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
|
/*
* git gc builtin command
*
* Cleanup unreachable files and optimize the repository.
*
* Copyright (c) 2007 James Bowes
*
* Based on git-gc.sh, which is
*
* Copyright (c) 2006 Shawn O. Pearce
*/
#include "builtin.h"
#include "repository.h"
#include "config.h"
#include "tempfile.h"
#include "lockfile.h"
#include "parse-options.h"
#include "run-command.h"
#include "sigchain.h"
#include "strvec.h"
#include "commit.h"
#include "commit-graph.h"
#include "packfile.h"
#include "object-store.h"
#include "pack.h"
#include "pack-objects.h"
#include "blob.h"
#include "tree.h"
#include "promisor-remote.h"
#include "refs.h"
#include "remote.h"
#include "object-store.h"
#include "exec-cmd.h"
#define FAILED_RUN "failed to run %s"
static const char * const builtin_gc_usage[] = {
N_("git gc [<options>]"),
NULL
};
static int pack_refs = 1;
static int prune_reflogs = 1;
static int aggressive_depth = 50;
static int aggressive_window = 250;
static int gc_auto_threshold = 6700;
static int gc_auto_pack_limit = 50;
static int detach_auto = 1;
static timestamp_t gc_log_expire_time;
static const char *gc_log_expire = "1.day.ago";
static const char *prune_expire = "2.weeks.ago";
static const char *prune_worktrees_expire = "3.months.ago";
static unsigned long big_pack_threshold;
static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
static struct strvec reflog = STRVEC_INIT;
static struct strvec repack = STRVEC_INIT;
static struct strvec prune = STRVEC_INIT;
static struct strvec prune_worktrees = STRVEC_INIT;
static struct strvec rerere = STRVEC_INIT;
static struct tempfile *pidfile;
static struct lock_file log_lock;
static struct string_list pack_garbage = STRING_LIST_INIT_DUP;
static void clean_pack_garbage(void)
{
int i;
for (i = 0; i < pack_garbage.nr; i++)
unlink_or_warn(pack_garbage.items[i].string);
string_list_clear(&pack_garbage, 0);
}
static void report_pack_garbage(unsigned seen_bits, const char *path)
{
if (seen_bits == PACKDIR_FILE_IDX)
string_list_append(&pack_garbage, path);
}
static void process_log_file(void)
{
struct stat st;
if (fstat(get_lock_file_fd(&log_lock), &st)) {
/*
* Perhaps there was an i/o error or another
* unlikely situation. Try to make a note of
* this in gc.log along with any existing
* messages.
*/
int saved_errno = errno;
fprintf(stderr, _("Failed to fstat %s: %s"),
get_lock_file_path(&log_lock),
strerror(saved_errno));
fflush(stderr);
commit_lock_file(&log_lock);
errno = saved_errno;
} else if (st.st_size) {
/* There was some error recorded in the lock file */
commit_lock_file(&log_lock);
} else {
/* No error, clean up any old gc.log */
unlink(git_path("gc.log"));
rollback_lock_file(&log_lock);
}
}
static void process_log_file_at_exit(void)
{
fflush(stderr);
process_log_file();
}
static void process_log_file_on_signal(int signo)
{
process_log_file();
sigchain_pop(signo);
raise(signo);
}
static int gc_config_is_timestamp_never(const char *var)
{
const char *value;
timestamp_t expire;
if (!git_config_get_value(var, &value) && value) {
if (parse_expiry_date(value, &expire))
die(_("failed to parse '%s' value '%s'"), var, value);
return expire == 0;
}
return 0;
}
static void gc_config(void)
{
const char *value;
if (!git_config_get_value("gc.packrefs", &value)) {
if (value && !strcmp(value, "notbare"))
pack_refs = -1;
else
pack_refs = git_config_bool("gc.packrefs", value);
}
if (gc_config_is_timestamp_never("gc.reflogexpire") &&
gc_config_is_timestamp_never("gc.reflogexpireunreachable"))
prune_reflogs = 0;
git_config_get_int("gc.aggressivewindow", &aggressive_window);
git_config_get_int("gc.aggressivedepth", &aggressive_depth);
git_config_get_int("gc.auto", &gc_auto_threshold);
git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
git_config_get_bool("gc.autodetach", &detach_auto);
git_config_get_expiry("gc.pruneexpire", &prune_expire);
git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
git_config_get_expiry("gc.logexpiry", &gc_log_expire);
git_config_get_ulong("gc.bigpackthreshold", &big_pack_threshold);
git_config_get_ulong("pack.deltacachesize", &max_delta_cache_size);
git_config(git_default_config, NULL);
}
struct maintenance_run_opts;
static int maintenance_task_pack_refs(MAYBE_UNUSED struct maintenance_run_opts *opts)
{
struct strvec pack_refs_cmd = STRVEC_INIT;
strvec_pushl(&pack_refs_cmd, "pack-refs", "--all", "--prune", NULL);
return run_command_v_opt(pack_refs_cmd.v, RUN_GIT_CMD);
}
static int too_many_loose_objects(void)
{
/*
* Quickly check if a "gc" is needed, by estimating how
* many loose objects there are. Because SHA-1 is evenly
* distributed, we can check only one and get a reasonable
* estimate.
*/
DIR *dir;
struct dirent *ent;
int auto_threshold;
int num_loose = 0;
int needed = 0;
const unsigned hexsz_loose = the_hash_algo->hexsz - 2;
dir = opendir(git_path("objects/17"));
if (!dir)
return 0;
auto_threshold = DIV_ROUND_UP(gc_auto_threshold, 256);
while ((ent = readdir(dir)) != NULL) {
if (strspn(ent->d_name, "0123456789abcdef") != hexsz_loose ||
ent->d_name[hexsz_loose] != '\0')
continue;
if (++num_loose > auto_threshold) {
needed = 1;
break;
}
}
closedir(dir);
return needed;
}
static struct packed_git *find_base_packs(struct string_list *packs,
unsigned long limit)
{
struct packed_git *p, *base = NULL;
for (p = get_all_packs(the_repository); p; p = p->next) {
if (!p->pack_local)
continue;
if (limit) {
if (p->pack_size >= limit)
string_list_append(packs, p->pack_name);
} else if (!base || base->pack_size < p->pack_size) {
base = p;
}
}
if (base)
string_list_append(packs, base->pack_name);
return base;
}
static int too_many_packs(void)
{
struct packed_git *p;
int cnt;
if (gc_auto_pack_limit <= 0)
return 0;
for (cnt = 0, p = get_all_packs(the_repository); p; p = p->next) {
if (!p->pack_local)
continue;
if (p->pack_keep)
continue;
/*
* Perhaps check the size of the pack and count only
* very small ones here?
*/
cnt++;
}
return gc_auto_pack_limit < cnt;
}
static uint64_t total_ram(void)
{
#if defined(HAVE_SYSINFO)
struct sysinfo si;
if (!sysinfo(&si))
return si.totalram;
#elif defined(HAVE_BSD_SYSCTL) && (defined(HW_MEMSIZE) || defined(HW_PHYSMEM))
int64_t physical_memory;
int mib[2];
size_t length;
mib[0] = CTL_HW;
# if defined(HW_MEMSIZE)
mib[1] = HW_MEMSIZE;
# else
mib[1] = HW_PHYSMEM;
# endif
length = sizeof(int64_t);
if (!sysctl(mib, 2, &physical_memory, &length, NULL, 0))
return physical_memory;
#elif defined(GIT_WINDOWS_NATIVE)
MEMORYSTATUSEX memInfo;
memInfo.dwLength = sizeof(MEMORYSTATUSEX);
if (GlobalMemoryStatusEx(&memInfo))
return memInfo.ullTotalPhys;
#endif
return 0;
}
static uint64_t estimate_repack_memory(struct packed_git *pack)
{
unsigned long nr_objects = approximate_object_count();
size_t os_cache, heap;
if (!pack || !nr_objects)
return 0;
/*
* First we have to scan through at least one pack.
