packfile: move packfile store into object source

The packfile store is a member of `struct object_database`, which means
that we have a single store per database. This doesn't really make much
sense though: each source connected to the database has its own set of
packfiles, so there is a conceptual mismatch here. This hasn't really
caused much of a problem in the past, but with the advent of pluggable
object databases this is becoming more of a problem because some of the
sources may not even use packfiles in the first place.

Move the packfile store down by one level from the object database into
the object database source. This ensures that each source now has its
own packfile store, and we can eventually start to abstract it away
entirely so that the caller doesn't even know what kind of store it
uses.

Note that we only need to adjust a relatively small number of callers,
way less than one might expect. This is because most callers are using
`repo_for_each_pack()`, which handles enumeration of all packfiles that
exist in the repository. So for now, none of these callers need to be
adapted. The remaining callers that iterate through the packfiles
directly and that need adjustment are those that are a bit more tangled
with packfiles. These will be adjusted over time.

Note that this patch only moves the packfile store, and there is still a
bunch of functions that seemingly operate on a packfile store but that
end up iterating over all sources. These will be adjusted in subsequent
commits.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

builtin/fast-import.c

@@ -900,7 +900,7 @@ static void end_packfile(void)
 		idx_name = keep_pack(create_index());
 
 		/* Register the packfile with core git's machinery. */
-		new_p = packfile_store_load_pack(pack_data->repo->objects->packfiles,
+		new_p = packfile_store_load_pack(pack_data->repo->objects->sources->packfiles,
 						 idx_name, 1);
 		if (!new_p)
 			die(_("core Git rejected index %s"), idx_name);
@@ -955,7 +955,7 @@ static int store_object(
 	struct object_id *oidout,
 	uintmax_t mark)
 {
-	struct packfile_store *packs = the_repository->objects->packfiles;
+	struct odb_source *source;
 	void *out, *delta;
 	struct object_entry *e;
 	unsigned char hdr[96];
@@ -979,7 +979,11 @@ static int store_object(
 	if (e->idx.offset) {
 		duplicate_count_by_type[type]++;
 		return 1;
-	} else if (packfile_list_find_oid(packfile_store_get_packs(packs), &oid)) {
+	}
+
+	for (source = the_repository->objects->sources; source; source = source->next) {
+		if (!packfile_list_find_oid(packfile_store_get_packs(source->packfiles), &oid))
+			continue;
 		e->type = type;
 		e->pack_id = MAX_PACK_ID;
 		e->idx.offset = 1; /* just not zero! */
@@ -1096,10 +1100,10 @@ static void truncate_pack(struct hashfile_checkpoint *checkpoint)
 
 static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
 {
-	struct packfile_store *packs = the_repository->objects->packfiles;
 	size_t in_sz = 64 * 1024, out_sz = 64 * 1024;
 	unsigned char *in_buf = xmalloc(in_sz);
 	unsigned char *out_buf = xmalloc(out_sz);
+	struct odb_source *source;
 	struct object_entry *e;
 	struct object_id oid;
 	unsigned long hdrlen;
@@ -1179,24 +1183,29 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
 	if (e->idx.offset) {
 		duplicate_count_by_type[OBJ_BLOB]++;
 		truncate_pack(&checkpoint);
+		goto out;
+	}
 
-	} else if (packfile_list_find_oid(packfile_store_get_packs(packs), &oid)) {
+	for (source = the_repository->objects->sources; source; source = source->next) {
+		if (!packfile_list_find_oid(packfile_store_get_packs(source->packfiles), &oid))
+			continue;
 		e->type = OBJ_BLOB;
 		e->pack_id = MAX_PACK_ID;
 		e->idx.offset = 1; /* just not zero! */
 		duplicate_count_by_type[OBJ_BLOB]++;
 		truncate_pack(&checkpoint);
-
-	} else {
-		e->depth = 0;
-		e->type = OBJ_BLOB;
-		e->pack_id = pack_id;
-		e->idx.offset = offset;
-		e->idx.crc32 = crc32_end(pack_file);
-		object_count++;
-		object_count_by_type[OBJ_BLOB]++;
+		goto out;
 	}
 
