[PATCH v3 0/6] odb: make creation of object database pluggable

Hi,

when creating a new repository we create a couple of on-disk data
structures for the object database. This includes the "objects/"
directory hierarchy with "objects/info" and "objects/pack", which are
specific to the backend.

This patch series makes the creation of the on-disk data structures
pluggable. While we continue to always create "objects/" regardless of
the backend (it's required for a repository to be recognized as such),
the other subdirectories are now created by the backend. This will allow
other backends to plug in their own logic.

The series starts with a small detour into the loose-object map. This
detour is required so that we can defer initialization of the object
database itself to a later point in time.

The series is based on 9a0c4701dc (The 7th batch, 2026-07-22).

Changes in v3:
  - Move handling of GIT_OBJECT_DIRECTORY and
    GIT_ALTERNATE_OBJECT_DIRECTORIES into `odb_new()` itself. This
    deduplicates some of the logic and also preps us for a future where
    alternates are handled in the "files" backend itself.
  - Link to v2: https://patch.msgid.link/20260804-pks-odb-create-on-disk-v2-0-ddf8b59bd207@pks.im

Changes in v2:
  - Add a testcase that demonstrates the bug fixed with alternate loose
    object maps.
  - Rename the "inmemory" bakcend to "in-memory".
  - Clarify some commit messages.
  - Link to v1: https://patch.msgid.link/20260724-pks-odb-create-on-disk-v1-0-3b3d265d979b@pks.im

Thanks!

Patrick

---
Patrick Steinhardt (6):
      loose: load loose object map for the correct source
      setup: detangle loading of loose object maps
      setup: handle ODB-related environment variables in `odb_new()`
      setup: defer object database creation
      odb/source: introduce function to map source type to name
      odb: make creation of on-disk structures pluggable

 loose.c                       | 25 +++++++++---------
 loose.h                       |  1 +
 odb.c                         | 20 +++++++++------
 odb.h                         | 17 ++++++++++--
 odb/source-files.c            | 19 ++++++++++++++
 odb/source-files.h            |  4 ++-
 odb/source-inmemory.h         |  4 ++-
 odb/source-loose.c            |  2 ++
 odb/source-loose.h            |  4 ++-
 odb/source-packed.h           |  4 ++-
 odb/source.c                  | 19 ++++++++++++++
 odb/source.h                  | 29 +++++++++++++++++++++
 repository.c                  |  2 --
 setup.c                       | 60 ++++++++++++++++++++++++-------------------
 setup.h                       |  9 +++++++
 t/t1016-compatObjectFormat.sh | 18 +++++++++++++
 t/unit-tests/u-odb-inmemory.c |  2 +-
 17 files changed, 183 insertions(+), 56 deletions(-)

Range-diff versus v2:

1:  b0beb61a74 = 1:  d384dd0635 loose: load loose object map for the correct source
2:  097bdcad14 = 2:  0ee1b3c032 setup: detangle loading of loose object maps
-:  ---------- > 3:  f52992b9bd setup: handle ODB-related environment variables in `odb_new()`
3:  06645224ef ! 4:  4524fc5ec4 setup: defer object database creation
    @@ Commit message
         Signed-off-by: Patrick Steinhardt [off-list ref]
     
      ## setup.c ##
    -@@ setup.c: enum discovery_result discover_git_directory_reason(struct strbuf *commondir,
    - 	return result;
    - }
    - 
    -+static void get_object_directories(char **object_directory,
    -+				   char **alternate_object_directories)
    -+{
    -+	*object_directory = xstrdup_or_null(getenv(DB_ENVIRONMENT));
    -+	*alternate_object_directories = xstrdup_or_null(getenv(ALTERNATE_DB_ENVIRONMENT));
    -+}
    -+
    - int apply_repository_format(struct repository *repo,
    - 			    const struct repository_format *format,
    - 			    enum apply_repository_format_flags flags,
     @@ setup.c: int apply_repository_format(struct repository *repo,
    - 	if (flags & APPLY_REPOSITORY_FORMAT_HONOR_ENV) {
    - 		const char *shallow_file;
    + 			    enum apply_repository_format_flags flags,
    + 			    struct strbuf *err)
    + {
    +-	enum odb_new_flags odb_new_flags = 0;
    +-
    + 	if (verify_repository_format(format, err) < 0)
    + 		return -1;
      
    --		object_directory = xstrdup_or_null(getenv(DB_ENVIRONMENT));
    --		alternate_object_directories = xstrdup_or_null(getenv(ALTERNATE_DB_ENVIRONMENT));
    -+		get_object_directories(&object_directory,
    -+				       &alternate_object_directories);
    -+
    - 		shallow_file = getenv(GIT_SHALLOW_FILE_ENVIRONMENT);
    - 		if (shallow_file)
    - 			set_alternate_shallow_file(repo, shallow_file);
     @@ setup.c: int apply_repository_format(struct repository *repo,
      	repo->repository_format_precious_objects =
      		format->precious_objects;
      