* Assume enough room in OS file cache to keep the entire pack
* or we may accidentally evict data of other processes from
* the cache.
*/
os_cache = pack->pack_size + pack->index_size;
/* then pack-objects needs lots more for book keeping */
heap = sizeof(struct object_entry) * nr_objects;
/*
* internal rev-list --all --objects takes up some memory too,
* let's say half of it is for blobs
*/
heap += sizeof(struct blob) * nr_objects / 2;
/*
* and the other half is for trees (commits and tags are
* usually insignificant)
*/
heap += sizeof(struct tree) * nr_objects / 2;
/* and then obj_hash[], underestimated in fact */
heap += sizeof(struct object *) * nr_objects;
/* revindex is used also */
heap += (sizeof(off_t) + sizeof(uint32_t)) * nr_objects;
/*
* read_sha1_file() (either at delta calculation phase, or
* writing phase) also fills up the delta base cache
*/
heap += delta_base_cache_limit;
/* and of course pack-objects has its own delta cache */
heap += max_delta_cache_size;
return os_cache + heap;
}
static int keep_one_pack(struct string_list_item *item, void *data)
{
strvec_pushf(&repack, "--keep-pack=%s", basename(item->string));
return 0;
}
static void add_repack_all_option(struct string_list *keep_pack)
{
if (prune_expire && !strcmp(prune_expire, "now"))
strvec_push(&repack, "-a");
else {
strvec_push(&repack, "-A");
if (prune_expire)
strvec_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
}
if (keep_pack)
for_each_string_list(keep_pack, keep_one_pack, NULL);
}
static void add_repack_incremental_option(void)
{
strvec_push(&repack, "--no-write-bitmap-index");
}
static int need_to_gc(void)
{
/*
* Setting gc.auto to 0 or negative can disable the
* automatic gc.
*/
if (gc_auto_threshold <= 0)
return 0;
/*
* If there are too many loose objects, but not too many
* packs, we run "repack -d -l". If there are too many packs,
* we run "repack -A -d -l". Otherwise we tell the caller
* there is no need.
*/
if (too_many_packs()) {
struct string_list keep_pack = STRING_LIST_INIT_NODUP;
if (big_pack_threshold) {
find_base_packs(&keep_pack, big_pack_threshold);
if (keep_pack.nr >= gc_auto_pack_limit) {
big_pack_threshold = 0;
string_list_clear(&keep_pack, 0);
find_base_packs(&keep_pack, 0);
}
} else {
struct packed_git *p = find_base_packs(&keep_pack, 0);
uint64_t mem_have, mem_want;
mem_have = total_ram();
mem_want = estimate_repack_memory(p);
/*
* Only allow 1/2 of memory for pack-objects, leave
* the rest for the OS and other processes in the
* system.
*/
if (!mem_have || mem_want < mem_have / 2)
string_list_clear(&keep_pack, 0);
}
add_repack_all_option(&keep_pack);
string_list_clear(&keep_pack, 0);
} else if (too_many_loose_objects())
add_repack_incremental_option();
else
return 0;
if (run_hook_le(NULL, "pre-auto-gc", NULL))
return 0;
return 1;
}
/* return NULL on success, else hostname running the gc */
static const char *lock_repo_for_gc(int force, pid_t* ret_pid)
{
struct lock_file lock = LOCK_INIT;
char my_host[HOST_NAME_MAX + 1];
struct strbuf sb = STRBUF_INIT;
struct stat st;
uintmax_t pid;
FILE *fp;
int fd;
char *pidfile_path;
if (is_tempfile_active(pidfile))
/* already locked */
return NULL;
if (xgethostname(my_host, sizeof(my_host)))
xsnprintf(my_host, sizeof(my_host), "unknown");
pidfile_path = git_pathdup("gc.pid");
fd = hold_lock_file_for_update(&lock, pidfile_path,
LOCK_DIE_ON_ERROR);
if (!force) {
static char locking_host[HOST_NAME_MAX + 1];
static char *scan_fmt;
int should_exit;
if (!scan_fmt)
scan_fmt = xstrfmt("%s %%%ds", "%"SCNuMAX, HOST_NAME_MAX);
fp = fopen(pidfile_path, "r");
memset(locking_host, 0, sizeof(locking_host));
should_exit =
fp != NULL &&
!fstat(fileno(fp), &st) &&
/*
* 12 hour limit is very generous as gc should
* never take that long. On the other hand we
* don't really need a strict limit here,
* running gc --auto one day late is not a big
* problem. --force can be used in manual gc
* after the user verifies that no gc is
* running.
*/
time(NULL) - st.st_mtime <= 12 * 3600 &&
fscanf(fp, scan_fmt, &pid, locking_host) == 2 &&
/* be gentle to concurrent "gc" on remote hosts */
(strcmp(locking_host, my_host) || !kill(pid, 0) || errno == EPERM);
if (fp != NULL)
fclose(fp);
if (should_exit) {
if (fd >= 0)
rollback_lock_file(&lock);
*ret_pid = pid;
free(pidfile_path);
return locking_host;
}
}
strbuf_addf(&sb, "%"PRIuMAX" %s",
(uintmax_t) getpid(), my_host);
write_in_full(fd, sb.buf, sb.len);
strbuf_release(&sb);
commit_lock_file(&lock);
pidfile = register_tempfile(pidfile_path);
free(pidfile_path);
return NULL;
}
/*
* Returns 0 if there was no previous error and gc can proceed, 1 if
* gc should not proceed due to an error in the last run. Prints a
* message and returns -1 if an error occurred while reading gc.log
*/
static int report_last_gc_error(void)
{
struct strbuf sb = STRBUF_INIT;
int ret = 0;
ssize_t len;
struct stat st;
char *gc_log_path = git_pathdup("gc.log");
if (stat(gc_log_path, &st)) {
if (errno == ENOENT)
goto done;
ret = error_errno(_("cannot stat '%s'"), gc_log_path);
goto done;
}
if (st.st_mtime < gc_log_expire_time)
goto done;
len = strbuf_read_file(&sb, gc_log_path, 0);
if (len < 0)
ret = error_errno(_("cannot read '%s'"), gc_log_path);
else if (len > 0) {
/*
* A previous gc failed. Report the error, and don't
* bother with an automatic gc run since it is likely
* to fail in the same way.
*/
warning(_("The last gc run reported the following. "
"Please correct the root cause\n"
"and remove %s\n"
"Automatic cleanup will not be performed "
"until the file is removed.\n\n"
"%s"),
gc_log_path, sb.buf);
ret = 1;
}
strbuf_release(&sb);
done:
free(gc_log_path);
return ret;
}
static void gc_before_repack(void)
{
/*
* We may be called twice, as both the pre- and
* post-daemonized phases will call us, but running these
* commands more than once is pointless and wasteful.
