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
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
|
/*
* 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 "lzf.h" /* LZF compression library */
#include "zipmap.h"
#include "endianconv.h"
#include "stream.h"
#include <math.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/wait.h>
#include <arpa/inet.h>
#include <sys/stat.h>
#include <sys/param.h>
/* This macro is called when the internal RDB stracture is corrupt */
#define rdbExitReportCorruptRDB(...) rdbReportError(1, __LINE__,__VA_ARGS__)
/* This macro is called when RDB read failed (possibly a short read) */
#define rdbReportReadError(...) rdbReportError(0, __LINE__,__VA_ARGS__)
char* rdbFileBeingLoaded = NULL; /* used for rdb checking on read error */
extern int rdbCheckMode;
void rdbCheckError(const char *fmt, ...);
void rdbCheckSetError(const char *fmt, ...);
void rdbReportError(int corruption_error, int linenum, char *reason, ...) {
va_list ap;
char msg[1024];
int len;
len = snprintf(msg,sizeof(msg),
"Internal error in RDB reading offset %llu, function at rdb.c:%d -> ",
(unsigned long long)server.loading_loaded_bytes, linenum);
va_start(ap,reason);
vsnprintf(msg+len,sizeof(msg)-len,reason,ap);
va_end(ap);
if (!rdbCheckMode) {
if (rdbFileBeingLoaded || corruption_error) {
serverLog(LL_WARNING, "%s", msg);
char *argv[2] = {"",rdbFileBeingLoaded};
redis_check_rdb_main(2,argv,NULL);
} else {
serverLog(LL_WARNING, "%s. Failure loading rdb format from socket, assuming connection error, resuming operation.", msg);
return;
}
} else {
rdbCheckError("%s",msg);
}
serverLog(LL_WARNING, "Terminating server after rdb file reading failure.");
exit(1);
}
static int rdbWriteRaw(rio *rdb, void *p, size_t len) {
if (rdb && rioWrite(rdb,p,len) == 0)
return -1;
return len;
}
int rdbSaveType(rio *rdb, unsigned char type) {
return rdbWriteRaw(rdb,&type,1);
}
/* Load a "type" in RDB format, that is a one byte unsigned integer.
* This function is not only used to load object types, but also special
* "types" like the end-of-file type, the EXPIRE type, and so forth. */
int rdbLoadType(rio *rdb) {
unsigned char type;
if (rioRead(rdb,&type,1) == 0) return -1;
return type;
}
/* This is only used to load old databases stored with the RDB_OPCODE_EXPIRETIME
* opcode. New versions of Redis store using the RDB_OPCODE_EXPIRETIME_MS
* opcode. On error -1 is returned, however this could be a valid time, so
* to check for loading errors the caller should call rioGetReadError() after
* calling this function. */
time_t rdbLoadTime(rio *rdb) {
int32_t t32;
if (rioRead(rdb,&t32,4) == 0) return -1;
return (time_t)t32;
}
int rdbSaveMillisecondTime(rio *rdb, long long t) {
int64_t t64 = (int64_t) t;
memrev64ifbe(&t64); /* Store in little endian. */
return rdbWriteRaw(rdb,&t64,8);
}
/* This function loads a time from the RDB file. It gets the version of the
* RDB because, unfortunately, before Redis 5 (RDB version 9), the function
* failed to convert data to/from little endian, so RDB files with keys having
* expires could not be shared between big endian and little endian systems
* (because the expire time will be totally wrong). The fix for this is just
* to call memrev64ifbe(), however if we fix this for all the RDB versions,
* this call will introduce an incompatibility for big endian systems:
* after upgrading to Redis version 5 they will no longer be able to load their
* own old RDB files. Because of that, we instead fix the function only for new
* RDB versions, and load older RDB versions as we used to do in the past,
* allowing big endian systems to load their own old RDB files.
*
* On I/O error the function returns LLONG_MAX, however if this is also a
* valid stored value, the caller should use rioGetReadError() to check for
* errors after calling this function. */
long long rdbLoadMillisecondTime(rio *rdb, int rdbver) {
int64_t t64;
if (rioRead(rdb,&t64,8) == 0) return LLONG_MAX;
if (rdbver >= 9) /* Check the top comment of this function. */
memrev64ifbe(&t64); /* Convert in big endian if the system is BE. */
return (long long)t64;
}
/* Saves an encoded length. The first two bits in the first byte are used to
* hold the encoding type. See the RDB_* definitions for more information
* on the types of encoding. */
int rdbSaveLen(rio *rdb, uint64_t len) {
unsigned char buf[2];
size_t nwritten;
if (len < (1<<6)) {
/* Save a 6 bit len */
buf[0] = (len&0xFF)|(RDB_6BITLEN<<6);
if (rdbWriteRaw(rdb,buf,1) == -1) return -1;
nwritten = 1;
} else if (len < (1<<14)) {
/* Save a 14 bit len */
buf[0] = ((len>>8)&0xFF)|(RDB_14BITLEN<<6);
buf[1] = len&0xFF;
if (rdbWriteRaw(rdb,buf,2) == -1) return -1;
nwritten = 2;
} else if (len <= UINT32_MAX) {
/* Save a 32 bit len */
buf[0] = RDB_32BITLEN;
if (rdbWriteRaw(rdb,buf,1) == -1) return -1;
uint32_t len32 = htonl(len);
if (rdbWriteRaw(rdb,&len32,4) == -1) return -1;
nwritten = 1+4;
} else {
/* Save a 64 bit len */
buf[0] = RDB_64BITLEN;
if (rdbWriteRaw(rdb,buf,1) == -1) return -1;
len = htonu64(len);
if (rdbWriteRaw(rdb,&len,8) == -1) return -1;
nwritten = 1+8;
}
return nwritten;
}
/* Load an encoded length. If the loaded length is a normal length as stored
* with rdbSaveLen(), the read length is set to '*lenptr'. If instead the
* loaded length describes a special encoding that follows, then '*isencoded'
* is set to 1 and the encoding format is stored at '*lenptr'.
*
* See the RDB_ENC_* definitions in rdb.h for more information on special
* encodings.
*
* The function returns -1 on error, 0 on success. */
int rdbLoadLenByRef(rio *rdb, int *isencoded, uint64_t *lenptr) {
unsigned char buf[2];
int type;
if (isencoded) *isencoded = 0;
if (rioRead(rdb,buf,1) == 0) return -1;
type = (buf[0]&0xC0)>>6;
if (type == RDB_ENCVAL) {
/* Read a 6 bit encoding type. */
if (isencoded) *isencoded = 1;
*lenptr = buf[0]&0x3F;
} else if (type == RDB_6BITLEN) {
/* Read a 6 bit len. */
*lenptr = buf[0]&0x3F;
} else if (type == RDB_14BITLEN) {
/* Read a 14 bit len. */
if (rioRead(rdb,buf+1,1) == 0) return -1;
*lenptr = ((buf[0]&0x3F)<<8)|buf[1];
} else if (buf[0] == RDB_32BITLEN) {
/* Read a 32 bit len. */
uint32_t len;
if (rioRead(rdb,&len,4) == 0) return -1;
*lenptr = ntohl(len);
} else if (buf[0] == RDB_64BITLEN) {
/* Read a 64 bit len. */
uint64_t len;
if (rioRead(rdb,&len,8) == 0) return -1;
*lenptr = ntohu64(len);
} else {
rdbExitReportCorruptRDB(
"Unknown length encoding %d in rdbLoadLen()",type);
return -1; /* Never reached. */
}
return 0;
}
/* This is like rdbLoadLenByRef() but directly returns the value read
* from the RDB stream, signaling an error by returning RDB_LENERR
* (since it is a too large count to be applicable in any Redis data
* structure). */
uint64_t rdbLoadLen(rio *rdb, int *isencoded) {
uint64_t len;
if (rdbLoadLenByRef(rdb,isencoded,&len) == -1) return RDB_LENERR;
return len;
}
/* Encodes the "value" argument as integer when it fits in the supported ranges
* for encoded types. If the function successfully encodes the integer, the
* representation is stored in the buffer pointer to by "enc" and the string
* length is returned. Otherwise 0 is returned. */
int rdbEncodeInteger(long long value, unsigned char *enc) {
if (value >= -(1<<7) && value <= (1<<7)-1) {
enc[0] = (RDB_ENCVAL<<6)|RDB_ENC_INT8;
enc[1] = value&0xFF;
return 2;
} else if (value >= -(1<<15) && value <= (1<<15)-1) {
enc[0] = (RDB_ENCVAL<<6)|RDB_ENC_INT16;
enc[1] = value&0xFF;
enc[2] = (value>>8)&0xFF;
return 3;
} else if (value >= -((long long)1<<31) && value <= ((long long)1<<31)-1) {
enc[0] = (RDB_ENCVAL<<6)|RDB_ENC_INT32;
enc[1] = value&0xFF;
enc[2] = (value>>8)&0xFF;
enc[3] = (value>>16)&0xFF;
enc[4] = (value>>24)&0xFF;
return 5;
} else {
return 0;
}
}
/* Loads an integer-encoded object with the specified encoding type "enctype".