    --	repo->objects = odb_new(repo, object_directory,
    --				alternate_object_directories);
    -+	if (!(flags & APPLY_REPOSITORY_FORMAT_SKIP_ODB_CREATION))
    -+		repo->objects = odb_new(repo, object_directory,
    -+					alternate_object_directories);
    +-	if (flags & APPLY_REPOSITORY_FORMAT_HONOR_ENV)
    +-		odb_new_flags |= ODB_NEW_HONOR_ENV;
    +-	repo->objects = odb_new(repo, odb_new_flags);
    ++	if (!(flags & APPLY_REPOSITORY_FORMAT_SKIP_ODB_CREATION)) {
    ++		enum odb_new_flags odb_new_flags = 0;
    ++		if (flags & APPLY_REPOSITORY_FORMAT_HONOR_ENV)
    ++			odb_new_flags |= ODB_NEW_HONOR_ENV;
    ++		repo->objects = odb_new(repo, odb_new_flags);
    ++	}
      
    - 	free(alternate_object_directories);
    - 	free(object_directory);
    + 	return 0;
    + }
     @@ setup.c: static int create_default_files(struct repository *repo,
      	return reinit;
      }
    @@ setup.c: static int create_default_files(struct repository *repo,
     -static void create_object_directory(struct repository *repo)
     +static void create_object_database(struct repository *repo)
      {
    -+	char *object_directory, *alternate_object_directories;
      	struct strbuf path = STRBUF_INIT;
      	size_t baselen;
      
    -+	get_object_directories(&object_directory, &alternate_object_directories);
    -+	repo->objects = odb_new(repo, object_directory,
    -+				alternate_object_directories);
    ++	repo->objects = odb_new(repo, ODB_NEW_HONOR_ENV);
     +
      	strbuf_addstr(&path, repo_get_object_directory(repo));
      	baselen = path.len;
      
    -@@ setup.c: static void create_object_directory(struct repository *repo)
    - 	strbuf_addstr(&path, "/info");
    - 	safe_create_dir(repo, path.buf, 1);
    - 
    -+	free(alternate_object_directories);
    -+	free(object_directory);
    - 	strbuf_release(&path);
    - }
    - 
     @@ setup.c: int init_db(struct repository *repo,
      	 */
      	read_and_verify_repository_format(&repo_fmt, repo_get_git_dir(repo), NULL);
4:  46ad0386bb = 5:  c526fd526b odb/source: introduce function to map source type to name
5:  3063325cf9 ! 6:  d752e48eba odb: make creation of on-disk structures pluggable
    @@ odb/source.h: static inline void odb_source_close(struct odb_source *source)
     
      ## setup.c ##
     @@ setup.c: static int create_default_files(struct repository *repo,
    + 
      static void create_object_database(struct repository *repo)
      {
    - 	char *object_directory, *alternate_object_directories;
     -	struct strbuf path = STRBUF_INIT;
     -	size_t baselen;
    - 
    - 	get_object_directories(&object_directory, &alternate_object_directories);
    --	repo->objects = odb_new(repo, object_directory,
    --				alternate_object_directories);
    - 
    --	strbuf_addstr(&path, repo_get_object_directory(repo));
    --	baselen = path.len;
    --
    --	safe_create_dir(repo, path.buf, 1);
     +	/*
     +	 * Create the "objects" directory in the common directory. This is done
     +	 * so that the repository can be discovered regardless of the backend
    @@ setup.c: static int create_default_files(struct repository *repo,
     +	 * then we skip this step, as the repository won't be discoverable
     +	 * anyway without the environment variable.
     +	 */
    -+	if (!object_directory) {
    ++	if (!getenv(DB_ENVIRONMENT)) {
     +		struct strbuf objects_dir = STRBUF_INIT;
     +		repo_common_path_append(repo, &objects_dir, "objects");
     +		safe_create_dir(repo, objects_dir.buf, 1);
     +		strbuf_release(&objects_dir);
     +	}
      
    + 	repo->objects = odb_new(repo, ODB_NEW_HONOR_ENV);
    + 
    +-	strbuf_addstr(&path, repo_get_object_directory(repo));
    +-	baselen = path.len;
    +-
    +-	safe_create_dir(repo, path.buf, 1);
    +-
     -	strbuf_setlen(&path, baselen);
     -	strbuf_addstr(&path, "/pack");
     -	safe_create_dir(repo, path.buf, 1);
    -+	repo->objects = odb_new(repo, object_directory,
    -+				alternate_object_directories);
    - 
    +-
     -	strbuf_setlen(&path, baselen);
     -	strbuf_addstr(&path, "/info");
     -	safe_create_dir(repo, path.buf, 1);
    +-
    +-	strbuf_release(&path);
     +	if (odb_source_create_on_disk(repo->objects->sources) < 0)
     +		die("failed creating object database");
    - 
    - 	free(alternate_object_directories);
    - 	free(object_directory);
    --	strbuf_release(&path);
      }
      
      static void separate_git_dir(const char *git_dir, const char *git_link)

---
base-commit: 9a0c4701dcd5725c4184599322b52933ff5005ca
change-id: 20260710-pks-odb-create-on-disk-ae8757861c69