forked from git/git
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmidx.c
1420 lines (1139 loc) · 36.2 KB
/
midx.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#include "cache.h"
#include "config.h"
#include "csum-file.h"
#include "dir.h"
#include "lockfile.h"
#include "packfile.h"
#include "object-store.h"
#include "sha1-lookup.h"
#include "midx.h"
#include "progress.h"
#include "trace2.h"
#include "run-command.h"
#define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */
#define MIDX_VERSION 1
#define MIDX_BYTE_FILE_VERSION 4
#define MIDX_BYTE_HASH_VERSION 5
#define MIDX_BYTE_NUM_CHUNKS 6
#define MIDX_BYTE_NUM_PACKS 8
#define MIDX_HASH_VERSION 1
#define MIDX_HEADER_SIZE 12
#define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz)
#define MIDX_MAX_CHUNKS 5
#define MIDX_CHUNK_ALIGNMENT 4
#define MIDX_CHUNKID_PACKNAMES 0x504e414d /* "PNAM" */
#define MIDX_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
#define MIDX_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
#define MIDX_CHUNKID_OBJECTOFFSETS 0x4f4f4646 /* "OOFF" */
#define MIDX_CHUNKID_LARGEOFFSETS 0x4c4f4646 /* "LOFF" */
#define MIDX_CHUNKLOOKUP_WIDTH (sizeof(uint32_t) + sizeof(uint64_t))
#define MIDX_CHUNK_FANOUT_SIZE (sizeof(uint32_t) * 256)
#define MIDX_CHUNK_OFFSET_WIDTH (2 * sizeof(uint32_t))
#define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
#define PACK_EXPIRED UINT_MAX
static char *get_midx_filename(const char *object_dir)
{
return xstrfmt("%s/pack/multi-pack-index", object_dir);
}
struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local)
{
struct multi_pack_index *m = NULL;
int fd;
struct stat st;
size_t midx_size;
void *midx_map = NULL;
uint32_t hash_version;
char *midx_name = get_midx_filename(object_dir);
uint32_t i;
const char *cur_pack_name;
fd = git_open(midx_name);
if (fd < 0)
goto cleanup_fail;
if (fstat(fd, &st)) {
error_errno(_("failed to read %s"), midx_name);
goto cleanup_fail;
}
midx_size = xsize_t(st.st_size);
if (midx_size < MIDX_MIN_SIZE) {
error(_("multi-pack-index file %s is too small"), midx_name);
goto cleanup_fail;
}
FREE_AND_NULL(midx_name);
midx_map = xmmap(NULL, midx_size, PROT_READ, MAP_PRIVATE, fd, 0);
FLEX_ALLOC_STR(m, object_dir, object_dir);
m->fd = fd;
m->data = midx_map;
m->data_len = midx_size;
m->local = local;
m->signature = get_be32(m->data);
if (m->signature != MIDX_SIGNATURE)
die(_("multi-pack-index signature 0x%08x does not match signature 0x%08x"),
m->signature, MIDX_SIGNATURE);
m->version = m->data[MIDX_BYTE_FILE_VERSION];
if (m->version != MIDX_VERSION)
die(_("multi-pack-index version %d not recognized"),
m->version);
hash_version = m->data[MIDX_BYTE_HASH_VERSION];
if (hash_version != MIDX_HASH_VERSION)
die(_("hash version %u does not match"), hash_version);
m->hash_len = the_hash_algo->rawsz;
m->num_chunks = m->data[MIDX_BYTE_NUM_CHUNKS];
m->num_packs = get_be32(m->data + MIDX_BYTE_NUM_PACKS);
for (i = 0; i < m->num_chunks; i++) {
uint32_t chunk_id = get_be32(m->data + MIDX_HEADER_SIZE +
MIDX_CHUNKLOOKUP_WIDTH * i);
uint64_t chunk_offset = get_be64(m->data + MIDX_HEADER_SIZE + 4 +
MIDX_CHUNKLOOKUP_WIDTH * i);
if (chunk_offset >= m->data_len)
die(_("invalid chunk offset (too large)"));
switch (chunk_id) {
case MIDX_CHUNKID_PACKNAMES:
m->chunk_pack_names = m->data + chunk_offset;
break;
case MIDX_CHUNKID_OIDFANOUT:
m->chunk_oid_fanout = (uint32_t *)(m->data + chunk_offset);
break;
case MIDX_CHUNKID_OIDLOOKUP:
m->chunk_oid_lookup = m->data + chunk_offset;
break;
case MIDX_CHUNKID_OBJECTOFFSETS:
m->chunk_object_offsets = m->data + chunk_offset;
break;
case MIDX_CHUNKID_LARGEOFFSETS:
m->chunk_large_offsets = m->data + chunk_offset;
break;
case 0:
die(_("terminating multi-pack-index chunk id appears earlier than expected"));
break;
default:
/*
* Do nothing on unrecognized chunks, allowing future
* extensions to add optional chunks.
