summaryrefslogtreecommitdiff
path: root/src/aof.c
blob: cbc0989d0e0955a5fd7cfe7aa6b3599547b235bf (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
/*
 * 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 server.aof_rewrite_buf_blocks equal to NULL
 * so can be used for the first initialization as well. */
void aofRewriteBufferReset(void) {
    if (server.aof_rewrite_buf_blocks)
        listRelease(server.aof_rewrite_buf_blocks);

    server.aof_rewrite_buf_blocks = listCreate();
    listSetFreeMethod(server.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(server.aof_rewrite_buf_blocks,&li);
    while((ln = listNext(&li))) {
        aofrwblock *block = 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;
    UNUSED(el);
    UNUSED(fd);
    UNUSED(privdata);
    UNUSED(mask);

    while(1) {
        ln = listFirst(server.aof_rewrite_buf_blocks);
        block = ln ? ln->value : NULL;
        if (server.aof_stop_sending_diff || !block) {
            aeDeleteFileEvent(server.el,server.aof_pipe_write_data_to_child,
                              AE_WRITABLE);
            return;
        }
        if (block->used > 0) {
            nwritten = write(server.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(server.aof_rewrite_buf_blocks,ln);
    }
}

/* Append data to the AOF rewrite buffer, allocating new blocks if needed. */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) {
    listNode *ln = listLast(server.aof_rewrite_buf_blocks);
    aofrwblock *block = 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 = zmalloc(sizeof(*block));
            block->free = AOF_RW_BUF_BLOCK_SIZE;
            block->used = 0;
            listAddNodeTail(server.aof_rewrite_buf_blocks,block);

            /* Log every time we cross more 10 or 100 blocks, respectively
             * as a notice or warning. */
            numblocks = listLength(server.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. */
    if (aeGetFileEvents(server.el,server.aof_pipe_write_data_to_child) == 0) {
        aeCreateFileEvent(server.el, server.aof_pipe_write_data_to_child,
            AE_WRITABLE, aofChildWriteDiffData, NULL);
    }
}

/* 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(server.aof_rewrite_buf_blocks,&li);
    while((ln = listNext(&li))) {
        aofrwblock *block = 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) {
    bioCreateBackgroundJob(BIO_AOF_FSYNC,(void*)(long)fd,NULL,NULL);
}

/* Kills an AOFRW child process if exists */
void killAppendOnlyChild(void) {
    int statloc;
    /* No AOFRW child? return. */
    if (server.aof_child_pid == -1) return;
    /* Kill AOFRW child, wait for child exit. */
    serverLog(LL_NOTICE,"Killing running AOF rewrite child: %ld",
        (long) server.aof_child_pid);
    if (kill(server.aof_child_pid,SIGUSR1) != -1) {
        while(wait3(&statloc,0,NULL) != server.aof_child_pid);
    }
    /* Reset the buffer accumulating changes while the child saves. */
    aofRewriteBufferReset();
    aofRemoveTempFile(server.aof_child_pid);
    server.aof_child_pid = -1;
    server.aof_rewrite_time_start = -1;
    /* Close pipes used for IPC between the two processes. */
    aofClosePipes();
    closeChildInfoPipe();
    updateDictResizePolicy();
}

/* Called when the user switches from "appendonly yes" to "appendonly no"
 * at runtime using the CONFIG command. */
void stopAppendOnly(void) {
    serverAssert(server.aof_state != AOF_OFF);
    flushAppendOnlyFile(1);
    redis_fsync(server.aof_fd);
    close(server.aof_fd);

    server.aof_fd = -1;
    server.aof_selected_db = -1;
    server.aof_state = AOF_OFF;
    server.aof_rewrite_scheduled = 0;
    killAppendOnlyChild();
}

/* 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(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
    serverAssert(server.aof_state == AOF_OFF);
    if (newfd == -1) {
        char *cwdp = getcwd(cwd,MAXPATHLEN);

        serverLog(LL_WARNING,
            "Redis needs to enable the AOF but can't open the "
            "append only file %s (in server root dir %s): %s",
            server.aof_filename,
            cwdp ? cwdp : "unknown",
            strerror(errno));
        return C_ERR;
    }
    if (hasActiveChildProcess() && server.aof_child_pid == -1) {
        server.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 (server.aof_child_pid != -1) {
            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,"Redis 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. */
    server.aof_state = AOF_WAIT_REWRITE;
    server.aof_last_fsync = server.unixtime;
    server.aof_fd = newfd;
    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 (sdslen(server.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 (server.aof_fsync == AOF_FSYNC_EVERYSEC &&
            server.aof_fsync_offset != server.aof_current_size &&
            server.unixtime > server.aof_last_fsync &&
            !(sync_in_progress = aofFsyncInProgress())) {
            goto try_fsync;
        } else {
            return;
        }
    }

    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = aofFsyncInProgress();

    if (server.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 (server.aof_flush_postponed_start == 0) {
                /* No previous write postponing, remember that we are
                 * postponing the flush and return. */
                server.aof_flush_postponed_start = server.unixtime;
                return;
            } else if (server.unixtime - server.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. */
            server.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 Redis.");
        }
    }
    /* 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 (server.aof_flush_sleep && sdslen(server.aof_buf)) {
        usleep(server.aof_flush_sleep);
    }

    latencyStartMonitor(latency);
    nwritten = aofWrite(server.aof_fd,server.aof_buf,sdslen(server.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 (hasActiveChildProcess()) {
        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. */
    server.aof_flush_postponed_start = 0;

    if (nwritten != (ssize_t)sdslen(server.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 ((server.unixtime - last_write_error_log) > AOF_WRITE_LOG_ERROR_RATE) {
            can_log = 1;
            last_write_error_log = server.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));
                server.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(server.aof_buf));
            }

            if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
                if (can_log) {
                    serverLog(LL_WARNING, "Could not remove short write "
                             "from the append-only file.  Redis 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;
            }
            server.aof_last_write_errno = ENOSPC;
        }