*/
static int done = 0;
if (done++)
return;
if (pack_refs && maintenance_task_pack_refs(NULL))
die(FAILED_RUN, "pack-refs");
if (prune_reflogs && run_command_v_opt(reflog.v, RUN_GIT_CMD))
die(FAILED_RUN, reflog.v[0]);
}
int cmd_gc(int argc, const char **argv, const char *prefix)
{
int aggressive = 0;
int auto_gc = 0;
int quiet = 0;
int force = 0;
const char *name;
pid_t pid;
int daemonized = 0;
int keep_largest_pack = -1;
timestamp_t dummy;
struct option builtin_gc_options[] = {
OPT__QUIET(&quiet, N_("suppress progress reporting")),
{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
N_("prune unreferenced objects"),
PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
PARSE_OPT_NOCOMPLETE),
OPT_BOOL_F(0, "force", &force,
N_("force running gc even if there may be another gc running"),
PARSE_OPT_NOCOMPLETE),
OPT_BOOL(0, "keep-largest-pack", &keep_largest_pack,
N_("repack all other packs except the largest pack")),
OPT_END()
};
if (argc == 2 && !strcmp(argv[1], "-h"))
usage_with_options(builtin_gc_usage, builtin_gc_options);
strvec_pushl(&reflog, "reflog", "expire", "--all", NULL);
strvec_pushl(&repack, "repack", "-d", "-l", NULL);
strvec_pushl(&prune, "prune", "--expire", NULL);
strvec_pushl(&prune_worktrees, "worktree", "prune", "--expire", NULL);
strvec_pushl(&rerere, "rerere", "gc", NULL);
/* default expiry time, overwritten in gc_config */
gc_config();
if (parse_expiry_date(gc_log_expire, &gc_log_expire_time))
die(_("failed to parse gc.logexpiry value %s"), gc_log_expire);
if (pack_refs < 0)
pack_refs = !is_bare_repository();
argc = parse_options(argc, argv, prefix, builtin_gc_options,
builtin_gc_usage, 0);
if (argc > 0)
usage_with_options(builtin_gc_usage, builtin_gc_options);
if (prune_expire && parse_expiry_date(prune_expire, &dummy))
die(_("failed to parse prune expiry value %s"), prune_expire);
if (aggressive) {
strvec_push(&repack, "-f");
if (aggressive_depth > 0)
strvec_pushf(&repack, "--depth=%d", aggressive_depth);
if (aggressive_window > 0)
strvec_pushf(&repack, "--window=%d", aggressive_window);
}
if (quiet)
strvec_push(&repack, "-q");
if (auto_gc) {
/*
* Auto-gc should be least intrusive as possible.
*/
if (!need_to_gc())
return 0;
if (!quiet) {
if (detach_auto)
fprintf(stderr, _("Auto packing the repository in background for optimum performance.\n"));
else
fprintf(stderr, _("Auto packing the repository for optimum performance.\n"));
fprintf(stderr, _("See \"git help gc\" for manual housekeeping.\n"));
}
if (detach_auto) {
int ret = report_last_gc_error();
if (ret < 0)
/* an I/O error occurred, already reported */
exit(128);
if (ret == 1)
/* Last gc --auto failed. Skip this one. */
return 0;
if (lock_repo_for_gc(force, &pid))
return 0;
gc_before_repack(); /* dies on failure */
delete_tempfile(&pidfile);
/*
* failure to daemonize is ok, we'll continue
* in foreground
*/
daemonized = !daemonize();
}
} else {
struct string_list keep_pack = STRING_LIST_INIT_NODUP;
if (keep_largest_pack != -1) {
if (keep_largest_pack)
find_base_packs(&keep_pack, 0);
} else if (big_pack_threshold) {
find_base_packs(&keep_pack, big_pack_threshold);
}
add_repack_all_option(&keep_pack);
string_list_clear(&keep_pack, 0);
}
name = lock_repo_for_gc(force, &pid);
if (name) {
if (auto_gc)
return 0; /* be quiet on --auto */
die(_("gc is already running on machine '%s' pid %"PRIuMAX" (use --force if not)"),
name, (uintmax_t)pid);
}
if (daemonized) {
hold_lock_file_for_update(&log_lock,
git_path("gc.log"),
LOCK_DIE_ON_ERROR);
dup2(get_lock_file_fd(&log_lock), 2);
sigchain_push_common(process_log_file_on_signal);
atexit(process_log_file_at_exit);
}
gc_before_repack();
if (!repository_format_precious_objects) {
close_object_store(the_repository->objects);
if (run_command_v_opt(repack.v, RUN_GIT_CMD))
die(FAILED_RUN, repack.v[0]);
if (prune_expire) {
strvec_push(&prune, prune_expire);
if (quiet)
strvec_push(&prune, "--no-progress");
if (has_promisor_remote())
strvec_push(&prune,
"--exclude-promisor-objects");
if (run_command_v_opt(prune.v, RUN_GIT_CMD))
die(FAILED_RUN, prune.v[0]);
}
}
if (prune_worktrees_expire) {
strvec_push(&prune_worktrees, prune_worktrees_expire);
if (run_command_v_opt(prune_worktrees.v, RUN_GIT_CMD))
die(FAILED_RUN, prune_worktrees.v[0]);
}
if (run_command_v_opt(rerere.v, RUN_GIT_CMD))
die(FAILED_RUN, rerere.v[0]);
report_garbage = report_pack_garbage;
reprepare_packed_git(the_repository);
if (pack_garbage.nr > 0) {
close_object_store(the_repository->objects);
clean_pack_garbage();
}
prepare_repo_settings(the_repository);
if (the_repository->settings.gc_write_commit_graph == 1)
write_commit_graph_reachable(the_repository->objects->odb,
!quiet && !daemonized ? COMMIT_GRAPH_WRITE_PROGRESS : 0,
NULL);
if (auto_gc && too_many_loose_objects())
warning(_("There are too many unreachable loose objects; "
"run 'git prune' to remove them."));
if (!daemonized)
unlink(git_path("gc.log"));
return 0;
}
static const char *const builtin_maintenance_run_usage[] = {
N_("git maintenance run [--auto] [--[no-]quiet] [--task=<task>] [--schedule]"),
NULL
};
enum schedule_priority {
SCHEDULE_NONE = 0,
SCHEDULE_WEEKLY = 1,
SCHEDULE_DAILY = 2,
SCHEDULE_HOURLY = 3,
};
static enum schedule_priority parse_schedule(const char *value)
{
if (!value)
return SCHEDULE_NONE;
if (!strcasecmp(value, "hourly"))
return SCHEDULE_HOURLY;
if (!strcasecmp(value, "daily"))
return SCHEDULE_DAILY;
if (!strcasecmp(value, "weekly"))
return SCHEDULE_WEEKLY;
return SCHEDULE_NONE;
}
static int maintenance_opt_schedule(const struct option *opt, const char *arg,
int unset)
{
enum schedule_priority *priority = opt->value;
if (unset)
die(_("--no-schedule is not allowed"));
*priority = parse_schedule(arg);
if (!*priority)
die(_("unrecognized --schedule argument '%s'"), arg);
return 0;
}
struct maintenance_run_opts {
int auto_flag;
int quiet;
enum schedule_priority schedule;
};
/* Remember to update object flag allocation in object.h */
#define SEEN (1u<<0)
struct cg_auto_data {
int num_not_in_graph;
int limit;
};
static int dfs_on_ref(const char *refname,
const struct object_id *oid, int flags,
void *cb_data)
{
struct cg_auto_data *data = (struct cg_auto_data *)cb_data;
int result = 0;
struct object_id peeled;
struct commit_list *stack = NULL;
struct commit *commit;
if (!peel_iterated_oid(oid, &peeled))
oid = &peeled;
if (oid_object_info(the_repository, oid, NULL) != OBJ_COMMIT)
return 0;
commit = lookup_commit(the_repository, oid);
if (!commit)
return 0;
if (parse_commit(commit) ||
commit_graph_position(commit) != COMMIT_NOT_FROM_GRAPH)
