nwritten,-1);
if (sdslen(slave->replpreamble) == 0) {
sdsfree(slave->replpreamble);
slave->replpreamble = NULL;
/* fall through sending data. */
} else {
return;
}
}
/* If the preamble was already transfered, send the RDB bulk data. */
lseek(slave->repldbfd,slave->repldboff,SEEK_SET);
buflen = read(slave->repldbfd,buf,REDIS_IOBUF_LEN);
if (buflen <= 0) {
redisLog(REDIS_WARNING,"Read error sending DB to slave: %s",
(buflen == 0) ? "premature EOF" : strerror(errno));
freeClient(slave);
return;
}
if ((nwritten = write(fd,buf,buflen)) == -1) {
if (errno != EAGAIN) {
redisLog(REDIS_WARNING,"Write error sending DB to slave: %s",
strerror(errno));
freeClient(slave);
}
return;
}
slave->repldboff += nwritten;
if (slave->repldboff == slave->repldbsize) {
close(slave->repldbfd);
slave->repldbfd = -1;
aeDeleteFileEvent(server.el,slave->fd,AE_WRITABLE);
slave->replstate = REDIS_REPL_ONLINE;
slave->repl_ack_time = server.unixtime;
if (aeCreateFileEvent(server.el, slave->fd, AE_WRITABLE,
sendReplyToClient, slave) == AE_ERR) {
redisLog(REDIS_WARNING,"Unable to register writable event for slave bulk transfer: %s", strerror(errno));
freeClient(slave);
return;
}
refreshGoodSlavesCount();
redisLog(REDIS_NOTICE,"Synchronization with slave succeeded");
}
}
/* This function is called at the end of every background saving.
* The argument bgsaveerr is REDIS_OK if the background saving succeeded
* otherwise REDIS_ERR is passed to the function.
*
* The goal of this function is to handle slaves waiting for a successful
* background saving in order to perform non-blocking synchronization. */
void updateSlavesWaitingBgsave(int bgsaveerr) {
listNode *ln;
int startbgsave = 0;
listIter li;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) {
startbgsave = 1;
slave->replstate = REDIS_REPL_WAIT_BGSAVE_END;
} else if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) {
struct redis_stat buf;
if (bgsaveerr != REDIS_OK) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE child returned an error");
continue;
}
if ((slave->repldbfd = open(server.rdb_filename,O_RDONLY)) == -1 ||
redis_fstat(slave->repldbfd,&buf) == -1) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. Can't open/stat DB after BGSAVE: %s", strerror(errno));
continue;
}
slave->repldboff = 0;
slave->repldbsize = buf.st_size;
slave->replstate = REDIS_REPL_SEND_BULK;
slave->replpreamble = sdscatprintf(sdsempty(),"$%lld\r\n",
(unsigned long long) slave->repldbsize);
aeDeleteFileEvent(server.el,slave->fd,AE_WRITABLE);
if (aeCreateFileEvent(server.el, slave->fd, AE_WRITABLE, sendBulkToSlave, slave) == AE_ERR) {
freeClient(slave);
continue;
}
}
}
if (startbgsave) {
/* Since we are starting a new background save for one or more slaves,
* we flush the Replication Script Cache to use EVAL to propagate every
* new EVALSHA for the first time, since all the new slaves don't know
* about previous scripts. */
replicationScriptCacheFlush();
if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
listIter li;
listRewind(server.slaves,&li);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE failed");
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START)
freeClient(slave);
}
}
}
}
/* ----------------------------------- SLAVE -------------------------------- */
/* Abort the async download of the bulk dataset while SYNC-ing with master */
void replicationAbortSyncTransfer(void) {
redisAssert(server.repl_state == REDIS_REPL_TRANSFER);
aeDeleteFileEvent(server.el,server.repl_transfer_s,AE_READABLE);
close(server.repl_transfer_s);
close(server.repl_transfer_fd);
unlink(server.repl_transfer_tmpfile);
zfree(server.repl_transfer_tmpfile);
server.repl_state = REDIS_REPL_CONNECT;
}
/* Avoid the master to detect the slave is timing out while loading the
* RDB file in initial synchronization. We send a single newline character
* that is valid protocol but is guaranteed to either be sent entierly or
* not, since the byte is indivisible.