        /* Handle the AOF write error. */
        if (server.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, and we
             * have the contract with the user that on acknowledged write data
             * is synced on disk. */
            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. */
            server.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) {
                server.aof_current_size += nwritten;
                sdsrange(server.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 (server.aof_last_write_status == C_ERR) {
            serverLog(LL_WARNING,
                "AOF write error looks solved, Redis can write again.");
            server.aof_last_write_status = C_OK;
        }
    }
    server.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(server.aof_buf)+sdsavail(server.aof_buf)) < 4000) {
        sdsclear(server.aof_buf);
    } else {
        sdsfree(server.aof_buf);
        server.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 (server.aof_no_fsync_on_rewrite && hasActiveChildProcess())
        return;

    /* Perform the fsync if needed. */
    if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
        /* redis_fsync is defined as fdatasync() for Linux in order to avoid
         * flushing metadata. */
        latencyStartMonitor(latency);
        redis_fsync(server.aof_fd); /* Let's try to get this data on the disk */
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-fsync-always",latency);
        server.aof_fsync_offset = server.aof_current_size;
        server.aof_last_fsync = server.unixtime;
    } else if ((server.aof_fsync == AOF_FSYNC_EVERYSEC &&
                server.unixtime > server.aof_last_fsync)) {
        if (!sync_in_progress) {
            aof_background_fsync(server.aof_fd);
            server.aof_fsync_offset = server.aof_current_size;
        }
        server.aof_last_fsync = server.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++) {
        o = getDecodedObject(argv[j]);
        buf[0] = '$';
        len = 1+ll2string(buf+1,sizeof(buf)-1,sdslen(o->ptr));
        buf[len++] = '\r';
        buf[len++] = '\n';
        dst = sdscatlen(dst,buf,len);
        dst = sdscatlen(dst,o->ptr,sdslen(o->ptr));
        dst = sdscatlen(dst,"\r\n",2);
        decrRefCount(o);
    }
    return dst;
}

/* Create the sds representation of an 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(seconds->ptr,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] = createStringObject("PEXPIREAT",9);
    argv[1] = key;
    argv[2] = createStringObjectFromLongLong(when);
    buf = catAppendOnlyGenericCommand(buf, 3, argv);
    decrRefCount(argv[0]);
    decrRefCount(argv[2]);
    return buf;
}

void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
    sds buf = sdsempty();
    robj *tmpargv[3];

    /* 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 != server.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);
        server.aof_selected_db = dictid;
    }

    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 == setexCommand || cmd->proc == psetexCommand) {
        /* Translate SETEX/PSETEX to SET and PEXPIREAT */
        tmpargv[0] = createStringObject("SET",3);
        tmpargv[1] = argv[1];
        tmpargv[2] = argv[3];
        buf = catAppendOnlyGenericCommand(buf,3,tmpargv);
        decrRefCount(tmpargv[0]);
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    } else if (cmd->proc == setCommand && argc > 3) {
        int i;
        robj *exarg = NULL, *pxarg = NULL;
        for (i = 3; i < argc; i ++) {
            if (!strcasecmp(argv[i]->ptr, "ex")) exarg = argv[i+1];
            if (!strcasecmp(argv[i]->ptr, "px")) pxarg = argv[i+1];
        }
        serverAssert(!(exarg && pxarg));

        if (exarg || pxarg) {
            /* Translate SET [EX seconds][PX milliseconds] to SET and PEXPIREAT */
            buf = catAppendOnlyGenericCommand(buf,3,argv);
            if (exarg)
                buf = catAppendOnlyExpireAtCommand(buf,server.expireCommand,argv[1],
                                                   exarg);
            if (pxarg)
                buf = catAppendOnlyExpireAtCommand(buf,server.pexpireCommand,argv[1],
                                                   pxarg);
        } else {
            buf = catAppendOnlyGenericCommand(buf,argc,argv);
        }
    } 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);
    }

    /* 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 (server.aof_state == AOF_ON)
        server.aof_buf = sdscatlen(server.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 (server.aof_child_pid != -1)
        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 = zmalloc(sizeof(*c));

    selectDb(c,0);
    c->id = CLIENT_ID_AOF; /* So modules can identify it's the AOF client. */
    c->conn = NULL;
    c->name = NULL;
    c->querybuf = sdsempty();
    c->querybuf_peak = 0;
    c->argc = 0;
    c->argv = NULL;
    c->bufpos = 0;
    c->flags = 0;
    c->btype = BLOCKED_NONE;
    /* We set the fake client as a slave 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->resp = 2;
    c->user = NULL;
    listSetFreeMethod(c->reply,freeClientReplyValue);
    listSetDupMethod(c->reply,dupClientReplyValue);
    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);
}

void freeFakeClient(struct client *c) {
    sdsfree(c->querybuf);
    listRelease(c->reply);
    listRelease(c->watched_keys);
    freeClientMultiState(c);
    zfree(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 = server.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. */

    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) {
        server.aof_current_size = 0;
        server.aof_fsync_offset = server.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. */
    server.aof_state = AOF_OFF;

    fakeClient = createAOFClient();
    startLoadingFile(fp, filename, RDBFLAGS_AOF_PREAMBLE);

    /* 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;

        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,NULL) != 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();
            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 = zmalloc(sizeof(robj*)*argc);
        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(argv[0]->ptr);
        if (!cmd) {
            serverLog(LL_WARNING,
                "Unknown command '%s' reading the append only file",
                (char*)argv[0]->ptr);
            exit(1);
        }

        if (cmd == server.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 (server.aof_load_truncated) valid_up_to = ftello(fp);
        if (server.key_load_delay)
            usleep(server.key_load_delay);
    }