return 0;
data->num_not_in_graph++;
if (data->num_not_in_graph >= data->limit)
return 1;
commit_list_append(commit, &stack);
while (!result && stack) {
struct commit_list *parent;
commit = pop_commit(&stack);
for (parent = commit->parents; parent; parent = parent->next) {
if (parse_commit(parent->item) ||
commit_graph_position(parent->item) != COMMIT_NOT_FROM_GRAPH ||
parent->item->object.flags & SEEN)
continue;
parent->item->object.flags |= SEEN;
data->num_not_in_graph++;
if (data->num_not_in_graph >= data->limit) {
result = 1;
break;
}
commit_list_append(parent->item, &stack);
}
}
free_commit_list(stack);
return result;
}
static int should_write_commit_graph(void)
{
int result;
struct cg_auto_data data;
data.num_not_in_graph = 0;
data.limit = 100;
git_config_get_int("maintenance.commit-graph.auto",
&data.limit);
if (!data.limit)
return 0;
if (data.limit < 0)
return 1;
result = for_each_ref(dfs_on_ref, &data);
repo_clear_commit_marks(the_repository, SEEN);
return result;
}
static int run_write_commit_graph(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_pushl(&child.args, "commit-graph", "write",
"--split", "--reachable", NULL);
if (opts->quiet)
strvec_push(&child.args, "--no-progress");
return !!run_command(&child);
}
static int maintenance_task_commit_graph(struct maintenance_run_opts *opts)
{
prepare_repo_settings(the_repository);
if (!the_repository->settings.core_commit_graph)
return 0;
close_object_store(the_repository->objects);
if (run_write_commit_graph(opts)) {
error(_("failed to write commit-graph"));
return 1;
}
return 0;
}
static int fetch_remote(struct remote *remote, void *cbdata)
{
struct maintenance_run_opts *opts = cbdata;
struct child_process child = CHILD_PROCESS_INIT;
if (remote->skip_default_update)
return 0;
child.git_cmd = 1;
strvec_pushl(&child.args, "fetch", remote->name,
"--prefetch", "--prune", "--no-tags",
"--no-write-fetch-head", "--recurse-submodules=no",
NULL);
if (opts->quiet)
strvec_push(&child.args, "--quiet");
return !!run_command(&child);
}
static int maintenance_task_prefetch(struct maintenance_run_opts *opts)
{
git_config_set_multivar_gently("log.excludedecoration",
"refs/prefetch/",
"refs/prefetch/",
CONFIG_FLAGS_FIXED_VALUE |
CONFIG_FLAGS_MULTI_REPLACE);
if (for_each_remote(fetch_remote, opts)) {
error(_("failed to prefetch remotes"));
return 1;
}
return 0;
}
static int maintenance_task_gc(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_push(&child.args, "gc");
if (opts->auto_flag)
strvec_push(&child.args, "--auto");
if (opts->quiet)
strvec_push(&child.args, "--quiet");
else
strvec_push(&child.args, "--no-quiet");
close_object_store(the_repository->objects);
return run_command(&child);
}
static int prune_packed(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_push(&child.args, "prune-packed");
if (opts->quiet)
strvec_push(&child.args, "--quiet");
return !!run_command(&child);
}
struct write_loose_object_data {
FILE *in;
int count;
int batch_size;
};
static int loose_object_auto_limit = 100;
static int loose_object_count(const struct object_id *oid,
const char *path,
void *data)
{
int *count = (int*)data;
if (++(*count) >= loose_object_auto_limit)
return 1;
return 0;
}
static int loose_object_auto_condition(void)
{
int count = 0;
git_config_get_int("maintenance.loose-objects.auto",
&loose_object_auto_limit);
if (!loose_object_auto_limit)
return 0;
if (loose_object_auto_limit < 0)
return 1;
return for_each_loose_file_in_objdir(the_repository->objects->odb->path,
loose_object_count,
NULL, NULL, &count);
}
static int bail_on_loose(const struct object_id *oid,
const char *path,
void *data)
{
return 1;
}
static int write_loose_object_to_stdin(const struct object_id *oid,
const char *path,
void *data)
{
struct write_loose_object_data *d = (struct write_loose_object_data *)data;
fprintf(d->in, "%s\n", oid_to_hex(oid));
return ++(d->count) > d->batch_size;
}
static int pack_loose(struct maintenance_run_opts *opts)
{
struct repository *r = the_repository;
int result = 0;
struct write_loose_object_data data;
struct child_process pack_proc = CHILD_PROCESS_INIT;
/*
* Do not start pack-objects process
* if there are no loose objects.
*/
if (!for_each_loose_file_in_objdir(r->objects->odb->path,
bail_on_loose,
NULL, NULL, NULL))
return 0;
pack_proc.git_cmd = 1;
strvec_push(&pack_proc.args, "pack-objects");
if (opts->quiet)
strvec_push(&pack_proc.args, "--quiet");
strvec_pushf(&pack_proc.args, "%s/pack/loose", r->objects->odb->path);
pack_proc.in = -1;
if (start_command(&pack_proc)) {
error(_("failed to start 'git pack-objects' process"));
return 1;
}
data.in = xfdopen(pack_proc.in, "w");
data.count = 0;
data.batch_size = 50000;
for_each_loose_file_in_objdir(r->objects->odb->path,
write_loose_object_to_stdin,
NULL,
NULL,
&data);
fclose(data.in);
if (finish_command(&pack_proc)) {
error(_("failed to finish 'git pack-objects' process"));
result = 1;
}
return result;
}
static int maintenance_task_loose_objects(struct maintenance_run_opts *opts)
{
return prune_packed(opts) || pack_loose(opts);
}
static int incremental_repack_auto_condition(void)
{
struct packed_git *p;
int enabled;
int incremental_repack_auto_limit = 10;
int count = 0;
if (git_config_get_bool("core.multiPackIndex", &enabled) ||
!enabled)
return 0;
git_config_get_int("maintenance.incremental-repack.auto",
&incremental_repack_auto_limit);
if (!incremental_repack_auto_limit)
return 0;
if (incremental_repack_auto_limit < 0)
return 1;
for (p = get_packed_git(the_repository);
count < incremental_repack_auto_limit && p;
p = p->next) {
if (!p->multi_pack_index)
count++;
}
return count >= incremental_repack_auto_limit;
}
static int multi_pack_index_write(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_pushl(&child.args, "multi-pack-index", "write", NULL);
if (opts->quiet)
strvec_push(&child.args, "--no-progress");
if (run_command(&child))
return error(_("failed to write multi-pack-index"));
return 0;
}
static int multi_pack_index_expire(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_pushl(&child.args, "multi-pack-index", "expire", NULL);
if (opts->quiet)
strvec_push(&child.args, "--no-progress");
close_object_store(the_repository->objects);
if (run_command(&child))
return error(_("'git multi-pack-index expire' failed"));
return 0;
}
#define TWO_GIGABYTES (INT32_MAX)
static off_t get_auto_pack_size(void)
{
/*
* The "auto" value is special: we optimize for
* one large pack-file (i.e. from a clone) and
* expect the rest to be small and they can be
* repacked quickly.