*
* The function is called in two contexts: while we flush the current
* data with emptyDb(), and while we load the new data received as an
* RDB file from the master. */
void replicationSendNewlineToMaster(void) {
static time_t newline_sent;
if (time(NULL) != newline_sent) {
newline_sent = time(NULL);
if (write(server.repl_transfer_s,"\n",1) == -1) {
/* Pinging back in this stage is best-effort. */
}
}
}
/* Callback used by emptyDb() while flushing away old data to load
* the new dataset received by the master. */
void replicationEmptyDbCallback(void *privdata) {
REDIS_NOTUSED(privdata);
replicationSendNewlineToMaster();
}
/* Asynchronously read the SYNC payload we receive from a master */
#define REPL_MAX_WRITTEN_BEFORE_FSYNC (1024*1024*8) /* 8 MB */
void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
char buf[4096];
ssize_t nread, readlen;
off_t left;
REDIS_NOTUSED(el);
REDIS_NOTUSED(privdata);
REDIS_NOTUSED(mask);
/* If repl_transfer_size == -1 we still have to read the bulk length
* from the master reply. */
if (server.repl_transfer_size == -1) {
if (syncReadLine(fd,buf,1024,server.repl_syncio_timeout*1000) == -1) {
redisLog(REDIS_WARNING,
"I/O error reading bulk count from MASTER: %s",
strerror(errno));
goto error;
}
if (buf[0] == '-') {
redisLog(REDIS_WARNING,
"MASTER aborted replication with an error: %s",
buf+1);
goto error;
} else if (buf[0] == '\0') {
/* At this stage just a newline works as a PING in order to take
* the connection live. So we refresh our last interaction
* timestamp. */
server.repl_transfer_lastio = server.unixtime;
return;
} else if (buf[0] != '$') {
redisLog(REDIS_WARNING,"Bad protocol from MASTER, the first byte is not '$' (we received '%s'), are you sure the host and port are right?", buf);
goto error;
}
server.repl_transfer_size = strtol(buf+1,NULL,10);
redisLog(REDIS_NOTICE,
"MASTER <-> SLAVE sync: receiving %lld bytes from master",
(long long) server.repl_transfer_size);
return;
}
/* Read bulk data */
left = server.repl_transfer_size - server.repl_transfer_read;
readlen = (left < (signed)sizeof(buf)) ? left : (signed)sizeof(buf);
nread = read(fd,buf,readlen);
if (nread <= 0) {
redisLog(REDIS_WARNING,"I/O error trying to sync with MASTER: %s",
(nread == -1) ? strerror(errno) : "connection lost");
replicationAbortSyncTransfer();
return;
}
server.repl_transfer_lastio = server.unixtime;
if (write(server.repl_transfer_fd,buf,nread) != nread) {
redisLog(REDIS_WARNING,"Write error or short write writing to the DB dump file needed for MASTER <-> SLAVE synchronization: %s", strerror(errno));
goto error;
}
server.repl_transfer_read += nread;
/* Sync data on disk from time to time, otherwise at the end of the transfer
* we may suffer a big delay as the memory buffers are copied into the
* actual disk. */
if (server.repl_transfer_read >=
server.repl_transfer_last_fsync_off + REPL_MAX_WRITTEN_BEFORE_FSYNC)
{
off_t sync_size = server.repl_transfer_read -
server.repl_transfer_last_fsync_off;
rdb_fsync_range(server.repl_transfer_fd,
server.repl_transfer_last_fsync_off, sync_size);
server.repl_transfer_last_fsync_off += sync_size;
}
/* Check if the transfer is now complete */
if (server.repl_transfer_read == server.repl_transfer_size) {
if (rename(server.repl_transfer_tmpfile,server.rdb_filename) == -1) {
redisLog(REDIS_WARNING,"Failed trying to rename the temp DB into dump.rdb in MASTER <-> SLAVE synchronization: %s", strerror(errno));
replicationAbortSyncTransfer();
return;
}
redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Flushing old data");
signalFlushedDb(-1);
emptyDb(replicationEmptyDbCallback);
/* Before loading the DB into memory we need to delete the readable
* handler, otherwise it will get called recursively since
* rdbLoad() will call the event loop to process events from time to
* time for non blocking loading. */
aeDeleteFileEvent(server.el,server.repl_transfer_s,AE_READABLE);
redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Loading DB in memory");
if (rdbLoad(server.rdb_filename) != REDIS_OK) {
redisLog(REDIS_WARNING,"Failed trying to load the MASTER synchronization DB from disk");
replicationAbortSyncTransfer();
return;
}
/* Final setup of the connected slave <- master link */
zfree(server.repl_transfer_tmpfile);
close(server.repl_transfer_fd);
server.master = createClient(server.repl_transfer_s);
server.master->flags |= REDIS_MASTER;
server.master->authenticated = 1;
server.repl_state = REDIS_REPL_CONNECTED;
server.master->reploff = server.repl_master_initial_offset;
memcpy(server.master->replrunid, server.repl_master_runid,
sizeof(server.repl_master_runid));
/* If master offset is set to -1, this master is old and is not
* PSYNC capable, so we flag it accordingly. */
if (server.master->reploff == -1)
server.master->flags |= REDIS_PRE_PSYNC;
redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Finished with success");
/* Restart the AOF subsystem now that we finished the sync. This
* will trigger an AOF rewrite, and when done will start appending
* to the new file. */
if (server.aof_state != REDIS_AOF_OFF) {
int retry = 10;
stopAppendOnly();
while (retry-- && startAppendOnly() == REDIS_ERR) {
redisLog(REDIS_WARNING,"Failed enabling the AOF after successful master synchronization! Trying it again in one second.");
sleep(1);
}
if (!retry) {
redisLog(REDIS_WARNING,"FATAL: this slave instance finished the synchronization with its master, but the AOF can't be turned on. Exiting now.");
exit(1);
}
}
}
return;
error:
replicationAbortSyncTransfer();
return;
}
/* Send a synchronous command to the master. Used to send AUTH and
* REPLCONF commands before starting the replication with SYNC.
