Merge branch 'ps/object-source-loose'

A part of code paths that deals with loose objects has been cleaned up. * ps/object-source-loose: object-file: refactor writing objects via a stream object-file: rename `write_object_file()` object-file: refactor freshening of objects object-file: rename `has_loose_object()` object-file: read objects via the loose object source object-file: move loose object map into loose source object-file: hide internals when we need to reprepare loose sources object-file: move loose object cache into loose source object-file: introduce `struct odb_source_loose` object-file: move `fetch_if_missing` odb: adjust naming to free object sources odb: introduce `odb_source_new()` odb: fix subtle logic to check whether an alternate is usable
2026-05-29 22:43:24 -05:00 · 2025-11-24 15:46:41 -08:00
parent 05ce3ab2c6 3e5e360888
commit a545103244
12 changed files with 287 additions and 207 deletions
--- a/object-file.c
+++ b/object-file.c
@@ -99,8 +99,8 @@ static int check_and_freshen_source(struct odb_source *source,
 	return check_and_freshen_file(path.buf, freshen);
 }

-int has_loose_object(struct odb_source *source,
-		     const struct object_id *oid)
+int odb_source_loose_has_object(struct odb_source *source,
+				const struct object_id *oid)
 {
 	return check_and_freshen_source(source, oid, 0);
 }
@@ -167,25 +167,22 @@ int stream_object_signature(struct repository *r, const struct object_id *oid)
 }

 /*
- * Find "oid" as a loose object in the local repository or in an alternate.
+ * Find "oid" as a loose object in given source.
 * Returns 0 on success, negative on failure.
 *
 * The "path" out-parameter will give the path of the object we found (if any).
 * Note that it may point to static storage and is only valid until another
 * call to stat_loose_object().
 */
-static int stat_loose_object(struct repository *r, const struct object_id *oid,
+static int stat_loose_object(struct odb_source_loose *loose,
+			     const struct object_id *oid,
 			     struct stat *st, const char **path)
 {
-	struct odb_source *source;
 	static struct strbuf buf = STRBUF_INIT;

-	odb_prepare_alternates(r->objects);
-	for (source = r->objects->sources; source; source = source->next) {
-		*path = odb_loose_path(source, &buf, oid);
-		if (!lstat(*path, st))
-			return 0;
-	}
+	*path = odb_loose_path(loose->source, &buf, oid);
+	if (!lstat(*path, st))
+		return 0;

 	return -1;
 }
@@ -194,39 +191,24 @@ static int stat_loose_object(struct repository *r, const struct object_id *oid,
 * Like stat_loose_object(), but actually open the object and return the
 * descriptor. See the caveats on the "path" parameter above.
 */
-static int open_loose_object(struct repository *r,
+static int open_loose_object(struct odb_source_loose *loose,
 			     const struct object_id *oid, const char **path)
 {
-	int fd;
-	struct odb_source *source;
-	int most_interesting_errno = ENOENT;
 	static struct strbuf buf = STRBUF_INIT;
+	int fd;

-	odb_prepare_alternates(r->objects);
-	for (source = r->objects->sources; source; source = source->next) {
-		*path = odb_loose_path(source, &buf, oid);
-		fd = git_open(*path);
-		if (fd >= 0)
-			return fd;
+	*path = odb_loose_path(loose->source, &buf, oid);
+	fd = git_open(*path);
+	if (fd >= 0)
+		return fd;

-		if (most_interesting_errno == ENOENT)
-			most_interesting_errno = errno;
-	}
-	errno = most_interesting_errno;
 	return -1;
 }

-static int quick_has_loose(struct repository *r,
+static int quick_has_loose(struct odb_source_loose *loose,
 			   const struct object_id *oid)
 {
-	struct odb_source *source;
-
-	odb_prepare_alternates(r->objects);
-	for (source = r->objects->sources; source; source = source->next) {
-		if (oidtree_contains(odb_loose_cache(source, oid), oid))
-			return 1;
-	}
-	return 0;
+	return !!oidtree_contains(odb_source_loose_cache(loose->source, oid), oid);
 }

 /*
@@ -252,12 +234,12 @@ static void *map_fd(int fd, const char *path, unsigned long *size)
 	return map;
 }