* The returned value changes according to the flags, see
* rdbGenericLoadStringObject() for more info. */
void *rdbLoadIntegerObject(rio *rdb, int enctype, int flags, size_t *lenptr) {
int plain = flags & RDB_LOAD_PLAIN;
int sds = flags & RDB_LOAD_SDS;
int encode = flags & RDB_LOAD_ENC;
unsigned char enc[4];
long long val;
if (enctype == RDB_ENC_INT8) {
if (rioRead(rdb,enc,1) == 0) return NULL;
val = (signed char)enc[0];
} else if (enctype == RDB_ENC_INT16) {
uint16_t v;
if (rioRead(rdb,enc,2) == 0) return NULL;
v = enc[0]|(enc[1]<<8);
val = (int16_t)v;
} else if (enctype == RDB_ENC_INT32) {
uint32_t v;
if (rioRead(rdb,enc,4) == 0) return NULL;
v = enc[0]|(enc[1]<<8)|(enc[2]<<16)|(enc[3]<<24);
val = (int32_t)v;
} else {
rdbExitReportCorruptRDB("Unknown RDB integer encoding type %d",enctype);
return NULL; /* Never reached. */
}
if (plain || sds) {
char buf[LONG_STR_SIZE], *p;
int len = ll2string(buf,sizeof(buf),val);
if (lenptr) *lenptr = len;
p = plain ? zmalloc(len) : sdsnewlen(SDS_NOINIT,len);
memcpy(p,buf,len);
return p;
} else if (encode) {
return createStringObjectFromLongLongForValue(val);
} else {
return createObject(OBJ_STRING,sdsfromlonglong(val));
}
}
/* String objects in the form "2391" "-100" without any space and with a
* range of values that can fit in an 8, 16 or 32 bit signed value can be
* encoded as integers to save space */
int rdbTryIntegerEncoding(char *s, size_t len, unsigned char *enc) {
long long value;
char *endptr, buf[32];
/* Check if it's possible to encode this value as a number */
value = strtoll(s, &endptr, 10);
if (endptr[0] != '\0') return 0;
ll2string(buf,32,value);
/* If the number converted back into a string is not identical
* then it's not possible to encode the string as integer */
if (strlen(buf) != len || memcmp(buf,s,len)) return 0;
return rdbEncodeInteger(value,enc);
}
ssize_t rdbSaveLzfBlob(rio *rdb, void *data, size_t compress_len,
size_t original_len) {
unsigned char byte;
ssize_t n, nwritten = 0;
/* Data compressed! Let's save it on disk */
byte = (RDB_ENCVAL<<6)|RDB_ENC_LZF;
if ((n = rdbWriteRaw(rdb,&byte,1)) == -1) goto writeerr;
nwritten += n;
if ((n = rdbSaveLen(rdb,compress_len)) == -1) goto writeerr;
nwritten += n;
if ((n = rdbSaveLen(rdb,original_len)) == -1) goto writeerr;
nwritten += n;
if ((n = rdbWriteRaw(rdb,data,compress_len)) == -1) goto writeerr;
nwritten += n;
return nwritten;
writeerr:
return -1;
}
ssize_t rdbSaveLzfStringObject(rio *rdb, unsigned char *s, size_t len) {
size_t comprlen, outlen;
void *out;
/* We require at least four bytes compression for this to be worth it */
if (len <= 4) return 0;
outlen = len-4;
if ((out = zmalloc(outlen+1)) == NULL) return 0;
comprlen = lzf_compress(s, len, out, outlen);
if (comprlen == 0) {
zfree(out);
return 0;
}
ssize_t nwritten = rdbSaveLzfBlob(rdb, out, comprlen, len);
zfree(out);
return nwritten;
}
/* Load an LZF compressed string in RDB format. The returned value
* changes according to 'flags'. For more info check the
* rdbGenericLoadStringObject() function. */
void *rdbLoadLzfStringObject(rio *rdb, int flags, size_t *lenptr) {
int plain = flags & RDB_LOAD_PLAIN;
int sds = flags & RDB_LOAD_SDS;
uint64_t len, clen;
unsigned char *c = NULL;
char *val = NULL;
if ((clen = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
if ((len = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
if ((c = zmalloc(clen)) == NULL) goto err;
/* Allocate our target according to the uncompressed size. */
if (plain) {
val = zmalloc(len);
} else {
val = sdsnewlen(SDS_NOINIT,len);
}
if (lenptr) *lenptr = len;
/* Load the compressed representation and uncompress it to target. */
if (rioRead(rdb,c,clen) == 0) goto err;
if (lzf_decompress(c,clen,val,len) == 0) {
rdbExitReportCorruptRDB("Invalid LZF compressed string");
}
zfree(c);
if (plain || sds) {
return val;
} else {
return createObject(OBJ_STRING,val);
}
err:
zfree(c);
if (plain)
zfree(val);
else
sdsfree(val);
return NULL;
}
/* Save a string object as [len][data] on disk. If the object is a string
* representation of an integer value we try to save it in a special form */
ssize_t rdbSaveRawString(rio *rdb, unsigned char *s, size_t len) {
int enclen;
ssize_t n, nwritten = 0;
/* Try integer encoding */
if (len <= 11) {
unsigned char buf[5];
if ((enclen = rdbTryIntegerEncoding((char*)s,len,buf)) > 0) {
if (rdbWriteRaw(rdb,buf,enclen) == -1) return -1;
return enclen;
}
}
/* Try LZF compression - under 20 bytes it's unable to compress even
* aaaaaaaaaaaaaaaaaa so skip it */
if (server.rdb_compression && len > 20) {
n = rdbSaveLzfStringObject(rdb,s,len);
if (n == -1) return -1;
if (n > 0) return n;
/* Return value of 0 means data can't be compressed, save the old way */
}
/* Store verbatim */
if ((n = rdbSaveLen(rdb,len)) == -1) return -1;
nwritten += n;
if (len > 0) {
if (rdbWriteRaw(rdb,s,len) == -1) return -1;
nwritten += len;
}
return nwritten;
}
/* Save a long long value as either an encoded string or a string. */
ssize_t rdbSaveLongLongAsStringObject(rio *rdb, long long value) {
unsigned char buf[32];
ssize_t n, nwritten = 0;
int enclen = rdbEncodeInteger(value,buf);
if (enclen > 0) {
return rdbWriteRaw(rdb,buf,enclen);
} else {
/* Encode as string */
enclen = ll2string((char*)buf,32,value);
serverAssert(enclen < 32);
if ((n = rdbSaveLen(rdb,enclen)) == -1) return -1;
nwritten += n;
if ((n = rdbWriteRaw(rdb,buf,enclen)) == -1) return -1;
nwritten += n;
}
return nwritten;
}
/* Like rdbSaveRawString() gets a Redis object instead. */
ssize_t rdbSaveStringObject(rio *rdb, robj *obj) {
/* Avoid to decode the object, then encode it again, if the
* object is already integer encoded. */
if (obj->encoding == OBJ_ENCODING_INT) {
return rdbSaveLongLongAsStringObject(rdb,(long)obj->ptr);
} else {
serverAssertWithInfo(NULL,obj,sdsEncodedObject(obj));
return rdbSaveRawString(rdb,obj->ptr,sdslen(obj->ptr));
}
}
/* Load a string object from an RDB file according to flags:
*
* RDB_LOAD_NONE (no flags): load an RDB object, unencoded.
* RDB_LOAD_ENC: If the returned type is a Redis object, try to
* encode it in a special way to be more memory
* efficient. When this flag is passed the function
* no longer guarantees that obj->ptr is an SDS string.
* RDB_LOAD_PLAIN: Return a plain string allocated with zmalloc()
* instead of a Redis object with an sds in it.
* RDB_LOAD_SDS: Return an SDS string instead of a Redis object.
*
* On I/O error NULL is returned.
*/
void *rdbGenericLoadStringObject(rio *rdb, int flags, size_t *lenptr) {
int encode = flags & RDB_LOAD_ENC;
int plain = flags & RDB_LOAD_PLAIN;
int sds = flags & RDB_LOAD_SDS;
int isencoded;
uint64_t len;
len = rdbLoadLen(rdb,&isencoded);
if (isencoded) {
switch(len) {
case RDB_ENC_INT8:
case RDB_ENC_INT16:
case RDB_ENC_INT32:
return rdbLoadIntegerObject(rdb,len,flags,lenptr);
case RDB_ENC_LZF:
return rdbLoadLzfStringObject(rdb,flags,lenptr);
default:
rdbExitReportCorruptRDB("Unknown RDB string encoding type %d",len);
return NULL; /* Never reached. */
}
}
if (len == RDB_LENERR) return NULL;
if (plain || sds) {
void *buf = plain ? zmalloc(len) : sdsnewlen(SDS_NOINIT,len);
if (lenptr) *lenptr = len;
if (len && rioRead(rdb,buf,len) == 0) {
if (plain)
zfree(buf);
else
sdsfree(buf);
return NULL;
}
return buf;
} else {
robj *o = encode ? createStringObject(SDS_NOINIT,len) :
createRawStringObject(SDS_NOINIT,len);
if (len && rioRead(rdb,o->ptr,len) == 0) {
decrRefCount(o);
return NULL;
}
return o;
}
}
robj *rdbLoadStringObject(rio *rdb) {
return rdbGenericLoadStringObject(rdb,RDB_LOAD_NONE,NULL);
}
robj *rdbLoadEncodedStringObject(rio *rdb) {
return rdbGenericLoadStringObject(rdb,RDB_LOAD_ENC,NULL);
}
/* Save a double value. Doubles are saved as strings prefixed by an unsigned
* 8 bit integer specifying the length of the representation.
* This 8 bit integer has special values in order to specify the following
* conditions:
* 253: not a number
* 254: + inf
* 255: - inf
*/
int rdbSaveDoubleValue(rio *rdb, double val) {
unsigned char buf[128];
int len;
if (isnan(val)) {
buf[0] = 253;
len = 1;
} else if (!isfinite(val)) {
len = 1;
buf[0] = (val < 0) ? 255 : 254;
} else {
#if (DBL_MANT_DIG >= 52) && (LLONG_MAX == 0x7fffffffffffffffLL)
/* Check if the float is in a safe range to be casted into a
* long long. We are assuming that long long is 64 bit here.
* Also we are assuming that there are no implementations around where
* double has precision < 52 bit.
*
* Under this assumptions we test if a double is inside an interval
* where casting to long long is safe. Then using two castings we
* make sure the decimal part is zero. If all this is true we use
* integer printing function that is much faster. */
double min = -4503599627370495; /* (2^52)-1 */
double max = 4503599627370496; /* -(2^52) */
if (val > min && val < max && val == ((double)((long long)val)))
ll2string((char*)buf+1,sizeof(buf)-1,(long long)val);
else
#endif
snprintf((char*)buf+1,sizeof(buf)-1,"%.17g",val);
buf[0] = strlen((char*)buf+1);
len = buf[0]+1;
}
return rdbWriteRaw(rdb,buf,len);
}
/* For information about double serialization check rdbSaveDoubleValue() */
int rdbLoadDoubleValue(rio *rdb, double *val) {
char buf[256];
unsigned char len;
if (rioRead(rdb,&len,1) == 0) return -1;
switch(len) {
case 255: *val = R_NegInf; return 0;
case 254: *val = R_PosInf; return 0;
case 253: *val = R_Nan; return 0;
default:
if (rioRead(rdb,buf,len) == 0) return -1;
buf[len] = '\0';
sscanf(buf, "%lg", val);
return 0;
}
}
/* Saves a double for RDB 8 or greater, where IE754 binary64 format is assumed.
* We just make sure the integer is always stored in little endian, otherwise
* the value is copied verbatim from memory to disk.
*
* Return -1 on error, the size of the serialized value on success. */
int rdbSaveBinaryDoubleValue(rio *rdb, double val) {
memrev64ifbe(&val);
return rdbWriteRaw(rdb,&val,sizeof(val));
}
/* Loads a double from RDB 8 or greater. See rdbSaveBinaryDoubleValue() for
* more info. On error -1 is returned, otherwise 0. */
int rdbLoadBinaryDoubleValue(rio *rdb, double *val) {
if (rioRead(rdb,val,sizeof(*val)) == 0) return -1;
memrev64ifbe(val);
return 0;
}
/* Like rdbSaveBinaryDoubleValue() but single precision. */
int rdbSaveBinaryFloatValue(rio *rdb, float val) {
memrev32ifbe(&val);
return rdbWriteRaw(rdb,&val,sizeof(val));
}
/* Like rdbLoadBinaryDoubleValue() but single precision. */
int rdbLoadBinaryFloatValue(rio *rdb, float *val) {
if (rioRead(rdb,val,sizeof(*val)) == 0) return -1;
memrev32ifbe(val);
return 0;
}
/* Save the object type of object "o". */
int rdbSaveObjectType(rio *rdb, robj *o) {
switch (o->type) {
case OBJ_STRING:
return rdbSaveType(rdb,RDB_TYPE_STRING);
case OBJ_LIST:
if (o->encoding == OBJ_ENCODING_QUICKLIST)
return rdbSaveType(rdb,RDB_TYPE_LIST_QUICKLIST);
else
serverPanic("Unknown list encoding");
case OBJ_SET:
if (o->encoding == OBJ_ENCODING_INTSET)
return rdbSaveType(rdb,RDB_TYPE_SET_INTSET);
else if (o->encoding == OBJ_ENCODING_HT)
return rdbSaveType(rdb,RDB_TYPE_SET);
else
serverPanic("Unknown set encoding");
case OBJ_ZSET:
if (o->encoding == OBJ_ENCODING_ZIPLIST)
return rdbSaveType(rdb,RDB_TYPE_ZSET_ZIPLIST);
else if (o->encoding == OBJ_ENCODING_SKIPLIST)
return rdbSaveType(rdb,RDB_TYPE_ZSET_2);
else
serverPanic("Unknown sorted set encoding");
case OBJ_HASH:
if (o->encoding == OBJ_ENCODING_ZIPLIST)
return rdbSaveType(rdb,RDB_TYPE_HASH_ZIPLIST);
else if (o->encoding == OBJ_ENCODING_HT)
return rdbSaveType(rdb,RDB_TYPE_HASH);
else
serverPanic("Unknown hash encoding");
case OBJ_STREAM:
return rdbSaveType(rdb,RDB_TYPE_STREAM_LISTPACKS);
case OBJ_MODULE:
return rdbSaveType(rdb,RDB_TYPE_MODULE_2);
default:
serverPanic("Unknown object type");
}
return -1; /* avoid warning */
}
/* Use rdbLoadType() to load a TYPE in RDB format, but returns -1 if the
* type is not specifically a valid Object Type. */
int rdbLoadObjectType(rio *rdb) {
int type;
if ((type = rdbLoadType(rdb)) == -1) return -1;
if (!rdbIsObjectType(type)) return -1;
return type;
}
/* This helper function serializes a consumer group Pending Entries List (PEL)
* into the RDB file. The 'nacks' argument tells the function if also persist
* the informations about the not acknowledged message, or if to persist
* just the IDs: this is useful because for the global consumer group PEL
* we serialized the NACKs as well, but when serializing the local consumer
* PELs we just add the ID, that will be resolved inside the global PEL to
* put a reference to the same structure. */
ssize_t rdbSaveStreamPEL(rio *rdb, rax *pel, int nacks) {
ssize_t n, nwritten = 0;
/* Number of entries in the PEL. */
if ((n = rdbSaveLen(rdb,raxSize(pel))) == -1) return -1;
nwritten += n;
/* Save each entry. */
raxIterator ri;
raxStart(&ri,pel);
raxSeek(&ri,"^",NULL,0);
while(raxNext(&ri)) {
/* We store IDs in raw form as 128 big big endian numbers, like
* they are inside the radix tree key. */
if ((n = rdbWriteRaw(rdb,ri.key,sizeof(streamID))) == -1) return -1;
nwritten += n;
if (nacks) {
streamNACK *nack = ri.data;
if ((n = rdbSaveMillisecondTime(rdb,nack->delivery_time)) == -1)
return -1;
nwritten += n;
if ((n = rdbSaveLen(rdb,nack->delivery_count)) == -1) return -1;
nwritten += n;
/* We don't save the consumer name: we'll save the pending IDs
* for each consumer in the consumer PEL, and resolve the consumer
* at loading time. */
}
}
raxStop(&ri);
return nwritten;
}
/* Serialize the consumers of a stream consumer group into the RDB. Helper
* function for the stream data type serialization. What we do here is to
* persist the consumer metadata, and it's PEL, for each consumer. */
size_t rdbSaveStreamConsumers(rio *rdb, streamCG *cg) {
ssize_t n, nwritten = 0;
/* Number of consumers in this consumer group. */
if ((n = rdbSaveLen(rdb,raxSize(cg->consumers))) == -1) return -1;
nwritten += n;
/* Save each consumer. */
raxIterator ri;
raxStart(&ri,cg->consumers);
raxSeek(&ri,"^",NULL,0);
while(raxNext(&ri)) {
streamConsumer *consumer = ri.data;
/* Consumer name. */
if ((n = rdbSaveRawString(rdb,ri.key,ri.key_len)) == -1) return -1;
nwritten += n;
/* Last seen time. */
if ((n = rdbSaveMillisecondTime(rdb,consumer->seen_time)) == -1)
return -1;
nwritten += n;
/* Consumer PEL, without the ACKs (see last parameter of the function
* passed with value of 0), at loading time we'll lookup the ID
* in the consumer group global PEL and will put a reference in the
* consumer local PEL. */
if ((n = rdbSaveStreamPEL(rdb,consumer->pel,0)) == -1)
return -1;
nwritten += n;
}
raxStop(&ri);
return nwritten;
}
/* Save a Redis object.
