-
Notifications
You must be signed in to change notification settings - Fork 600
/
Copy pathaof.cpp
2133 lines (1909 loc) · 82.7 KB
/
aof.cpp
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 "bio.h"
#include "rio.h"
#include <signal.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/wait.h>
#include <sys/param.h>
void aofUpdateCurrentSize(void);
void aofClosePipes(void);
/* ----------------------------------------------------------------------------
* AOF rewrite buffer implementation.
*
* The following code implement a simple buffer used in order to accumulate
* changes while the background process is rewriting the AOF file.
*
* We only need to append, but can't just use realloc with a large block
* because 'huge' reallocs are not always handled as one could expect
* (via remapping of pages at OS level) but may involve copying data.
*
* For this reason we use a list of blocks, every block is
* AOF_RW_BUF_BLOCK_SIZE bytes.
* ------------------------------------------------------------------------- */
#define AOF_RW_BUF_BLOCK_SIZE (1024*1024*10) /* 10 MB per block */
typedef struct aofrwblock {
unsigned long used, free;
char buf[AOF_RW_BUF_BLOCK_SIZE];
} aofrwblock;
/* This function free the old AOF rewrite buffer if needed, and initialize
* a fresh new one. It tests for g_pserver->aof_rewrite_buf_blocks equal to NULL
* so can be used for the first initialization as well. */
void aofRewriteBufferReset(void) {
if (g_pserver->aof_rewrite_buf_blocks)
listRelease(g_pserver->aof_rewrite_buf_blocks);
g_pserver->aof_rewrite_buf_blocks = listCreate();
listSetFreeMethod(g_pserver->aof_rewrite_buf_blocks,zfree);
}
/* Return the current size of the AOF rewrite buffer. */
unsigned long aofRewriteBufferSize(void) {
listNode *ln;
listIter li;
unsigned long size = 0;
listRewind(g_pserver->aof_rewrite_buf_blocks,&li);
while((ln = listNext(&li))) {
aofrwblock *block = (aofrwblock*)listNodeValue(ln);
size += block->used;
}
return size;
}
/* Event handler used to send data to the child process doing the AOF
* rewrite. We send pieces of our AOF differences buffer so that the final
* write when the child finishes the rewrite will be small. */
void aofChildWriteDiffData(aeEventLoop *el, int fd, void *privdata, int mask) {
listNode *ln;
aofrwblock *block;
ssize_t nwritten;
serverAssert(GlobalLocksAcquired());
serverAssert(el == g_pserver->rgthreadvar[IDX_EVENT_LOOP_MAIN].el); // MUST run on main thread
UNUSED(el);
UNUSED(fd);
UNUSED(privdata);
UNUSED(mask);
while(1) {
ln = listFirst(g_pserver->aof_rewrite_buf_blocks);
block = (aofrwblock*)(ln ? ln->value : NULL);
if (g_pserver->aof_stop_sending_diff || !block) {
aeDeleteFileEvent(el,g_pserver->aof_pipe_write_data_to_child,
AE_WRITABLE);
return;
}
if (block->used > 0) {
nwritten = write(g_pserver->aof_pipe_write_data_to_child,
block->buf,block->used);
if (nwritten <= 0) return;
memmove(block->buf,block->buf+nwritten,block->used-nwritten);
block->used -= nwritten;
block->free += nwritten;
}
if (block->used == 0) listDelNode(g_pserver->aof_rewrite_buf_blocks,ln);
}
}
void installAofRewriteEvent()
{
serverTL->fRetrySetAofEvent = false;
if (!g_pserver->aof_rewrite_pending) {
g_pserver->aof_rewrite_pending = true;
int res = aePostFunction(g_pserver->rgthreadvar[IDX_EVENT_LOOP_MAIN].el, [] {
g_pserver->aof_rewrite_pending = false;
if (!g_pserver->aof_stop_sending_diff && g_pserver->aof_pipe_write_data_to_child >= 0)
aeCreateFileEvent(g_pserver->rgthreadvar[IDX_EVENT_LOOP_MAIN].el, g_pserver->aof_pipe_write_data_to_child, AE_WRITABLE, aofChildWriteDiffData, NULL);
});
if (res != AE_OK)
serverTL->fRetrySetAofEvent = true;
}
}
/* Append data to the AOF rewrite buffer, allocating new blocks if needed. */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) {
listNode *ln = listLast(g_pserver->aof_rewrite_buf_blocks);
aofrwblock *block = (aofrwblock*)(ln ? ln->value : NULL);
while(len) {
/* If we already got at least an allocated block, try appending
* at least some piece into it. */
if (block) {
unsigned long thislen = (block->free < len) ? block->free : len;
if (thislen) { /* The current block is not already full. */
memcpy(block->buf+block->used, s, thislen);