+	e->depth = 0;
+	e->type = OBJ_BLOB;
+	e->pack_id = pack_id;
+	e->idx.offset = offset;
+	e->idx.crc32 = crc32_end(pack_file);
+	object_count++;
+	object_count_by_type[OBJ_BLOB]++;
+
+out:
 	free(in_buf);
 	free(out_buf);
 }

builtin/grep.c

@@ -1213,8 +1213,12 @@ int cmd_grep(int argc,
 		 */
 		if (recurse_submodules)
 			repo_read_gitmodules(the_repository, 1);
+		/*
+		 * Note: `packfile_store_prepare()` prepares stores from all
+		 * sources. This will be fixed in a subsequent commit.
+		 */
 		if (startup_info->have_repository)
-			packfile_store_prepare(the_repository->objects->packfiles);
+			packfile_store_prepare(the_repository->objects->sources->packfiles);
 
 		start_threads(&opt);
 	} else {

builtin/index-pack.c

@@ -1638,7 +1638,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 			    hash, "idx", 1);
 
 	if (do_fsck_object && startup_info->have_repository)
-		packfile_store_load_pack(the_repository->objects->packfiles,
+		packfile_store_load_pack(the_repository->objects->sources->packfiles,
 					 final_index_name, 0);
 
 	if (!from_stdin) {

builtin/pack-objects.c

@@ -1529,49 +1529,53 @@ static int want_cruft_object_mtime(struct repository *r,
 				   const struct object_id *oid,
 				   unsigned flags, uint32_t mtime)
 {
-	struct packed_git **cache = packfile_store_get_kept_pack_cache(r->objects->packfiles, flags);
+	struct odb_source *source;
 
-	for (; *cache; cache++) {
-		struct packed_git *p = *cache;
-		off_t ofs;
-		uint32_t candidate_mtime;
+	for (source = r->objects->sources; source; source = source->next) {
+		struct packed_git **cache = packfile_store_get_kept_pack_cache(source->packfiles, flags);
 
-		ofs = find_pack_entry_one(oid, p);
-		if (!ofs)
-			continue;
+		for (; *cache; cache++) {
+			struct packed_git *p = *cache;
+			off_t ofs;
+			uint32_t candidate_mtime;
 
-		/*
-		 * We have a copy of the object 'oid' in a non-cruft
-		 * pack. We can avoid packing an additional copy
-		 * regardless of what the existing copy's mtime is since
-		 * it is outside of a cruft pack.
-		 */
-		if (!p->is_cruft)
-			return 0;
-
-		/*
-		 * If we have a copy of the object 'oid' in a cruft
-		 * pack, then either read the cruft pack's mtime for
-		 * that object, or, if that can't be loaded, assume the
-		 * pack's mtime itself.
-		 */
-		if (!load_pack_mtimes(p)) {
-			uint32_t pos;
-			if (offset_to_pack_pos(p, ofs, &pos) < 0)
+			ofs = find_pack_entry_one(oid, p);
+			if (!ofs)
 				continue;
-			candidate_mtime = nth_packed_mtime(p, pos);
-		} else {
-			candidate_mtime = p->mtime;
-		}
 
-		/*
-		 * We have a surviving copy of the object in a cruft
-		 * pack whose mtime is greater than or equal to the one
-		 * we are considering. We can thus avoid packing an
-		 * additional copy of that object.
-		 */
-		if (mtime <= candidate_mtime)
-			return 0;
+			/*
+			 * We have a copy of the object 'oid' in a non-cruft
+			 * pack. We can avoid packing an additional copy
+			 * regardless of what the existing copy's mtime is since
+			 * it is outside of a cruft pack.
+			 */
+			if (!p->is_cruft)
+				return 0;
+
+			/*
+			 * If we have a copy of the object 'oid' in a cruft
+			 * pack, then either read the cruft pack's mtime for
+			 * that object, or, if that can't be loaded, assume the
+			 * pack's mtime itself.
+			 */
+			if (!load_pack_mtimes(p)) {
+				uint32_t pos;
+				if (offset_to_pack_pos(p, ofs, &pos) < 0)
+					continue;
+				candidate_mtime = nth_packed_mtime(p, pos);
+			} else {
+				candidate_mtime = p->mtime;
+			}
+
+			/*
+			 * We have a surviving copy of the object in a cruft
+			 * pack whose mtime is greater than or equal to the one
+			 * we are considering. We can thus avoid packing an
+			 * additional copy of that object.
+			 */
+			if (mtime <= candidate_mtime)
+				return 0;
+		}
 	}
 