*/
break;
}
}
if (!m->chunk_pack_names)
die(_("multi-pack-index missing required pack-name chunk"));
if (!m->chunk_oid_fanout)
die(_("multi-pack-index missing required OID fanout chunk"));
if (!m->chunk_oid_lookup)
die(_("multi-pack-index missing required OID lookup chunk"));
if (!m->chunk_object_offsets)
die(_("multi-pack-index missing required object offsets chunk"));
m->num_objects = ntohl(m->chunk_oid_fanout[255]);
m->pack_names = xcalloc(m->num_packs, sizeof(*m->pack_names));
m->packs = xcalloc(m->num_packs, sizeof(*m->packs));
cur_pack_name = (const char *)m->chunk_pack_names;
for (i = 0; i < m->num_packs; i++) {
m->pack_names[i] = cur_pack_name;
cur_pack_name += strlen(cur_pack_name) + 1;
if (i && strcmp(m->pack_names[i], m->pack_names[i - 1]) <= 0)
die(_("multi-pack-index pack names out of order: '%s' before '%s'"),
m->pack_names[i - 1],
m->pack_names[i]);
}
trace2_data_intmax("midx", the_repository, "load/num_packs", m->num_packs);
trace2_data_intmax("midx", the_repository, "load/num_objects", m->num_objects);
return m;
cleanup_fail:
free(m);
free(midx_name);
if (midx_map)
munmap(midx_map, midx_size);
if (0 <= fd)
close(fd);
return NULL;
}
void close_midx(struct multi_pack_index *m)
{
uint32_t i;
if (!m)
return;
munmap((unsigned char *)m->data, m->data_len);
close(m->fd);
m->fd = -1;
for (i = 0; i < m->num_packs; i++) {
if (m->packs[i])
m->packs[i]->multi_pack_index = 0;
}
FREE_AND_NULL(m->packs);
FREE_AND_NULL(m->pack_names);
}
int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id)
{
struct strbuf pack_name = STRBUF_INIT;
struct packed_git *p;
if (pack_int_id >= m->num_packs)
die(_("bad pack-int-id: %u (%u total packs)"),
pack_int_id, m->num_packs);
if (m->packs[pack_int_id])
return 0;
strbuf_addf(&pack_name, "%s/pack/%s", m->object_dir,
m->pack_names[pack_int_id]);
p = add_packed_git(pack_name.buf, pack_name.len, m->local);
strbuf_release(&pack_name);
if (!p)
return 1;
p->multi_pack_index = 1;
m->packs[pack_int_id] = p;
install_packed_git(r, p);
list_add_tail(&p->mru, &r->objects->packed_git_mru);
return 0;
}
int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result)
{
return bsearch_hash(oid->hash, m->chunk_oid_fanout, m->chunk_oid_lookup,
the_hash_algo->rawsz, result);
}
struct object_id *nth_midxed_object_oid(struct object_id *oid,
struct multi_pack_index *m,
uint32_t n)
{
if (n >= m->num_objects)
return NULL;
hashcpy(oid->hash, m->chunk_oid_lookup + m->hash_len * n);
return oid;
}
static off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos)
{
const unsigned char *offset_data;
uint32_t offset32;
offset_data = m->chunk_object_offsets + pos * MIDX_CHUNK_OFFSET_WIDTH;
offset32 = get_be32(offset_data + sizeof(uint32_t));
if (m->chunk_large_offsets && offset32 & MIDX_LARGE_OFFSET_NEEDED) {
if (sizeof(off_t) < sizeof(uint64_t))
die(_("multi-pack-index stores a 64-bit offset, but off_t is too small"));
offset32 ^= MIDX_LARGE_OFFSET_NEEDED;
return get_be64(m->chunk_large_offsets + sizeof(uint64_t) * offset32);
}
return offset32;
}
static uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos)
{
return get_be32(m->chunk_object_offsets + pos * MIDX_CHUNK_OFFSET_WIDTH);
}
static int nth_midxed_pack_entry(struct repository *r,
struct multi_pack_index *m,
struct pack_entry *e,
uint32_t pos)
{
uint32_t pack_int_id;
struct packed_git *p;
if (pos >= m->num_objects)
return 0;
pack_int_id = nth_midxed_pack_int_id(m, pos);
if (prepare_midx_pack(r, m, pack_int_id))
die(_("error preparing packfile from multi-pack-index"));
p = m->packs[pack_int_id];
/*
* We are about to tell the caller where they can locate the
* requested object. We better make sure the packfile is
* still here and can be accessed before supplying that
* answer, as it may have been deleted since the MIDX was
* loaded!