block->used += thislen;
block->free -= thislen;
s += thislen;
len -= thislen;
}
}
if (len) { /* First block to allocate, or need another block. */
int numblocks;
block = (aofrwblock*)zmalloc(sizeof(*block), MALLOC_LOCAL);
block->free = AOF_RW_BUF_BLOCK_SIZE;
block->used = 0;
listAddNodeTail(g_pserver->aof_rewrite_buf_blocks,block);
/* Log every time we cross more 10 or 100 blocks, respectively
* as a notice or warning. */
numblocks = listLength(g_pserver->aof_rewrite_buf_blocks);
if (((numblocks+1) % 10) == 0) {
int level = ((numblocks+1) % 100) == 0 ? LL_WARNING :
LL_NOTICE;
serverLog(level,"Background AOF buffer size: %lu MB",
aofRewriteBufferSize()/(1024*1024));
}
}
}
/* Install a file event to send data to the rewrite child if there is
* not one already. */
installAofRewriteEvent();
}
/* Write the buffer (possibly composed of multiple blocks) into the specified
* fd. If a short write or any other error happens -1 is returned,
* otherwise the number of bytes written is returned. */
ssize_t aofRewriteBufferWrite(int fd) {
listNode *ln;
listIter li;
ssize_t count = 0;
listRewind(g_pserver->aof_rewrite_buf_blocks,&li);
while((ln = listNext(&li))) {
aofrwblock *block = (aofrwblock*)listNodeValue(ln);
ssize_t nwritten;
if (block->used) {
nwritten = write(fd,block->buf,block->used);
if (nwritten != (ssize_t)block->used) {
if (nwritten == 0) errno = EIO;
return -1;
}
count += nwritten;
}
}
return count;
}
/* ----------------------------------------------------------------------------
* AOF file implementation
* ------------------------------------------------------------------------- */
/* Return true if an AOf fsync is currently already in progress in a
* BIO thread. */
int aofFsyncInProgress(void) {
return bioPendingJobsOfType(BIO_AOF_FSYNC) != 0;
}
/* Starts a background task that performs fsync() against the specified
* file descriptor (the one of the AOF file) in another thread. */
void aof_background_fsync(int fd) {
bioCreateFsyncJob(fd);
}
/* Kills an AOFRW child process if exists */
void killAppendOnlyChild(void) {
int statloc;
/* No AOFRW child? return. */
if (g_pserver->child_type != CHILD_TYPE_AOF) return;
/* Kill AOFRW child, wait for child exit. */
serverLog(LL_NOTICE,"Killing running AOF rewrite child: %ld",
(long) g_pserver->child_pid);
if (kill(g_pserver->child_pid,SIGUSR1) != -1) {
while(waitpid(-1, &statloc, 0) != g_pserver->child_pid);
}
/* Reset the buffer accumulating changes while the child saves. */
aofRewriteBufferReset();
aofRemoveTempFile(g_pserver->child_pid);
resetChildState();
g_pserver->aof_rewrite_time_start = -1;
/* Close pipes used for IPC between the two processes. */
aofClosePipes();
}
/* Called when the user switches from "appendonly yes" to "appendonly no"
* at runtime using the CONFIG command. */
void stopAppendOnly(void) {
serverAssert(g_pserver->aof_state != AOF_OFF);
flushAppendOnlyFile(1);
if (redis_fsync(g_pserver->aof_fd) == -1) {
serverLog(LL_WARNING,"Fail to fsync the AOF file: %s",strerror(errno));
} else {
g_pserver->aof_fsync_offset = g_pserver->aof_current_size;
g_pserver->aof_last_fsync = g_pserver->unixtime;
}
close(g_pserver->aof_fd);
g_pserver->aof_fd = -1;
g_pserver->aof_selected_db = -1;
g_pserver->aof_state = AOF_OFF;
g_pserver->aof_rewrite_scheduled = 0;
killAppendOnlyChild();
sdsfree(g_pserver->aof_buf);
g_pserver->aof_buf = sdsempty();
}
/* Called when the user switches from "appendonly no" to "appendonly yes"
* at runtime using the CONFIG command. */
int startAppendOnly(void) {
char cwd[MAXPATHLEN]; /* Current working dir path for error messages. */
int newfd;
newfd = open(g_pserver->aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
serverAssert(g_pserver->aof_state == AOF_OFF);
if (newfd == -1) {
char *cwdp = getcwd(cwd,MAXPATHLEN);
serverLog(LL_WARNING,
"KeyDB needs to enable the AOF but can't open the "
"append only file %s (in server root dir %s): %s",
g_pserver->aof_filename,
cwdp ? cwdp : "unknown",
strerror(errno));
return C_ERR;
}
if (hasActiveChildProcessOrBGSave() && g_pserver->child_type != CHILD_TYPE_AOF) {
g_pserver->aof_rewrite_scheduled = 1;
serverLog(LL_WARNING,"AOF was enabled but there is already another background operation. An AOF background was scheduled to start when possible.");