    /* This point can only be reached when EOF is reached without errors.
     * If the client is in the middle of a MULTI/EXEC, handle it as it was
     * a short read, even if technically the protocol is correct: we want
     * to remove the unprocessed tail and continue. */
    if (fakeClient->flags & CLIENT_MULTI) {
        serverLog(LL_WARNING,
            "Revert incomplete MULTI/EXEC transaction in AOF file");
        valid_up_to = valid_before_multi;
        goto uxeof;
    }

loaded_ok: /* DB loaded, cleanup and return C_OK to the caller. */
    fclose(fp);
    freeFakeClient(fakeClient);
    server.aof_state = old_aof_state;
    stopLoading(1);
    aofUpdateCurrentSize();
    server.aof_rewrite_base_size = server.aof_current_size;
    server.aof_fsync_offset = server.aof_current_size;
    return C_OK;

readerr: /* Read error. If feof(fp) is true, fall through to unexpected EOF. */
    if (!feof(fp)) {
        if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
        fclose(fp);
        serverLog(LL_WARNING,"Unrecoverable error reading the append only file: %s", strerror(errno));
        exit(1);
    }

uxeof: /* Unexpected AOF end of file. */
    if (server.aof_load_truncated) {
        serverLog(LL_WARNING,"!!! Warning: short read while loading the AOF file !!!");
        serverLog(LL_WARNING,"!!! Truncating the AOF at offset %llu !!!",
            (unsigned long long) valid_up_to);
        if (valid_up_to == -1 || truncate(filename,valid_up_to) == -1) {
            if (valid_up_to == -1) {
                serverLog(LL_WARNING,"Last valid command offset is invalid");
            } else {
                serverLog(LL_WARNING,"Error truncating the AOF file: %s",
                    strerror(errno));
            }
        } else {
            /* Make sure the AOF file descriptor points to the end of the
             * file after the truncate call. */
            if (server.aof_fd != -1 && lseek(server.aof_fd,0,SEEK_END) == -1) {
                serverLog(LL_WARNING,"Can't seek the end of the AOF file: %s",
                    strerror(errno));
            } else {
                serverLog(LL_WARNING,
                    "AOF loaded anyway because aof-load-truncated is enabled");
                goto loaded_ok;
            }
        }
    }
    if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
    fclose(fp);
    serverLog(LL_WARNING,"Unexpected end of file reading the append only file. You can: 1) Make a backup of your AOF file, then use ./redis-check-aof --fix <filename>. 2) Alternatively you can set the 'aof-load-truncated' configuration option to yes and restart the server.");
    exit(1);

fmterr: /* Format error. */
    if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
    fclose(fp);
    serverLog(LL_WARNING,"Bad file format reading the append only file: make a backup of your AOF file, then use ./redis-check-aof --fix <filename>");
    exit(1);
}

/* ----------------------------------------------------------------------------
 * AOF rewrite
 * ------------------------------------------------------------------------- */

/* Delegate writing an object to writing a bulk string or bulk long long.
 * This is not placed in rio.c since that adds the server.h dependency. */
int rioWriteBulkObject(rio *r, robj *obj) {
    /* Avoid using getDecodedObject to help copy-on-write (we are often
     * in a child process when this function is called). */
    if (obj->encoding == OBJ_ENCODING_INT) {
        return rioWriteBulkLongLong(r,(long)obj->ptr);
    } else if (sdsEncodedObject(obj)) {
        return rioWriteBulkString(r,obj->ptr,sdslen(obj->ptr));
    } else {
        serverPanic("Unknown string encoding");
    }
}

/* Emit the commands needed to rebuild a list object.
 * The function returns 0 on error, 1 on success. */
int rewriteListObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = listTypeLength(o);

    if (o->encoding == OBJ_ENCODING_QUICKLIST) {
        quicklist *list = o->ptr;
        quicklistIter *li = quicklistGetIterator(list, AL_START_HEAD);
        quicklistEntry entry;

        while (quicklistNext(li,&entry)) {
            if (count == 0) {
                int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                    AOF_REWRITE_ITEMS_PER_CMD : items;
                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"RPUSH",5) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }

            if (entry.value) {
                if (rioWriteBulkString(r,(char*)entry.value,entry.sz) == 0) return 0;
            } else {
                if (rioWriteBulkLongLong(r,entry.longval) == 0) return 0;
            }
            if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
        quicklistReleaseIterator(li);
    } else {
        serverPanic("Unknown list encoding");
    }
    return 1;
}

/* Emit the commands needed to rebuild a set object.
 * The function returns 0 on error, 1 on success. */
int rewriteSetObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = setTypeSize(o);

    if (o->encoding == OBJ_ENCODING_INTSET) {
        int ii = 0;
        int64_t llval;

        while(intsetGet(o->ptr,ii++,&llval)) {
            if (count == 0) {
                int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                    AOF_REWRITE_ITEMS_PER_CMD : items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"SADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkLongLong(r,llval) == 0) return 0;
            if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
    } else if (o->encoding == OBJ_ENCODING_HT) {
        dictIterator *di = dictGetIterator(o->ptr);
        dictEntry *de;

        while((de = dictNext(di)) != NULL) {
            sds ele = dictGetKey(de);
            if (count == 0) {
                int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                    AOF_REWRITE_ITEMS_PER_CMD : items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"SADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkString(r,ele,sdslen(ele)) == 0) return 0;
            if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
        dictReleaseIterator(di);
    } else {
        serverPanic("Unknown set encoding");
    }
    return 1;
}

/* Emit the commands needed to rebuild a sorted set object.
 * The function returns 0 on error, 1 on success. */
int rewriteSortedSetObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = zsetLength(o);

    if (o->encoding == OBJ_ENCODING_ZIPLIST) {
        unsigned char *zl = o->ptr;
        unsigned char *eptr, *sptr;
        unsigned char *vstr;
        unsigned int vlen;
        long long vll;
        double score;

        eptr = ziplistIndex(zl,0);
        serverAssert(eptr != NULL);
        sptr = ziplistNext(zl,eptr);
        serverAssert(sptr != NULL);

        while (eptr != NULL) {
            serverAssert(ziplistGet(eptr,&vstr,&vlen,&vll));
            score = zzlGetScore(sptr);

            if (count == 0) {
                int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                    AOF_REWRITE_ITEMS_PER_CMD : items;

                if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
                if (rioWriteBulkString(r,"ZADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkDouble(r,score) == 0) return 0;
            if (vstr != NULL) {
                if (rioWriteBulkString(r,(char*)vstr,vlen) == 0) return 0;
            } else {
                if (rioWriteBulkLongLong(r,vll) == 0) return 0;
            }
            zzlNext(zl,&eptr,&sptr);
            if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
    } else if (o->encoding == OBJ_ENCODING_SKIPLIST) {
        zset *zs = o->ptr;
        dictIterator *di = dictGetIterator(zs->dict);
        dictEntry *de;

        while((de = dictNext(di)) != NULL) {
            sds ele = dictGetKey(de);
            double *score = dictGetVal(de);

            if (count == 0) {
                int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                    AOF_REWRITE_ITEMS_PER_CMD : items;

                if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
                if (rioWriteBulkString(r,"ZADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkDouble(r,*score) == 0) return 0;
            if (rioWriteBulkString(r,ele,sdslen(ele)) == 0) return 0;
            if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
        dictReleaseIterator(di);
    } else {
        serverPanic("Unknown sorted zset encoding");
    }
    return 1;
}

