midx: support reading incremental MIDX chains
Now that the MIDX machinery's internals have been taught to understand incremental MIDXs over the previous handful of commits, the MIDX machinery itself can begin reading incremental MIDXs. (Note that while the on-disk format for incremental MIDXs has been defined, the writing end has not been implemented. This will take place in the commit after next.) The core of this change involves following the order specified in the MIDX chain in reverse and opening up MIDXs in the chain one-by-one, adding them to the previous layer's `->base_midx` pointer at each step. In order to implement this, the `load_multi_pack_index()` function is taught to call a new `load_multi_pack_index_chain()` function if loading a non-incremental MIDX failed via `load_multi_pack_index_one()`. When loading a MIDX chain, `load_midx_chain_fd_st()` reads each line in the file one-by-one and dispatches calls to `load_multi_pack_index_one()` to read each layer of the MIDX chain. When a layer was successfully read, it is added to the MIDX chain by calling `add_midx_to_chain()` which validates the contents of the `BASE` chunk, performs some bounds checks on the number of combined packs and objects, and attaches the new MIDX by assigning its `base_midx` pointer to the existing part of the chain. As a supplement to this, introduce a new mode in the test-read-midx test-tool which allows us to read the information for a specific MIDX in the chain by specifying its trailing checksum via the command-line arguments like so: $ test-tool read-midx .git/objects [checksum] Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Taylor Blau committed
Aug 6, 2024 at 11:37 UTC
b80236d0e3386e5fdfaff0a7480212a3f39cbee3
4 files changed
+201
-19
midx.c
+174
-10
@@ -91,7 +91,9 @@ static int midx_read_object_offsets(const unsigned char *chunk_start,
91
92
#define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz)
93
94
-struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local)
94
+static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir,
95
+ const char *midx_name,
96
+ int local)
97
{
98
struct multi_pack_index *m = NULL;
99
int fd;
@@ -99,31 +101,26 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
101
size_t midx_size;
102
void *midx_map = NULL;
103
uint32_t hash_version;
102
- struct strbuf midx_name = STRBUF_INIT;
104
uint32_t i;
105
const char *cur_pack_name;
106
struct chunkfile *cf = NULL;
107
107
- get_midx_filename(&midx_name, object_dir);
108
-
109
- fd = git_open(midx_name.buf);
108
+ fd = git_open(midx_name);
109
110
if (fd < 0)
111
goto cleanup_fail;
112
if (fstat(fd, &st)) {
114
- error_errno(_("failed to read %s"), midx_name.buf);
113
+ error_errno(_("failed to read %s"), midx_name);
114
goto cleanup_fail;
115
}
116
117
midx_size = xsize_t(st.st_size);
118
119
if (midx_size < MIDX_MIN_SIZE) {
121
- error(_("multi-pack-index file %s is too small"), midx_name.buf);
120
+ error(_("multi-pack-index file %s is too small"), midx_name);
121
goto cleanup_fail;
122
}
123
125
- strbuf_release(&midx_name);
126
-
124
midx_map = xmmap(NULL, midx_size, PROT_READ, MAP_PRIVATE, fd, 0);
125
close(fd);
126
@@ -213,7 +210,6 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