} else {
/* If there is a pending AOF rewrite, we need to switch it off and
* start a new one: the old one cannot be reused because it is not
* accumulating the AOF buffer. */
if (g_pserver->child_type == CHILD_TYPE_AOF) {
serverLog(LL_WARNING,"AOF was enabled but there is already an AOF rewriting in background. Stopping background AOF and starting a rewrite now.");
killAppendOnlyChild();
}
if (rewriteAppendOnlyFileBackground() == C_ERR) {
close(newfd);
serverLog(LL_WARNING,"KeyDB needs to enable the AOF but can't trigger a background AOF rewrite operation. Check the above logs for more info about the error.");
return C_ERR;
}
}
/* We correctly switched on AOF, now wait for the rewrite to be complete
* in order to append data on disk. */
g_pserver->aof_state = AOF_WAIT_REWRITE;
g_pserver->aof_last_fsync = g_pserver->unixtime;
g_pserver->aof_fd = newfd;
/* If AOF fsync error in bio job, we just ignore it and log the event. */
int aof_bio_fsync_status;
atomicGet(g_pserver->aof_bio_fsync_status, aof_bio_fsync_status);
if (aof_bio_fsync_status == C_ERR) {
serverLog(LL_WARNING,
"AOF reopen, just ignore the AOF fsync error in bio job");
atomicSet(g_pserver->aof_bio_fsync_status,C_OK);
}
/* If AOF was in error state, we just ignore it and log the event. */
if (g_pserver->aof_last_write_status == C_ERR) {
serverLog(LL_WARNING,"AOF reopen, just ignore the last error.");
g_pserver->aof_last_write_status = C_OK;
}
return C_OK;
}
/* This is a wrapper to the write syscall in order to retry on short writes
* or if the syscall gets interrupted. It could look strange that we retry
* on short writes given that we are writing to a block device: normally if
* the first call is short, there is a end-of-space condition, so the next
* is likely to fail. However apparently in modern systems this is no longer
* true, and in general it looks just more resilient to retry the write. If
* there is an actual error condition we'll get it at the next try. */
ssize_t aofWrite(int fd, const char *buf, size_t len) {
ssize_t nwritten = 0, totwritten = 0;
while(len) {
nwritten = write(fd, buf, len);
if (nwritten < 0) {
if (errno == EINTR) continue;
return totwritten ? totwritten : -1;
}
len -= nwritten;
buf += nwritten;
totwritten += nwritten;
}
return totwritten;
}
/* Write the append only file buffer on disk.
*
* Since we are required to write the AOF before replying to the client,
* and the only way the client socket can get a write is entering when the
* the event loop, we accumulate all the AOF writes in a memory
* buffer and write it on disk using this function just before entering
* the event loop again.
*
* About the 'force' argument:
*
* When the fsync policy is set to 'everysec' we may delay the flush if there
* is still an fsync() going on in the background thread, since for instance
* on Linux write(2) will be blocked by the background fsync anyway.
* When this happens we remember that there is some aof buffer to be
* flushed ASAP, and will try to do that in the serverCron() function.
*
* However if force is set to 1 we'll write regardless of the background
* fsync. */
#define AOF_WRITE_LOG_ERROR_RATE 30 /* Seconds between errors logging. */
void flushAppendOnlyFile(int force) {
ssize_t nwritten;
int sync_in_progress = 0;
mstime_t latency;
if (serverTL->fRetrySetAofEvent)
installAofRewriteEvent();
if (sdslen(g_pserver->aof_buf) == 0) {
/* Check if we need to do fsync even the aof buffer is empty,
* because previously in AOF_FSYNC_EVERYSEC mode, fsync is
* called only when aof buffer is not empty, so if users
* stop write commands before fsync called in one second,
* the data in page cache cannot be flushed in time. */
if (g_pserver->aof_fsync == AOF_FSYNC_EVERYSEC &&
g_pserver->aof_fsync_offset != g_pserver->aof_current_size &&
g_pserver->unixtime > g_pserver->aof_last_fsync &&
!(sync_in_progress = aofFsyncInProgress())) {
goto try_fsync;
} else {
return;
}
}
if (g_pserver->aof_fsync == AOF_FSYNC_EVERYSEC)
sync_in_progress = aofFsyncInProgress();
if (g_pserver->aof_fsync == AOF_FSYNC_EVERYSEC && !force) {
/* With this append fsync policy we do background fsyncing.