/* Write either the key or the value of the currently selected item of a hash.
 * The 'hi' argument passes a valid Redis hash iterator.
 * The 'what' filed specifies if to write a key or a value and can be
 * either OBJ_HASH_KEY or OBJ_HASH_VALUE.
 *
 * The function returns 0 on error, non-zero on success. */
static int rioWriteHashIteratorCursor(rio *r, hashTypeIterator *hi, int what) {
    if (hi->encoding == OBJ_ENCODING_ZIPLIST) {
        unsigned char *vstr = NULL;
        unsigned int vlen = UINT_MAX;
        long long vll = LLONG_MAX;

        hashTypeCurrentFromZiplist(hi, what, &vstr, &vlen, &vll);
        if (vstr)
            return rioWriteBulkString(r, (char*)vstr, vlen);
        else
            return rioWriteBulkLongLong(r, vll);
    } else if (hi->encoding == OBJ_ENCODING_HT) {
        sds value = hashTypeCurrentFromHashTable(hi, what);
        return rioWriteBulkString(r, value, sdslen(value));
    }

    serverPanic("Unknown hash encoding");
    return 0;
}

/* Emit the commands needed to rebuild a hash object.
 * The function returns 0 on error, 1 on success. */
int rewriteHashObject(rio *r, robj *key, robj *o) {
    hashTypeIterator *hi;
    long long count = 0, items = hashTypeLength(o);

    hi = hashTypeInitIterator(o);
    while (hashTypeNext(hi) != C_ERR) {
        if (count == 0) {
            int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
                AOF_REWRITE_ITEMS_PER_CMD : items;

            if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
            if (rioWriteBulkString(r,"HMSET",5) == 0) return 0;
            if (rioWriteBulkObject(r,key) == 0) return 0;
        }

        if (rioWriteHashIteratorCursor(r, hi, OBJ_HASH_KEY) == 0) return 0;
        if (rioWriteHashIteratorCursor(r, hi, OBJ_HASH_VALUE) == 0) return 0;
        if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
        items--;
    }

    hashTypeReleaseIterator(hi);

    return 1;
}

/* Helper for rewriteStreamObject() that generates a bulk string into the
 * AOF representing the ID 'id'. */
int rioWriteBulkStreamID(rio *r,streamID *id) {
    int retval;

    sds replyid = sdscatfmt(sdsempty(),"%U-%U",id->ms,id->seq);
    retval = rioWriteBulkString(r,replyid,sdslen(replyid));
    sdsfree(replyid);
    return retval;
}

/* Helper for rewriteStreamObject(): emit the XCLAIM needed in order to
 * add the message described by 'nack' having the id 'rawid', into the pending
 * list of the specified consumer. All this in the context of the specified
 * key and group. */
int rioWriteStreamPendingEntry(rio *r, robj *key, const char *groupname, size_t groupname_len, streamConsumer *consumer, unsigned char *rawid, streamNACK *nack) {
     /* XCLAIM <key> <group> <consumer> 0 <id> TIME <milliseconds-unix-time>
               RETRYCOUNT <count> JUSTID FORCE. */
    streamID id;
    streamDecodeID(rawid,&id);
    if (rioWriteBulkCount(r,'*',12) == 0) return 0;
    if (rioWriteBulkString(r,"XCLAIM",6) == 0) return 0;
    if (rioWriteBulkObject(r,key) == 0) return 0;
    if (rioWriteBulkString(r,groupname,groupname_len) == 0) return 0;
    if (rioWriteBulkString(r,consumer->name,sdslen(consumer->name)) == 0) return 0;
    if (rioWriteBulkString(r,"0",1) == 0) return 0;
    if (rioWriteBulkStreamID(r,&id) == 0) return 0;
    if (rioWriteBulkString(r,"TIME",4) == 0) return 0;
    if (rioWriteBulkLongLong(r,nack->delivery_time) == 0) return 0;
    if (rioWriteBulkString(r,"RETRYCOUNT",10) == 0) return 0;
    if (rioWriteBulkLongLong(r,nack->delivery_count) == 0) return 0;
    if (rioWriteBulkString(r,"JUSTID",6) == 0) return 0;
    if (rioWriteBulkString(r,"FORCE",5) == 0) return 0;
    return 1;
}

/* Emit the commands needed to rebuild a stream object.
 * The function returns 0 on error, 1 on success. */
int rewriteStreamObject(rio *r, robj *key, robj *o) {
    stream *s = o->ptr;
    streamIterator si;
    streamIteratorStart(&si,s,NULL,NULL,0);
    streamID id;
    int64_t numfields;

    if (s->length) {
        /* Reconstruct the stream data using XADD commands. */
        while(streamIteratorGetID(&si,&id,&numfields)) {
            /* Emit a two elements array for each item. The first is
             * the ID, the second is an array of field-value pairs. */

            /* Emit the XADD <key> <id> ...fields... command. */
            if (rioWriteBulkCount(r,'*',3+numfields*2) == 0) return 0;
            if (rioWriteBulkString(r,"XADD",4) == 0) return 0;
            if (rioWriteBulkObject(r,key) == 0) return 0;
            if (rioWriteBulkStreamID(r,&id) == 0) return 0;
            while(numfields--) {
                unsigned char *field, *value;
                int64_t field_len, value_len;
                streamIteratorGetField(&si,&field,&value,&field_len,&value_len);
                if (rioWriteBulkString(r,(char*)field,field_len) == 0) return 0;
                if (rioWriteBulkString(r,(char*)value,value_len) == 0) return 0;
            }
        }
    } else {
        /* Use the XADD MAXLEN 0 trick to generate an empty stream if
         * the key we are serializing is an empty string, which is possible
         * for the Stream type. */
        id.ms = 0; id.seq = 1; 
        if (rioWriteBulkCount(r,'*',7) == 0) return 0;
        if (rioWriteBulkString(r,"XADD",4) == 0) return 0;
        if (rioWriteBulkObject(r,key) == 0) return 0;
        if (rioWriteBulkString(r,"MAXLEN",6) == 0) return 0;
        if (rioWriteBulkString(r,"0",1) == 0) return 0;
        if (rioWriteBulkStreamID(r,&id) == 0) return 0;
        if (rioWriteBulkString(r,"x",1) == 0) return 0;
        if (rioWriteBulkString(r,"y",1) == 0) return 0;
    }