* Returns -1 on error, number of bytes written on success. */
ssize_t rdbSaveObject(rio *rdb, robj *o, robj *key) {
ssize_t n = 0, nwritten = 0;
if (o->type == OBJ_STRING) {
/* Save a string value */
if ((n = rdbSaveStringObject(rdb,o)) == -1) return -1;
nwritten += n;
} else if (o->type == OBJ_LIST) {
/* Save a list value */
if (o->encoding == OBJ_ENCODING_QUICKLIST) {
quicklist *ql = o->ptr;
quicklistNode *node = ql->head;
if ((n = rdbSaveLen(rdb,ql->len)) == -1) return -1;
nwritten += n;
while(node) {
if (quicklistNodeIsCompressed(node)) {
void *data;
size_t compress_len = quicklistGetLzf(node, &data);
if ((n = rdbSaveLzfBlob(rdb,data,compress_len,node->sz)) == -1) return -1;
nwritten += n;
} else {
if ((n = rdbSaveRawString(rdb,node->zl,node->sz)) == -1) return -1;
nwritten += n;
}
node = node->next;
}
} else {
serverPanic("Unknown list encoding");
}
} else if (o->type == OBJ_SET) {
/* Save a set value */
if (o->encoding == OBJ_ENCODING_HT) {
dict *set = o->ptr;
dictIterator *di = dictGetIterator(set);
dictEntry *de;
if ((n = rdbSaveLen(rdb,dictSize(set))) == -1) {
dictReleaseIterator(di);
return -1;
}
nwritten += n;
while((de = dictNext(di)) != NULL) {
sds ele = dictGetKey(de);
if ((n = rdbSaveRawString(rdb,(unsigned char*)ele,sdslen(ele)))
== -1)
{
dictReleaseIterator(di);
return -1;
}
nwritten += n;
}
dictReleaseIterator(di);
} else if (o->encoding == OBJ_ENCODING_INTSET) {
size_t l = intsetBlobLen((intset*)o->ptr);
if ((n = rdbSaveRawString(rdb,o->ptr,l)) == -1) return -1;
nwritten += n;
} else {
serverPanic("Unknown set encoding");
}
} else if (o->type == OBJ_ZSET) {
/* Save a sorted set value */
if (o->encoding == OBJ_ENCODING_ZIPLIST) {
size_t l = ziplistBlobLen((unsigned char*)o->ptr);
if ((n = rdbSaveRawString(rdb,o->ptr,l)) == -1) return -1;
nwritten += n;
} else if (o->encoding == OBJ_ENCODING_SKIPLIST) {
zset *zs = o->ptr;
zskiplist *zsl = zs->zsl;
if ((n = rdbSaveLen(rdb,zsl->length)) == -1) return -1;
nwritten += n;
/* We save the skiplist elements from the greatest to the smallest
* (that's trivial since the elements are already ordered in the
* skiplist): this improves the load process, since the next loaded
* element will always be the smaller, so adding to the skiplist
* will always immediately stop at the head, making the insertion
* O(1) instead of O(log(N)). */
zskiplistNode *zn = zsl->tail;
while (zn != NULL) {
if ((n = rdbSaveRawString(rdb,
(unsigned char*)zn->ele,sdslen(zn->ele))) == -1)
{
return -1;
}
nwritten += n;
if ((n = rdbSaveBinaryDoubleValue(rdb,zn->score)) == -1)
return -1;
nwritten += n;
zn = zn->backward;
}
} else {
serverPanic("Unknown sorted set encoding");
}
} else if (o->type == OBJ_HASH) {
/* Save a hash value */
if (o->encoding == OBJ_ENCODING_ZIPLIST) {
size_t l = ziplistBlobLen((unsigned char*)o->ptr);
if ((n = rdbSaveRawString(rdb,o->ptr,l)) == -1) return -1;
nwritten += n;
} else if (o->encoding == OBJ_ENCODING_HT) {
dictIterator *di = dictGetIterator(o->ptr);
dictEntry *de;
if ((n = rdbSaveLen(rdb,dictSize((dict*)o->ptr))) == -1) {
dictReleaseIterator(di);
return -1;
}
nwritten += n;
while((de = dictNext(di)) != NULL) {
sds field = dictGetKey(de);
sds value = dictGetVal(de);
if ((n = rdbSaveRawString(rdb,(unsigned char*)field,
sdslen(field))) == -1)
{
dictReleaseIterator(di);
return -1;
}
nwritten += n;
if ((n = rdbSaveRawString(rdb,(unsigned char*)value,
sdslen(value))) == -1)
{
dictReleaseIterator(di);
return -1;
}
nwritten += n;
}
dictReleaseIterator(di);
} else {
serverPanic("Unknown hash encoding");
}
} else if (o->type == OBJ_STREAM) {
/* Store how many listpacks we have inside the radix tree. */
stream *s = o->ptr;
rax *rax = s->rax;
if ((n = rdbSaveLen(rdb,raxSize(rax))) == -1) return -1;
nwritten += n;
/* Serialize all the listpacks inside the radix tree as they are,
* when loading back, we'll use the first entry of each listpack
* to insert it back into the radix tree. */
raxIterator ri;
raxStart(&ri,rax);
raxSeek(&ri,"^",NULL,0);
while (raxNext(&ri)) {
unsigned char *lp = ri.data;
size_t lp_bytes = lpBytes(lp);
if ((n = rdbSaveRawString(rdb,ri.key,ri.key_len)) == -1) return -1;
nwritten += n;
if ((n = rdbSaveRawString(rdb,lp,lp_bytes)) == -1) return -1;
nwritten += n;
}
raxStop(&ri);
/* Save the number of elements inside the stream. We cannot obtain
* this easily later, since our macro nodes should be checked for
* number of items: not a great CPU / space tradeoff. */
if ((n = rdbSaveLen(rdb,s->length)) == -1) return -1;
nwritten += n;
/* Save the last entry ID. */
if ((n = rdbSaveLen(rdb,s->last_id.ms)) == -1) return -1;
nwritten += n;
if ((n = rdbSaveLen(rdb,s->last_id.seq)) == -1) return -1;
nwritten += n;
/* The consumer groups and their clients are part of the stream
* type, so serialize every consumer group. */
/* Save the number of groups. */
size_t num_cgroups = s->cgroups ? raxSize(s->cgroups) : 0;
if ((n = rdbSaveLen(rdb,num_cgroups)) == -1) return -1;
nwritten += n;
if (num_cgroups) {
/* Serialize each consumer group. */
raxStart(&ri,s->cgroups);
raxSeek(&ri,"^",NULL,0);
while(raxNext(&ri)) {
streamCG *cg = ri.data;
/* Save the group name. */
if ((n = rdbSaveRawString(rdb,ri.key,ri.key_len)) == -1)
return -1;
nwritten += n;
/* Last ID. */
if ((n = rdbSaveLen(rdb,cg->last_id.ms)) == -1) return -1;
nwritten += n;
if ((n = rdbSaveLen(rdb,cg->last_id.seq)) == -1) return -1;
nwritten += n;
/* Save the global PEL. */
if ((n = rdbSaveStreamPEL(rdb,cg->pel,1)) == -1) return -1;
nwritten += n;
/* Save the consumers of this group. */
if ((n = rdbSaveStreamConsumers(rdb,cg)) == -1) return -1;
nwritten += n;
}
raxStop(&ri);
}
} else if (o->type == OBJ_MODULE) {
/* Save a module-specific value. */
RedisModuleIO io;
moduleValue *mv = o->ptr;
moduleType *mt = mv->type;
/* Write the "module" identifier as prefix, so that we'll be able
* to call the right module during loading. */
int retval = rdbSaveLen(rdb,mt->id);
if (retval == -1) return -1;
io.bytes += retval;
/* Then write the module-specific representation + EOF marker. */
moduleInitIOContext(io,mt,rdb,key);
mt->rdb_save(&io,mv->value);
retval = rdbSaveLen(rdb,RDB_MODULE_OPCODE_EOF);
if (retval == -1)
io.error = 1;
else
io.bytes += retval;
if (io.ctx) {
moduleFreeContext(io.ctx);
zfree(io.ctx);
}
return io.error ? -1 : (ssize_t)io.bytes;
} else {
serverPanic("Unknown object type");
}
return nwritten;
}
/* Return the length the object will have on disk if saved with
* the rdbSaveObject() function. Currently we use a trick to get
* this length with very little changes to the code. In the future
* we could switch to a faster solution. */
size_t rdbSavedObjectLen(robj *o) {
ssize_t len = rdbSaveObject(NULL,o,NULL);
serverAssertWithInfo(NULL,o,len != -1);
return len;
}
/* Save a key-value pair, with expire time, type, key, value.
* On error -1 is returned.
