Re: [PATCH 1/8] odb: store locality in object database sources
- From
Karthik Nayak <karthik.188@gmail.com>
- Date
- Aug 7, 2025, 08:12 UTC
- Message-ID
- <CAOLa=ZTr6pkYHu05xBKJwY+6RL215o06c=qgZ1b=4MTMxyV6cg@mail.gmail.com>
- In-Reply-To
- <20250729-b4-pks-midx-deduplicate-source-info-v1-1-748db2eda3b5@pks.im>
Patrick Steinhardt <ps@pks.im> writes:
Show 88 quoted lines
> Object database sources are classified either as:
>
> - Local, which means that the source is the repository's primary
> source. This is typically ".git/objects".
>
> - Non-local, which is everything else. Most importantly this includes
> alternates and quarantine directories.
>
> This locality is often computed ad-hoc by checking whether a given
> object source is the first one. This works, but it is quite roundabout.
>
> Refactor the code so that we store locality when creating the sources in
> the first place. This makes it both more accessible and robust.
>
> Signed-off-by: Patrick Steinhardt <ps@pks.im>
> ---
> midx.c | 5 +++--
> midx.h | 2 +-
> odb.c | 1 +
> odb.h | 8 ++++++++
> packfile.c | 9 ++++-----
> repository.c | 1 +
> 6 files changed, 18 insertions(+), 8 deletions(-)
>
> diff --git a/midx.c b/midx.c
> index 7d407682e6..b9ca0915a6 100644
> --- a/midx.c
> +++ b/midx.c
> @@ -723,7 +723,7 @@ int midx_preferred_pack(struct multi_pack_index *m, uint32_t *pack_int_id)
> return 0;
> }
>
> -int prepare_multi_pack_index_one(struct odb_source *source, int local)
> +int prepare_multi_pack_index_one(struct odb_source *source)
> {
> struct repository *r = source->odb->repo;
>
> @@ -734,7 +734,8 @@ int prepare_multi_pack_index_one(struct odb_source *source, int local)
> if (source->midx)
> return 1;
>
> - source->midx = load_multi_pack_index(r, source->path, local);
> + source->midx = load_multi_pack_index(r, source->path,
> + source->local);
>
> return !!source->midx;
> }
> diff --git a/midx.h b/midx.h
> index 076382de8a..28c426a823 100644
> --- a/midx.h
> +++ b/midx.h
> @@ -122,7 +122,7 @@ int fill_midx_entry(struct repository *r, const struct object_id *oid, struct pa
> int midx_contains_pack(struct multi_pack_index *m,
> const char *idx_or_pack_name);
> int midx_preferred_pack(struct multi_pack_index *m, uint32_t *pack_int_id);
> -int prepare_multi_pack_index_one(struct odb_source *source, int local);
> +int prepare_multi_pack_index_one(struct odb_source *source);
>
> /*
> * Variant of write_midx_file which writes a MIDX containing only the packs
> diff --git a/odb.c b/odb.c
> index 1f48a0448e..1761a50840 100644
> --- a/odb.c
> +++ b/odb.c
> @@ -176,6 +176,7 @@ static int link_alt_odb_entry(struct object_database *odb,
>
> CALLOC_ARRAY(alternate, 1);
> alternate->odb = odb;
> + alternate->local = false;
> /* pathbuf.buf is already in r->objects->source_by_path */
> alternate->path = strbuf_detach(&pathbuf, NULL);
>
> diff --git a/odb.h b/odb.h
> index 09177bf430..d9f4dcf79f 100644
> --- a/odb.h
> +++ b/odb.h
> @@ -63,6 +63,14 @@ struct odb_source {
> */
> struct multi_pack_index *midx;
>
> + /*
> + * Figure out whether this is the local alternate of the owning
> + * repository, which would typically be its ".git/objects" directory.
> + * This local object directory is usually where objects would be
> + * written to.
> + */
> + bool local;
> +So now, each 'obd_source' has a 'local' field, which would be false by default. But when the local 'odb_source' is setup, we set it to true.
Show 22 quoted lines
> /*
> * This is a temporary object store created by the tmp_objdir
> * facility. Disable ref updates since the objects in the store
> diff --git a/packfile.c b/packfile.c
> index 5d73932f50..a38544b87b 100644
> --- a/packfile.c
> +++ b/packfile.c
> @@ -935,14 +935,14 @@ static void prepare_pack(const char *full_name, size_t full_name_len,
> report_garbage(PACKDIR_FILE_GARBAGE, full_name);
> }
>
> -static void prepare_packed_git_one(struct odb_source *source, int local)
> +static void prepare_packed_git_one(struct odb_source *source)
> {
> struct string_list garbage = STRING_LIST_INIT_DUP;
> struct prepare_pack_data data = {
> .m = source->midx,
> .r = source->odb->repo,
> .garbage = &garbage,
> - .local = local,
> + .local = source->local,
>The 'prepare_pack_data' already has a 'local' field, so we can now simply set it using the 'odb_source's field of the same name. Nice.
Show 28 quoted lines
> };
>
> for_each_file_in_pack_dir(source->path, prepare_pack, &data);
> @@ -1037,9 +1037,8 @@ static void prepare_packed_git(struct repository *r)
>
> odb_prepare_alternates(r->objects);
> for (source = r->objects->sources; source; source = source->next) {
> - int local = (source == r->objects->sources);
> - prepare_multi_pack_index_one(source, local);
> - prepare_packed_git_one(source, local);
> + prepare_multi_pack_index_one(source);
> + prepare_packed_git_one(source);
> }
> rearrange_packed_git(r);
>
> diff --git a/repository.c b/repository.c
> index ecd691181f..97f0578381 100644
> --- a/repository.c
> +++ b/repository.c
> @@ -168,6 +168,7 @@ void repo_set_gitdir(struct repository *repo,
> if (!repo->objects->sources) {
> CALLOC_ARRAY(repo->objects->sources, 1);
> repo->objects->sources->odb = repo->objects;
> + repo->objects->sources->local = true;
> repo->objects->sources_tail = &repo->objects->sources->next;
> }
> expand_base_dir(&repo->objects->sources->path, o->object_dir,
>So this sets up the local 'odb_source' and as such sets 'local' to true.
Looks good.
> -- > 2.50.1.619.g074bbf1d35.dirty