    /* Append XSETID after XADD, make sure lastid is correct,
     * in case of XDEL lastid. */
    if (rioWriteBulkCount(r,'*',3) == 0) return 0;
    if (rioWriteBulkString(r,"XSETID",6) == 0) return 0;
    if (rioWriteBulkObject(r,key) == 0) return 0;
    if (rioWriteBulkStreamID(r,&s->last_id) == 0) return 0;


    /* Create all the stream consumer groups. */
    if (s->cgroups) {
        raxIterator ri;
        raxStart(&ri,s->cgroups);
        raxSeek(&ri,"^",NULL,0);
        while(raxNext(&ri)) {
            streamCG *group = ri.data;
            /* Emit the XGROUP CREATE in order to create the group. */
            if (!rioWriteBulkCount(r,'*',5) ||
                !rioWriteBulkString(r,"XGROUP",6) ||
                !rioWriteBulkString(r,"CREATE",6) ||
                !rioWriteBulkObject(r,key) ||
                !rioWriteBulkString(r,(char*)ri.key,ri.key_len) ||
                !rioWriteBulkStreamID(r,&group->last_id)) 
            {
                raxStop(&ri);
                return 0;
            }

            /* Generate XCLAIMs for each consumer that happens to
             * have pending entries. Empty consumers have no semantical
             * value so they are discarded. */
            raxIterator ri_cons;
            raxStart(&ri_cons,group->consumers);
            raxSeek(&ri_cons,"^",NULL,0);
            while(raxNext(&ri_cons)) {
                streamConsumer *consumer = ri_cons.data;
                /* For the current consumer, iterate all the PEL entries
                 * to emit the XCLAIM protocol. */
                raxIterator ri_pel;
                raxStart(&ri_pel,consumer->pel);
                raxSeek(&ri_pel,"^",NULL,0);
                while(raxNext(&ri_pel)) {
                    streamNACK *nack = ri_pel.data;
                    if (rioWriteStreamPendingEntry(r,key,(char*)ri.key,
                                                   ri.key_len,consumer,
                                                   ri_pel.key,nack) == 0)
                    {
                        raxStop(&ri_pel);
                        raxStop(&ri_cons);
                        raxStop(&ri);
                        return 0;
                    }
                }
                raxStop(&ri_pel);
            }
            raxStop(&ri_cons);
        }
        raxStop(&ri);
    }

    streamIteratorStop(&si);
    return 1;
}

/* Call the module type callback in order to rewrite a data type
 * that is exported by a module and is not handled by Redis itself.
 * The function returns 0 on error, 1 on success. */
int rewriteModuleObject(rio *r, robj *key, robj *o) {
    RedisModuleIO io;
    moduleValue *mv = o->ptr;
    moduleType *mt = mv->type;
    moduleInitIOContext(io,mt,r,key);
    mt->aof_rewrite(&io,key,mv->value);
    if (io.ctx) {
        moduleFreeContext(io.ctx);
        zfree(io.ctx);
    }
    return io.error ? 0 : 1;
}

/* This function is called by the child rewriting the AOF file to read
 * the difference accumulated from the parent into a buffer, that is
 * concatenated at the end of the rewrite. */
ssize_t aofReadDiffFromParent(void) {
    char buf[65536]; /* Default pipe buffer size on most Linux systems. */
    ssize_t nread, total = 0;

    while ((nread =
            read(server.aof_pipe_read_data_from_parent,buf,sizeof(buf))) > 0) {
        server.aof_child_diff = sdscatlen(server.aof_child_diff,buf,nread);
        total += nread;
    }
    return total;
}

int rewriteAppendOnlyFileRio(rio *aof) {
    dictIterator *di = NULL;
    dictEntry *de;
    size_t processed = 0;
    int j;

    for (j = 0; j < server.dbnum; j++) {
        char selectcmd[] = "*2\r\n$6\r\nSELECT\r\n";
        redisDb *db = server.db+j;
        dict *d = db->dict;
        if (dictSize(d) == 0) continue;
        di = dictGetSafeIterator(d);

        /* SELECT the new DB */
        if (rioWrite(aof,selectcmd,sizeof(selectcmd)-1) == 0) goto werr;
        if (rioWriteBulkLongLong(aof,j) == 0) goto werr;

        /* Iterate this DB writing every entry */
        while((de = dictNext(di)) != NULL) {
            sds keystr;
            robj key, *o;
            long long expiretime;

            keystr = dictGetKey(de);
            o = dictGetVal(de);
            initStaticStringObject(key,keystr);

            expiretime = getExpire(db,&key);

