odb: make backend-specific fields optional
The `struct object_info` carries two pieces of information about how an object was looked up: - The `whence` enum identifying the backend. - The backend-tagged union `u` exposing backend-specific details (currently only the packed-source case, which records the owning pack, offset and packed object type). The union is populated unconditionally, even though most callers don't care about provenance at all. Split the backend-specific union out into a new public type, `struct object_info_source`, and make the object info structure carry it via just another opt-in request pointer. As with all the other requestable information, callers that need source info allocate a `struct object_info_source` on the stack and point `sourcep` at it; callers that don't care about it simply leave the field as a `NULL` pointer. Adapt callers accordingly. Note that the `whence` enum is strictly-speaking also backend-specific information, so it would be another good candidate to be moved into the `struct object_info_source`. For now though it is left alone, as it will be replaced by a `struct odb_source` pointer in a subsequent commit. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Patrick Steinhardt committed
Jul 2, 2026 at 14:02 UTC
126076b62f5164f9da6bbe454fc71c164ea5cb42
7 files changed
+87
-45
builtin/cat-file.c
+6
-2
@@ -835,7 +835,8 @@ static int batch_one_object_oi(const struct object_id *oid,
835
{
836
struct for_each_object_payload *payload = _payload;
837
if (oi && oi->whence == OI_PACKED)
838
- return payload->callback(oid, oi->u.packed.pack, oi->u.packed.offset,
838
+ return payload->callback(oid, oi->sourcep->u.packed.pack,
839
+ oi->sourcep->u.packed.offset,
840
payload->payload);
841
return payload->callback(oid, NULL, 0, payload->payload);
842
}
@@ -906,7 +907,10 @@ static void batch_each_object(struct batch_options *opt,
907
&payload, flags);
908
}
909
} else {
909
- struct object_info oi = { 0 };
910
+ struct object_info_source oi_source;
911
+ struct object_info oi = {
912
+ .sourcep = &oi_source,
913
+ };
914
915
for (source = the_repository->objects->sources; source; source = source->next) {
916
struct odb_source_files *files = odb_source_files_downcast(source);
builtin/index-pack.c
+6
-2
@@ -1825,11 +1825,15 @@ static void repack_local_links(void)
1825
1826
oidset_iter_init(&outgoing_links, &iter);
1827
while ((oid = oidset_iter_next(&iter))) {
1828
- struct object_info info = OBJECT_INFO_INIT;
1828
+ struct object_info_source info_source;
1829
+ struct object_info info = {
1830
+ .sourcep = &info_source,
1831
+ };
1832
+
1833
if (odb_read_object_info_extended(the_repository->objects, oid, &info, 0))
1834
/* Missing; assume it is a promisor object */
1835
continue;
1832
- if (info.whence == OI_PACKED && info.u.packed.pack->pack_promisor)
1836
+ if (info.whence == OI_PACKED && info_source.u.packed.pack->pack_promisor)
1837
continue;
1838
1839
if (!cmd.args.nr) {
builtin/pack-objects.c
+11
-4
@@ -4491,8 +4491,9 @@ static int add_object_in_unpacked_pack(const struct object_id *oid,
4491
void *data UNUSED)
4492
{
4493
if (cruft) {
4494
- add_cruft_object_entry(oid, OBJ_NONE, oi->u.packed.pack,
4495
- oi->u.packed.offset, NULL, *oi->mtimep);
4494
+ add_cruft_object_entry(oid, OBJ_NONE, oi->sourcep->u.packed.pack,
4495
+ oi->sourcep->u.packed.offset, NULL,
4496
+ *oi->mtimep);
4497
} else {
4498
add_object_entry(oid, OBJ_NONE, "", 0);
4499
}
@@ -4509,8 +4510,10 @@ static void add_objects_in_unpacked_packs(void)
4510
ODB_FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS |
4511
ODB_FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS,
4512
};
4513
+ struct object_info_source oi_source;
4514
struct object_info oi = {
4515
.mtimep = &mtime,
4516
+ .sourcep = &oi_source,
4517
};
4518
4519
odb_prepare_alternates(to_pack.repo->objects);
@@ -5000,10 +5003,14 @@ static int option_parse_cruft_expiration(const struct option *opt UNUSED,
5003
5004
static int is_not_in_promisor_pack_obj(struct object *obj, void *data UNUSED)
5005
{
5003
- struct object_info info = OBJECT_INFO_INIT;
5006
+ struct object_info_source info_source;
5007
+ struct object_info info = {
5008
+ .sourcep = &info_source,
5009
+ };
5010
+
5011
if (odb_read_object_info_extended(the_repository->objects, &obj->oid, &info, 0))
5012
BUG("should_include_obj should only be called on existing objects");
5006
- return info.whence != OI_PACKED || !info.u.packed.pack->pack_promisor;
5013
+ return info.whence != OI_PACKED || !info_source.u.packed.pack->pack_promisor;
5014
}
5015
5016
static int is_not_in_promisor_pack(struct commit *commit, void *data) {
odb.c
+2
-1
@@ -692,7 +692,8 @@ static int oid_object_info_convert(struct repository *r,
692
}
693
}
694
input_oi->whence = new_oi.whence;
695
- input_oi->u = new_oi.u;
695
+ if (input_oi->sourcep)
696
+ *input_oi->sourcep = *new_oi.sourcep;
697
return ret;
698
}
699
odb.h
+40
-20
@@ -248,6 +248,38 @@ int odb_pretend_object(struct object_database *odb,
248
void *buf, size_t len, enum object_type type,
249
struct object_id *oid);
250
251
+/*
252
+ * Object information that can be used to uniquely identify an object and learn
253
+ * more about how exactly it is stored.