* If the fsync is still in progress we can try to delay
* the write for a couple of seconds. */
if (sync_in_progress) {
if (g_pserver->aof_flush_postponed_start == 0) {
/* No previous write postponing, remember that we are
* postponing the flush and return. */
g_pserver->aof_flush_postponed_start = g_pserver->unixtime;
return;
} else if (g_pserver->unixtime - g_pserver->aof_flush_postponed_start < 2) {
/* We were already waiting for fsync to finish, but for less
* than two seconds this is still ok. Postpone again. */
return;
}
/* Otherwise fall trough, and go write since we can't wait
* over two seconds. */
g_pserver->aof_delayed_fsync++;
serverLog(LL_NOTICE,"Asynchronous AOF fsync is taking too long (disk is busy?). Writing the AOF buffer without waiting for fsync to complete, this may slow down KeyDB.");
}
}
/* We want to perform a single write. This should be guaranteed atomic
* at least if the filesystem we are writing is a real physical one.
* While this will save us against the server being killed I don't think
* there is much to do about the whole server stopping for power problems
* or alike */
if (g_pserver->aof_flush_sleep && sdslen(g_pserver->aof_buf)) {
usleep(g_pserver->aof_flush_sleep);
}
latencyStartMonitor(latency);
nwritten = aofWrite(g_pserver->aof_fd,g_pserver->aof_buf,sdslen(g_pserver->aof_buf));
latencyEndMonitor(latency);
/* We want to capture different events for delayed writes:
* when the delay happens with a pending fsync, or with a saving child
* active, and when the above two conditions are missing.
* We also use an additional event name to save all samples which is
* useful for graphing / monitoring purposes. */
if (sync_in_progress) {
latencyAddSampleIfNeeded("aof-write-pending-fsync",latency);
} else if (hasActiveChildProcessOrBGSave()) {
latencyAddSampleIfNeeded("aof-write-active-child",latency);
} else {
latencyAddSampleIfNeeded("aof-write-alone",latency);
}
latencyAddSampleIfNeeded("aof-write",latency);
/* We performed the write so reset the postponed flush sentinel to zero. */
g_pserver->aof_flush_postponed_start = 0;
if (nwritten != (ssize_t)sdslen(g_pserver->aof_buf)) {
static time_t last_write_error_log = 0;
int can_log = 0;
/* Limit logging rate to 1 line per AOF_WRITE_LOG_ERROR_RATE seconds. */
if ((g_pserver->unixtime - last_write_error_log) > AOF_WRITE_LOG_ERROR_RATE) {
can_log = 1;
last_write_error_log = g_pserver->unixtime;
}
/* Log the AOF write error and record the error code. */
if (nwritten == -1) {
if (can_log) {
serverLog(LL_WARNING,"Error writing to the AOF file: %s",
strerror(errno));
g_pserver->aof_last_write_errno = errno;
}
} else {
if (can_log) {
serverLog(LL_WARNING,"Short write while writing to "
"the AOF file: (nwritten=%lld, "
"expected=%lld)",
(long long)nwritten,
(long long)sdslen(g_pserver->aof_buf));
}
if (ftruncate(g_pserver->aof_fd, g_pserver->aof_current_size) == -1) {
if (can_log) {
serverLog(LL_WARNING, "Could not remove short write "
"from the append-only file. KeyDB may refuse "
"to load the AOF the next time it starts. "
"ftruncate: %s", strerror(errno));
}
} else {
/* If the ftruncate() succeeded we can set nwritten to
* -1 since there is no longer partial data into the AOF. */
nwritten = -1;
}
g_pserver->aof_last_write_errno = ENOSPC;
}
/* Handle the AOF write error. */
if (g_pserver->aof_fsync == AOF_FSYNC_ALWAYS) {
/* We can't recover when the fsync policy is ALWAYS since the reply
* for the client is already in the output buffers (both writes and