* On success if the key was actually saved 1 is returned, otherwise 0
* is returned (the key was already expired). */
int rdbSaveKeyValuePair(rio *rdb, robj *key, robj *val, long long expiretime) {
int savelru = server.maxmemory_policy & MAXMEMORY_FLAG_LRU;
int savelfu = server.maxmemory_policy & MAXMEMORY_FLAG_LFU;
/* Save the expire time */
if (expiretime != -1) {
if (rdbSaveType(rdb,RDB_OPCODE_EXPIRETIME_MS) == -1) return -1;
if (rdbSaveMillisecondTime(rdb,expiretime) == -1) return -1;
}
/* Save the LRU info. */
if (savelru) {
uint64_t idletime = estimateObjectIdleTime(val);
idletime /= 1000; /* Using seconds is enough and requires less space.*/
if (rdbSaveType(rdb,RDB_OPCODE_IDLE) == -1) return -1;
if (rdbSaveLen(rdb,idletime) == -1) return -1;
}
/* Save the LFU info. */
if (savelfu) {
uint8_t buf[1];
buf[0] = LFUDecrAndReturn(val);
/* We can encode this in exactly two bytes: the opcode and an 8
* bit counter, since the frequency is logarithmic with a 0-255 range.
* Note that we do not store the halving time because to reset it
* a single time when loading does not affect the frequency much. */
if (rdbSaveType(rdb,RDB_OPCODE_FREQ) == -1) return -1;
if (rdbWriteRaw(rdb,buf,1) == -1) return -1;
}
/* Save type, key, value */
if (rdbSaveObjectType(rdb,val) == -1) return -1;
if (rdbSaveStringObject(rdb,key) == -1) return -1;
if (rdbSaveObject(rdb,val,key) == -1) return -1;
/* Delay return if required (for testing) */
if (server.rdb_key_save_delay)
usleep(server.rdb_key_save_delay);
return 1;
}
/* Save an AUX field. */
ssize_t rdbSaveAuxField(rio *rdb, void *key, size_t keylen, void *val, size_t vallen) {
ssize_t ret, len = 0;
if ((ret = rdbSaveType(rdb,RDB_OPCODE_AUX)) == -1) return -1;
len += ret;
if ((ret = rdbSaveRawString(rdb,key,keylen)) == -1) return -1;
len += ret;
if ((ret = rdbSaveRawString(rdb,val,vallen)) == -1) return -1;
len += ret;
return len;
}
/* Wrapper for rdbSaveAuxField() used when key/val length can be obtained
* with strlen(). */
ssize_t rdbSaveAuxFieldStrStr(rio *rdb, char *key, char *val) {
return rdbSaveAuxField(rdb,key,strlen(key),val,strlen(val));
}
/* Wrapper for strlen(key) + integer type (up to long long range). */
ssize_t rdbSaveAuxFieldStrInt(rio *rdb, char *key, long long val) {
char buf[LONG_STR_SIZE];
int vlen = ll2string(buf,sizeof(buf),val);
return rdbSaveAuxField(rdb,key,strlen(key),buf,vlen);
}
/* Save a few default AUX fields with information about the RDB generated. */
int rdbSaveInfoAuxFields(rio *rdb, int rdbflags, rdbSaveInfo *rsi) {
int redis_bits = (sizeof(void*) == 8) ? 64 : 32;
int aof_preamble = (rdbflags & RDBFLAGS_AOF_PREAMBLE) != 0;
/* Add a few fields about the state when the RDB was created. */
if (rdbSaveAuxFieldStrStr(rdb,"redis-ver",REDIS_VERSION) == -1) return -1;
if (rdbSaveAuxFieldStrInt(rdb,"redis-bits",redis_bits) == -1) return -1;
if (rdbSaveAuxFieldStrInt(rdb,"ctime",time(NULL)) == -1) return -1;
if (rdbSaveAuxFieldStrInt(rdb,"used-mem",zmalloc_used_memory()) == -1) return -1;
/* Handle saving options that generate aux fields. */
if (rsi) {
if (rdbSaveAuxFieldStrInt(rdb,"repl-stream-db",rsi->repl_stream_db)
== -1) return -1;
if (rdbSaveAuxFieldStrStr(rdb,"repl-id",server.replid)
== -1) return -1;
if (rdbSaveAuxFieldStrInt(rdb,"repl-offset",server.master_repl_offset)
== -1) return -1;
}
if (rdbSaveAuxFieldStrInt(rdb,"aof-preamble",aof_preamble) == -1) return -1;
return 1;
}
ssize_t rdbSaveSingleModuleAux(rio *rdb, int when, moduleType *mt) {
/* Save a module-specific aux value. */
RedisModuleIO io;
int retval = rdbSaveType(rdb, RDB_OPCODE_MODULE_AUX);
/* Write the "module" identifier as prefix, so that we'll be able
* to call the right module during loading. */
retval = rdbSaveLen(rdb,mt->id);
if (retval == -1) return -1;
io.bytes += retval;
/* write the 'when' so that we can provide it on loading. add a UINT opcode
* for backwards compatibility, everything after the MT needs to be prefixed
* by an opcode. */
retval = rdbSaveLen(rdb,RDB_MODULE_OPCODE_UINT);
if (retval == -1) return -1;
io.bytes += retval;
retval = rdbSaveLen(rdb,when);
if (retval == -1) return -1;
io.bytes += retval;
/* Then write the module-specific representation + EOF marker. */
moduleInitIOContext(io,mt,rdb,NULL);
mt->aux_save(&io,when);
retval = rdbSaveLen(rdb,RDB_MODULE_OPCODE_EOF);
if (retval == -1)
io.error = 1;
else
io.bytes += retval;
if (io.ctx) {
moduleFreeContext(io.ctx);
zfree(io.ctx);
}
if (io.error)
return -1;
return io.bytes;
}
/* Produces a dump of the database in RDB format sending it to the specified
* Redis I/O channel. On success C_OK is returned, otherwise C_ERR
* is returned and part of the output, or all the output, can be
* missing because of I/O errors.
*
* When the function returns C_ERR and if 'error' is not NULL, the
* integer pointed by 'error' is set to the value of errno just after the I/O
* error. */
int rdbSaveRio(rio *rdb, int *error, int rdbflags, rdbSaveInfo *rsi) {
dictIterator *di = NULL;
dictEntry *de;
char magic[10];
int j;
uint64_t cksum;
size_t processed = 0;
if (server.rdb_checksum)
rdb->update_cksum = rioGenericUpdateChecksum;
snprintf(magic,sizeof(magic),"REDIS%04d",RDB_VERSION);
if (rdbWriteRaw(rdb,magic,9) == -1) goto werr;
if (rdbSaveInfoAuxFields(rdb,rdbflags,rsi) == -1) goto werr;
if (rdbSaveModulesAux(rdb, REDISMODULE_AUX_BEFORE_RDB) == -1) goto werr;
for (j = 0; j < server.dbnum; j++) {
redisDb *db = server.db+j;
dict *d = db->dict;
if (dictSize(d) == 0) continue;
di = dictGetSafeIterator(d);
/* Write the SELECT DB opcode */
if (rdbSaveType(rdb,RDB_OPCODE_SELECTDB) == -1) goto werr;
if (rdbSaveLen(rdb,j) == -1) goto werr;
/* Write the RESIZE DB opcode. We trim the size to UINT32_MAX, which
* is currently the largest type we are able to represent in RDB sizes.
* However this does not limit the actual size of the DB to load since
* these sizes are just hints to resize the hash tables. */
uint64_t db_size, expires_size;
db_size = dictSize(db->dict);
expires_size = dictSize(db->expires);
if (rdbSaveType(rdb,RDB_OPCODE_RESIZEDB) == -1) goto werr;
if (rdbSaveLen(rdb,db_size) == -1) goto werr;
if (rdbSaveLen(rdb,expires_size) == -1) goto werr;
/* Iterate this DB writing every entry */
while((de = dictNext(di)) != NULL) {
sds keystr = dictGetKey(de);
robj key, *o = dictGetVal(de);
long long expire;
initStaticStringObject(key,keystr);
expire = getExpire(db,&key);
if (rdbSaveKeyValuePair(rdb,&key,o,expire) == -1) goto werr;
/* When this RDB is produced as part of an AOF rewrite, move
* accumulated diff from parent to child while rewriting in
* order to have a smaller final write. */
if (rdbflags & RDBFLAGS_AOF_PREAMBLE &&
rdb->processed_bytes > processed+AOF_READ_DIFF_INTERVAL_BYTES)
{
processed = rdb->processed_bytes;
aofReadDiffFromParent();
}
}
dictReleaseIterator(di);
di = NULL; /* So that we don't release it again on error. */
}
/* If we are storing the replication information on disk, persist
* the script cache as well: on successful PSYNC after a restart, we need
* to be able to process any EVALSHA inside the replication backlog the
* master will send us. */
if (rsi && dictSize(server.lua_scripts)) {
di = dictGetIterator(server.lua_scripts);
while((de = dictNext(di)) != NULL) {
robj *body = dictGetVal(de);
if (rdbSaveAuxField(rdb,"lua",3,body->ptr,sdslen(body->ptr)) == -1)
goto werr;
}
dictReleaseIterator(di);
di = NULL; /* So that we don't release it again on error. */
}
if (rdbSaveModulesAux(rdb, REDISMODULE_AUX_AFTER_RDB) == -1) goto werr;
/* EOF opcode */
if (rdbSaveType(rdb,RDB_OPCODE_EOF) == -1) goto werr;
/* CRC64 checksum. It will be zero if checksum computation is disabled, the
* loading code skips the check in this case. */
cksum = rdb->cksum;
memrev64ifbe(&cksum);
if (rioWrite(rdb,&cksum,8) == 0) goto werr;
return C_OK;
werr:
if (error) *error = errno;
if (di) dictReleaseIterator(di);
return C_ERR;
}
/* This is just a wrapper to rdbSaveRio() that additionally adds a prefix
* and a suffix to the generated RDB dump. The prefix is:
*
* $EOF:<40 bytes unguessable hex string>\r\n
*
* While the suffix is the 40 bytes hex string we announced in the prefix.