-void *map_loose_object(struct repository *r,
-		       const struct object_id *oid,
-		       unsigned long *size)
+void *odb_source_loose_map_object(struct odb_source *source,
+				  const struct object_id *oid,
+				  unsigned long *size)
 {
 	const char *p;
-	int fd = open_loose_object(r, oid, &p);
+	int fd = open_loose_object(source->loose, oid, &p);

 	if (fd < 0)
 		return NULL;
@@ -407,9 +389,9 @@ int parse_loose_header(const char *hdr, struct object_info *oi)
 	return 0;
 }

-int loose_object_info(struct repository *r,
-		      const struct object_id *oid,
-		      struct object_info *oi, int flags)
+int odb_source_loose_read_object_info(struct odb_source *source,
+				      const struct object_id *oid,
+				      struct object_info *oi, int flags)
 {
 	int status = 0;
 	int fd;
@@ -422,7 +404,7 @@ int loose_object_info(struct repository *r,
 	enum object_type type_scratch;

 	if (oi->delta_base_oid)
-		oidclr(oi->delta_base_oid, r->hash_algo);
+		oidclr(oi->delta_base_oid, source->odb->repo->hash_algo);

 	/*
 	 * If we don't care about type or size, then we don't
@@ -435,15 +417,15 @@ int loose_object_info(struct repository *r,
 	if (!oi->typep && !oi->sizep && !oi->contentp) {
 		struct stat st;
 		if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK))
-			return quick_has_loose(r, oid) ? 0 : -1;
-		if (stat_loose_object(r, oid, &st, &path) < 0)
+			return quick_has_loose(source->loose, oid) ? 0 : -1;
+		if (stat_loose_object(source->loose, oid, &st, &path) < 0)
 			return -1;
 		if (oi->disk_sizep)
 			*oi->disk_sizep = st.st_size;
 		return 0;
 	}

-	fd = open_loose_object(r, oid, &path);
+	fd = open_loose_object(source->loose, oid, &path);
 	if (fd < 0) {
 		if (errno != ENOENT)
 			error_errno(_("unable to open loose object %s"), oid_to_hex(oid));
@@ -986,35 +968,15 @@ static int write_loose_object(struct odb_source *source,
 					  FOF_SKIP_COLLISION_CHECK);
 }

-static int freshen_loose_object(struct object_database *odb,
-				const struct object_id *oid)
+int odb_source_loose_freshen_object(struct odb_source *source,
+				    const struct object_id *oid)
 {
-	odb_prepare_alternates(odb);
-	for (struct odb_source *source = odb->sources; source; source = source->next)
-		if (check_and_freshen_source(source, oid, 1))
-			return 1;
-	return 0;
+	return !!check_and_freshen_source(source, oid, 1);
 }

-static int freshen_packed_object(struct object_database *odb,
-				 const struct object_id *oid)
-{
-	struct pack_entry e;
-	if (!find_pack_entry(odb->repo, oid, &e))
-		return 0;
-	if (e.p->is_cruft)
-		return 0;
-	if (e.p->freshened)
-		return 1;
-	if (!freshen_file(e.p->pack_name))
-		return 0;
-	e.p->freshened = 1;
-	return 1;
-}
-
-int stream_loose_object(struct odb_source *source,
-			struct input_stream *in_stream, size_t len,
-			struct object_id *oid)
+int odb_source_loose_write_stream(struct odb_source *source,
+				  struct odb_write_stream *in_stream, size_t len,
+				  struct object_id *oid)
 {
 	const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo;
 	struct object_id compat_oid;
@@ -1091,12 +1053,10 @@ int stream_loose_object(struct odb_source *source,
 		die(_("deflateEnd on stream object failed (%d)"), ret);
 	close_loose_object(source, fd, tmp_file.buf);

-	if (freshen_packed_object(source->odb, oid) ||
-	    freshen_loose_object(source->odb, oid)) {
+	if (odb_freshen_object(source->odb, oid)) {
 		unlink_or_warn(tmp_file.buf);
 		goto cleanup;
 	}
-
 	odb_loose_path(source, &filename, oid);

 	/* We finally know the object path, and create the missing dir. */
@@ -1124,10 +1084,10 @@ cleanup:
 	return err;
 }

