midx: introduce `bsearch_one_midx()`
The `bsearch_midx()` function will be extended in a following commit to search for the location of a given object ID across all MIDXs in a chain (or the single non-chain MIDX if no chain is available). While most callers will naturally want to use the updated `bsearch_midx()` function, there are a handful of special cases that will want finer control and will only want to search through a single MIDX. For instance, the object abbreviation code, which cares about object IDs near to where we'd expect to find a match in a MIDX. In that case, we want to look at the nearby matches in each layer of the MIDX chain, not just a single one). Split the more fine-grained control out into a separate function called `bsearch_one_midx()` which searches only a single MIDX. At present both `bsearch_midx()` and `bsearch_one_midx()` have identical behavior, but the following commit will rewrite the former to be aware of incremental MIDXs for the remaining non-special case callers. 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
3f5f1cff92dfe64bbbfa9f2fb4ed810125810b1b
3 files changed
+71
-50
midx.c
+14
-3
@@ -330,10 +330,21 @@ int nth_bitmapped_pack(struct repository *r, struct multi_pack_index *m,
330
return 0;
331
}
332
333
-int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result)
333
+int bsearch_one_midx(const struct object_id *oid, struct multi_pack_index *m,
334
+ uint32_t *result)
335
{
335
- return bsearch_hash(oid->hash, m->chunk_oid_fanout, m->chunk_oid_lookup,
336
- the_hash_algo->rawsz, result);
336
+ int ret = bsearch_hash(oid->hash, m->chunk_oid_fanout,
337
+ m->chunk_oid_lookup, the_hash_algo->rawsz,
338
+ result);
339
+ if (result)
340
+ *result += m->num_objects_in_base;
341
+ return ret;
342
+}
343
+
344
+int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m,
345
+ uint32_t *result)
346
+{
347
+ return bsearch_one_midx(oid, m, result);
348
}
349
350
struct object_id *nth_midxed_object_oid(struct object_id *oid,
midx.h
+4
-1
@@ -90,7 +90,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
90
int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id);
91
int nth_bitmapped_pack(struct repository *r, struct multi_pack_index *m,
92
struct bitmapped_pack *bp, uint32_t pack_int_id);
93
-int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result);
93
+int bsearch_one_midx(const struct object_id *oid, struct multi_pack_index *m,
94
+ uint32_t *result);
95
+int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m,
96
+ uint32_t *result);
97
off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos);
98
uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos);
99
struct object_id *nth_midxed_object_oid(struct object_id *oid,
object-name.c
+53
-46
@@ -134,28 +134,32 @@ static int match_hash(unsigned len, const unsigned char *a, const unsigned char
134
static void unique_in_midx(struct multi_pack_index *m,
135
struct disambiguate_state *ds)
136
{
137
- uint32_t num, i, first = 0;
138
- const struct object_id *current = NULL;
139
- int len = ds->len > ds->repo->hash_algo->hexsz ?
140
- ds->repo->hash_algo->hexsz : ds->len;
141
- num = m->num_objects;
137
+ for (; m; m = m->base_midx) {
138
+ uint32_t num, i, first = 0;
139
+ const struct object_id *current = NULL;
140
+ int len = ds->len > ds->repo->hash_algo->hexsz ?
141
+ ds->repo->hash_algo->hexsz : ds->len;
142
143
- if (!num)
144
- return;
143
+ if (!m->num_objects)
144
+ continue;
145
146
- bsearch_midx(&ds->bin_pfx, m, &first);
146
+ num = m->num_objects + m->num_objects_in_base;
147
148
- /*
149
- * At this point, "first" is the location of the lowest object
150
- * with an object name that could match "bin_pfx". See if we have
151
- * 0, 1 or more objects that actually match(es).
152
- */
153
- for (i = first; i < num && !ds->ambiguous; i++) {
154
- struct object_id oid;
155
- current = nth_midxed_object_oid(&oid, m, i);
156
- if (!match_hash(len, ds->bin_pfx.hash, current->hash))
157
- break;
158
- update_candidates(ds, current);
148
+ bsearch_one_midx(&ds->bin_pfx, m, &first);
149
+
150
+ /*
151
+ * At this point, "first" is the location of the lowest
152
+ * object with an object name that could match
153
+ * "bin_pfx". See if we have 0, 1 or more objects that
154
+ * actually match(es).
155
+ */
156
+ for (i = first; i < num && !ds->ambiguous; i++) {
157
+ struct object_id oid;
158
+ current = nth_midxed_object_oid(&oid, m, i);
159
+ if (!match_hash(len, ds->bin_pfx.hash, current->hash))
160
+ break;
161
+ update_candidates(ds, current);
162
+ }
163
}
164
}
165
@@ -708,37 +712,40 @@ static int repo_extend_abbrev_len(struct repository *r UNUSED,
712
static void find_abbrev_len_for_midx(struct multi_pack_index *m,
713
struct min_abbrev_data *mad)
714
{
711
- int match = 0;
712
- uint32_t num, first = 0;
713
- struct object_id oid;
714
- const struct object_id *mad_oid;
715
+ for (; m; m = m->base_midx) {
716
+ int match = 0;
717
+ uint32_t num, first = 0;
718
+ struct object_id oid;
719
+ const struct object_id *mad_oid;
720
716
- if (!m->num_objects)
717
- return;
721
+ if (!m->num_objects)
722
+ continue;
723
719
- num = m->num_objects;
720
- mad_oid = mad->oid;
721
- match = bsearch_midx(mad_oid, m, &first);
724
+ num = m->num_objects + m->num_objects_in_base;
725
+ mad_oid = mad->oid;
726
+ match = bsearch_one_midx(mad_oid, m, &first);
727
723
- /*
724
- * first is now the position in the packfile where we would insert
725
- * mad->hash if it does not exist (or the position of mad->hash if
726
- * it does exist). Hence, we consider a maximum of two objects
727
- * nearby for the abbreviation length.
728
- */
729
- mad->init_len = 0;
730
- if (!match) {
731
- if (nth_midxed_object_oid(&oid, m, first))
732
- extend_abbrev_len(&oid, mad);
733
- } else if (first < num - 1) {
734
- if (nth_midxed_object_oid(&oid, m, first + 1))
735
- extend_abbrev_len(&oid, mad);
736
- }
737
- if (first > 0) {
738
- if (nth_midxed_object_oid(&oid, m, first - 1))
739
- extend_abbrev_len(&oid, mad);
728
+ /*
729
+ * first is now the position in the packfile where we
730
+ * would insert mad->hash if it does not exist (or the
731
+ * position of mad->hash if it does exist). Hence, we
732
+ * consider a maximum of two objects nearby for the
733
+ * abbreviation length.
734
+ */
735
+ mad->init_len = 0;
736
+ if (!match) {
737
+ if (nth_midxed_object_oid(&oid, m, first))
738
+ extend_abbrev_len(&oid, mad);
739
+ } else if (first < num - 1) {
740
+ if (nth_midxed_object_oid(&oid, m, first + 1))
741
+ extend_abbrev_len(&oid, mad);
742
+ }
743
+ if (first > 0) {
744
+ if (nth_midxed_object_oid(&oid, m, first - 1))
745
+ extend_abbrev_len(&oid, mad);
746
+ }
747
+ mad->init_len = mad->cur_len;
748
}
741
- mad->init_len = mad->cur_len;
749
}
750
751
static void find_abbrev_len_for_pack(struct packed_git *p,