*
* The command returns an sds string representing the result of the
* operation. On error the first byte is a "-".
*/
char *sendSynchronousCommand(int fd, ...) {
va_list ap;
sds cmd = sdsempty();
char *arg, buf[256];
/* Create the command to send to the master, we use simple inline
* protocol for simplicity as currently we only send simple strings. */
va_start(ap,fd);
while(1) {
arg = va_arg(ap, char*);
if (arg == NULL) break;
if (sdslen(cmd) != 0) cmd = sdscatlen(cmd," ",1);
cmd = sdscat(cmd,arg);
}
cmd = sdscatlen(cmd,"\r\n",2);
/* Transfer command to the server. */
if (syncWrite(fd,cmd,sdslen(cmd),server.repl_syncio_timeout*1000) == -1) {
sdsfree(cmd);
return sdscatprintf(sdsempty(),"-Writing to master: %s",
strerror(errno));
}
sdsfree(cmd);
/* Read the reply from the server. */
if (syncReadLine(fd,buf,sizeof(buf),server.repl_syncio_timeout*1000) == -1)
{
return sdscatprintf(sdsempty(),"-Reading from master: %s",
strerror(errno));
}
return sdsnew(buf);
}
/* Try a partial resynchronization with the master if we are about to reconnect.
* If there is no cached master structure, at least try to issue a
* "PSYNC ? -1" command in order to trigger a full resync using the PSYNC
* command in order to obtain the master run id and the master replication
* global offset.
*
* This function is designed to be called from syncWithMaster(), so the
* following assumptions are made:
*
* 1) We pass the function an already connected socket "fd".
* 2) This function does not close the file descriptor "fd". However in case
* of successful partial resynchronization, the function will reuse
* 'fd' as file descriptor of the server.master client structure.
*
* The function returns:
*
* PSYNC_CONTINUE: If the PSYNC command succeded and we can continue.
* PSYNC_FULLRESYNC: If PSYNC is supported but a full resync is needed.
* In this case the master run_id and global replication
* offset is saved.
* PSYNC_NOT_SUPPORTED: If the server does not understand PSYNC at all and
* the caller should fall back to SYNC.
*/
#define PSYNC_CONTINUE 0
#define PSYNC_FULLRESYNC 1
#define PSYNC_NOT_SUPPORTED 2
int slaveTryPartialResynchronization(int fd) {
char *psync_runid;
char psync_offset[32];
sds reply;
/* Initially set repl_master_initial_offset to -1 to mark the current
* master run_id and offset as not valid. Later if we'll be able to do
* a FULL resync using the PSYNC command we'll set the offset at the
* right value, so that this information will be propagated to the
* client structure representing the master into server.master. */
server.repl_master_initial_offset = -1;
if (server.cached_master) {
psync_runid = server.cached_master->replrunid;
snprintf(psync_offset,sizeof(psync_offset),"%lld", server.cached_master->reploff+1);
redisLog(REDIS_NOTICE,"Trying a partial resynchronization (request %s:%s).", psync_runid, psync_offset);
} else {
redisLog(REDIS_NOTICE,"Partial resynchronization not possible (no cached master)");
psync_runid = "?";
memcpy(psync_offset,"-1",3);
}
/* Issue the PSYNC command */
reply = sendSynchronousCommand(fd,"PSYNC",psync_runid,psync_offset,NULL);
if (!strncmp(reply,"+FULLRESYNC",11)) {
char *runid = NULL, *offset = NULL;
/* FULL RESYNC, parse the reply in order to extract the run id
* and the replication offset. */
runid = strchr(reply,' ');
if (runid) {
runid++;
offset = strchr(runid,' ');
if (offset) offset++;
}
if (!runid || !offset || (offset-runid-1) != REDIS_RUN_ID_SIZE) {
redisLog(REDIS_WARNING,
"Master replied with wrong +FULLRESYNC syntax.");
/* This is an unexpected condition, actually the +FULLRESYNC
* reply means that the master supports PSYNC, but the reply
* format seems wrong. To stay safe we blank the master
* runid to make sure next PSYNCs will fail. */
memset(server.repl_master_runid,0,REDIS_RUN_ID_SIZE+1);
} else {
memcpy(server.repl_master_runid, runid, offset-runid-1);
server.repl_master_runid[REDIS_RUN_ID_SIZE] = '\0';
server.repl_master_initial_offset = strtoll(offset,NULL,10);
redisLog(REDIS_NOTICE,"Full resync from master: %s:%lld",
server.repl_master_runid,
server.repl_master_initial_offset);
}
/* We are going to full resync, discard the cached master structure. */
replicationDiscardCachedMaster();
sdsfree(reply);
return PSYNC_FULLRESYNC;
}