-int write_object_file(struct odb_source *source,
-		      const void *buf, unsigned long len,
-		      enum object_type type, struct object_id *oid,
-		      struct object_id *compat_oid_in, unsigned flags)
+int odb_source_loose_write_object(struct odb_source *source,
+				  const void *buf, unsigned long len,
+				  enum object_type type, struct object_id *oid,
+				  struct object_id *compat_oid_in, unsigned flags)
 {
 	const struct git_hash_algo *algo = source->odb->repo->hash_algo;
 	const struct git_hash_algo *compat = source->odb->repo->compat_hash_algo;
@@ -1155,8 +1115,7 @@ int write_object_file(struct odb_source *source,
 	 * it out into .git/objects/??/?{38} file.
 	 */
 	write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen);
-	if (freshen_packed_object(source->odb, oid) ||
-	    freshen_loose_object(source->odb, oid))
+	if (odb_freshen_object(source->odb, oid))
 		return 0;
 	if (write_loose_object(source, oid, hdr, hdrlen, buf, len, 0, flags))
 		return -1;
@@ -1179,7 +1138,7 @@ int force_object_loose(struct odb_source *source,
 	int ret;

 	for (struct odb_source *s = source->odb->sources; s; s = s->next)
-		if (has_loose_object(s, oid))
+		if (odb_source_loose_has_object(s, oid))
 			return 0;

 	oi.typep = &type;
@@ -1806,44 +1765,49 @@ static int append_loose_object(const struct object_id *oid,
 	return 0;
 }

-struct oidtree *odb_loose_cache(struct odb_source *source,
-				const struct object_id *oid)
+struct oidtree *odb_source_loose_cache(struct odb_source *source,
+				       const struct object_id *oid)
 {
 	int subdir_nr = oid->hash[0];
 	struct strbuf buf = STRBUF_INIT;
-	size_t word_bits = bitsizeof(source->loose_objects_subdir_seen[0]);
+	size_t word_bits = bitsizeof(source->loose->subdir_seen[0]);
 	size_t word_index = subdir_nr / word_bits;
 	size_t mask = (size_t)1u << (subdir_nr % word_bits);
 	uint32_t *bitmap;

 	if (subdir_nr < 0 ||
-	    (size_t) subdir_nr >= bitsizeof(source->loose_objects_subdir_seen))
+	    (size_t) subdir_nr >= bitsizeof(source->loose->subdir_seen))
 		BUG("subdir_nr out of range");

-	bitmap = &source->loose_objects_subdir_seen[word_index];
+	bitmap = &source->loose->subdir_seen[word_index];
 	if (*bitmap & mask)
-		return source->loose_objects_cache;
-	if (!source->loose_objects_cache) {
-		ALLOC_ARRAY(source->loose_objects_cache, 1);
-		oidtree_init(source->loose_objects_cache);
+		return source->loose->cache;
+	if (!source->loose->cache) {
+		ALLOC_ARRAY(source->loose->cache, 1);
+		oidtree_init(source->loose->cache);
 	}
 	strbuf_addstr(&buf, source->path);
 	for_each_file_in_obj_subdir(subdir_nr, &buf,
 				    source->odb->repo->hash_algo,
 				    append_loose_object,
 				    NULL, NULL,
-				    source->loose_objects_cache);
+				    source->loose->cache);
 	*bitmap |= mask;
 	strbuf_release(&buf);
-	return source->loose_objects_cache;
+	return source->loose->cache;
 }

-void odb_clear_loose_cache(struct odb_source *source)
+static void odb_source_loose_clear_cache(struct odb_source_loose *loose)
 {
-	oidtree_clear(source->loose_objects_cache);
-	FREE_AND_NULL(source->loose_objects_cache);
-	memset(&source->loose_objects_subdir_seen, 0,
-	       sizeof(source->loose_objects_subdir_seen));
+	oidtree_clear(loose->cache);
+	FREE_AND_NULL(loose->cache);
+	memset(&loose->subdir_seen, 0,
+	       sizeof(loose->subdir_seen));
+}
+
+void odb_source_loose_reprepare(struct odb_source *source)
+{
+	odb_source_loose_clear_cache(source->loose);
 }

 static int check_stream_oid(git_zstream *stream,
@@ -1999,3 +1963,20 @@ void object_file_transaction_commit(struct odb_transaction *transaction)
 	transaction->odb->transaction = NULL;
 	free(transaction);
 }
+
+struct odb_source_loose *odb_source_loose_new(struct odb_source *source)
+{
+	struct odb_source_loose *loose;
+	CALLOC_ARRAY(loose, 1);
+	loose->source = source;
+	return loose;
+}
+
+void odb_source_loose_free(struct odb_source_loose *loose)
+{
+	if (!loose)
+		return;
+	odb_source_loose_clear_cache(loose);
+	loose_object_map_clear(&loose->map);
+	free(loose);
+}