*
* The strategy we select here is to select a
* size that is one more than the second largest
* pack-file. This ensures that we will repack
* at least two packs if there are three or more
* packs.
*/
off_t max_size = 0;
off_t second_largest_size = 0;
off_t result_size;
struct packed_git *p;
struct repository *r = the_repository;
reprepare_packed_git(r);
for (p = get_all_packs(r); p; p = p->next) {
if (p->pack_size > max_size) {
second_largest_size = max_size;
max_size = p->pack_size;
} else if (p->pack_size > second_largest_size)
second_largest_size = p->pack_size;
}
result_size = second_largest_size + 1;
/* But limit ourselves to a batch size of 2g */
if (result_size > TWO_GIGABYTES)
result_size = TWO_GIGABYTES;
return result_size;
}
static int multi_pack_index_repack(struct maintenance_run_opts *opts)
{
struct child_process child = CHILD_PROCESS_INIT;
child.git_cmd = 1;
strvec_pushl(&child.args, "multi-pack-index", "repack", NULL);
if (opts->quiet)
strvec_push(&child.args, "--no-progress");
strvec_pushf(&child.args, "--batch-size=%"PRIuMAX,
(uintmax_t)get_auto_pack_size());
close_object_store(the_repository->objects);
if (run_command(&child))
return error(_("'git multi-pack-index repack' failed"));
return 0;
}
static int maintenance_task_incremental_repack(struct maintenance_run_opts *opts)
{
prepare_repo_settings(the_repository);
if (!the_repository->settings.core_multi_pack_index) {
warning(_("skipping incremental-repack task because core.multiPackIndex is disabled"));
return 0;
}
if (multi_pack_index_write(opts))
return 1;
if (multi_pack_index_expire(opts))
return 1;
if (multi_pack_index_repack(opts))
return 1;
return 0;
}
typedef int maintenance_task_fn(struct maintenance_run_opts *opts);
/*
* An auto condition function returns 1 if the task should run
* and 0 if the task should NOT run. See needs_to_gc() for an
* example.
*/
typedef int maintenance_auto_fn(void);
struct maintenance_task {
const char *name;
maintenance_task_fn *fn;
maintenance_auto_fn *auto_condition;
unsigned enabled:1;
enum schedule_priority schedule;
/* -1 if not selected. */
int selected_order;
};
enum maintenance_task_label {
TASK_PREFETCH,
TASK_LOOSE_OBJECTS,
TASK_INCREMENTAL_REPACK,
TASK_GC,
TASK_COMMIT_GRAPH,
TASK_PACK_REFS,
/* Leave as final value */
TASK__COUNT
};
static struct maintenance_task tasks[] = {
[TASK_PREFETCH] = {
"prefetch",
maintenance_task_prefetch,
},
[TASK_LOOSE_OBJECTS] = {
"loose-objects",
maintenance_task_loose_objects,
loose_object_auto_condition,
},
[TASK_INCREMENTAL_REPACK] = {
"incremental-repack",
maintenance_task_incremental_repack,
incremental_repack_auto_condition,
},
[TASK_GC] = {
"gc",
maintenance_task_gc,
need_to_gc,
1,
},
[TASK_COMMIT_GRAPH] = {
"commit-graph",
maintenance_task_commit_graph,
should_write_commit_graph,
},
[TASK_PACK_REFS] = {
"pack-refs",
maintenance_task_pack_refs,
NULL,
},
};
static int compare_tasks_by_selection(const void *a_, const void *b_)
{
const struct maintenance_task *a = a_;
const struct maintenance_task *b = b_;
return b->selected_order - a->selected_order;
}
static int maintenance_run_tasks(struct maintenance_run_opts *opts)
{
int i, found_selected = 0;
int result = 0;
struct lock_file lk;
struct repository *r = the_repository;
char *lock_path = xstrfmt("%s/maintenance", r->objects->odb->path);
if (hold_lock_file_for_update(&lk, lock_path, LOCK_NO_DEREF) < 0) {
/*
* Another maintenance command is running.
*
* If --auto was provided, then it is likely due to a
* recursive process stack. Do not report an error in
* that case.
*/
if (!opts->auto_flag && !opts->quiet)
warning(_("lock file '%s' exists, skipping maintenance"),
lock_path);
free(lock_path);
return 0;
}
free(lock_path);
for (i = 0; !found_selected && i < TASK__COUNT; i++)
found_selected = tasks[i].selected_order >= 0;
if (found_selected)
QSORT(tasks, TASK__COUNT, compare_tasks_by_selection);
for (i = 0; i < TASK__COUNT; i++) {
if (found_selected && tasks[i].selected_order < 0)
continue;
if (!found_selected && !tasks[i].enabled)
continue;
if (opts->auto_flag &&
(!tasks[i].auto_condition ||
!tasks[i].auto_condition()))
continue;
if (opts->schedule && tasks[i].schedule < opts->schedule)
continue;
trace2_region_enter("maintenance", tasks[i].name, r);
if (tasks[i].fn(opts)) {
error(_("task '%s' failed"), tasks[i].name);
result = 1;
}
trace2_region_leave("maintenance", tasks[i].name, r);
}
rollback_lock_file(&lk);
return result;
}
static void initialize_maintenance_strategy(void)
{
char *config_str;
if (git_config_get_string("maintenance.strategy", &config_str))
return;
if (!strcasecmp(config_str, "incremental")) {
tasks[TASK_GC].schedule = SCHEDULE_NONE;
tasks[TASK_COMMIT_GRAPH].enabled = 1;
tasks[TASK_COMMIT_GRAPH].schedule = SCHEDULE_HOURLY;
tasks[TASK_PREFETCH].enabled = 1;
tasks[TASK_PREFETCH].schedule = SCHEDULE_HOURLY;
tasks[TASK_INCREMENTAL_REPACK].enabled = 1;
tasks[TASK_INCREMENTAL_REPACK].schedule = SCHEDULE_DAILY;
tasks[TASK_LOOSE_OBJECTS].enabled = 1;
tasks[TASK_LOOSE_OBJECTS].schedule = SCHEDULE_DAILY;
tasks[TASK_PACK_REFS].enabled = 1;
tasks[TASK_PACK_REFS].schedule = SCHEDULE_WEEKLY;
}
}
static void initialize_task_config(int schedule)
{
int i;
struct strbuf config_name = STRBUF_INIT;
gc_config();
if (schedule)
initialize_maintenance_strategy();
for (i = 0; i < TASK__COUNT; i++) {
int config_value;
char *config_str;
strbuf_reset(&config_name);
strbuf_addf(&config_name, "maintenance.%s.enabled",
tasks[i].name);
if (!git_config_get_bool(config_name.buf, &config_value))
tasks[i].enabled = config_value;
strbuf_reset(&config_name);
strbuf_addf(&config_name, "maintenance.%s.schedule",
tasks[i].name);
if (!git_config_get_string(config_name.buf, &config_str)) {
tasks[i].schedule = parse_schedule(config_str);
free(config_str);
}
}
strbuf_release(&config_name);
}
static int task_option_parse(const struct option *opt,
const char *arg, int unset)
{
int i, num_selected = 0;
struct maintenance_task *task = NULL;
BUG_ON_OPT_NEG(unset);
for (i = 0; i < TASK__COUNT; i++) {
if (tasks[i].selected_order >= 0)
num_selected++;
if (!strcasecmp(tasks[i].name, arg)) {
task = &tasks[i];
}
}
if (!task) {
error(_("'%s' is not a valid task"), arg);
return 1;
}
if (task->selected_order >= 0) {
error(_("task '%s' cannot be selected multiple times"), arg);
return 1;
}
task->selected_order = num_selected + 1;
return 0;
}
static int maintenance_run(int argc, const char **argv, const char *prefix)
{
int i;
struct maintenance_run_opts opts;
struct option builtin_maintenance_run_options[] = {
OPT_BOOL(0, "auto", &opts.auto_flag,
N_("run tasks based on the state of the repository")),
OPT_CALLBACK(0, "schedule", &opts.schedule, N_("frequency"),
N_("run tasks based on frequency"),
maintenance_opt_schedule),
OPT_BOOL(0, "quiet", &opts.quiet,
N_("do not report progress or other information over stderr")),
OPT_CALLBACK_F(0, "task", NULL, N_("task"),
N_("run a specific task"),
PARSE_OPT_NONEG, task_option_parse),
OPT_END()
};
memset(&opts, 0, sizeof(opts));
opts.quiet = !isatty(2);
for (i = 0; i < TASK__COUNT; i++)
tasks[i].selected_order = -1;
argc = parse_options(argc, argv, prefix,
builtin_maintenance_run_options,
builtin_maintenance_run_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (opts.auto_flag && opts.schedule)
die(_("use at most one of --auto and --schedule=<frequency>"));
initialize_task_config(opts.schedule);
if (argc != 0)
usage_with_options(builtin_maintenance_run_usage,
builtin_maintenance_run_options);
return maintenance_run_tasks(&opts);
}
static char *get_maintpath(void)
{
struct strbuf sb = STRBUF_INIT;
const char *p = the_repository->worktree ?