* This way processes receiving the payload can understand when it ends
* without doing any processing of the content. */
int rdbSaveRioWithEOFMark(rio *rdb, int *error, rdbSaveInfo *rsi) {
char eofmark[RDB_EOF_MARK_SIZE];
startSaving(RDBFLAGS_REPLICATION);
getRandomHexChars(eofmark,RDB_EOF_MARK_SIZE);
if (error) *error = 0;
if (rioWrite(rdb,"$EOF:",5) == 0) goto werr;
if (rioWrite(rdb,eofmark,RDB_EOF_MARK_SIZE) == 0) goto werr;
if (rioWrite(rdb,"\r\n",2) == 0) goto werr;
if (rdbSaveRio(rdb,error,RDBFLAGS_NONE,rsi) == C_ERR) goto werr;
if (rioWrite(rdb,eofmark,RDB_EOF_MARK_SIZE) == 0) goto werr;
stopSaving(1);
return C_OK;
werr: /* Write error. */
/* Set 'error' only if not already set by rdbSaveRio() call. */
if (error && *error == 0) *error = errno;
stopSaving(0);
return C_ERR;
}
/* Save the DB on disk. Return C_ERR on error, C_OK on success. */
int rdbSave(char *filename, rdbSaveInfo *rsi) {
char tmpfile[256];
char cwd[MAXPATHLEN]; /* Current working dir path for error messages. */
FILE *fp;
rio rdb;
int error = 0;
snprintf(tmpfile,256,"temp-%d.rdb", (int) getpid());
fp = fopen(tmpfile,"w");
if (!fp) {
char *cwdp = getcwd(cwd,MAXPATHLEN);
serverLog(LL_WARNING,
"Failed opening the RDB file %s (in server root dir %s) "
"for saving: %s",
filename,
cwdp ? cwdp : "unknown",
strerror(errno));
return C_ERR;
}
rioInitWithFile(&rdb,fp);
startSaving(RDBFLAGS_NONE);
if (server.rdb_save_incremental_fsync)
rioSetAutoSync(&rdb,REDIS_AUTOSYNC_BYTES);
if (rdbSaveRio(&rdb,&error,RDBFLAGS_NONE,rsi) == C_ERR) {
errno = error;
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) {
char *cwdp = getcwd(cwd,MAXPATHLEN);
serverLog(LL_WARNING,
"Error moving temp DB file %s on the final "
"destination %s (in server root dir %s): %s",
tmpfile,
filename,
cwdp ? cwdp : "unknown",
strerror(errno));
unlink(tmpfile);
stopSaving(0);
return C_ERR;
}
serverLog(LL_NOTICE,"DB saved on disk");
server.dirty = 0;
server.lastsave = time(NULL);
server.lastbgsave_status = C_OK;
stopSaving(1);
return C_OK;
werr:
serverLog(LL_WARNING,"Write error saving DB on disk: %s", strerror(errno));
fclose(fp);
unlink(tmpfile);
stopSaving(0);
return C_ERR;
}
int rdbSaveBackground(char *filename, rdbSaveInfo *rsi) {
pid_t childpid;
if (hasActiveChildProcess()) return C_ERR;
server.dirty_before_bgsave = server.dirty;
server.lastbgsave_try = time(NULL);
openChildInfoPipe();
if ((childpid = redisFork()) == 0) {
int retval;
/* Child */
redisSetProcTitle("redis-rdb-bgsave");
retval = rdbSave(filename,rsi);
if (retval == C_OK) {
sendChildCOWInfo(CHILD_INFO_TYPE_RDB, "RDB");
}
exitFromChild((retval == C_OK) ? 0 : 1);
} else {
/* Parent */
if (childpid == -1) {
closeChildInfoPipe();
server.lastbgsave_status = C_ERR;
serverLog(LL_WARNING,"Can't save in background: fork: %s",
strerror(errno));
return C_ERR;
}
serverLog(LL_NOTICE,"Background saving started by pid %d",childpid);
server.rdb_save_time_start = time(NULL);
server.rdb_child_pid = childpid;
server.rdb_child_type = RDB_CHILD_TYPE_DISK;
return C_OK;
}
return C_OK; /* unreached */
}
void rdbRemoveTempFile(pid_t childpid) {
char tmpfile[256];
snprintf(tmpfile,sizeof(tmpfile),"temp-%d.rdb", (int) childpid);
unlink(tmpfile);
}
/* This function is called by rdbLoadObject() when the code is in RDB-check
* mode and we find a module value of type 2 that can be parsed without
* the need of the actual module. The value is parsed for errors, finally
* a dummy redis object is returned just to conform to the API. */
robj *rdbLoadCheckModuleValue(rio *rdb, char *modulename) {
uint64_t opcode;
while((opcode = rdbLoadLen(rdb,NULL)) != RDB_MODULE_OPCODE_EOF) {
if (opcode == RDB_MODULE_OPCODE_SINT ||
opcode == RDB_MODULE_OPCODE_UINT)
{
uint64_t len;
if (rdbLoadLenByRef(rdb,NULL,&len) == -1) {
rdbExitReportCorruptRDB(
"Error reading integer from module %s value", modulename);
}
} else if (opcode == RDB_MODULE_OPCODE_STRING) {
robj *o = rdbGenericLoadStringObject(rdb,RDB_LOAD_NONE,NULL);
if (o == NULL) {
rdbExitReportCorruptRDB(
"Error reading string from module %s value", modulename);
}
decrRefCount(o);
} else if (opcode == RDB_MODULE_OPCODE_FLOAT) {
float val;
if (rdbLoadBinaryFloatValue(rdb,&val) == -1) {
rdbExitReportCorruptRDB(
"Error reading float from module %s value", modulename);
}
} else if (opcode == RDB_MODULE_OPCODE_DOUBLE) {
double val;
if (rdbLoadBinaryDoubleValue(rdb,&val) == -1) {
rdbExitReportCorruptRDB(
"Error reading double from module %s value", modulename);
}
}
}
return createStringObject("module-dummy-value",18);
}
/* Load a Redis object of the specified type from the specified file.
* On success a newly allocated object is returned, otherwise NULL. */
robj *rdbLoadObject(int rdbtype, rio *rdb, robj *key) {
robj *o = NULL, *ele, *dec;
uint64_t len;
unsigned int i;
if (rdbtype == RDB_TYPE_STRING) {
/* Read string value */
if ((o = rdbLoadEncodedStringObject(rdb)) == NULL) return NULL;
o = tryObjectEncoding(o);
} else if (rdbtype == RDB_TYPE_LIST) {
/* Read list value */
if ((len = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
o = createQuicklistObject();
quicklistSetOptions(o->ptr, server.list_max_ziplist_size,
server.list_compress_depth);
/* Load every single element of the list */
while(len--) {
if ((ele = rdbLoadEncodedStringObject(rdb)) == NULL) return NULL;
dec = getDecodedObject(ele);
size_t len = sdslen(dec->ptr);
quicklistPushTail(o->ptr, dec->ptr, len);
decrRefCount(dec);
decrRefCount(ele);
}
} else if (rdbtype == RDB_TYPE_SET) {
/* Read Set value */
if ((len = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
/* Use a regular set when there are too many entries. */
if (len > server.set_max_intset_entries) {
o = createSetObject();
/* It's faster to expand the dict to the right size asap in order
* to avoid rehashing */
if (len > DICT_HT_INITIAL_SIZE)
dictExpand(o->ptr,len);
} else {
o = createIntsetObject();
}
/* Load every single element of the set */
for (i = 0; i < len; i++) {
long long llval;
sds sdsele;
if ((sdsele = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
if (o->encoding == OBJ_ENCODING_INTSET) {
/* Fetch integer value from element. */
if (isSdsRepresentableAsLongLong(sdsele,&llval) == C_OK) {
o->ptr = intsetAdd(o->ptr,llval,NULL);
} else {
setTypeConvert(o,OBJ_ENCODING_HT);
dictExpand(o->ptr,len);
}
}
/* This will also be called when the set was just converted
* to a regular hash table encoded set. */
if (o->encoding == OBJ_ENCODING_HT) {
dictAdd((dict*)o->ptr,sdsele,NULL);
} else {
sdsfree(sdsele);
}
}
} else if (rdbtype == RDB_TYPE_ZSET_2 || rdbtype == RDB_TYPE_ZSET) {
/* Read list/set value. */
uint64_t zsetlen;
size_t maxelelen = 0;
zset *zs;
if ((zsetlen = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
o = createZsetObject();
zs = o->ptr;
if (zsetlen > DICT_HT_INITIAL_SIZE)
dictExpand(zs->dict,zsetlen);
/* Load every single element of the sorted set. */
while(zsetlen--) {
sds sdsele;
double score;
zskiplistNode *znode;
if ((sdsele = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
if (rdbtype == RDB_TYPE_ZSET_2) {
if (rdbLoadBinaryDoubleValue(rdb,&score) == -1) return NULL;
} else {
if (rdbLoadDoubleValue(rdb,&score) == -1) return NULL;
}
/* Don't care about integer-encoded strings. */
if (sdslen(sdsele) > maxelelen) maxelelen = sdslen(sdsele);
znode = zslInsert(zs->zsl,score,sdsele);
dictAdd(zs->dict,sdsele,&znode->score);
}
/* Convert *after* loading, since sorted sets are not stored ordered. */
if (zsetLength(o) <= server.zset_max_ziplist_entries &&
maxelelen <= server.zset_max_ziplist_value)
zsetConvert(o,OBJ_ENCODING_ZIPLIST);
} else if (rdbtype == RDB_TYPE_HASH) {
uint64_t len;
int ret;
sds field, value;
len = rdbLoadLen(rdb, NULL);
if (len == RDB_LENERR) return NULL;
o = createHashObject();
/* Too many entries? Use a hash table. */
if (len > server.hash_max_ziplist_entries)
hashTypeConvert(o, OBJ_ENCODING_HT);
/* Load every field and value into the ziplist */
while (o->encoding == OBJ_ENCODING_ZIPLIST && len > 0) {
len--;
/* Load raw strings */
if ((field = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
if ((value = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
/* Add pair to ziplist */
o->ptr = ziplistPush(o->ptr, (unsigned char*)field,
sdslen(field), ZIPLIST_TAIL);
o->ptr = ziplistPush(o->ptr, (unsigned char*)value,
sdslen(value), ZIPLIST_TAIL);
/* Convert to hash table if size threshold is exceeded */
if (sdslen(field) > server.hash_max_ziplist_value ||
sdslen(value) > server.hash_max_ziplist_value)
{
sdsfree(field);
sdsfree(value);
hashTypeConvert(o, OBJ_ENCODING_HT);
break;
}
sdsfree(field);
sdsfree(value);
}
if (o->encoding == OBJ_ENCODING_HT && len > DICT_HT_INITIAL_SIZE)
dictExpand(o->ptr,len);
/* Load remaining fields and values into the hash table */
while (o->encoding == OBJ_ENCODING_HT && len > 0) {
len--;
/* Load encoded strings */
if ((field = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
if ((value = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL))
== NULL) return NULL;
/* Add pair to hash table */
ret = dictAdd((dict*)o->ptr, field, value);
if (ret == DICT_ERR) {
rdbExitReportCorruptRDB("Duplicate keys detected");
}
}
/* All pairs should be read by now */
serverAssert(len == 0);
} else if (rdbtype == RDB_TYPE_LIST_QUICKLIST) {
if ((len = rdbLoadLen(rdb,NULL)) == RDB_LENERR) return NULL;
o = createQuicklistObject();
quicklistSetOptions(o->ptr, server.list_max_ziplist_size,
server.list_compress_depth);
while (len--) {
unsigned char *zl =
rdbGenericLoadStringObject(rdb,RDB_LOAD_PLAIN,NULL);
if (zl == NULL) return NULL;
quicklistAppendZiplist(o->ptr, zl);
}
} else if (rdbtype == RDB_TYPE_HASH_ZIPMAP ||
rdbtype == RDB_TYPE_LIST_ZIPLIST ||
rdbtype == RDB_TYPE_SET_INTSET ||
rdbtype == RDB_TYPE_ZSET_ZIPLIST ||
rdbtype == RDB_TYPE_HASH_ZIPLIST)
{
unsigned char *encoded =
rdbGenericLoadStringObject(rdb,RDB_LOAD_PLAIN,NULL);
if (encoded == NULL) return NULL;
o = createObject(OBJ_STRING,encoded); /* Obj type fixed below. */
/* Fix the object encoding, and make sure to convert the encoded
* data type into the base type if accordingly to the current
* configuration there are too many elements in the encoded data
* type. Note that we only check the length and not max element
* size as this is an O(N) scan. Eventually everything will get
* converted. */
switch(rdbtype) {
case RDB_TYPE_HASH_ZIPMAP:
/* Convert to ziplist encoded hash. This must be deprecated
* when loading dumps created by Redis 2.4 gets deprecated. */
{
unsigned char *zl = ziplistNew();
unsigned char *zi = zipmapRewind(o->ptr);
unsigned char *fstr, *vstr;
unsigned int flen, vlen;
unsigned int maxlen = 0;
