[PATCH v3 07/19] midx: introduce `bsearch_one_midx()`
- From
Taylor Blau <me@ttaylorr.com>
- Date
- Aug 6, 2024, 15:37 UTC
- Message-ID
- <32c3fceada73e8d53f4239eafc1f440c072920c8.1722958596.git.me@ttaylorr.com>
- In-Reply-To
- <cover.1722958595.git.me@ttaylorr.com>
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> --- midx.c | 17 +++++++-- midx.h | 5 ++- object-name.c | 99 +++++++++++++++++++++++++++------------------------ 3 files changed, 71 insertions(+), 50 deletions(-)
diff --git a/midx.c b/midx.c index 25350152f1..bd6e3f26c9 100644 --- a/midx.c +++ b/midx.c @@ -330,10 +330,21 @@ int nth_bitmapped_pack(struct repository *r, struct multi_pack_index *m, return 0; } -int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result) +int bsearch_one_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); + int ret = bsearch_hash(oid->hash, m->chunk_oid_fanout, + m->chunk_oid_lookup, the_hash_algo->rawsz, + result); + if (result) + *result += m->num_objects_in_base; + return ret; +} + +int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, + uint32_t *result) +{ + return bsearch_one_midx(oid, m, result); } struct object_id *nth_midxed_object_oid(struct object_id *oid, diff --git a/midx.h b/midx.h index 020e49f77c..46c53d69ff 100644 --- a/midx.h +++ b/midx.h @@ -90,7 +90,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id); int nth_bitmapped_pack(struct repository *r, struct multi_pack_index *m, struct bitmapped_pack *bp, uint32_t pack_int_id); -int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result); +int bsearch_one_midx(const struct object_id *oid, struct multi_pack_index *m, + uint32_t *result); +int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, + uint32_t *result); off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos); uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos); struct object_id *nth_midxed_object_oid(struct object_id *oid, diff --git a/object-name.c b/object-name.c index 527b853ac4..739d46f9cf 100644 --- a/object-name.c +++ b/object-name.c @@ -134,28 +134,32 @@ static int match_hash(unsigned len, const unsigned char *a, const unsigned char static void unique_in_midx(struct multi_pack_index *m, struct disambiguate_state *ds) { - uint32_t num, i, first = 0; - const struct object_id *current = NULL; - int len = ds->len > ds->repo->hash_algo->hexsz ? - ds->repo->hash_algo->hexsz : ds->len; - num = m->num_objects; + for (; m; m = m->base_midx) { + uint32_t num, i, first = 0; + const struct object_id *current = NULL; + int len = ds->len > ds->repo->hash_algo->hexsz ? + ds->repo->hash_algo->hexsz : ds->len; - if (!num) - return; + if (!m->num_objects) + continue; - bsearch_midx(&ds->bin_pfx, m, &first); + num = m->num_objects + m->num_objects_in_base; - /* - * At this point, "first" is the location of the lowest object - * with an object name that could match "bin_pfx". See if we have - * 0, 1 or more objects that actually match(es). - */ - for (i = first; i < num && !ds->ambiguous; i++) { - struct object_id oid; - current = nth_midxed_object_oid(&oid, m, i); - if (!match_hash(len, ds->bin_pfx.hash, current->hash)) - break; - update_candidates(ds, current); + bsearch_one_midx(&ds->bin_pfx, m, &first); + + /* + * At this point, "first" is the location of the lowest + * object with an object name that could match + * "bin_pfx". See if we have 0, 1 or more objects that + * actually match(es). + */ + for (i = first; i < num && !ds->ambiguous; i++) { + struct object_id oid; + current = nth_midxed_object_oid(&oid, m, i); + if (!match_hash(len, ds->bin_pfx.hash, current->hash)) + break; + update_candidates(ds, current); + } } } @@ -708,37 +712,40 @@ static int repo_extend_abbrev_len(struct repository *r UNUSED, static void find_abbrev_len_for_midx(struct multi_pack_index *m, struct min_abbrev_data *mad) { - int match = 0; - uint32_t num, first = 0; - struct object_id oid; - const struct object_id *mad_oid; + for (; m; m = m->base_midx) { + int match = 0; + uint32_t num, first = 0; + struct object_id oid; + const struct object_id *mad_oid; - if (!m->num_objects) - return; + if (!m->num_objects) + continue; - num = m->num_objects; - mad_oid = mad->oid; - match = bsearch_midx(mad_oid, m, &first); + num = m->num_objects + m->num_objects_in_base; + mad_oid = mad->oid; + match = bsearch_one_midx(mad_oid, m, &first); - /* - * first is now the position in the packfile where we would insert - * mad->hash if it does not exist (or the position of mad->hash if - * it does exist). Hence, we consider a maximum of two objects - * nearby for the abbreviation length. - */ - mad->init_len = 0; - if (!match) { - if (nth_midxed_object_oid(&oid, m, first)) - extend_abbrev_len(&oid, mad); - } else if (first < num - 1) { - if (nth_midxed_object_oid(&oid, m, first + 1)) - extend_abbrev_len(&oid, mad); + /* + * first is now the position in the packfile where we + * would insert mad->hash if it does not exist (or the + * position of mad->hash if it does exist). Hence, we + * consider a maximum of two objects nearby for the + * abbreviation length. + */ + mad->init_len = 0; + if (!match) { + if (nth_midxed_object_oid(&oid, m, first)) + extend_abbrev_len(&oid, mad); + } else if (first < num - 1) { + if (nth_midxed_object_oid(&oid, m, first + 1)) + extend_abbrev_len(&oid, mad); + } + if (first > 0) { + if (nth_midxed_object_oid(&oid, m, first - 1)) + extend_abbrev_len(&oid, mad); + } + mad->init_len = mad->cur_len; } - if (first > 0) { - if (nth_midxed_object_oid(&oid, m, first - 1)) - extend_abbrev_len(&oid, mad); - } - mad->init_len = mad->cur_len; } static void find_abbrev_len_for_pack(struct packed_git *p,
-- 2.46.0.46.g406f326d27.dirty