 	return -1;
@@ -1749,13 +1753,15 @@ static int want_object_in_pack_mtime(const struct object_id *oid,
 		}
 	}
 
-	for (e = the_repository->objects->packfiles->packs.head; e; e = e->next) {
-		struct packed_git *p = e->pack;
-		want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset, found_mtime);
-		if (!exclude && want > 0)
-			packfile_list_prepend(&the_repository->objects->packfiles->packs, p);
-		if (want != -1)
-			return want;
+	for (source = the_repository->objects->sources; source; source = source->next) {
+		for (e = source->packfiles->packs.head; e; e = e->next) {
+			struct packed_git *p = e->pack;
+			want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset, found_mtime);
+			if (!exclude && want > 0)
+				packfile_list_prepend(&source->packfiles->packs, p);
+			if (want != -1)
+				return want;
+		}
 	}
 
 	if (uri_protocols.nr) {

http.c

@@ -2544,7 +2544,7 @@ void http_install_packfile(struct packed_git *p,
 			   struct packfile_list *list_to_remove_from)
 {
 	packfile_list_remove(list_to_remove_from, p);
-	packfile_store_add_pack(the_repository->objects->packfiles, p);
+	packfile_store_add_pack(the_repository->objects->sources->packfiles, p);
 }
 
 struct http_pack_request *new_http_pack_request(

midx.c

@@ -95,7 +95,7 @@ static int midx_read_object_offsets(const unsigned char *chunk_start,
 
 struct multi_pack_index *get_multi_pack_index(struct odb_source *source)
 {
-	packfile_store_prepare(source->odb->packfiles);
+	packfile_store_prepare(source->packfiles);
 	return source->midx;
 }
 
@@ -447,7 +447,6 @@ static uint32_t midx_for_pack(struct multi_pack_index **_m,
 int prepare_midx_pack(struct multi_pack_index *m,
 		      uint32_t pack_int_id)
 {
-	struct repository *r = m->source->odb->repo;
 	struct strbuf pack_name = STRBUF_INIT;
 	struct packed_git *p;
 
@@ -460,7 +459,7 @@ int prepare_midx_pack(struct multi_pack_index *m,
 
 	strbuf_addf(&pack_name, "%s/pack/%s", m->source->path,
 		    m->pack_names[pack_int_id]);
-	p = packfile_store_load_pack(r->objects->packfiles,
+	p = packfile_store_load_pack(m->source->packfiles,
 				     pack_name.buf, m->source->local);
 	strbuf_release(&pack_name);
 

odb.c

@@ -155,6 +155,7 @@ static struct odb_source *odb_source_new(struct object_database *odb,
 	source->local = local;
 	source->path = xstrdup(path);
 	source->loose = odb_source_loose_new(source);
+	source->packfiles = packfile_store_new(source);
 
 	return source;
 }
@@ -373,6 +374,7 @@ static void odb_source_free(struct odb_source *source)
 {
 	free(source->path);
 	odb_source_loose_free(source->loose);
+	packfile_store_free(source->packfiles);
 	free(source);
 }
 
@@ -704,19 +706,19 @@ static int do_oid_object_info_extended(struct object_database *odb,
 	while (1) {
 		struct odb_source *source;
 
-		if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags))
-			return 0;
-
 		/* Most likely it's a loose object. */
-		for (source = odb->sources; source; source = source->next)
-			if (!odb_source_loose_read_object_info(source, real, oi, flags))
+		for (source = odb->sources; source; source = source->next) {
+			if (!packfile_store_read_object_info(source->packfiles, real, oi, flags) ||
+			    !odb_source_loose_read_object_info(source, real, oi, flags))
 				return 0;
+		}
 