while ((zi = zipmapNext(zi, &fstr, &flen, &vstr, &vlen)) != NULL) {
if (flen > maxlen) maxlen = flen;
if (vlen > maxlen) maxlen = vlen;
zl = ziplistPush(zl, fstr, flen, ZIPLIST_TAIL);
zl = ziplistPush(zl, vstr, vlen, ZIPLIST_TAIL);
}
zfree(o->ptr);
o->ptr = zl;
o->type = OBJ_HASH;
o->encoding = OBJ_ENCODING_ZIPLIST;
if (hashTypeLength(o) > server.hash_max_ziplist_entries ||
maxlen > server.hash_max_ziplist_value)
{
hashTypeConvert(o, OBJ_ENCODING_HT);
}
}
break;
case RDB_TYPE_LIST_ZIPLIST:
o->type = OBJ_LIST;
o->encoding = OBJ_ENCODING_ZIPLIST;
listTypeConvert(o,OBJ_ENCODING_QUICKLIST);
break;
case RDB_TYPE_SET_INTSET:
o->type = OBJ_SET;
o->encoding = OBJ_ENCODING_INTSET;
if (intsetLen(o->ptr) > server.set_max_intset_entries)
setTypeConvert(o,OBJ_ENCODING_HT);
break;
case RDB_TYPE_ZSET_ZIPLIST:
o->type = OBJ_ZSET;
o->encoding = OBJ_ENCODING_ZIPLIST;
if (zsetLength(o) > server.zset_max_ziplist_entries)
zsetConvert(o,OBJ_ENCODING_SKIPLIST);
break;
case RDB_TYPE_HASH_ZIPLIST:
o->type = OBJ_HASH;
o->encoding = OBJ_ENCODING_ZIPLIST;
if (hashTypeLength(o) > server.hash_max_ziplist_entries)
hashTypeConvert(o, OBJ_ENCODING_HT);
break;
default:
/* totally unreachable */
rdbExitReportCorruptRDB("Unknown RDB encoding type %d",rdbtype);
break;
}
} else if (rdbtype == RDB_TYPE_STREAM_LISTPACKS) {
o = createStreamObject();
stream *s = o->ptr;
uint64_t listpacks = rdbLoadLen(rdb,NULL);
if (listpacks == RDB_LENERR) {
rdbReportReadError("Stream listpacks len loading failed.");
decrRefCount(o);
return NULL;
}
while(listpacks--) {
/* Get the master ID, the one we'll use as key of the radix tree
* node: the entries inside the listpack itself are delta-encoded
* relatively to this ID. */
sds nodekey = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL);
if (nodekey == NULL) {
rdbReportReadError("Stream master ID loading failed: invalid encoding or I/O error.");
decrRefCount(o);
return NULL;
}
if (sdslen(nodekey) != sizeof(streamID)) {
rdbExitReportCorruptRDB("Stream node key entry is not the "
"size of a stream ID");
}
/* Load the listpack. */
unsigned char *lp =
rdbGenericLoadStringObject(rdb,RDB_LOAD_PLAIN,NULL);
if (lp == NULL) {
rdbReportReadError("Stream listpacks loading failed.");
sdsfree(nodekey);
decrRefCount(o);
return NULL;
}
unsigned char *first = lpFirst(lp);
if (first == NULL) {
/* Serialized listpacks should never be empty, since on
* deletion we should remove the radix tree key if the
* resulting listpack is empty. */
rdbExitReportCorruptRDB("Empty listpack inside stream");
}
/* Insert the key in the radix tree. */
int retval = raxInsert(s->rax,
(unsigned char*)nodekey,sizeof(streamID),lp,NULL);
sdsfree(nodekey);
if (!retval)
rdbExitReportCorruptRDB("Listpack re-added with existing key");
}
/* Load total number of items inside the stream. */
s->length = rdbLoadLen(rdb,NULL);
/* Load the last entry ID. */
s->last_id.ms = rdbLoadLen(rdb,NULL);
s->last_id.seq = rdbLoadLen(rdb,NULL);
if (rioGetReadError(rdb)) {
rdbReportReadError("Stream object metadata loading failed.");
decrRefCount(o);
return NULL;
}
/* Consumer groups loading */
uint64_t cgroups_count = rdbLoadLen(rdb,NULL);
if (cgroups_count == RDB_LENERR) {
rdbReportReadError("Stream cgroup count loading failed.");
decrRefCount(o);
return NULL;
}
while(cgroups_count--) {
/* Get the consumer group name and ID. We can then create the
* consumer group ASAP and populate its structure as
* we read more data. */
streamID cg_id;
sds cgname = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL);
if (cgname == NULL) {
rdbReportReadError(
"Error reading the consumer group name from Stream");
decrRefCount(o);
return NULL;
}
cg_id.ms = rdbLoadLen(rdb,NULL);
cg_id.seq = rdbLoadLen(rdb,NULL);
if (rioGetReadError(rdb)) {
rdbReportReadError("Stream cgroup ID loading failed.");
sdsfree(cgname);
decrRefCount(o);
return NULL;
}
streamCG *cgroup = streamCreateCG(s,cgname,sdslen(cgname),&cg_id);
if (cgroup == NULL)
rdbExitReportCorruptRDB("Duplicated consumer group name %s",
cgname);
sdsfree(cgname);
/* Load the global PEL for this consumer group, however we'll
* not yet populate the NACK structures with the message
* owner, since consumers for this group and their messages will
* be read as a next step. So for now leave them not resolved
* and later populate it. */
uint64_t pel_size = rdbLoadLen(rdb,NULL);
if (pel_size == RDB_LENERR) {
rdbReportReadError("Stream PEL size loading failed.");
decrRefCount(o);
return NULL;
}
while(pel_size--) {
unsigned char rawid[sizeof(streamID)];
if (rioRead(rdb,rawid,sizeof(rawid)) == 0) {
rdbReportReadError("Stream PEL ID loading failed.");
decrRefCount(o);
return NULL;
}
streamNACK *nack = streamCreateNACK(NULL);
nack->delivery_time = rdbLoadMillisecondTime(rdb,RDB_VERSION);
nack->delivery_count = rdbLoadLen(rdb,NULL);
if (rioGetReadError(rdb)) {
rdbReportReadError("Stream PEL NACK loading failed.");
decrRefCount(o);
streamFreeNACK(nack);
return NULL;
}
if (!raxInsert(cgroup->pel,rawid,sizeof(rawid),nack,NULL))
rdbExitReportCorruptRDB("Duplicated gobal PEL entry "
"loading stream consumer group");
}
/* Now that we loaded our global PEL, we need to load the
* consumers and their local PELs. */
uint64_t consumers_num = rdbLoadLen(rdb,NULL);
if (consumers_num == RDB_LENERR) {
rdbReportReadError("Stream consumers num loading failed.");
decrRefCount(o);
return NULL;
}
while(consumers_num--) {
sds cname = rdbGenericLoadStringObject(rdb,RDB_LOAD_SDS,NULL);
if (cname == NULL) {
rdbReportReadError(
"Error reading the consumer name from Stream group.");
decrRefCount(o);
return NULL;
}
streamConsumer *consumer = streamLookupConsumer(cgroup,cname,
1);
sdsfree(cname);
consumer->seen_time = rdbLoadMillisecondTime(rdb,RDB_VERSION);
if (rioGetReadError(rdb)) {
rdbReportReadError("Stream short read reading seen time.");
decrRefCount(o);
return NULL;
}
/* Load the PEL about entries owned by this specific
* consumer. */
pel_size = rdbLoadLen(rdb,NULL);
if (pel_size == RDB_LENERR) {
rdbReportReadError(
"Stream consumer PEL num loading failed.");
decrRefCount(o);
return NULL;
}
while(pel_size--) {
unsigned char rawid[sizeof(streamID)];
if (rioRead(rdb,rawid,sizeof(rawid)) == 0) {
rdbReportReadError(
"Stream short read reading PEL streamID.");
decrRefCount(o);
return NULL;
}
streamNACK *nack = raxFind(cgroup->pel,rawid,sizeof(rawid));
if (nack == raxNotFound)
rdbExitReportCorruptRDB("Consumer entry not found in "
"group global PEL");
/* Set the NACK consumer, that was left to NULL when
* loading the global PEL. Then set the same shared
* NACK structure also in the consumer-specific PEL. */
nack->consumer = consumer;
if (!raxInsert(consumer->pel,rawid,sizeof(rawid),nack,NULL))
rdbExitReportCorruptRDB("Duplicated consumer PEL entry "
" loading a stream consumer "
"group");
}
}
}
} else if (rdbtype == RDB_TYPE_MODULE || rdbtype == RDB_TYPE_MODULE_2) {
uint64_t moduleid = rdbLoadLen(rdb,NULL);
if (rioGetReadError(rdb)) {
rdbReportReadError("Short read module id");
return NULL;
}
moduleType *mt = moduleTypeLookupModuleByID(moduleid);
char name[10];
if (rdbCheckMode && rdbtype == RDB_TYPE_MODULE_2) {
moduleTypeNameByID(name,moduleid);
return rdbLoadCheckModuleValue(rdb,name);
}
if (mt == NULL) {
moduleTypeNameByID(name,moduleid);
serverLog(LL_WARNING,"The RDB file contains module data I can't load: no matching module '%s'", name);
exit(1);
}
RedisModuleIO io;
moduleInitIOContext(io,mt,rdb,key);
io.ver = (rdbtype == RDB_TYPE_MODULE) ? 1 : 2;
/* Call the rdb_load method of the module providing the 10 bit
* encoding version in the lower 10 bits of the module ID. */
void *ptr = mt->rdb_load(&io,moduleid&1023);
if (io.ctx) {
moduleFreeContext(io.ctx);
zfree(io.ctx);
}
/* Module v2 serialization has an EOF mark at the end. */
if (io.ver == 2) {
uint64_t eof = rdbLoadLen(rdb,NULL);
if (eof == RDB_LENERR) {
o = createModuleObject(mt,ptr); /* creating just in order to easily destroy */
decrRefCount(o);
return NULL;
}
if (eof != RDB_MODULE_OPCODE_EOF) {
serverLog(LL_WARNING,"The RDB file contains module data for the module '%s' that is not terminated by the proper module value EOF marker", name);
exit(1);
}
}
if (ptr == NULL) {
moduleTypeNameByID(name,moduleid);
serverLog(LL_WARNING,"The RDB file contains module data for the module type '%s', that the responsible module is not able to load. Check for modules log above for additional clues.", name);
exit(1);
}
o = createModuleObject(mt,ptr);
} else {
rdbReportReadError("Unknown RDB encoding type %d",rdbtype);
return NULL;
}
return o;
}
/* Mark that we are loading in the global state and setup the fields
* needed to provide loading stats. */
void startLoading(size_t size, int rdbflags) {
/* Load the DB */
server.loading = 1;
server.loading_start_time = time(NULL);
server.loading_loaded_bytes = 0;
server.loading_total_bytes = size;
/* Fire the loading modules start event. */
int subevent;
if (rdbflags & RDBFLAGS_AOF_PREAMBLE)
subevent = REDISMODULE_SUBEVENT_LOADING_AOF_START;
else if(rdbflags & RDBFLAGS_REPLICATION)
subevent = REDISMODULE_SUBEVENT_LOADING_REPL_START;
else
subevent = REDISMODULE_SUBEVENT_LOADING_RDB_START;
moduleFireServerEvent(REDISMODULE_EVENT_LOADING,subevent,NULL);
}
/* Mark that we are loading in the global state and setup the fields
* needed to provide loading stats.
* 'filename' is optional and used for rdb-check on error */
void startLoadingFile(FILE *fp, char* filename, int rdbflags) {
struct stat sb;
if (fstat(fileno(fp), &sb) == -1)
sb.st_size = 0;
rdbFileBeingLoaded = filename;
startLoading(sb.st_size, rdbflags);
}
/* Refresh the loading progress info */
void loadingProgress(off_t pos) {
server.loading_loaded_bytes = pos;
if (server.stat_peak_memory < zmalloc_used_memory())
server.stat_peak_memory = zmalloc_used_memory();
}
/* Loading finished */
void stopLoading(int success) {
server.loading = 0;
rdbFileBeingLoaded = NULL;
/* Fire the loading modules end event. */
moduleFireServerEvent(REDISMODULE_EVENT_LOADING,
success?
REDISMODULE_SUBEVENT_LOADING_ENDED:
REDISMODULE_SUBEVENT_LOADING_FAILED,
NULL);
}
void startSaving(int rdbflags) {
/* Fire the persistence modules end event. */
int subevent;
if (rdbflags & RDBFLAGS_AOF_PREAMBLE)
subevent = REDISMODULE_SUBEVENT_PERSISTENCE_AOF_START;
else if (getpid()!=server.pid)
subevent = REDISMODULE_SUBEVENT_PERSISTENCE_RDB_START;
else
subevent = REDISMODULE_SUBEVENT_PERSISTENCE_SYNC_RDB_START;
moduleFireServerEvent(REDISMODULE_EVENT_PERSISTENCE,subevent,NULL);
}
void stopSaving(int success) {
/* Fire the persistence modules end event. */
moduleFireServerEvent(REDISMODULE_EVENT_PERSISTENCE,
success?