*/
if (!is_pack_valid(p))
return 0;
if (p->num_bad_objects) {
uint32_t i;
struct object_id oid;
nth_midxed_object_oid(&oid, m, pos);
for (i = 0; i < p->num_bad_objects; i++)
if (hasheq(oid.hash,
p->bad_object_sha1 + the_hash_algo->rawsz * i))
return 0;
}
e->offset = nth_midxed_offset(m, pos);
e->p = p;
return 1;
}
int fill_midx_entry(struct repository * r,
const struct object_id *oid,
struct pack_entry *e,
struct multi_pack_index *m)
{
uint32_t pos;
if (!bsearch_midx(oid, m, &pos))
return 0;
return nth_midxed_pack_entry(r, m, e, pos);
}
/* Match "foo.idx" against either "foo.pack" _or_ "foo.idx". */
static int cmp_idx_or_pack_name(const char *idx_or_pack_name,
const char *idx_name)
{
/* Skip past any initial matching prefix. */
while (*idx_name && *idx_name == *idx_or_pack_name) {
idx_name++;
idx_or_pack_name++;
}
/*
* If we didn't match completely, we may have matched "pack-1234." and
* be left with "idx" and "pack" respectively, which is also OK. We do
* not have to check for "idx" and "idx", because that would have been
* a complete match (and in that case these strcmps will be false, but
* we'll correctly return 0 from the final strcmp() below.
*
* Technically this matches "fooidx" and "foopack", but we'd never have
* such names in the first place.
*/
if (!strcmp(idx_name, "idx") && !strcmp(idx_or_pack_name, "pack"))
return 0;
/*
* This not only checks for a complete match, but also orders based on
* the first non-identical character, which means our ordering will
* match a raw strcmp(). That makes it OK to use this to binary search
* a naively-sorted list.
*/
return strcmp(idx_or_pack_name, idx_name);
}
int midx_contains_pack(struct multi_pack_index *m, const char *idx_or_pack_name)
{
uint32_t first = 0, last = m->num_packs;
while (first < last) {
uint32_t mid = first + (last - first) / 2;
const char *current;
int cmp;
current = m->pack_names[mid];
cmp = cmp_idx_or_pack_name(idx_or_pack_name, current);
if (!cmp)
return 1;
if (cmp > 0) {
first = mid + 1;
continue;
}
last = mid;
}
return 0;
}
int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, int local)
{
struct multi_pack_index *m;
struct multi_pack_index *m_search;
int config_value;
static int env_value = -1;
if (env_value < 0)
env_value = git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0);
if (!env_value &&
(repo_config_get_bool(r, "core.multipackindex", &config_value) ||
!config_value))
return 0;
for (m_search = r->objects->multi_pack_index; m_search; m_search = m_search->next)
if (!strcmp(object_dir, m_search->object_dir))
return 1;
m = load_multi_pack_index(object_dir, local);
if (m) {
m->next = r->objects->multi_pack_index;
r->objects->multi_pack_index = m;
return 1;
}
return 0;
}
static size_t write_midx_header(struct hashfile *f,
unsigned char num_chunks,
uint32_t num_packs)
{
unsigned char byte_values[4];
hashwrite_be32(f, MIDX_SIGNATURE);
byte_values[0] = MIDX_VERSION;
byte_values[1] = MIDX_HASH_VERSION;
byte_values[2] = num_chunks;
byte_values[3] = 0; /* unused */
hashwrite(f, byte_values, sizeof(byte_values));
hashwrite_be32(f, num_packs);
return MIDX_HEADER_SIZE;
}
struct pack_info {
uint32_t orig_pack_int_id;
char *pack_name;
struct packed_git *p;
unsigned expired : 1;
};
static int pack_info_compare(const void *_a, const void *_b)
{
struct pack_info *a = (struct pack_info *)_a;
struct pack_info *b = (struct pack_info *)_b;
return strcmp(a->pack_name, b->pack_name);
}
struct pack_list {
struct pack_info *info;
uint32_t nr;