210
211
cleanup_fail:
212
free(m);
216
- strbuf_release(&midx_name);
213
free_chunkfile(cf);
214
if (midx_map)
215
munmap(midx_map, midx_size);
@@ -222,6 +218,173 @@ cleanup_fail:
218
return NULL;
219
}
220
221
+void get_midx_chain_dirname(struct strbuf *buf, const char *object_dir)
222
+{
223
+ strbuf_addf(buf, "%s/pack/multi-pack-index.d", object_dir);
224
+}
225
+
226
+void get_midx_chain_filename(struct strbuf *buf, const char *object_dir)
227
+{
228
+ get_midx_chain_dirname(buf, object_dir);
229
+ strbuf_addstr(buf, "/multi-pack-index-chain");
230
+}
231
+
232
+void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir,
233
+ const unsigned char *hash, const char *ext)
234
+{
235
+ get_midx_chain_dirname(buf, object_dir);
236
+ strbuf_addf(buf, "/multi-pack-index-%s.%s", hash_to_hex(hash), ext);
237
+}
238
+
239
+static int open_multi_pack_index_chain(const char *chain_file,
240
+ int *fd, struct stat *st)
241
+{
242
+ *fd = git_open(chain_file);
243
+ if (*fd < 0)
244
+ return 0;
245
+ if (fstat(*fd, st)) {
246
+ close(*fd);
247
+ return 0;
248
+ }
249
+ if (st->st_size < the_hash_algo->hexsz) {
250
+ close(*fd);
251
+ if (!st->st_size) {
252
+ /* treat empty files the same as missing */
253
+ errno = ENOENT;
254
+ } else {
255
+ warning(_("multi-pack-index chain file too small"));
256
+ errno = EINVAL;
257
+ }
258
+ return 0;
259
+ }
260
+ return 1;
261
+}
262
+
263
+static int add_midx_to_chain(struct multi_pack_index *midx,
264
+ struct multi_pack_index *midx_chain,
265
+ struct object_id *oids,
266
+ int n)
267
+{
268
+ if (midx_chain) {
269
+ if (unsigned_add_overflows(midx_chain->num_packs,
270
+ midx_chain->num_packs_in_base)) {
271
+ warning(_("pack count in base MIDX too high: %"PRIuMAX),
272
+ (uintmax_t)midx_chain->num_packs_in_base);
273
+ return 0;
274
+ }
275
+ if (unsigned_add_overflows(midx_chain->num_objects,
276
+ midx_chain->num_objects_in_base)) {
277
+ warning(_("object count in base MIDX too high: %"PRIuMAX),
278
+ (uintmax_t)midx_chain->num_objects_in_base);
279
+ return 0;
280
+ }
281
+ midx->num_packs_in_base = midx_chain->num_packs +
282
+ midx_chain->num_packs_in_base;
283
+ midx->num_objects_in_base = midx_chain->num_objects +
284
+ midx_chain->num_objects_in_base;
285
+ }
286
+
287
+ midx->base_midx = midx_chain;
288
+ midx->has_chain = 1;
289
+
290
+ return 1;
291
+}
292
+
293
+static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir,
294
+ int local,
295
+ int fd, struct stat *st,
296
+ int *incomplete_chain)
297
+{
298
+ struct multi_pack_index *midx_chain = NULL;
299
+ struct strbuf buf = STRBUF_INIT;
300
+ struct object_id *layers = NULL;
301
+ int valid = 1;
302
+ uint32_t i, count;
303
+ FILE *fp = xfdopen(fd, "r");
304
+
305
+ count = st->st_size / (the_hash_algo->hexsz + 1);
306
+ CALLOC_ARRAY(layers, count);
307
+
308
+ for (i = 0; i < count; i++) {
309
+ struct multi_pack_index *m;
310
+
311
+ if (strbuf_getline_lf(&buf, fp) == EOF)
312
+ break;
313
+
314
+ if (get_oid_hex(buf.buf, &layers[i])) {
315
+ warning(_("invalid multi-pack-index chain: line '%s' "
316
+ "not a hash"),
317
+ buf.buf);
318
+ valid = 0;
319
+ break;
320
+ }
321
+
322
+ valid = 0;
323
+
324
+ strbuf_reset(&buf);