* reads), and the changes to the db can't be rolled back. Since we
* have a contract with the user that on acknowledged or observed
* writes are is synced on disk, we must exit. */
serverLog(LL_WARNING,"Can't recover from AOF write error when the AOF fsync policy is 'always'. Exiting...");
exit(1);
} else {
/* Recover from failed write leaving data into the buffer. However
* set an error to stop accepting writes as long as the error
* condition is not cleared. */
g_pserver->aof_last_write_status = C_ERR;
/* Trim the sds buffer if there was a partial write, and there
* was no way to undo it with ftruncate(2). */
if (nwritten > 0) {
g_pserver->aof_current_size += nwritten;
sdsrange(g_pserver->aof_buf,nwritten,-1);
}
return; /* We'll try again on the next call... */
}
} else {
/* Successful write(2). If AOF was in error state, restore the
* OK state and log the event. */
if (g_pserver->aof_last_write_status == C_ERR) {
serverLog(LL_WARNING,
"AOF write error looks solved, KeyDB can write again.");
g_pserver->aof_last_write_status = C_OK;
}
}
g_pserver->aof_current_size += nwritten;
/* Re-use AOF buffer when it is small enough. The maximum comes from the
* arena size of 4k minus some overhead (but is otherwise arbitrary). */
if ((sdslen(g_pserver->aof_buf)+sdsavail(g_pserver->aof_buf)) < 4000) {
sdsclear(g_pserver->aof_buf);
} else {
sdsfree(g_pserver->aof_buf);
g_pserver->aof_buf = sdsempty();
}
try_fsync:
/* Don't fsync if no-appendfsync-on-rewrite is set to yes and there are
* children doing I/O in the background. */
if (g_pserver->aof_no_fsync_on_rewrite && hasActiveChildProcessOrBGSave())
return;
/* Perform the fsync if needed. */
if (g_pserver->aof_fsync == AOF_FSYNC_ALWAYS) {
/* redis_fsync is defined as fdatasync() for Linux in order to avoid
* flushing metadata. */
latencyStartMonitor(latency);
/* Let's try to get this data on the disk. To guarantee data safe when
* the AOF fsync policy is 'always', we should exit if failed to fsync
* AOF (see comment next to the exit(1) after write error above). */
if (redis_fsync(g_pserver->aof_fd) == -1) {
serverLog(LL_WARNING,"Can't persist AOF for fsync error when the "
"AOF fsync policy is 'always': %s. Exiting...", strerror(errno));
exit(1);
}
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("aof-fsync-always",latency);
g_pserver->aof_fsync_offset = g_pserver->aof_current_size;
g_pserver->aof_last_fsync = g_pserver->unixtime;
} else if ((g_pserver->aof_fsync == AOF_FSYNC_EVERYSEC &&
g_pserver->unixtime > g_pserver->aof_last_fsync)) {
if (!sync_in_progress) {
aof_background_fsync(g_pserver->aof_fd);
g_pserver->aof_fsync_offset = g_pserver->aof_current_size;
}
g_pserver->aof_last_fsync = g_pserver->unixtime;
}
}
sds catAppendOnlyGenericCommand(sds dst, int argc, robj **argv) {
char buf[32];
int len, j;
robj *o;
buf[0] = '*';
len = 1+ll2string(buf+1,sizeof(buf)-1,argc);
buf[len++] = '\r';
buf[len++] = '\n';
dst = sdscatlen(dst,buf,len);
for (j = 0; j < argc; j++) {
if (sdsEncodedObject(argv[j]))
o = argv[j];
else
o = getDecodedObject(argv[j]);
buf[0] = '$';
len = 1+ll2string(buf+1,sizeof(buf)-1,sdslen(szFromObj(o)));
buf[len++] = '\r';
buf[len++] = '\n';
dst = sdscatlen(dst,buf,len);
dst = sdscatlen(dst,ptrFromObj(o),sdslen(szFromObj(o)));
dst = sdscatlen(dst,"\r\n",2);
if (o != argv[j])
decrRefCount(o);
}
return dst;
}
/* Create the sds representation of a PEXPIREAT command, using
* 'seconds' as time to live and 'cmd' to understand what command
* we are translating into a PEXPIREAT.