REDISMODULE_SUBEVENT_PERSISTENCE_ENDED:
REDISMODULE_SUBEVENT_PERSISTENCE_FAILED,
NULL);
}
/* Track loading progress in order to serve client's from time to time
and if needed calculate rdb checksum */
void rdbLoadProgressCallback(rio *r, const void *buf, size_t len) {
if (server.rdb_checksum)
rioGenericUpdateChecksum(r, buf, len);
if (server.loading_process_events_interval_bytes &&
(r->processed_bytes + len)/server.loading_process_events_interval_bytes > r->processed_bytes/server.loading_process_events_interval_bytes)
{
/* The DB can take some non trivial amount of time to load. Update
* our cached time since it is used to create and update the last
* interaction time with clients and for other important things. */
updateCachedTime(0);
if (server.masterhost && server.repl_state == REPL_STATE_TRANSFER)
replicationSendNewlineToMaster();
loadingProgress(r->processed_bytes);
processEventsWhileBlocked();
processModuleLoadingProgressEvent(0);
}
}
/* Load an RDB file from the rio stream 'rdb'. On success C_OK is returned,
* otherwise C_ERR is returned and 'errno' is set accordingly. */
int rdbLoadRio(rio *rdb, int rdbflags, rdbSaveInfo *rsi) {
uint64_t dbid;
int type, rdbver;
redisDb *db = server.db+0;
char buf[1024];
rdb->update_cksum = rdbLoadProgressCallback;
rdb->max_processing_chunk = server.loading_process_events_interval_bytes;
if (rioRead(rdb,buf,9) == 0) goto eoferr;
buf[9] = '\0';
if (memcmp(buf,"REDIS",5) != 0) {
serverLog(LL_WARNING,"Wrong signature trying to load DB from file");
errno = EINVAL;
return C_ERR;
}
rdbver = atoi(buf+5);
if (rdbver < 1 || rdbver > RDB_VERSION) {
serverLog(LL_WARNING,"Can't handle RDB format version %d",rdbver);
errno = EINVAL;
return C_ERR;
}
/* Key-specific attributes, set by opcodes before the key type. */
long long lru_idle = -1, lfu_freq = -1, expiretime = -1, now = mstime();
long long lru_clock = LRU_CLOCK();
while(1) {
robj *key, *val;
/* Read type. */
if ((type = rdbLoadType(rdb)) == -1) goto eoferr;
/* Handle special types. */
if (type == RDB_OPCODE_EXPIRETIME) {
/* EXPIRETIME: load an expire associated with the next key
* to load. Note that after loading an expire we need to
* load the actual type, and continue. */
expiretime = rdbLoadTime(rdb);
expiretime *= 1000;
if (rioGetReadError(rdb)) goto eoferr;
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_EXPIRETIME_MS) {
/* EXPIRETIME_MS: milliseconds precision expire times introduced
* with RDB v3. Like EXPIRETIME but no with more precision. */
expiretime = rdbLoadMillisecondTime(rdb,rdbver);
if (rioGetReadError(rdb)) goto eoferr;
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_FREQ) {
/* FREQ: LFU frequency. */
uint8_t byte;
if (rioRead(rdb,&byte,1) == 0) goto eoferr;
lfu_freq = byte;
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_IDLE) {
/* IDLE: LRU idle time. */
uint64_t qword;
if ((qword = rdbLoadLen(rdb,NULL)) == RDB_LENERR) goto eoferr;
lru_idle = qword;
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_EOF) {
/* EOF: End of file, exit the main loop. */
break;
} else if (type == RDB_OPCODE_SELECTDB) {
/* SELECTDB: Select the specified database. */
if ((dbid = rdbLoadLen(rdb,NULL)) == RDB_LENERR) goto eoferr;
if (dbid >= (unsigned)server.dbnum) {
serverLog(LL_WARNING,
"FATAL: Data file was created with a Redis "
"server configured to handle more than %d "
"databases. Exiting\n", server.dbnum);
exit(1);
}
db = server.db+dbid;
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_RESIZEDB) {
/* RESIZEDB: Hint about the size of the keys in the currently
* selected data base, in order to avoid useless rehashing. */
uint64_t db_size, expires_size;
if ((db_size = rdbLoadLen(rdb,NULL)) == RDB_LENERR)
goto eoferr;
if ((expires_size = rdbLoadLen(rdb,NULL)) == RDB_LENERR)
goto eoferr;
dictExpand(db->dict,db_size);
dictExpand(db->expires,expires_size);
continue; /* Read next opcode. */
} else if (type == RDB_OPCODE_AUX) {
/* AUX: generic string-string fields. Use to add state to RDB
* which is backward compatible. Implementations of RDB loading
* are requierd to skip AUX fields they don't understand.
*
* An AUX field is composed of two strings: key and value. */
robj *auxkey, *auxval;
if ((auxkey = rdbLoadStringObject(rdb)) == NULL) goto eoferr;
if ((auxval = rdbLoadStringObject(rdb)) == NULL) goto eoferr;
if (((char*)auxkey->ptr)[0] == '%') {
/* All the fields with a name staring with '%' are considered
* information fields and are logged at startup with a log
* level of NOTICE. */
serverLog(LL_NOTICE,"RDB '%s': %s",
(char*)auxkey->ptr,
(char*)auxval->ptr);
} else if (!strcasecmp(auxkey->ptr,"repl-stream-db")) {
if (rsi) rsi->repl_stream_db = atoi(auxval->ptr);
} else if (!strcasecmp(auxkey->ptr,"repl-id")) {
if (rsi && sdslen(auxval->ptr) == CONFIG_RUN_ID_SIZE) {
memcpy(rsi->repl_id,auxval->ptr,CONFIG_RUN_ID_SIZE+1);
rsi->repl_id_is_set = 1;
}
} else if (!strcasecmp(auxkey->ptr,"repl-offset")) {
if (rsi) rsi->repl_offset = strtoll(auxval->ptr,NULL,10);
} else if (!strcasecmp(auxkey->ptr,"lua")) {
/* Load the script back in memory. */
if (luaCreateFunction(NULL,server.lua,auxval) == NULL) {
rdbExitReportCorruptRDB(
"Can't load Lua script from RDB file! "
"BODY: %s", auxval->ptr);
}
} else if (!strcasecmp(auxkey->ptr,"redis-ver")) {
serverLog(LL_NOTICE,"Loading RDB produced by version %s",
(char*)auxval->ptr);
} else if (!strcasecmp(auxkey->ptr,"ctime")) {
time_t age = time(NULL)-strtol(auxval->ptr,NULL,10);
if (age < 0) age = 0;
serverLog(LL_NOTICE,"RDB age %ld seconds",
(unsigned long) age);
} else if (!strcasecmp(auxkey->ptr,"used-mem")) {
long long usedmem = strtoll(auxval->ptr,NULL,10);
serverLog(LL_NOTICE,"RDB memory usage when created %.2f Mb",
(double) usedmem / (1024*1024));
} else if (!strcasecmp(auxkey->ptr,"aof-preamble")) {
long long haspreamble = strtoll(auxval->ptr,NULL,10);
if (haspreamble) serverLog(LL_NOTICE,"RDB has an AOF tail");
} else if (!strcasecmp(auxkey->ptr,"redis-bits")) {
/* Just ignored. */
} else {
/* We ignore fields we don't understand, as by AUX field
* contract. */
serverLog(LL_DEBUG,"Unrecognized RDB AUX field: '%s'",
(char*)auxkey->ptr);
}
decrRefCount(auxkey);
decrRefCount(auxval);
continue; /* Read type again. */
} else if (type == RDB_OPCODE_MODULE_AUX) {
/* Load module data that is not related to the Redis key space.
* Such data can be potentially be stored both before and after the
* RDB keys-values section. */
uint64_t moduleid = rdbLoadLen(rdb,NULL);
int when_opcode = rdbLoadLen(rdb,NULL);
int when = rdbLoadLen(rdb,NULL);
if (rioGetReadError(rdb)) goto eoferr;
if (when_opcode != RDB_MODULE_OPCODE_UINT)
rdbReportReadError("bad when_opcode");
moduleType *mt = moduleTypeLookupModuleByID(moduleid);
char name[10];
moduleTypeNameByID(name,moduleid);
if (!rdbCheckMode && mt == NULL) {
/* Unknown module. */
serverLog(LL_WARNING,"The RDB file contains AUX module data I can't load: no matching module '%s'", name);
exit(1);
} else if (!rdbCheckMode && mt != NULL) {
if (!mt->aux_load) {
/* Module doesn't support AUX. */
serverLog(LL_WARNING,"The RDB file contains module AUX data, but the module '%s' doesn't seem to support it.", name);
exit(1);
}
RedisModuleIO io;
moduleInitIOContext(io,mt,rdb,NULL);
io.ver = 2;
/* Call the rdb_load method of the module providing the 10 bit
* encoding version in the lower 10 bits of the module ID. */
if (mt->aux_load(&io,moduleid&1023, when) || io.error) {
moduleTypeNameByID(name,moduleid);
serverLog(LL_WARNING,"The RDB file contains module AUX data for the module type '%s', that the responsible module is not able to load. Check for modules log above for additional clues.", name);
exit(1);
}
if (io.ctx) {
moduleFreeContext(io.ctx);
zfree(io.ctx);
}
uint64_t eof = rdbLoadLen(rdb,NULL);
if (eof != RDB_MODULE_OPCODE_EOF) {
serverLog(LL_WARNING,"The RDB file contains module AUX data for the module '%s' that is not terminated by the proper module value EOF marker", name);
exit(1);
}
continue;
} else {
/* RDB check mode. */
robj *aux = rdbLoadCheckModuleValue(rdb,name);
decrRefCount(aux);
continue; /* Read next opcode. */
}
}
/* Read key */
if ((key = rdbLoadStringObject(rdb)) == NULL) goto eoferr;
/* Read value */
if ((val = rdbLoadObject(type,rdb,key)) == NULL) {
decrRefCount(key);
goto eoferr;
}
/* Check if the key already expired. This function is used when loading
* an RDB file from disk, either at startup, or when an RDB was
* received from the master. In the latter case, the master is
* responsible for key expiry. If we would expire keys here, the
* snapshot taken by the master may not be reflected on the slave. */
if (server.masterhost == NULL && !(rdbflags&RDBFLAGS_AOF_PREAMBLE) && expiretime != -1 && expiretime < now) {
decrRefCount(key);
decrRefCount(val);
} else {
/* Add the new object in the hash table */
dbAdd(db,key,val);
/* Set the expire time if needed */
if (expiretime != -1) setExpire(NULL,db,key,expiretime);
/* Set usage information (for eviction). */
objectSetLRUOrLFU(val,lfu_freq,lru_idle,lru_clock,1000);
/* Decrement the key refcount since dbAdd() will take its
* own reference. */
decrRefCount(key);
}
if (server.key_load_delay)
usleep(server.key_load_delay);
/* Reset the state that is key-specified and is populated by
* opcodes before the key, so that we start from scratch again. */
expiretime = -1;
lfu_freq = -1;
lru_idle = -1;
}
/* Verify the checksum if RDB version is >= 5 */
if (rdbver >= 5) {
uint64_t cksum, expected = rdb->cksum;
if (rioRead(rdb,&cksum,8) == 0) goto eoferr;
if (server.rdb_checksum) {
memrev64ifbe(&cksum);
if (cksum == 0) {
serverLog(LL_WARNING,"RDB file was saved with checksum disabled: no check performed.");
} else if (cksum != expected) {
serverLog(LL_WARNING,"Wrong RDB checksum. Aborting now.");
rdbExitReportCorruptRDB("RDB CRC error");
}
}
}
return C_OK;
/* Unexpected end of file is handled here calling rdbReportReadError():
* this will in turn either abort Redis in most cases, or if we are loading
* the RDB file from a socket during initial SYNC (diskless replica mode),
* we'll report the error to the caller, so that we can retry. */
eoferr:
serverLog(LL_WARNING,
"Short read or OOM loading DB. Unrecoverable error, aborting now.");
rdbReportReadError("Unexpected EOF reading RDB file");
return C_ERR;
}
/* Like rdbLoadRio() but takes a filename instead of a rio stream. The
* filename is open for reading and a rio stream object created in order
* to do the actual loading. Moreover the ETA displayed in the INFO
* output is initialized and finalized.