the_repository->worktree : the_repository->gitdir;
strbuf_realpath(&sb, p, 1);
return strbuf_detach(&sb, NULL);
}
static int maintenance_register(void)
{
int rc;
char *config_value;
struct child_process config_set = CHILD_PROCESS_INIT;
struct child_process config_get = CHILD_PROCESS_INIT;
char *maintpath = get_maintpath();
/* Disable foreground maintenance */
git_config_set("maintenance.auto", "false");
/* Set maintenance strategy, if unset */
if (!git_config_get_string("maintenance.strategy", &config_value))
free(config_value);
else
git_config_set("maintenance.strategy", "incremental");
config_get.git_cmd = 1;
strvec_pushl(&config_get.args, "config", "--global", "--get",
"--fixed-value", "maintenance.repo", maintpath, NULL);
config_get.out = -1;
if (start_command(&config_get)) {
rc = error(_("failed to run 'git config'"));
goto done;
}
/* We already have this value in our config! */
if (!finish_command(&config_get)) {
rc = 0;
goto done;
}
config_set.git_cmd = 1;
strvec_pushl(&config_set.args, "config", "--add", "--global", "maintenance.repo",
maintpath, NULL);
rc = run_command(&config_set);
done:
free(maintpath);
return rc;
}
static int maintenance_unregister(void)
{
int rc;
struct child_process config_unset = CHILD_PROCESS_INIT;
char *maintpath = get_maintpath();
config_unset.git_cmd = 1;
strvec_pushl(&config_unset.args, "config", "--global", "--unset",
"--fixed-value", "maintenance.repo", maintpath, NULL);
rc = run_command(&config_unset);
free(maintpath);
return rc;
}
static const char *get_frequency(enum schedule_priority schedule)
{
switch (schedule) {
case SCHEDULE_HOURLY:
return "hourly";
case SCHEDULE_DAILY:
return "daily";
case SCHEDULE_WEEKLY:
return "weekly";
default:
BUG("invalid schedule %d", schedule);
}
}
static char *launchctl_service_name(const char *frequency)
{
struct strbuf label = STRBUF_INIT;
strbuf_addf(&label, "org.git-scm.git.%s", frequency);
return strbuf_detach(&label, NULL);
}
static char *launchctl_service_filename(const char *name)
{
char *expanded;
struct strbuf filename = STRBUF_INIT;
strbuf_addf(&filename, "~/Library/LaunchAgents/%s.plist", name);
expanded = expand_user_path(filename.buf, 1);
if (!expanded)
die(_("failed to expand path '%s'"), filename.buf);
strbuf_release(&filename);
return expanded;
}
static char *launchctl_get_uid(void)
{
return xstrfmt("gui/%d", getuid());
}
static int launchctl_boot_plist(int enable, const char *filename, const char *cmd)
{
int result;
struct child_process child = CHILD_PROCESS_INIT;
char *uid = launchctl_get_uid();
strvec_split(&child.args, cmd);
if (enable)
strvec_push(&child.args, "bootstrap");
else
strvec_push(&child.args, "bootout");
strvec_push(&child.args, uid);
strvec_push(&child.args, filename);
child.no_stderr = 1;
child.no_stdout = 1;
if (start_command(&child))
die(_("failed to start launchctl"));
result = finish_command(&child);
free(uid);
return result;
}
static int launchctl_remove_plist(enum schedule_priority schedule, const char *cmd)
{
const char *frequency = get_frequency(schedule);
char *name = launchctl_service_name(frequency);
char *filename = launchctl_service_filename(name);
int result = launchctl_boot_plist(0, filename, cmd);
unlink(filename);
free(filename);
free(name);
return result;
}
static int launchctl_remove_plists(const char *cmd)
{
return launchctl_remove_plist(SCHEDULE_HOURLY, cmd) ||
launchctl_remove_plist(SCHEDULE_DAILY, cmd) ||
launchctl_remove_plist(SCHEDULE_WEEKLY, cmd);
}
static int launchctl_list_contains_plist(const char *name, const char *cmd)
{
int result;
struct child_process child = CHILD_PROCESS_INIT;
char *uid = launchctl_get_uid();
strvec_split(&child.args, cmd);
strvec_pushl(&child.args, "list", name, NULL);
child.no_stderr = 1;
child.no_stdout = 1;
if (start_command(&child))
die(_("failed to start launchctl"));
result = finish_command(&child);
free(uid);
/* Returns failure if 'name' doesn't exist. */
return !result;
}
static int launchctl_schedule_plist(const char *exec_path, enum schedule_priority schedule, const char *cmd)
{
int i, fd;
const char *preamble, *repeat;
const char *frequency = get_frequency(schedule);
char *name = launchctl_service_name(frequency);
char *filename = launchctl_service_filename(name);
struct lock_file lk = LOCK_INIT;
static unsigned long lock_file_timeout_ms = ULONG_MAX;
struct strbuf plist = STRBUF_INIT, plist2 = STRBUF_INIT;
struct stat st;
preamble = "<?xml version=\"1.0\"?>\n"
"<!DOCTYPE plist PUBLIC \"-//Apple//DTD PLIST 1.0//EN\" \"http://www.apple.com/DTDs/PropertyList-1.0.dtd\">\n"
"<plist version=\"1.0\">"
"<dict>\n"
"<key>Label</key><string>%s</string>\n"
"<key>ProgramArguments</key>\n"
"<array>\n"
"<string>%s/git</string>\n"
"<string>--exec-path=%s</string>\n"
"<string>for-each-repo</string>\n"
"<string>--config=maintenance.repo</string>\n"
"<string>maintenance</string>\n"
"<string>run</string>\n"
"<string>--schedule=%s</string>\n"
"</array>\n"
"<key>StartCalendarInterval</key>\n"
"<array>\n";
strbuf_addf(&plist, preamble, name, exec_path, exec_path, frequency);
switch (schedule) {
case SCHEDULE_HOURLY:
repeat = "<dict>\n"
"<key>Hour</key><integer>%d</integer>\n"
"<key>Minute</key><integer>0</integer>\n"
"</dict>\n";
for (i = 1; i <= 23; i++)
strbuf_addf(&plist, repeat, i);
break;
case SCHEDULE_DAILY:
repeat = "<dict>\n"
"<key>Day</key><integer>%d</integer>\n"
"<key>Hour</key><integer>0</integer>\n"
"<key>Minute</key><integer>0</integer>\n"
"</dict>\n";
for (i = 1; i <= 6; i++)
strbuf_addf(&plist, repeat, i);
break;
case SCHEDULE_WEEKLY:
strbuf_addstr(&plist,
"<dict>\n"
"<key>Day</key><integer>0</integer>\n"
"<key>Hour</key><integer>0</integer>\n"
"<key>Minute</key><integer>0</integer>\n"
"</dict>\n");
break;
default:
/* unreachable */
break;
}
strbuf_addstr(&plist, "</array>\n</dict>\n</plist>\n");
if (safe_create_leading_directories(filename))
die(_("failed to create directories for '%s'"), filename);
if ((long)lock_file_timeout_ms < 0 &&
git_config_get_ulong("gc.launchctlplistlocktimeoutms",
&lock_file_timeout_ms))
lock_file_timeout_ms = 150;
fd = hold_lock_file_for_update_timeout(&lk, filename, LOCK_DIE_ON_ERROR,
lock_file_timeout_ms);
/*
* Does this file already exist? With the intended contents? Is it
* registered already? Then it does not need to be re-registered.