 		/* Not a loose object; someone else may have just packed it. */
 		if (!(flags & OBJECT_INFO_QUICK)) {
 			odb_reprepare(odb->repo->objects);
-			if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags))
-				return 0;
+			for (source = odb->sources; source; source = source->next)
+				if (!packfile_store_read_object_info(source->packfiles, real, oi, flags))
+					return 0;
 		}
 
 		/*
@@ -975,13 +977,14 @@ int odb_freshen_object(struct object_database *odb,
 {
 	struct odb_source *source;
 
-	if (packfile_store_freshen_object(odb->packfiles, oid))
-		return 1;
-
 	odb_prepare_alternates(odb);
-	for (source = odb->sources; source; source = source->next)
+	for (source = odb->sources; source; source = source->next) {
+		if (packfile_store_freshen_object(source->packfiles, oid))
+			return 1;
+
 		if (odb_source_loose_freshen_object(source, oid))
 			return 1;
+	}
 
 	return 0;
 }
@@ -1064,7 +1067,6 @@ struct object_database *odb_new(struct repository *repo,
 	o->sources = odb_source_new(o, primary_source, true);
 	o->sources_tail = &o->sources->next;
 	o->alternate_db = xstrdup_or_null(secondary_sources);
-	o->packfiles = packfile_store_new(o->sources);
 
 	free(to_free);
 
@@ -1077,9 +1079,8 @@ void odb_close(struct object_database *o)
 {
 	struct odb_source *source;
 
-	packfile_store_close(o->packfiles);
-
 	for (source = o->sources; source; source = source->next) {
+		packfile_store_close(source->packfiles);
 		if (source->midx)
 			close_midx(source->midx);
 		source->midx = NULL;
@@ -1118,7 +1119,6 @@ void odb_free(struct object_database *o)
 		free((char *) o->cached_objects[i].value.buf);
 	free(o->cached_objects);
 
-	packfile_store_free(o->packfiles);
 	string_list_clear(&o->submodule_source_paths, 0);
 
 	chdir_notify_unregister(NULL, odb_update_commondir, o);
@@ -1141,13 +1141,13 @@ void odb_reprepare(struct object_database *o)
 	o->loaded_alternates = 0;
 	odb_prepare_alternates(o);
 
-	for (source = o->sources; source; source = source->next)
+	for (source = o->sources; source; source = source->next) {
 		odb_source_loose_reprepare(source);
+		packfile_store_reprepare(source->packfiles);
+	}
 
 	o->approximate_object_count_valid = 0;
 
-	packfile_store_reprepare(o->packfiles);
-
 	obj_read_unlock();
 }
 

odb.h

@@ -51,6 +51,9 @@ struct odb_source {
 	/* Private state for loose objects. */
 	struct odb_source_loose *loose;
 
+	/* Should only be accessed directly by packfile.c and midx.c. */
+	struct packfile_store *packfiles;
+
 	/*
 	 * private data
 	 *
@@ -128,9 +131,6 @@ struct object_database {
 	struct commit_graph *commit_graph;
 	unsigned commit_graph_attempted : 1; /* if loading has been attempted */
 
-	/* Should only be accessed directly by packfile.c and midx.c. */
-	struct packfile_store *packfiles;
-
 	/*
 	 * This is meant to hold a *small* number of objects that you would
 	 * want odb_read_object() to be able to return, but yet you do not want

odb/streaming.c

@@ -185,13 +185,12 @@ static int istream_source(struct odb_read_stream **out,
 {
 	struct odb_source *source;
 
-	if (!packfile_store_read_object_stream(out, odb->packfiles, oid))
-		return 0;
-
 	odb_prepare_alternates(odb);
-	for (source = odb->sources; source; source = source->next)
-		if (!odb_source_loose_read_object_stream(out, source, oid))
+	for (source = odb->sources; source; source = source->next) {
+		if (!packfile_store_read_object_stream(out, source->packfiles, oid) ||
+		    !odb_source_loose_read_object_stream(out, source, oid))
 			return 0;
+	}
 
 	return open_istream_incore(out, odb, oid);
 }