uint32_t alloc;
struct multi_pack_index *m;
struct progress *progress;
unsigned pack_paths_checked;
};
static void add_pack_to_midx(const char *full_path, size_t full_path_len,
const char *file_name, void *data)
{
struct pack_list *packs = (struct pack_list *)data;
if (ends_with(file_name, ".idx")) {
display_progress(packs->progress, ++packs->pack_paths_checked);
if (packs->m && midx_contains_pack(packs->m, file_name))
return;
ALLOC_GROW(packs->info, packs->nr + 1, packs->alloc);
packs->info[packs->nr].p = add_packed_git(full_path,
full_path_len,
0);
if (!packs->info[packs->nr].p) {
warning(_("failed to add packfile '%s'"),
full_path);
return;
}
if (open_pack_index(packs->info[packs->nr].p)) {
warning(_("failed to open pack-index '%s'"),
full_path);
close_pack(packs->info[packs->nr].p);
FREE_AND_NULL(packs->info[packs->nr].p);
return;
}
packs->info[packs->nr].pack_name = xstrdup(file_name);
packs->info[packs->nr].orig_pack_int_id = packs->nr;
packs->info[packs->nr].expired = 0;
packs->nr++;
}
}
struct pack_midx_entry {
struct object_id oid;
uint32_t pack_int_id;
time_t pack_mtime;
uint64_t offset;
};
static int midx_oid_compare(const void *_a, const void *_b)
{
const struct pack_midx_entry *a = (const struct pack_midx_entry *)_a;
const struct pack_midx_entry *b = (const struct pack_midx_entry *)_b;
int cmp = oidcmp(&a->oid, &b->oid);
if (cmp)
return cmp;
if (a->pack_mtime > b->pack_mtime)
return -1;
else if (a->pack_mtime < b->pack_mtime)
return 1;
return a->pack_int_id - b->pack_int_id;
}
static int nth_midxed_pack_midx_entry(struct multi_pack_index *m,
struct pack_midx_entry *e,
uint32_t pos)
{
if (pos >= m->num_objects)
return 1;
nth_midxed_object_oid(&e->oid, m, pos);
e->pack_int_id = nth_midxed_pack_int_id(m, pos);
e->offset = nth_midxed_offset(m, pos);
/* consider objects in midx to be from "old" packs */
e->pack_mtime = 0;
return 0;
}
static void fill_pack_entry(uint32_t pack_int_id,
struct packed_git *p,
uint32_t cur_object,
struct pack_midx_entry *entry)
{
if (nth_packed_object_id(&entry->oid, p, cur_object) < 0)
die(_("failed to locate object %d in packfile"), cur_object);
entry->pack_int_id = pack_int_id;
entry->pack_mtime = p->mtime;
entry->offset = nth_packed_object_offset(p, cur_object);
}
/*
* It is possible to artificially get into a state where there are many
* duplicate copies of objects. That can create high memory pressure if
* we are to create a list of all objects before de-duplication. To reduce
* this memory pressure without a significant performance drop, automatically
* group objects by the first byte of their object id. Use the IDX fanout
* tables to group the data, copy to a local array, then sort.
*
* Copy only the de-duplicated entries (selected by most-recent modified time
* of a packfile containing the object).
*/
static struct pack_midx_entry *get_sorted_entries(struct multi_pack_index *m,
struct pack_info *info,
uint32_t nr_packs,
uint32_t *nr_objects)
{
uint32_t cur_fanout, cur_pack, cur_object;
uint32_t alloc_fanout, alloc_objects, total_objects = 0;
struct pack_midx_entry *entries_by_fanout = NULL;
struct pack_midx_entry *deduplicated_entries = NULL;
uint32_t start_pack = m ? m->num_packs : 0;
for (cur_pack = start_pack; cur_pack < nr_packs; cur_pack++)
total_objects += info[cur_pack].p->num_objects;
/*
* As we de-duplicate by fanout value, we expect the fanout
* slices to be evenly distributed, with some noise. Hence,
* allocate slightly more than one 256th.