*/
if (!stat(filename, &st) && st.st_size == plist.len &&
strbuf_read_file(&plist2, filename, plist.len) == plist.len &&
!strbuf_cmp(&plist, &plist2) &&
launchctl_list_contains_plist(name, cmd))
rollback_lock_file(&lk);
else {
if (write_in_full(fd, plist.buf, plist.len) < 0 ||
commit_lock_file(&lk))
die_errno(_("could not write '%s'"), filename);
/* bootout might fail if not already running, so ignore */
launchctl_boot_plist(0, filename, cmd);
if (launchctl_boot_plist(1, filename, cmd))
die(_("failed to bootstrap service %s"), filename);
}
free(filename);
free(name);
strbuf_release(&plist);
strbuf_release(&plist2);
return 0;
}
static int launchctl_add_plists(const char *cmd)
{
const char *exec_path = git_exec_path();
return launchctl_schedule_plist(exec_path, SCHEDULE_HOURLY, cmd) ||
launchctl_schedule_plist(exec_path, SCHEDULE_DAILY, cmd) ||
launchctl_schedule_plist(exec_path, SCHEDULE_WEEKLY, cmd);
}
static int launchctl_update_schedule(int run_maintenance, int fd, const char *cmd)
{
if (run_maintenance)
return launchctl_add_plists(cmd);
else
return launchctl_remove_plists(cmd);
}
static char *schtasks_task_name(const char *frequency)
{
struct strbuf label = STRBUF_INIT;
strbuf_addf(&label, "Git Maintenance (%s)", frequency);
return strbuf_detach(&label, NULL);
}
static int schtasks_remove_task(enum schedule_priority schedule, const char *cmd)
{
int result;
struct strvec args = STRVEC_INIT;
const char *frequency = get_frequency(schedule);
char *name = schtasks_task_name(frequency);
strvec_split(&args, cmd);
strvec_pushl(&args, "/delete", "/tn", name, "/f", NULL);
result = run_command_v_opt(args.v, 0);
strvec_clear(&args);
free(name);
return result;
}
static int schtasks_remove_tasks(const char *cmd)
{
return schtasks_remove_task(SCHEDULE_HOURLY, cmd) ||
schtasks_remove_task(SCHEDULE_DAILY, cmd) ||
schtasks_remove_task(SCHEDULE_WEEKLY, cmd);
}
static int schtasks_schedule_task(const char *exec_path, enum schedule_priority schedule, const char *cmd)
{
int result;
struct child_process child = CHILD_PROCESS_INIT;
const char *xml;
struct tempfile *tfile;
const char *frequency = get_frequency(schedule);
char *name = schtasks_task_name(frequency);
struct strbuf tfilename = STRBUF_INIT;
strbuf_addf(&tfilename, "%s/schedule_%s_XXXXXX",
get_git_common_dir(), frequency);
tfile = xmks_tempfile(tfilename.buf);
strbuf_release(&tfilename);
if (!fdopen_tempfile(tfile, "w"))
die(_("failed to create temp xml file"));
xml = "<?xml version=\"1.0\" ?>\n"
"<Task version=\"1.4\" xmlns=\"http://schemas.microsoft.com/windows/2004/02/mit/task\">\n"
"<Triggers>\n"
"<CalendarTrigger>\n";
fputs(xml, tfile->fp);
switch (schedule) {
case SCHEDULE_HOURLY:
fprintf(tfile->fp,
"<StartBoundary>2020-01-01T01:00:00</StartBoundary>\n"
"<Enabled>true</Enabled>\n"
"<ScheduleByDay>\n"
"<DaysInterval>1</DaysInterval>\n"
"</ScheduleByDay>\n"
"<Repetition>\n"
"<Interval>PT1H</Interval>\n"
"<Duration>PT23H</Duration>\n"
"<StopAtDurationEnd>false</StopAtDurationEnd>\n"
"</Repetition>\n");
break;
case SCHEDULE_DAILY:
fprintf(tfile->fp,
"<StartBoundary>2020-01-01T00:00:00</StartBoundary>\n"
"<Enabled>true</Enabled>\n"
"<ScheduleByWeek>\n"
"<DaysOfWeek>\n"
"<Monday />\n"
"<Tuesday />\n"
"<Wednesday />\n"
"<Thursday />\n"
"<Friday />\n"
"<Saturday />\n"
"</DaysOfWeek>\n"
"<WeeksInterval>1</WeeksInterval>\n"
"</ScheduleByWeek>\n");
break;
case SCHEDULE_WEEKLY:
fprintf(tfile->fp,
"<StartBoundary>2020-01-01T00:00:00</StartBoundary>\n"
"<Enabled>true</Enabled>\n"
"<ScheduleByWeek>\n"
"<DaysOfWeek>\n"
"<Sunday />\n"
"</DaysOfWeek>\n"
"<WeeksInterval>1</WeeksInterval>\n"
"</ScheduleByWeek>\n");
break;
default:
break;
}
xml = "</CalendarTrigger>\n"
"</Triggers>\n"
"<Principals>\n"
"<Principal id=\"Author\">\n"
"<LogonType>InteractiveToken</LogonType>\n"
"<RunLevel>LeastPrivilege</RunLevel>\n"
"</Principal>\n"
"</Principals>\n"
"<Settings>\n"
"<MultipleInstancesPolicy>IgnoreNew</MultipleInstancesPolicy>\n"
"<Enabled>true</Enabled>\n"
"<Hidden>true</Hidden>\n"
"<UseUnifiedSchedulingEngine>true</UseUnifiedSchedulingEngine>\n"
"<WakeToRun>false</WakeToRun>\n"
"<ExecutionTimeLimit>PT72H</ExecutionTimeLimit>\n"
"<Priority>7</Priority>\n"
"</Settings>\n"
"<Actions Context=\"Author\">\n"
"<Exec>\n"
"<Command>\"%s\\git.exe\"</Command>\n"
"<Arguments>--exec-path=\"%s\" for-each-repo --config=maintenance.repo maintenance run --schedule=%s</Arguments>\n"
"</Exec>\n"
"</Actions>\n"
"</Task>\n";
fprintf(tfile->fp, xml, exec_path, exec_path, frequency);
strvec_split(&child.args, cmd);
strvec_pushl(&child.args, "/create", "/tn", name, "/f", "/xml",
get_tempfile_path(tfile), NULL);
close_tempfile_gently(tfile);
child.no_stdout = 1;
child.no_stderr = 1;
if (start_command(&child))
die(_("failed to start schtasks"));
result = finish_command(&child);
delete_tempfile(&tfile);
free(name);
return result;
}
static int schtasks_schedule_tasks(const char *cmd)
{
const char *exec_path = git_exec_path();
return schtasks_schedule_task(exec_path, SCHEDULE_HOURLY, cmd) ||