            /* Save the key and associated value */
            if (o->type == OBJ_STRING) {
                /* Emit a SET command */
                char cmd[]="*3\r\n$3\r\nSET\r\n";
                if (rioWrite(aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                /* Key and value */
                if (rioWriteBulkObject(aof,&key) == 0) goto werr;
                if (rioWriteBulkObject(aof,o) == 0) goto werr;
            } else if (o->type == OBJ_LIST) {
                if (rewriteListObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_SET) {
                if (rewriteSetObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_ZSET) {
                if (rewriteSortedSetObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_HASH) {
                if (rewriteHashObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_STREAM) {
                if (rewriteStreamObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_MODULE) {
                if (rewriteModuleObject(aof,&key,o) == 0) goto werr;
            } else {
                serverPanic("Unknown object type");
            }
            /* Save the expire time */
            if (expiretime != -1) {
                char cmd[]="*3\r\n$9\r\nPEXPIREAT\r\n";
                if (rioWrite(aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                if (rioWriteBulkObject(aof,&key) == 0) goto werr;
                if (rioWriteBulkLongLong(aof,expiretime) == 0) goto werr;
            }
            /* Read some diff from the parent process from time to time. */
            if (aof->processed_bytes > processed+AOF_READ_DIFF_INTERVAL_BYTES) {
                processed = aof->processed_bytes;
                aofReadDiffFromParent();
            }
        }
        dictReleaseIterator(di);
        di = NULL;
    }
    return C_OK;

werr:
    if (di) dictReleaseIterator(di);
    return C_ERR;
}

/* Write a sequence of commands able to fully rebuild the dataset into
 * "filename". Used both by REWRITEAOF and BGREWRITEAOF.
 *
 * In order to minimize the number of commands needed in the rewritten
 * log Redis uses variadic commands when possible, such as RPUSH, SADD
 * and ZADD. However at max AOF_REWRITE_ITEMS_PER_CMD items per time
 * are inserted using a single command. */
int rewriteAppendOnlyFile(char *filename) {
    rio aof;
    FILE *fp;
    char tmpfile[256];
    char byte;

    /* Note that we have to use a different temp name here compared to the
     * one used by rewriteAppendOnlyFileBackground() function. */
    snprintf(tmpfile,256,"temp-rewriteaof-%d.aof", (int) getpid());
    fp = fopen(tmpfile,"w");
    if (!fp) {
        serverLog(LL_WARNING, "Opening the temp file for AOF rewrite in rewriteAppendOnlyFile(): %s", strerror(errno));
        return C_ERR;
    }

    server.aof_child_diff = sdsempty();
    rioInitWithFile(&aof,fp);

    if (server.aof_rewrite_incremental_fsync)
        rioSetAutoSync(&aof,REDIS_AUTOSYNC_BYTES);

    startSaving(RDBFLAGS_AOF_PREAMBLE);

    if (server.aof_use_rdb_preamble) {
        int error;
        if (rdbSaveRio(&aof,&error,RDBFLAGS_AOF_PREAMBLE,NULL) == C_ERR) {
            errno = error;
            goto werr;
        }
    } else {
        if (rewriteAppendOnlyFileRio(&aof) == C_ERR) goto werr;
    }

    /* Do an initial slow fsync here while the parent is still sending
     * data, in order to make the next final fsync faster. */
    if (fflush(fp) == EOF) goto werr;
    if (fsync(fileno(fp)) == -1) goto werr;

    /* Read again a few times to get more data from the parent.
     * We can't read forever (the server may receive data from clients
     * faster than it is able to send data to the child), so we try to read
     * some more data in a loop as soon as there is a good chance more data
     * will come. If it looks like we are wasting time, we abort (this
     * happens after 20 ms without new data). */
    int nodata = 0;
    mstime_t start = mstime();
    while(mstime()-start < 1000 && nodata < 20) {
        if (aeWait(server.aof_pipe_read_data_from_parent, AE_READABLE, 1) <= 0)
        {
            nodata++;
            continue;
        }
        nodata = 0; /* Start counting from zero, we stop on N *contiguous*
                       timeouts. */
        aofReadDiffFromParent();
    }

    /* Ask the master to stop sending diffs. */
    if (write(server.aof_pipe_write_ack_to_parent,"!",1) != 1) goto werr;
    if (anetNonBlock(NULL,server.aof_pipe_read_ack_from_parent) != ANET_OK)
        goto werr;
    /* We read the ACK from the server using a 10 seconds timeout. Normally
     * it should reply ASAP, but just in case we lose its reply, we are sure
     * the child will eventually get terminated. */
    if (syncRead(server.aof_pipe_read_ack_from_parent,&byte,1,5000) != 1 ||
        byte != '!') goto werr;
    serverLog(LL_NOTICE,"Parent agreed to stop sending diffs. Finalizing AOF...");

    /* Read the final diff if any. */
    aofReadDiffFromParent();

    /* Write the received diff to the file. */
    serverLog(LL_NOTICE,
        "Concatenating %.2f MB of AOF diff received from parent.",
        (double) sdslen(server.aof_child_diff) / (1024*1024));
    if (rioWrite(&aof,server.aof_child_diff,sdslen(server.aof_child_diff)) == 0)
        goto werr;

    /* Make sure data will not remain on the OS's output buffers */
    if (fflush(fp) == EOF) goto werr;
    if (fsync(fileno(fp)) == -1) goto werr;
    if (fclose(fp) == EOF) goto werr;

    /* Use RENAME to make sure the DB file is changed atomically only
     * if the generate DB file is ok. */
    if (rename(tmpfile,filename) == -1) {
        serverLog(LL_WARNING,"Error moving temp append only file on the final destination: %s", strerror(errno));
        unlink(tmpfile);
        stopSaving(0);
        return C_ERR;
    }
    serverLog(LL_NOTICE,"SYNC append only file rewrite performed");
    stopSaving(1);
    return C_OK;

werr:
    serverLog(LL_WARNING,"Write error writing append only file on disk: %s", strerror(errno));
    fclose(fp);
    unlink(tmpfile);
    stopSaving(0);
    return C_ERR;
}

/* ----------------------------------------------------------------------------
 * AOF rewrite pipes for IPC
 * -------------------------------------------------------------------------- */

/* This event handler is called when the AOF rewriting child sends us a
 * single '!' char to signal we should stop sending buffer diffs. The
 * parent sends a '!' as well to acknowledge. */
void aofChildPipeReadable(aeEventLoop *el, int fd, void *privdata, int mask) {
    char byte;
    UNUSED(el);
    UNUSED(privdata);
    UNUSED(mask);

    if (read(fd,&byte,1) == 1 && byte == '!') {
        serverLog(LL_NOTICE,"AOF rewrite child asks to stop sending diffs.");
        server.aof_stop_sending_diff = 1;
        if (write(server.aof_pipe_write_ack_to_child,"!",1) != 1) {
            /* If we can't send the ack, inform the user, but don't try again
             * since in the other side the children will use a timeout if the
             * kernel can't buffer our write, or, the children was
             * terminated. */
            serverLog(LL_WARNING,"Can't send ACK to AOF child: %s",
                strerror(errno));
        }
    }
    /* Remove the handler since this can be called only one time during a
     * rewrite. */
    aeDeleteFileEvent(server.el,server.aof_pipe_read_ack_from_child,AE_READABLE);
}