*/
alloc_objects = alloc_fanout = total_objects > 3200 ? total_objects / 200 : 16;
ALLOC_ARRAY(entries_by_fanout, alloc_fanout);
ALLOC_ARRAY(deduplicated_entries, alloc_objects);
*nr_objects = 0;
for (cur_fanout = 0; cur_fanout < 256; cur_fanout++) {
uint32_t nr_fanout = 0;
if (m) {
uint32_t start = 0, end;
if (cur_fanout)
start = ntohl(m->chunk_oid_fanout[cur_fanout - 1]);
end = ntohl(m->chunk_oid_fanout[cur_fanout]);
for (cur_object = start; cur_object < end; cur_object++) {
ALLOC_GROW(entries_by_fanout, nr_fanout + 1, alloc_fanout);
nth_midxed_pack_midx_entry(m,
&entries_by_fanout[nr_fanout],
cur_object);
nr_fanout++;
}
}
for (cur_pack = start_pack; cur_pack < nr_packs; cur_pack++) {
uint32_t start = 0, end;
if (cur_fanout)
start = get_pack_fanout(info[cur_pack].p, cur_fanout - 1);
end = get_pack_fanout(info[cur_pack].p, cur_fanout);
for (cur_object = start; cur_object < end; cur_object++) {
ALLOC_GROW(entries_by_fanout, nr_fanout + 1, alloc_fanout);
fill_pack_entry(cur_pack, info[cur_pack].p, cur_object, &entries_by_fanout[nr_fanout]);
nr_fanout++;
}
}
QSORT(entries_by_fanout, nr_fanout, midx_oid_compare);
/*
* The batch is now sorted by OID and then mtime (descending).
* Take only the first duplicate.
*/
for (cur_object = 0; cur_object < nr_fanout; cur_object++) {
if (cur_object && oideq(&entries_by_fanout[cur_object - 1].oid,
&entries_by_fanout[cur_object].oid))
continue;
ALLOC_GROW(deduplicated_entries, *nr_objects + 1, alloc_objects);
memcpy(&deduplicated_entries[*nr_objects],
&entries_by_fanout[cur_object],
sizeof(struct pack_midx_entry));
(*nr_objects)++;
}
}
free(entries_by_fanout);
return deduplicated_entries;
}
static size_t write_midx_pack_names(struct hashfile *f,
struct pack_info *info,
uint32_t num_packs)
{
uint32_t i;
unsigned char padding[MIDX_CHUNK_ALIGNMENT];
size_t written = 0;
for (i = 0; i < num_packs; i++) {
size_t writelen;
if (info[i].expired)
continue;
if (i && strcmp(info[i].pack_name, info[i - 1].pack_name) <= 0)
BUG("incorrect pack-file order: %s before %s",
info[i - 1].pack_name,
info[i].pack_name);
writelen = strlen(info[i].pack_name) + 1;
hashwrite(f, info[i].pack_name, writelen);
written += writelen;
}
/* add padding to be aligned */
i = MIDX_CHUNK_ALIGNMENT - (written % MIDX_CHUNK_ALIGNMENT);
if (i < MIDX_CHUNK_ALIGNMENT) {
memset(padding, 0, sizeof(padding));
hashwrite(f, padding, i);
written += i;
}
return written;
}
static size_t write_midx_oid_fanout(struct hashfile *f,
struct pack_midx_entry *objects,
uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
struct pack_midx_entry *last = objects + nr_objects;
uint32_t count = 0;
uint32_t i;
/*
* Write the first-level table (the list is sorted,
* but we use a 256-entry lookup to be able to avoid
* having to do eight extra binary search iterations).