*
* This command is used in order to translate EXPIRE and PEXPIRE commands
* into PEXPIREAT command so that we retain precision in the append only
* file, and the time is always absolute and not relative. */
sds catAppendOnlyExpireAtCommand(sds buf, struct redisCommand *cmd, robj *key, robj *seconds) {
long long when;
robj *argv[3];
/* Make sure we can use strtoll */
seconds = getDecodedObject(seconds);
when = strtoll(szFromObj(seconds),NULL,10);
/* Convert argument into milliseconds for EXPIRE, SETEX, EXPIREAT */
if (cmd->proc == expireCommand || cmd->proc == setexCommand ||
cmd->proc == expireatCommand)
{
when *= 1000;
}
/* Convert into absolute time for EXPIRE, PEXPIRE, SETEX, PSETEX */
if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
cmd->proc == setexCommand || cmd->proc == psetexCommand)
{
when += mstime();
}
decrRefCount(seconds);
argv[0] = shared.pexpireat;
argv[1] = key;
argv[2] = createStringObjectFromLongLong(when);
buf = catAppendOnlyGenericCommand(buf, 3, argv);
decrRefCount(argv[2]);
return buf;
}
sds catAppendOnlyExpireMemberAtCommand(sds buf, struct redisCommand *cmd, robj **argv, const size_t argc) {
long long when = 0;
int unit = UNIT_SECONDS;
bool fAbsolute = false;
if (cmd->proc == expireMemberCommand) {
if (getLongLongFromObject(argv[3], &when) != C_OK)
serverPanic("propogating invalid EXPIREMEMBER command");
if (argc == 5) {
unit = parseUnitString(szFromObj(argv[4]));
}
} else if (cmd->proc == expireMemberAtCommand) {
if (getLongLongFromObject(argv[3], &when) != C_OK)
serverPanic("propogating invalid EXPIREMEMBERAT command");
fAbsolute = true;
} else if (cmd->proc == pexpireMemberAtCommand) {
if (getLongLongFromObject(argv[3], &when) != C_OK)
serverPanic("propogating invalid PEXPIREMEMBERAT command");
fAbsolute = true;
unit = UNIT_MILLISECONDS;
} else {
serverPanic("Unknown expiremember command");
}
switch (unit)
{
case UNIT_SECONDS:
when *= 1000;
break;
case UNIT_MILLISECONDS:
break;
}
if (!fAbsolute)
when += mstime();
robj *argvNew[4];
argvNew[0] = shared.pexpirememberat;
argvNew[1] = argv[1];
argvNew[2] = argv[2];
argvNew[3] = createStringObjectFromLongLong(when);
buf = catAppendOnlyGenericCommand(buf, 4, argvNew);
decrRefCount(argvNew[0]);
decrRefCount(argvNew[3]);
return buf;
}
sds catCommandForAofAndActiveReplication(sds buf, struct redisCommand *cmd, robj **argv, int argc)
{
if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
cmd->proc == expireatCommand) {
/* Translate EXPIRE/PEXPIRE/EXPIREAT into PEXPIREAT */
buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
} else if (cmd->proc == setCommand && argc > 3) {
robj *pxarg = NULL;
/* When SET is used with EX/PX argument setGenericCommand propagates them with PX millisecond argument.
* So since the command arguments are re-written there, we can rely here on the index of PX being 3. */
if (!strcasecmp(szFromObj(argv[3]), "px")) {
pxarg = argv[4];
}
/* For AOF we convert SET key value relative time in milliseconds to SET key value absolute time in
* millisecond. Whenever the condition is true it implies that original SET has been transformed
* to SET PX with millisecond time argument so we do not need to worry about unit here.*/
if (pxarg) {
robj *millisecond = getDecodedObject(pxarg);
long long when = strtoll(szFromObj(millisecond),NULL,10);
when += mstime();
decrRefCount(millisecond);
robj *newargs[5];
newargs[0] = argv[0];
newargs[1] = argv[1];
newargs[2] = argv[2];
newargs[3] = shared.pxat;
newargs[4] = createStringObjectFromLongLong(when);
buf = catAppendOnlyGenericCommand(buf,5,newargs);
decrRefCount(newargs[4]);
} else {
buf = catAppendOnlyGenericCommand(buf,argc,argv);
}
} else if (cmd->proc == expireMemberCommand || cmd->proc == expireMemberAtCommand || cmd->proc == pexpireMemberAtCommand) {
/* Translate subkey expire commands to PEXPIREMEMBERAT */
buf = catAppendOnlyExpireMemberAtCommand(buf, cmd, argv, argc);
} else {
/* All the other commands don't need translation or need the
* same translation already operated in the command vector
* for the replication itself. */
buf = catAppendOnlyGenericCommand(buf,argc,argv);