/* Create the pipes used for parent - child process IPC during rewrite.
 * We have a data pipe used to send AOF incremental diffs to the child,
 * and two other pipes used by the children to signal it finished with
 * the rewrite so no more data should be written, and another for the
 * parent to acknowledge it understood this new condition. */
int aofCreatePipes(void) {
    int fds[6] = {-1, -1, -1, -1, -1, -1};
    int j;

    if (pipe(fds) == -1) goto error; /* parent -> children data. */
    if (pipe(fds+2) == -1) goto error; /* children -> parent ack. */
    if (pipe(fds+4) == -1) goto error; /* parent -> children ack. */
    /* Parent -> children data is non blocking. */
    if (anetNonBlock(NULL,fds[0]) != ANET_OK) goto error;
    if (anetNonBlock(NULL,fds[1]) != ANET_OK) goto error;
    if (aeCreateFileEvent(server.el, fds[2], AE_READABLE, aofChildPipeReadable, NULL) == AE_ERR) goto error;

    server.aof_pipe_write_data_to_child = fds[1];
    server.aof_pipe_read_data_from_parent = fds[0];
    server.aof_pipe_write_ack_to_parent = fds[3];
    server.aof_pipe_read_ack_from_child = fds[2];
    server.aof_pipe_write_ack_to_child = fds[5];
    server.aof_pipe_read_ack_from_parent = fds[4];
    server.aof_stop_sending_diff = 0;
    return C_OK;

error:
    serverLog(LL_WARNING,"Error opening /setting AOF rewrite IPC pipes: %s",
        strerror(errno));
    for (j = 0; j < 6; j++) if(fds[j] != -1) close(fds[j]);
    return C_ERR;
}

void aofClosePipes(void) {
    aeDeleteFileEvent(server.el,server.aof_pipe_read_ack_from_child,AE_READABLE);
    aeDeleteFileEvent(server.el,server.aof_pipe_write_data_to_child,AE_WRITABLE);
    close(server.aof_pipe_write_data_to_child);
    close(server.aof_pipe_read_data_from_parent);
    close(server.aof_pipe_write_ack_to_parent);
    close(server.aof_pipe_read_ack_from_child);
    close(server.aof_pipe_write_ack_to_child);
    close(server.aof_pipe_read_ack_from_parent);
}

/* ----------------------------------------------------------------------------
 * AOF background rewrite
 * ------------------------------------------------------------------------- */

/* This is how rewriting of the append only file in background works:
 *
 * 1) The user calls BGREWRITEAOF
 * 2) Redis calls this function, that forks():
 *    2a) the child rewrite the append only file in a temp file.
 *    2b) the parent accumulates differences in server.aof_rewrite_buf.
 * 3) When the child finished '2a' exists.
 * 4) The parent will trap the exit code, if it's OK, will append the
 *    data accumulated into server.aof_rewrite_buf into the temp file, and
 *    finally will rename(2) the temp file in the actual file name.
 *    The the new file is reopened as the new append only file. Profit!
 */
int rewriteAppendOnlyFileBackground(void) {
    pid_t childpid;

    if (hasActiveChildProcess()) return C_ERR;
    if (aofCreatePipes() != C_OK) return C_ERR;
    openChildInfoPipe();
    if ((childpid = redisFork()) == 0) {
        char tmpfile[256];

        /* Child */
        redisSetProcTitle("redis-aof-rewrite");
        redisSetCpuAffinity(server.aof_rewrite_cpulist);
        snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) getpid());
        if (rewriteAppendOnlyFile(tmpfile) == C_OK) {
            sendChildCOWInfo(CHILD_INFO_TYPE_AOF, "AOF rewrite");
            exitFromChild(0);
        } else {
            exitFromChild(1);
        }
    } else {
        /* Parent */
        if (childpid == -1) {
            closeChildInfoPipe();
            serverLog(LL_WARNING,
                "Can't rewrite append only file in background: fork: %s",
                strerror(errno));
            aofClosePipes();
            return C_ERR;
        }
        serverLog(LL_NOTICE,
            "Background append only file rewriting started by pid %d",childpid);
        server.aof_rewrite_scheduled = 0;
        server.aof_rewrite_time_start = time(NULL);
        server.aof_child_pid = childpid;
        /* We set appendseldb to -1 in order to force the next call to the
         * feedAppendOnlyFile() to issue a SELECT command, so the differences
         * accumulated by the parent into server.aof_rewrite_buf will start
         * with a SELECT statement and it will be safe to merge. */
        server.aof_selected_db = -1;
        replicationScriptCacheFlush();
        return C_OK;
    }
    return C_OK; /* unreached */
}

void bgrewriteaofCommand(client *c) {
    if (server.aof_child_pid != -1) {
        addReplyError(c,"Background append only file rewriting already in progress");
    } else if (hasActiveChildProcess()) {
        server.aof_rewrite_scheduled = 1;
        addReplyStatus(c,"Background append only file rewriting scheduled");
    } else if (rewriteAppendOnlyFileBackground() == C_OK) {
        addReplyStatus(c,"Background append only file rewriting started");
    } else {
        addReplyError(c,"Can't execute an AOF background rewriting. "
                        "Please check the server logs for more information.");
    }
}

void aofRemoveTempFile(pid_t childpid) {
    char tmpfile[256];

    snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) childpid);
    unlink(tmpfile);

    snprintf(tmpfile,256,"temp-rewriteaof-%d.aof", (int) childpid);
    unlink(tmpfile);
}

/* Update the server.aof_current_size field explicitly using stat(2)
 * to check the size of the file. This is useful after a rewrite or after
 * a restart, normally the size is updated just adding the write length
 * to the current length, that is much faster. */
void aofUpdateCurrentSize(void) {
    struct redis_stat sb;
    mstime_t latency;

    latencyStartMonitor(latency);
    if (redis_fstat(server.aof_fd,&sb) == -1) {
        serverLog(LL_WARNING,"Unable to obtain the AOF file length. stat: %s",
            strerror(errno));
    } else {
        server.aof_current_size = sb.st_size;
    }
    latencyEndMonitor(latency);
    latencyAddSampleIfNeeded("aof-fstat",latency);
}