*/
for (i = 0; i < 256; i++) {
struct pack_midx_entry *next = list;
while (next < last && next->oid.hash[0] == i) {
count++;
next++;
}
hashwrite_be32(f, count);
list = next;
}
return MIDX_CHUNK_FANOUT_SIZE;
}
static size_t write_midx_oid_lookup(struct hashfile *f, unsigned char hash_len,
struct pack_midx_entry *objects,
uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
uint32_t i;
size_t written = 0;
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
if (i < nr_objects - 1) {
struct pack_midx_entry *next = list;
if (oidcmp(&obj->oid, &next->oid) >= 0)
BUG("OIDs not in order: %s >= %s",
oid_to_hex(&obj->oid),
oid_to_hex(&next->oid));
}
hashwrite(f, obj->oid.hash, (int)hash_len);
written += hash_len;
}
return written;
}
static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_needed,
uint32_t *perm,
struct pack_midx_entry *objects, uint32_t nr_objects)
{
struct pack_midx_entry *list = objects;
uint32_t i, nr_large_offset = 0;
size_t written = 0;
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
if (perm[obj->pack_int_id] == PACK_EXPIRED)
BUG("object %s is in an expired pack with int-id %d",
oid_to_hex(&obj->oid),
obj->pack_int_id);
hashwrite_be32(f, perm[obj->pack_int_id]);
if (large_offset_needed && obj->offset >> 31)
hashwrite_be32(f, MIDX_LARGE_OFFSET_NEEDED | nr_large_offset++);
else if (!large_offset_needed && obj->offset >> 32)
BUG("object %s requires a large offset (%"PRIx64") but the MIDX is not writing large offsets!",
oid_to_hex(&obj->oid),
obj->offset);
else
hashwrite_be32(f, (uint32_t)obj->offset);
written += MIDX_CHUNK_OFFSET_WIDTH;
}
return written;
}
static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_offset,
struct pack_midx_entry *objects, uint32_t nr_objects)
{
struct pack_midx_entry *list = objects, *end = objects + nr_objects;
size_t written = 0;
while (nr_large_offset) {
struct pack_midx_entry *obj;
uint64_t offset;
if (list >= end)
BUG("too many large-offset objects");
obj = list++;
offset = obj->offset;
if (!(offset >> 31))
continue;
hashwrite_be32(f, offset >> 32);
hashwrite_be32(f, offset & 0xffffffffUL);
written += 2 * sizeof(uint32_t);
nr_large_offset--;
}
return written;
}
static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
struct string_list *packs_to_drop, unsigned flags)
{
unsigned char cur_chunk, num_chunks = 0;
char *midx_name;
uint32_t i;
struct hashfile *f = NULL;
struct lock_file lk;
struct pack_list packs;
uint32_t *pack_perm = NULL;
uint64_t written = 0;
uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
uint32_t nr_entries, num_large_offsets = 0;
struct pack_midx_entry *entries = NULL;
struct progress *progress = NULL;
int large_offsets_needed = 0;
int pack_name_concat_len = 0;
int dropped_packs = 0;
int result = 0;
midx_name = get_midx_filename(object_dir);
if (safe_create_leading_directories(midx_name)) {
UNLEAK(midx_name);
die_errno(_("unable to create leading directories of %s"),
midx_name);
}
if (m)
packs.m = m;
else
packs.m = load_multi_pack_index(object_dir, 1);
packs.nr = 0;
packs.alloc = packs.m ? packs.m->num_packs : 16;
packs.info = NULL;
ALLOC_ARRAY(packs.info, packs.alloc);
if (packs.m) {
for (i = 0; i < packs.m->num_packs; i++) {
ALLOC_GROW(packs.info, packs.nr + 1, packs.alloc);
packs.info[packs.nr].orig_pack_int_id = i;
packs.info[packs.nr].pack_name = xstrdup(packs.m->pack_names[i]);
packs.info[packs.nr].p = NULL;
packs.info[packs.nr].expired = 0;
packs.nr++;
}
}
packs.pack_paths_checked = 0;
if (flags & MIDX_PROGRESS)
packs.progress = start_progress(_("Adding packfiles to multi-pack-index"), 0);
else
packs.progress = NULL;
for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
stop_progress(&packs.progress);
if (packs.m && packs.nr == packs.m->num_packs && !packs_to_drop)
goto cleanup;
entries = get_sorted_entries(packs.m, packs.info, packs.nr, &nr_entries);