254
+ */
255
+struct object_info_source {
256
+ /*
257
+ * Backend-specific information about the specific object. This can be
258
+ * used for example to uniquely identify a given object in case it
259
+ * exists multiple times.
260
+ */
261
+ union {
262
+ /*
263
+ * struct {
264
+ * ... Nothing to expose in this case
265
+ * } cached;
266
+ * struct {
267
+ * ... Nothing to expose in this case
268
+ * } loose;
269
+ */
270
+ struct {
271
+ struct packed_git *pack;
272
+ off_t offset;
273
+ enum packed_object_type {
274
+ PACKED_OBJECT_TYPE_UNKNOWN,
275
+ PACKED_OBJECT_TYPE_FULL,
276
+ PACKED_OBJECT_TYPE_OFS_DELTA,
277
+ PACKED_OBJECT_TYPE_REF_DELTA,
278
+ } type;
279
+ } packed;
280
+ } u;
281
+};
282
+
283
struct object_info {
284
/* Request */
285
enum object_type *typep;
@@ -269,32 +301,20 @@ struct object_info {
301
*/
302
time_t *mtimep;
303
304
+ /*
305
+ * Backend-specific information that tells the caller where exactly an
306
+ * object was looked up from. This information should help disambiguate
307
+ * object lookups in case the same object exists in multiple sources,
308
+ * or multiple times in the same source.
309
+ */
310
+ struct object_info_source *sourcep;
311
+
312
/* Response */
313
enum {
314
OI_CACHED,
315
OI_LOOSE,
316
OI_PACKED,
317
} whence;
278
- union {
279
- /*
280
- * struct {
281
- * ... Nothing to expose in this case
282
- * } cached;
283
- * struct {
284
- * ... Nothing to expose in this case
285
- * } loose;
286
- */
287
- struct {
288
- struct packed_git *pack;
289
- off_t offset;
290
- enum packed_object_type {
291
- PACKED_OBJECT_TYPE_UNKNOWN,
292
- PACKED_OBJECT_TYPE_FULL,
293
- PACKED_OBJECT_TYPE_OFS_DELTA,
294
- PACKED_OBJECT_TYPE_REF_DELTA,
295
- } type;
296
- } packed;
297
- } u;
318
};
319
320
/*
packfile.c
+18
-15
@@ -1422,22 +1422,25 @@ int packed_object_info_with_index_pos(struct odb_source_packed *source UNUSED,
1422
}
1423
1424
oi->whence = OI_PACKED;
1425
- oi->u.packed.offset = obj_offset;
1426
- oi->u.packed.pack = p;
1425
1428
- switch (type) {
1429
- case OBJ_NONE:
1430
- oi->u.packed.type = PACKED_OBJECT_TYPE_UNKNOWN;
1431
- break;
1432
- case OBJ_REF_DELTA:
1433
- oi->u.packed.type = PACKED_OBJECT_TYPE_REF_DELTA;
1434
- break;
1435
- case OBJ_OFS_DELTA:
1436
- oi->u.packed.type = PACKED_OBJECT_TYPE_OFS_DELTA;
1437
- break;
1438
- default:
1439
- oi->u.packed.type = PACKED_OBJECT_TYPE_FULL;
1440
- break;
1426
+ if (oi->sourcep) {
1427
+ oi->sourcep->u.packed.offset = obj_offset;
1428
+ oi->sourcep->u.packed.pack = p;
1429
+
1430
+ switch (type) {
1431
+ case OBJ_NONE:
1432
+ oi->sourcep->u.packed.type = PACKED_OBJECT_TYPE_UNKNOWN;
1433
+ break;
1434
+ case OBJ_REF_DELTA:
1435
+ oi->sourcep->u.packed.type = PACKED_OBJECT_TYPE_REF_DELTA;
1436
+ break;
1437
+ case OBJ_OFS_DELTA:
1438
+ oi->sourcep->u.packed.type = PACKED_OBJECT_TYPE_OFS_DELTA;
1439
+ break;
1440
+ default:
1441
+ oi->sourcep->u.packed.type = PACKED_OBJECT_TYPE_FULL;
1442
+ break;
1443
+ }
1444
}
1445
1446
ret = 0;
reachable.c
+4
-1
@@ -235,7 +235,8 @@ static int add_recent_object(const struct object_id *oid,
235
add_pending_object(data->revs, obj, "");
236
if (data->cb) {
237
if (oi->whence == OI_PACKED)
238
- data->cb(obj, oi->u.packed.pack, oi->u.packed.offset, *oi->mtimep);
238
+ data->cb(obj, oi->sourcep->u.packed.pack,
239
+ oi->sourcep->u.packed.offset, *oi->mtimep);
240
else
241
data->cb(obj, NULL, 0, *oi->mtimep);
242
}
@@ -252,9 +253,11 @@ int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
253
unsigned flags;
254
enum object_type type;
255
time_t mtime;
256
+ struct object_info_source oi_source;
257
struct object_info oi = {
258
.mtimep = &mtime,
259
.typep = &type,
260
+ .sourcep = &oi_source,
261
};
262
int r;
263