*
* If you pass an 'rsi' structure initialied with RDB_SAVE_OPTION_INIT, the
* loading code will fiil the information fields in the structure. */
int rdbLoad(char *filename, rdbSaveInfo *rsi, int rdbflags) {
FILE *fp;
rio rdb;
int retval;
if ((fp = fopen(filename,"r")) == NULL) return C_ERR;
startLoadingFile(fp, filename,rdbflags);
rioInitWithFile(&rdb,fp);
retval = rdbLoadRio(&rdb,rdbflags,rsi);
fclose(fp);
stopLoading(retval==C_OK);
return retval;
}
/* A background saving child (BGSAVE) terminated its work. Handle this.
* This function covers the case of actual BGSAVEs. */
void backgroundSaveDoneHandlerDisk(int exitcode, int bysignal) {
if (!bysignal && exitcode == 0) {
serverLog(LL_NOTICE,
"Background saving terminated with success");
server.dirty = server.dirty - server.dirty_before_bgsave;
server.lastsave = time(NULL);
server.lastbgsave_status = C_OK;
} else if (!bysignal && exitcode != 0) {
serverLog(LL_WARNING, "Background saving error");
server.lastbgsave_status = C_ERR;
} else {
mstime_t latency;
serverLog(LL_WARNING,
"Background saving terminated by signal %d", bysignal);
latencyStartMonitor(latency);
rdbRemoveTempFile(server.rdb_child_pid);
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("rdb-unlink-temp-file",latency);
/* SIGUSR1 is whitelisted, so we have a way to kill a child without
* tirggering an error condition. */
if (bysignal != SIGUSR1)
server.lastbgsave_status = C_ERR;
}
server.rdb_child_pid = -1;
server.rdb_child_type = RDB_CHILD_TYPE_NONE;
server.rdb_save_time_last = time(NULL)-server.rdb_save_time_start;
server.rdb_save_time_start = -1;
/* Possibly there are slaves waiting for a BGSAVE in order to be served
* (the first stage of SYNC is a bulk transfer of dump.rdb) */
updateSlavesWaitingBgsave((!bysignal && exitcode == 0) ? C_OK : C_ERR, RDB_CHILD_TYPE_DISK);
}
/* A background saving child (BGSAVE) terminated its work. Handle this.
* This function covers the case of RDB -> Slaves socket transfers for
* diskless replication. */
void backgroundSaveDoneHandlerSocket(int exitcode, int bysignal) {
if (!bysignal && exitcode == 0) {
serverLog(LL_NOTICE,
"Background RDB transfer terminated with success");
} else if (!bysignal && exitcode != 0) {
serverLog(LL_WARNING, "Background transfer error");
} else {
serverLog(LL_WARNING,
"Background transfer terminated by signal %d", bysignal);
}
server.rdb_child_pid = -1;
server.rdb_child_type = RDB_CHILD_TYPE_NONE;
server.rdb_save_time_start = -1;
updateSlavesWaitingBgsave((!bysignal && exitcode == 0) ? C_OK : C_ERR, RDB_CHILD_TYPE_SOCKET);
}
/* When a background RDB saving/transfer terminates, call the right handler. */
void backgroundSaveDoneHandler(int exitcode, int bysignal) {
switch(server.rdb_child_type) {
case RDB_CHILD_TYPE_DISK:
backgroundSaveDoneHandlerDisk(exitcode,bysignal);
break;
case RDB_CHILD_TYPE_SOCKET:
backgroundSaveDoneHandlerSocket(exitcode,bysignal);
break;
default:
serverPanic("Unknown RDB child type.");
break;
}
}
/* Kill the RDB saving child using SIGUSR1 (so that the parent will know
* the child did not exit for an error, but because we wanted), and performs
* the cleanup needed. */
void killRDBChild(void) {
kill(server.rdb_child_pid,SIGUSR1);
rdbRemoveTempFile(server.rdb_child_pid);
closeChildInfoPipe();
updateDictResizePolicy();
}
/* Spawn an RDB child that writes the RDB to the sockets of the slaves
* that are currently in SLAVE_STATE_WAIT_BGSAVE_START state. */
int rdbSaveToSlavesSockets(rdbSaveInfo *rsi) {
listNode *ln;
listIter li;
pid_t childpid;
int pipefds[2];
if (hasActiveChildProcess()) return C_ERR;
/* Even if the previous fork child exited, don't start a new one until we
* drained the pipe. */
if (server.rdb_pipe_conns) return C_ERR;
/* Before to fork, create a pipe that is used to transfer the rdb bytes to
* the parent, we can't let it write directly to the sockets, since in case
* of TLS we must let the parent handle a continuous TLS state when the
* child terminates and parent takes over. */
if (pipe(pipefds) == -1) return C_ERR;
server.rdb_pipe_read = pipefds[0];
server.rdb_pipe_write = pipefds[1];
anetNonBlock(NULL, server.rdb_pipe_read);
/* Collect the connections of the replicas we want to transfer
* the RDB to, which are i WAIT_BGSAVE_START state. */
server.rdb_pipe_conns = zmalloc(sizeof(connection *)*listLength(server.slaves));
server.rdb_pipe_numconns = 0;
server.rdb_pipe_numconns_writing = 0;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
client *slave = ln->value;
if (slave->replstate == SLAVE_STATE_WAIT_BGSAVE_START) {
server.rdb_pipe_conns[server.rdb_pipe_numconns++] = slave->conn;
replicationSetupSlaveForFullResync(slave,getPsyncInitialOffset());
}
}
/* Create the child process. */
openChildInfoPipe();
if ((childpid = redisFork()) == 0) {
/* Child */
int retval;
rio rdb;
rioInitWithFd(&rdb,server.rdb_pipe_write);
redisSetProcTitle("redis-rdb-to-slaves");
retval = rdbSaveRioWithEOFMark(&rdb,NULL,rsi);
if (retval == C_OK && rioFlush(&rdb) == 0)
retval = C_ERR;
if (retval == C_OK) {
sendChildCOWInfo(CHILD_INFO_TYPE_RDB, "RDB");
}
rioFreeFd(&rdb);
close(server.rdb_pipe_write); /* wake up the reader, tell it we're done. */
exitFromChild((retval == C_OK) ? 0 : 1);
} else {
/* Parent */
if (childpid == -1) {
serverLog(LL_WARNING,"Can't save in background: fork: %s",
strerror(errno));
/* Undo the state change. The caller will perform cleanup on
* all the slaves in BGSAVE_START state, but an early call to
* replicationSetupSlaveForFullResync() turned it into BGSAVE_END */
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
client *slave = ln->value;
if (slave->replstate == SLAVE_STATE_WAIT_BGSAVE_END) {
slave->replstate = SLAVE_STATE_WAIT_BGSAVE_START;
}
}
close(server.rdb_pipe_write);
close(server.rdb_pipe_read);
zfree(server.rdb_pipe_conns);
server.rdb_pipe_conns = NULL;
server.rdb_pipe_numconns = 0;
server.rdb_pipe_numconns_writing = 0;
closeChildInfoPipe();
} else {
serverLog(LL_NOTICE,"Background RDB transfer started by pid %d",
childpid);
server.rdb_save_time_start = time(NULL);
server.rdb_child_pid = childpid;
server.rdb_child_type = RDB_CHILD_TYPE_SOCKET;
close(server.rdb_pipe_write); /* close write in parent so that it can detect the close on the child. */
if (aeCreateFileEvent(server.el, server.rdb_pipe_read, AE_READABLE, rdbPipeReadHandler,NULL) == AE_ERR) {
serverPanic("Unrecoverable error creating server.rdb_pipe_read file event.");
}
}
return (childpid == -1) ? C_ERR : C_OK;
}
return C_OK; /* Unreached. */
}
void saveCommand(client *c) {
if (server.rdb_child_pid != -1) {
addReplyError(c,"Background save already in progress");
return;
}
rdbSaveInfo rsi, *rsiptr;
rsiptr = rdbPopulateSaveInfo(&rsi);
if (rdbSave(server.rdb_filename,rsiptr) == C_OK) {
addReply(c,shared.ok);
} else {
addReply(c,shared.err);
}
}
/* BGSAVE [SCHEDULE] */
void bgsaveCommand(client *c) {
int schedule = 0;
/* The SCHEDULE option changes the behavior of BGSAVE when an AOF rewrite
* is in progress. Instead of returning an error a BGSAVE gets scheduled. */
if (c->argc > 1) {
if (c->argc == 2 && !strcasecmp(c->argv[1]->ptr,"schedule")) {
schedule = 1;
} else {
addReply(c,shared.syntaxerr);
return;
}
}
rdbSaveInfo rsi, *rsiptr;
rsiptr = rdbPopulateSaveInfo(&rsi);
if (server.rdb_child_pid != -1) {
addReplyError(c,"Background save already in progress");
} else if (hasActiveChildProcess()) {
if (schedule) {
server.rdb_bgsave_scheduled = 1;
addReplyStatus(c,"Background saving scheduled");
} else {
addReplyError(c,
"Another child process is active (AOF?): can't BGSAVE right now. "
"Use BGSAVE SCHEDULE in order to schedule a BGSAVE whenever "
"possible.");
}
} else if (rdbSaveBackground(server.rdb_filename,rsiptr) == C_OK) {
addReplyStatus(c,"Background saving started");
} else {
addReply(c,shared.err);
}
}
/* Populate the rdbSaveInfo structure used to persist the replication
* information inside the RDB file. Currently the structure explicitly
* contains just the currently selected DB from the master stream, however
* if the rdbSave*() family functions receive a NULL rsi structure also
* the Replication ID/offset is not saved. The function popultes 'rsi'
* that is normally stack-allocated in the caller, returns the populated
* pointer if the instance has a valid master client, otherwise NULL
* is returned, and the RDB saving will not persist any replication related
* information. */
rdbSaveInfo *rdbPopulateSaveInfo(rdbSaveInfo *rsi) {
rdbSaveInfo rsi_init = RDB_SAVE_INFO_INIT;
*rsi = rsi_init;
/* If the instance is a master, we can populate the replication info
* only when repl_backlog is not NULL. If the repl_backlog is NULL,
* it means that the instance isn't in any replication chains. In this
* scenario the replication info is useless, because when a slave
* connects to us, the NULL repl_backlog will trigger a full
* synchronization, at the same time we will use a new replid and clear
* replid2. */
if (!server.masterhost && server.repl_backlog) {
/* Note that when server.slaveseldb is -1, it means that this master
* didn't apply any write commands after a full synchronization.
* So we can let repl_stream_db be 0, this allows a restarted slave
* to reload replication ID/offset, it's safe because the next write
* command must generate a SELECT statement. */
rsi->repl_stream_db = server.slaveseldb == -1 ? 0 : server.slaveseldb;
return rsi;
}
/* If the instance is a slave we need a connected master
* in order to fetch the currently selected DB. */
if (server.master) {
rsi->repl_stream_db = server.master->db->id;
return rsi;
}
/* If we have a cached master we can use it in order to populate the
* replication selected DB info inside the RDB file: the slave can
* increment the master_repl_offset only from data arriving from the
* master, so if we are disconnected the offset in the cached master
* is valid. */
if (server.cached_master) {
rsi->repl_stream_db = server.cached_master->db->id;
return rsi;
}
return NULL;
}
|