for (i = 0; i < nr_entries; i++) {
if (entries[i].offset > 0x7fffffff)
num_large_offsets++;
if (entries[i].offset > 0xffffffff)
large_offsets_needed = 1;
}
QSORT(packs.info, packs.nr, pack_info_compare);
if (packs_to_drop && packs_to_drop->nr) {
int drop_index = 0;
int missing_drops = 0;
for (i = 0; i < packs.nr && drop_index < packs_to_drop->nr; i++) {
int cmp = strcmp(packs.info[i].pack_name,
packs_to_drop->items[drop_index].string);
if (!cmp) {
drop_index++;
packs.info[i].expired = 1;
} else if (cmp > 0) {
error(_("did not see pack-file %s to drop"),
packs_to_drop->items[drop_index].string);
drop_index++;
missing_drops++;
i--;
} else {
packs.info[i].expired = 0;
}
}
if (missing_drops) {
result = 1;
goto cleanup;
}
}
/*
* pack_perm stores a permutation between pack-int-ids from the
* previous multi-pack-index to the new one we are writing:
*
* pack_perm[old_id] = new_id
*/
ALLOC_ARRAY(pack_perm, packs.nr);
for (i = 0; i < packs.nr; i++) {
if (packs.info[i].expired) {
dropped_packs++;
pack_perm[packs.info[i].orig_pack_int_id] = PACK_EXPIRED;
} else {
pack_perm[packs.info[i].orig_pack_int_id] = i - dropped_packs;
}
}
for (i = 0; i < packs.nr; i++) {
if (!packs.info[i].expired)
pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
}
if (pack_name_concat_len % MIDX_CHUNK_ALIGNMENT)
pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
(pack_name_concat_len % MIDX_CHUNK_ALIGNMENT);
hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR);
f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
FREE_AND_NULL(midx_name);
if (packs.m)
close_midx(packs.m);
cur_chunk = 0;
num_chunks = large_offsets_needed ? 5 : 4;
written = write_midx_header(f, num_chunks, packs.nr - dropped_packs);
chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDFANOUT;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + pack_name_concat_len;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDLOOKUP;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + MIDX_CHUNK_FANOUT_SIZE;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OBJECTOFFSETS;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * the_hash_algo->rawsz;
cur_chunk++;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_CHUNK_OFFSET_WIDTH;
if (large_offsets_needed) {
chunk_ids[cur_chunk] = MIDX_CHUNKID_LARGEOFFSETS;
cur_chunk++;
chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] +
num_large_offsets * MIDX_CHUNK_LARGE_OFFSET_WIDTH;
}
chunk_ids[cur_chunk] = 0;
for (i = 0; i <= num_chunks; i++) {
if (i && chunk_offsets[i] < chunk_offsets[i - 1])
BUG("incorrect chunk offsets: %"PRIu64" before %"PRIu64,
chunk_offsets[i - 1],
chunk_offsets[i]);
if (chunk_offsets[i] % MIDX_CHUNK_ALIGNMENT)
BUG("chunk offset %"PRIu64" is not properly aligned",
chunk_offsets[i]);
hashwrite_be32(f, chunk_ids[i]);
hashwrite_be32(f, chunk_offsets[i] >> 32);
hashwrite_be32(f, chunk_offsets[i]);
written += MIDX_CHUNKLOOKUP_WIDTH;
}
if (flags & MIDX_PROGRESS)
progress = start_progress(_("Writing chunks to multi-pack-index"),
num_chunks);
for (i = 0; i < num_chunks; i++) {
if (written != chunk_offsets[i])
BUG("incorrect chunk offset (%"PRIu64" != %"PRIu64") for chunk id %"PRIx32,
chunk_offsets[i],
written,
chunk_ids[i]);
switch (chunk_ids[i]) {
case MIDX_CHUNKID_PACKNAMES:
written += write_midx_pack_names(f, packs.info, packs.nr);
break;
case MIDX_CHUNKID_OIDFANOUT:
written += write_midx_oid_fanout(f, entries, nr_entries);
break;
case MIDX_CHUNKID_OIDLOOKUP:
written += write_midx_oid_lookup(f, the_hash_algo->rawsz, entries, nr_entries);
break;
case MIDX_CHUNKID_OBJECTOFFSETS:
written += write_midx_object_offsets(f, large_offsets_needed, pack_perm, entries, nr_entries);
break;
case MIDX_CHUNKID_LARGEOFFSETS:
written += write_midx_large_offsets(f, num_large_offsets, entries, nr_entries);