}
return buf;
}
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
sds buf = sdsempty();
/* The DB this command was targeting is not the same as the last command
* we appended. To issue a SELECT command is needed. */
if (dictid != g_pserver->aof_selected_db) {
char seldb[64];
snprintf(seldb,sizeof(seldb),"%d",dictid);
buf = sdscatprintf(buf,"*2\r\n$6\r\nSELECT\r\n$%lu\r\n%s\r\n",
(unsigned long)strlen(seldb),seldb);
g_pserver->aof_selected_db = dictid;
}
buf = catCommandForAofAndActiveReplication(buf, cmd, argv, argc);
/* Append to the AOF buffer. This will be flushed on disk just before
* of re-entering the event loop, so before the client will get a
* positive reply about the operation performed. */
if (g_pserver->aof_state == AOF_ON)
g_pserver->aof_buf = sdscatlen(g_pserver->aof_buf,buf,sdslen(buf));
/* If a background append only file rewriting is in progress we want to
* accumulate the differences between the child DB and the current one
* in a buffer, so that when the child process will do its work we
* can append the differences to the new append only file. */
if (hasActiveChildProcess() && g_pserver->child_type == CHILD_TYPE_AOF)
aofRewriteBufferAppend((unsigned char*)buf,sdslen(buf));
sdsfree(buf);
}
/* ----------------------------------------------------------------------------
* AOF loading
* ------------------------------------------------------------------------- */
/* In Redis commands are always executed in the context of a client, so in
* order to load the append only file we need to create a fake client. */
struct client *createAOFClient(void) {
struct client *c = new client();
selectDb(c,0);
c->id = CLIENT_ID_AOF; /* So modules can identify it's the AOF client. */
c->conn = NULL;
c->iel = IDX_EVENT_LOOP_MAIN;
c->name = NULL;
c->querybuf = sdsempty();
c->querybuf_peak = 0;
c->argc = 0;
c->argv = NULL;
c->original_argc = 0;
c->original_argv = NULL;
c->bufpos = 0;
c->fPendingAsyncWrite = FALSE;
c->fPendingAsyncWriteHandler = FALSE;
/*
* The AOF client should never be blocked (unlike master
* replication connection).
* This is because blocking the AOF client might cause
* deadlock (because potentially no one will unblock it).
* Also, if the AOF client will be blocked just for
* background processing there is a chance that the
* command execution order will be violated.
*/
c->flags = CLIENT_DENY_BLOCKING;
c->btype = BLOCKED_NONE;
/* We set the fake client as a replica waiting for the synchronization
* so that Redis will not try to send replies to this client. */
c->replstate = SLAVE_STATE_WAIT_BGSAVE_START;
c->reply = listCreate();
c->reply_bytes = 0;
c->obuf_soft_limit_reached_time = 0;
c->watched_keys = listCreate();
c->peerid = NULL;
c->sockname = NULL;
c->resp = 2;
c->user = NULL;
c->mvccCheckpoint = 0;
listSetFreeMethod(c->reply,freeClientReplyValue);
listSetDupMethod(c->reply,dupClientReplyValue);
fastlock_init(&c->lock, "fake client");
fastlock_lock(&c->lock);
initClientMultiState(c);
return c;
}
void freeFakeClientArgv(struct client *c) {
int j;
for (j = 0; j < c->argc; j++)
decrRefCount(c->argv[j]);
zfree(c->argv);
c->argv_len_sumActive = 0;
}
void freeFakeClient(struct client *c) {
sdsfree(c->querybuf);
listRelease(c->reply);
listRelease(c->watched_keys);
freeClientMultiState(c);
freeClientOriginalArgv(c);
fastlock_unlock(&c->lock);
fastlock_free(&c->lock);
delete c;
}
/* Replay the append log file. On success C_OK is returned. On non fatal
* error (the append only file is zero-length) C_ERR is returned. On
* fatal error an error message is logged and the program exists. */
int loadAppendOnlyFile(char *filename) {
struct client *fakeClient;
FILE *fp = fopen(filename,"r");
struct redis_stat sb;
int old_aof_state = g_pserver->aof_state;
long loops = 0;
off_t valid_up_to = 0; /* Offset of latest well-formed command loaded. */
off_t valid_before_multi = 0; /* Offset before MULTI command loaded. */
serverAssert(serverTL != NULL); // This happens early in boot, ensure serverTL was setup
if (fp == NULL) {
serverLog(LL_WARNING,"Fatal error: can't open the append log file for reading: %s",strerror(errno));