/* A background append only file rewriting (BGREWRITEAOF) terminated its work.
 * Handle this. */
void backgroundRewriteDoneHandler(int exitcode, int bysignal) {
    if (!bysignal && exitcode == 0) {
        int newfd, oldfd;
        char tmpfile[256];
        long long now = ustime();
        mstime_t latency;

        serverLog(LL_NOTICE,
            "Background AOF rewrite terminated with success");

        /* Flush the differences accumulated by the parent to the
         * rewritten AOF. */
        latencyStartMonitor(latency);
        snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof",
            (int)server.aof_child_pid);
        newfd = open(tmpfile,O_WRONLY|O_APPEND);
        if (newfd == -1) {
            serverLog(LL_WARNING,
                "Unable to open the temporary AOF produced by the child: %s", strerror(errno));
            goto cleanup;
        }

        if (aofRewriteBufferWrite(newfd) == -1) {
            serverLog(LL_WARNING,
                "Error trying to flush the parent diff to the rewritten AOF: %s", strerror(errno));
            close(newfd);
            goto cleanup;
        }
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-rewrite-diff-write",latency);

        serverLog(LL_NOTICE,
            "Residual parent diff successfully flushed to the rewritten AOF (%.2f MB)", (double) aofRewriteBufferSize() / (1024*1024));

        /* The only remaining thing to do is to rename the temporary file to
         * the configured file and switch the file descriptor used to do AOF
         * writes. We don't want close(2) or rename(2) calls to block the
         * server on old file deletion.
         *
         * There are two possible scenarios:
         *
         * 1) AOF is DISABLED and this was a one time rewrite. The temporary
         * file will be renamed to the configured file. When this file already
         * exists, it will be unlinked, which may block the server.
         *
         * 2) AOF is ENABLED and the rewritten AOF will immediately start
         * receiving writes. After the temporary file is renamed to the
         * configured file, the original AOF file descriptor will be closed.
         * Since this will be the last reference to that file, closing it
         * causes the underlying file to be unlinked, which may block the
         * server.
         *
         * To mitigate the blocking effect of the unlink operation (either
         * caused by rename(2) in scenario 1, or by close(2) in scenario 2), we
         * use a background thread to take care of this. First, we
         * make scenario 1 identical to scenario 2 by opening the target file
         * when it exists. The unlink operation after the rename(2) will then
         * be executed upon calling close(2) for its descriptor. Everything to
         * guarantee atomicity for this switch has already happened by then, so
         * we don't care what the outcome or duration of that close operation
         * is, as long as the file descriptor is released again. */
        if (server.aof_fd == -1) {
            /* AOF disabled */

            /* Don't care if this fails: oldfd will be -1 and we handle that.
             * One notable case of -1 return is if the old file does
             * not exist. */
            oldfd = open(server.aof_filename,O_RDONLY|O_NONBLOCK);
        } else {
            /* AOF enabled */
            oldfd = -1; /* We'll set this to the current AOF filedes later. */
        }

        /* Rename the temporary file. This will not unlink the target file if
         * it exists, because we reference it with "oldfd". */
        latencyStartMonitor(latency);
        if (rename(tmpfile,server.aof_filename) == -1) {
            serverLog(LL_WARNING,
                "Error trying to rename the temporary AOF file %s into %s: %s",
                tmpfile,
                server.aof_filename,
                strerror(errno));
            close(newfd);
            if (oldfd != -1) close(oldfd);
            goto cleanup;
        }
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-rename",latency);

        if (server.aof_fd == -1) {
            /* AOF disabled, we don't need to set the AOF file descriptor
             * to this new file, so we can close it. */
            close(newfd);
        } else {
            /* AOF enabled, replace the old fd with the new one. */
            oldfd = server.aof_fd;
            server.aof_fd = newfd;
            if (server.aof_fsync == AOF_FSYNC_ALWAYS)
                redis_fsync(newfd);
            else if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
                aof_background_fsync(newfd);
            server.aof_selected_db = -1; /* Make sure SELECT is re-issued */
            aofUpdateCurrentSize();
            server.aof_rewrite_base_size = server.aof_current_size;
            server.aof_fsync_offset = server.aof_current_size;

            /* Clear regular AOF buffer since its contents was just written to
             * the new AOF from the background rewrite buffer. */
            sdsfree(server.aof_buf);
            server.aof_buf = sdsempty();
        }

        server.aof_lastbgrewrite_status = C_OK;

        serverLog(LL_NOTICE, "Background AOF rewrite finished successfully");
        /* Change state from WAIT_REWRITE to ON if needed */
        if (server.aof_state == AOF_WAIT_REWRITE)
            server.aof_state = AOF_ON;

        /* Asynchronously close the overwritten AOF. */
        if (oldfd != -1) bioCreateBackgroundJob(BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL);

        serverLog(LL_VERBOSE,
            "Background AOF rewrite signal handler took %lldus", ustime()-now);
    } else if (!bysignal && exitcode != 0) {
        server.aof_lastbgrewrite_status = C_ERR;

        serverLog(LL_WARNING,
            "Background AOF rewrite terminated with error");
    } else {
        /* SIGUSR1 is whitelisted, so we have a way to kill a child without
         * tirggering an error condition. */
        if (bysignal != SIGUSR1)
            server.aof_lastbgrewrite_status = C_ERR;

        serverLog(LL_WARNING,
            "Background AOF rewrite terminated by signal %d", bysignal);
    }

cleanup:
    aofClosePipes();
    aofRewriteBufferReset();
    aofRemoveTempFile(server.aof_child_pid);
    server.aof_child_pid = -1;
    server.aof_rewrite_time_last = time(NULL)-server.aof_rewrite_time_start;
    server.aof_rewrite_time_start = -1;
    /* Schedule a new rewrite if we are waiting for it to switch the AOF ON. */
    if (server.aof_state == AOF_WAIT_REWRITE)
        server.aof_rewrite_scheduled = 1;
}