schtasks_schedule_task(exec_path, SCHEDULE_DAILY, cmd) ||
schtasks_schedule_task(exec_path, SCHEDULE_WEEKLY, cmd);
}
static int schtasks_update_schedule(int run_maintenance, int fd, const char *cmd)
{
if (run_maintenance)
return schtasks_schedule_tasks(cmd);
else
return schtasks_remove_tasks(cmd);
}
#define BEGIN_LINE "# BEGIN GIT MAINTENANCE SCHEDULE"
#define END_LINE "# END GIT MAINTENANCE SCHEDULE"
static int crontab_update_schedule(int run_maintenance, int fd, const char *cmd)
{
int result = 0;
int in_old_region = 0;
struct child_process crontab_list = CHILD_PROCESS_INIT;
struct child_process crontab_edit = CHILD_PROCESS_INIT;
FILE *cron_list, *cron_in;
struct strbuf line = STRBUF_INIT;
strvec_split(&crontab_list.args, cmd);
strvec_push(&crontab_list.args, "-l");
crontab_list.in = -1;
crontab_list.out = dup(fd);
crontab_list.git_cmd = 0;
if (start_command(&crontab_list))
return error(_("failed to run 'crontab -l'; your system might not support 'cron'"));
/* Ignore exit code, as an empty crontab will return error. */
finish_command(&crontab_list);
/*
* Read from the .lock file, filtering out the old
* schedule while appending the new schedule.
*/
cron_list = fdopen(fd, "r");
rewind(cron_list);
strvec_split(&crontab_edit.args, cmd);
crontab_edit.in = -1;
crontab_edit.git_cmd = 0;
if (start_command(&crontab_edit))
return error(_("failed to run 'crontab'; your system might not support 'cron'"));
cron_in = fdopen(crontab_edit.in, "w");
if (!cron_in) {
result = error(_("failed to open stdin of 'crontab'"));
goto done_editing;
}
while (!strbuf_getline_lf(&line, cron_list)) {
if (!in_old_region && !strcmp(line.buf, BEGIN_LINE))
in_old_region = 1;
else if (in_old_region && !strcmp(line.buf, END_LINE))
in_old_region = 0;
else if (!in_old_region)
fprintf(cron_in, "%s\n", line.buf);
}
strbuf_release(&line);
if (run_maintenance) {
struct strbuf line_format = STRBUF_INIT;
const char *exec_path = git_exec_path();
fprintf(cron_in, "%s\n", BEGIN_LINE);
fprintf(cron_in,
"# The following schedule was created by Git\n");
fprintf(cron_in, "# Any edits made in this region might be\n");
fprintf(cron_in,
"# replaced in the future by a Git command.\n\n");
strbuf_addf(&line_format,
"%%s %%s * * %%s \"%s/git\" --exec-path=\"%s\" for-each-repo --config=maintenance.repo maintenance run --schedule=%%s\n",
exec_path, exec_path);
fprintf(cron_in, line_format.buf, "0", "1-23", "*", "hourly");
fprintf(cron_in, line_format.buf, "0", "0", "1-6", "daily");
fprintf(cron_in, line_format.buf, "0", "0", "0", "weekly");
strbuf_release(&line_format);
fprintf(cron_in, "\n%s\n", END_LINE);
}
fflush(cron_in);
fclose(cron_in);
close(crontab_edit.in);
done_editing:
if (finish_command(&crontab_edit))
result = error(_("'crontab' died"));
else
fclose(cron_list);
return result;
}
#if defined(__APPLE__)
static const char platform_scheduler[] = "launchctl";
#elif defined(GIT_WINDOWS_NATIVE)
static const char platform_scheduler[] = "schtasks";
#else
static const char platform_scheduler[] = "crontab";
#endif
static int update_background_schedule(int enable)
{
int result;
const char *scheduler = platform_scheduler;
const char *cmd = scheduler;
char *testing;
struct lock_file lk;
char *lock_path = xstrfmt("%s/schedule", the_repository->objects->odb->path);
testing = xstrdup_or_null(getenv("GIT_TEST_MAINT_SCHEDULER"));
if (testing) {
char *sep = strchr(testing, ':');
if (!sep)
die("GIT_TEST_MAINT_SCHEDULER unparseable: %s", testing);
*sep = '\0';
scheduler = testing;
cmd = sep + 1;
}
if (hold_lock_file_for_update(&lk, lock_path, LOCK_NO_DEREF) < 0) {
result = error(_("another process is scheduling background maintenance"));
goto cleanup;
}
if (!strcmp(scheduler, "launchctl"))
result = launchctl_update_schedule(enable, get_lock_file_fd(&lk), cmd);
else if (!strcmp(scheduler, "schtasks"))
result = schtasks_update_schedule(enable, get_lock_file_fd(&lk), cmd);
else if (!strcmp(scheduler, "crontab"))
result = crontab_update_schedule(enable, get_lock_file_fd(&lk), cmd);
else
die("unknown background scheduler: %s", scheduler);
rollback_lock_file(&lk);
cleanup:
free(lock_path);
free(testing);
return result;
}
static int maintenance_start(void)
{
if (maintenance_register())
warning(_("failed to add repo to global config"));
return update_background_schedule(1);
}
static int maintenance_stop(void)
{
return update_background_schedule(0);
}
static const char builtin_maintenance_usage[] = N_("git maintenance <subcommand> [<options>]");
int cmd_maintenance(int argc, const char **argv, const char *prefix)
{
if (argc < 2 ||
(argc == 2 && !strcmp(argv[1], "-h")))
usage(builtin_maintenance_usage);
if (!strcmp(argv[1], "run"))
return maintenance_run(argc - 1, argv + 1, prefix);
if (!strcmp(argv[1], "start"))
return maintenance_start();
if (!strcmp(argv[1], "stop"))
return maintenance_stop();
if (!strcmp(argv[1], "register"))
return maintenance_register();
if (!strcmp(argv[1], "unregister"))
return maintenance_unregister();
die(_("invalid subcommand: %s"), argv[1]);
}
|