325
+ get_split_midx_filename_ext(&buf, object_dir, layers[i].hash,
326
+ MIDX_EXT_MIDX);
327
+ m = load_multi_pack_index_one(object_dir, buf.buf, local);
328
+
329
+ if (m) {
330
+ if (add_midx_to_chain(m, midx_chain, layers, i)) {
331
+ midx_chain = m;
332
+ valid = 1;
333
+ } else {
334
+ close_midx(m);
335
+ }
336
+ }
337
+ if (!valid) {
338
+ warning(_("unable to find all multi-pack index files"));
339
+ break;
340
+ }
341
+ }
342
+
343
+ free(layers);
344
+ fclose(fp);
345
+ strbuf_release(&buf);
346
+
347
+ *incomplete_chain = !valid;
348
+ return midx_chain;
349
+}
350
+
351
+static struct multi_pack_index *load_multi_pack_index_chain(const char *object_dir,
352
+ int local)
353
+{
354
+ struct strbuf chain_file = STRBUF_INIT;
355
+ struct stat st;
356
+ int fd;
357
+ struct multi_pack_index *m = NULL;
358
+
359
+ get_midx_chain_filename(&chain_file, object_dir);
360
+ if (open_multi_pack_index_chain(chain_file.buf, &fd, &st)) {
361
+ int incomplete;
362
+ /* ownership of fd is taken over by load function */
363
+ m = load_midx_chain_fd_st(object_dir, local, fd, &st,
364
+ &incomplete);
365
+ }
366
+
367
+ strbuf_release(&chain_file);
368
+ return m;
369
+}
370
+
371
+struct multi_pack_index *load_multi_pack_index(const char *object_dir,
372
+ int local)
373
+{
374
+ struct strbuf midx_name = STRBUF_INIT;
375
+ struct multi_pack_index *m;
376
+
377
+ get_midx_filename(&midx_name, object_dir);
378
+
379
+ m = load_multi_pack_index_one(object_dir, midx_name.buf, local);
380
+ if (!m)
381
+ m = load_multi_pack_index_chain(object_dir, local);
382
+
383
+ strbuf_release(&midx_name);
384
+
385
+ return m;
386
+}
387
+
388
void close_midx(struct multi_pack_index *m)
389
{
390
uint32_t i;
@@ -230,6 +393,7 @@ void close_midx(struct multi_pack_index *m)
393
return;
394
395
close_midx(m->next);
396
+ close_midx(m->base_midx);
397
398
munmap((unsigned char *)m->data, m->data_len);
399
midx.h
+7
@@ -24,6 +24,7 @@ struct bitmapped_pack;
24
#define MIDX_CHUNKID_OBJECTOFFSETS 0x4f4f4646 /* "OOFF" */
25
#define MIDX_CHUNKID_LARGEOFFSETS 0x4c4f4646 /* "LOFF" */
26
#define MIDX_CHUNKID_REVINDEX 0x52494458 /* "RIDX" */
27
+#define MIDX_CHUNKID_BASE 0x42415345 /* "BASE" */
28
#define MIDX_CHUNK_OFFSET_WIDTH (2 * sizeof(uint32_t))
29
#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
30
@@ -50,6 +51,7 @@ struct multi_pack_index {
51
int preferred_pack_idx;
52
53
int local;
54
+ int has_chain;
55
56
const unsigned char *chunk_pack_names;
57
size_t chunk_pack_names_len;
@@ -80,11 +82,16 @@ struct multi_pack_index {
82
83
#define MIDX_EXT_REV "rev"
84
#define MIDX_EXT_BITMAP "bitmap"
85
+#define MIDX_EXT_MIDX "midx"
86
87
const unsigned char *get_midx_checksum(struct multi_pack_index *m);
88
void get_midx_filename(struct strbuf *out, const char *object_dir);
89
void get_midx_filename_ext(struct strbuf *out, const char *object_dir,
90
const unsigned char *hash, const char *ext);
91
+void get_midx_chain_dirname(struct strbuf *buf, const char *object_dir);
92
+void get_midx_chain_filename(struct strbuf *buf, const char *object_dir);
93
+void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir,
94
+ const unsigned char *hash, const char *ext);
95
96
struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local);
97
int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id);
packfile.c
+3
-2
@@ -880,7 +880,8 @@ static void prepare_pack(const char *full_name, size_t full_name_len,
880
if (!report_garbage)
881
return;
882
883
- if (!strcmp(file_name, "multi-pack-index"))
883
+ if (!strcmp(file_name, "multi-pack-index") ||
884
+ !strcmp(file_name, "multi-pack-index.d"))
885
return;
886
if (starts_with(file_name, "multi-pack-index") &&
887
(ends_with(file_name, ".bitmap") || ends_with(file_name, ".rev")))
@@ -1064,7 +1065,7 @@ struct packed_git *get_all_packs(struct repository *r)
1065
prepare_packed_git(r);
1066
for (m = r->objects->multi_pack_index; m; m = m->next) {
1067
uint32_t i;
1067
- for (i = 0; i < m->num_packs; i++)
1068
+ for (i = 0; i < m->num_packs + m->num_packs_in_base; i++)
1069
prepare_midx_pack(r, m, i);
1070
}
1071
t/helper/test-read-midx.c
+17
-7
@@ -9,8 +9,10 @@
9
#include "packfile.h"
10
#include "setup.h"
11
#include "gettext.h"
12
+#include "pack-revindex.h"
13
13
-static int read_midx_file(const char *object_dir, int show_objects)
14
+static int read_midx_file(const char *object_dir, const char *checksum,
15
+ int show_objects)
16
{
17
uint32_t i;
18
struct multi_pack_index *m;
@@ -21,6 +23,13 @@ static int read_midx_file(const char *object_dir, int show_objects)
23
if (!m)
24
return 1;
25
26
+ if (checksum) {
27
+ while (m && strcmp(hash_to_hex(get_midx_checksum(m)), checksum))
28
+ m = m->base_midx;
29
+ if (!m)
30
+ return 1;
31
+ }
32
+
33
printf("header: %08x %d %d %d %d\n",
34
m->signature,
35
m->version,
@@ -54,7 +63,8 @@ static int read_midx_file(const char *object_dir, int show_objects)
63
struct pack_entry e;
64
65
for (i = 0; i < m->num_objects; i++) {
57
- nth_midxed_object_oid(&oid, m, i);
66
+ nth_midxed_object_oid(&oid, m,
67
+ i + m->num_objects_in_base);
68
fill_midx_entry(the_repository, &oid, &e, m);
69
70
printf("%s %"PRIu64"\t%s\n",
@@ -111,7 +121,7 @@ static int read_midx_bitmapped_packs(const char *object_dir)
121
if (!midx)
122
return 1;
123
114
- for (i = 0; i < midx->num_packs; i++) {
124
+ for (i = 0; i < midx->num_packs + midx->num_packs_in_base; i++) {
125
if (nth_bitmapped_pack(the_repository, midx, &pack, i) < 0)
126
return 1;
127
@@ -127,16 +137,16 @@ static int read_midx_bitmapped_packs(const char *object_dir)
137
138
int cmd__read_midx(int argc, const char **argv)
139
{
130
- if (!(argc == 2 || argc == 3))
131
- usage("read-midx [--show-objects|--checksum|--preferred-pack|--bitmap] <object-dir>");
140
+ if (!(argc == 2 || argc == 3 || argc == 4))
141
+ usage("read-midx [--show-objects|--checksum|--preferred-pack|--bitmap] <object-dir> <checksum>");
142
143
if (!strcmp(argv[1], "--show-objects"))
134
- return read_midx_file(argv[2], 1);
144
+ return read_midx_file(argv[2], argv[3], 1);
145
else if (!strcmp(argv[1], "--checksum"))
146
return read_midx_checksum(argv[2]);
147
else if (!strcmp(argv[1], "--preferred-pack"))
148
return read_midx_preferred_pack(argv[2]);
149
else if (!strcmp(argv[1], "--bitmap"))
150
return read_midx_bitmapped_packs(argv[2]);
141
- return read_midx_file(argv[1], 0);
151
+ return read_midx_file(argv[1], argv[2], 0);
152
}