exit(1);
}
/* Handle a zero-length AOF file as a special case. An empty AOF file
* is a valid AOF because an empty server with AOF enabled will create
* a zero length file at startup, that will remain like that if no write
* operation is received. */
if (fp && redis_fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {
g_pserver->aof_current_size = 0;
g_pserver->aof_fsync_offset = g_pserver->aof_current_size;
fclose(fp);
return C_ERR;
}
/* Temporarily disable AOF, to prevent EXEC from feeding a MULTI
* to the same file we're about to read. */
g_pserver->aof_state = AOF_OFF;
fakeClient = createAOFClient();
startLoadingFile(fp, filename, RDBFLAGS_AOF_PREAMBLE);
for (int idb = 0; idb < cserver.dbnum; ++idb)
{
g_pserver->db[idb]->trackChanges(true);
}
/* Check if this AOF file has an RDB preamble. In that case we need to
* load the RDB file and later continue loading the AOF tail. */
char sig[5]; /* "REDIS" */
if (fread(sig,1,5,fp) != 5 || memcmp(sig,"REDIS",5) != 0) {
/* No RDB preamble, seek back at 0 offset. */
if (fseek(fp,0,SEEK_SET) == -1) goto readerr;
} else {
/* RDB preamble. Pass loading the RDB functions. */
rio rdb;
rdbSaveInfo rsi;
serverLog(LL_NOTICE,"Reading RDB preamble from AOF file...");
if (fseek(fp,0,SEEK_SET) == -1) goto readerr;
rioInitWithFile(&rdb,fp);
if (rdbLoadRio(&rdb,RDBFLAGS_AOF_PREAMBLE,&rsi) != C_OK) {
serverLog(LL_WARNING,"Error reading the RDB preamble of the AOF file, AOF loading aborted");
goto readerr;
} else {
serverLog(LL_NOTICE,"Reading the remaining AOF tail...");
}
}
/* Read the actual AOF file, in REPL format, command by command. */
while(1) {
int argc, j;
unsigned long len;
robj **argv;
char buf[128];
sds argsds;
struct redisCommand *cmd;
/* Serve the clients from time to time */
if (!(loops++ % 1000)) {
loadingProgress(ftello(fp));
processEventsWhileBlocked(serverTL - g_pserver->rgthreadvar);
processModuleLoadingProgressEvent(1);
}
if (fgets(buf,sizeof(buf),fp) == NULL) {
if (feof(fp))
break;
else
goto readerr;
}
if (buf[0] != '*') goto fmterr;
if (buf[1] == '\0') goto readerr;
argc = atoi(buf+1);
if (argc < 1) goto fmterr;
/* Load the next command in the AOF as our fake client
* argv. */
argv = (robj**)zmalloc(sizeof(robj*)*argc, MALLOC_LOCAL);
fakeClient->argc = argc;
fakeClient->argv = argv;
for (j = 0; j < argc; j++) {
/* Parse the argument len. */
char *readres = fgets(buf,sizeof(buf),fp);
if (readres == NULL || buf[0] != '$') {
fakeClient->argc = j; /* Free up to j-1. */
freeFakeClientArgv(fakeClient);
if (readres == NULL)
goto readerr;
else
goto fmterr;
}
len = strtol(buf+1,NULL,10);
/* Read it into a string object. */
argsds = sdsnewlen(SDS_NOINIT,len);
if (len && fread(argsds,len,1,fp) == 0) {
sdsfree(argsds);
fakeClient->argc = j; /* Free up to j-1. */
freeFakeClientArgv(fakeClient);
goto readerr;
}
argv[j] = createObject(OBJ_STRING,argsds);
/* Discard CRLF. */
if (fread(buf,2,1,fp) == 0) {
fakeClient->argc = j+1; /* Free up to j. */
freeFakeClientArgv(fakeClient);
goto readerr;
}
}
/* Command lookup */
cmd = lookupCommand(szFromObj(argv[0]));
if (!cmd) {
serverLog(LL_WARNING,
"Unknown command '%s' reading the append only file",
(char*)ptrFromObj(argv[0]));
exit(1);
}
if (cmd == cserver.multiCommand) valid_before_multi = valid_up_to;
/* Run the command in the context of a fake client */
fakeClient->cmd = fakeClient->lastcmd = cmd;
if (fakeClient->flags & CLIENT_MULTI &&
fakeClient->cmd->proc != execCommand)
{
queueMultiCommand(fakeClient);
} else {
cmd->proc(fakeClient);
}
/* The fake client should not have a reply */
serverAssert(fakeClient->bufpos == 0 &&
listLength(fakeClient->reply) == 0);
/* The fake client should never get blocked */
serverAssert((fakeClient->flags & CLIENT_BLOCKED) == 0);
/* Clean up. Command code may have changed argv/argc so we use the
* argv/argc of the client instead of the local variables. */
freeFakeClientArgv(fakeClient);
fakeClient->cmd = NULL;
if (g_pserver->aof_load_truncated) valid_up_to = ftello(fp);
if (g_pserver->key_load_delay)
debugDelay(g_pserver->key_load_delay);
}