Merge branch 'ds/commit-graph-write-refactor'

Renamed from commit-graph-format-v2 and changed scope.

* ds/commit-graph-write-refactor:
  commit-graph: extract write_commit_graph_file()
  commit-graph: extract copy_oids_to_commits()
  commit-graph: extract count_distinct_commits()
  commit-graph: extract fill_oids_from_all_packs()
  commit-graph: extract fill_oids_from_commit_hex()
  commit-graph: extract fill_oids_from_packs()
  commit-graph: create write_commit_graph_context
  commit-graph: remove Future Work section
  commit-graph: collapse parameters into flags
  commit-graph: return with errors during write
  commit-graph: fix the_repository reference

Documentation/technical/commit-graph.txt

@@ -127,23 +127,6 @@ Design Details
   helpful for these clones, anyway. The commit-graph will not be read or
   written when shallow commits are present.
 
-Future Work
------------
-
-- After computing and storing generation numbers, we must make graph
-  walks aware of generation numbers to gain the performance benefits they
-  enable. This will mostly be accomplished by swapping a commit-date-ordered
-  priority queue with one ordered by generation number. The following
-  operations are important candidates:
-
-    - 'log --topo-order'
-    - 'tag --merged'
-
-- A server could provide a commit-graph file as part of the network protocol
-  to avoid extra calculations by clients. This feature is only of benefit if
-  the user is willing to trust the file, because verifying the file is correct
-  is as hard as computing it from scratch.
-
 Related Links
 -------------
 [0] https://bugs.chromium.org/p/git/issues/detail?id=8

builtin/commit-graph.c

@@ -141,6 +141,8 @@ static int graph_write(int argc, const char **argv)
 	struct string_list *pack_indexes = NULL;
 	struct string_list *commit_hex = NULL;
 	struct string_list lines;
+	int result = 0;
+	unsigned int flags = COMMIT_GRAPH_PROGRESS;
 
 	static struct option builtin_commit_graph_write_options[] = {
 		OPT_STRING(0, "object-dir", &opts.obj_dir,
@@ -165,13 +167,13 @@ static int graph_write(int argc, const char **argv)
 		die(_("use at most one of --reachable, --stdin-commits, or --stdin-packs"));
 	if (!opts.obj_dir)
 		opts.obj_dir = get_object_directory();
+	if (opts.append)
+		flags |= COMMIT_GRAPH_APPEND;
 
 	read_replace_refs = 0;
 
-	if (opts.reachable) {
-		write_commit_graph_reachable(opts.obj_dir, opts.append, 1);
-		return 0;
-	}
+	if (opts.reachable)
+		return write_commit_graph_reachable(opts.obj_dir, flags);
 
 	string_list_init(&lines, 0);
 	if (opts.stdin_packs || opts.stdin_commits) {
@@ -188,14 +190,14 @@ static int graph_write(int argc, const char **argv)
 		UNLEAK(buf);
 	}
 
-	write_commit_graph(opts.obj_dir,
-			   pack_indexes,
-			   commit_hex,
-			   opts.append,
-			   1);
+	if (write_commit_graph(opts.obj_dir,
+			       pack_indexes,
+			       commit_hex,
+			       flags))
+		result = 1;
 
 	UNLEAK(lines);
-	return 0;
+	return result;
 }
 
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)

builtin/commit.c

@@ -1669,8 +1669,9 @@ int cmd_commit(int argc, const char **argv, const char *prefix)
 		      "new_index file. Check that disk is not full and quota is\n"
 		      "not exceeded, and then \"git reset HEAD\" to recover."));
 
-	if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0))
-		write_commit_graph_reachable(get_object_directory(), 0, 0);
+	if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
+	    write_commit_graph_reachable(get_object_directory(), 0))
+		return 1;
 
 	repo_rerere(the_repository, 0);
 	run_command_v_opt(argv_gc_auto, RUN_GIT_CMD);

builtin/gc.c

@@ -685,9 +685,10 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		clean_pack_garbage();
 	}
 
-	if (gc_write_commit_graph)
-		write_commit_graph_reachable(get_object_directory(), 0,
-					     !quiet && !daemonized);
+	if (gc_write_commit_graph &&
+	    write_commit_graph_reachable(get_object_directory(),
+					 !quiet && !daemonized ? COMMIT_GRAPH_PROGRESS : 0))
+		return 1;
 
 	if (auto_gc && too_many_loose_objects())
 		warning(_("There are too many unreachable loose objects; "

commit-graph.c

@@ -525,14 +525,38 @@ struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit
 	return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
 }
 
+struct packed_commit_list {
+	struct commit **list;
+	int nr;
+	int alloc;
+};
+
+struct packed_oid_list {
+	struct object_id *list;
+	int nr;
+	int alloc;
+};
+
+struct write_commit_graph_context {
+	struct repository *r;
+	const char *obj_dir;
+	char *graph_name;
+	struct packed_oid_list oids;
+	struct packed_commit_list commits;
+	int num_extra_edges;
+	unsigned long approx_nr_objects;
+	struct progress *progress;
+	int progress_done;
+	uint64_t progress_cnt;
+	unsigned append:1,
+		 report_progress:1;
+};
+
 static void write_graph_chunk_fanout(struct hashfile *f,
-				     struct commit **commits,
-				     int nr_commits,
-				     struct progress *progress,
-				     uint64_t *progress_cnt)
+				     struct write_commit_graph_context *ctx)
 {
 	int i, count = 0;
-	struct commit **list = commits;
+	struct commit **list = ctx->commits.list;
 
 	/*
 	 * Write the first-level table (the list is sorted,
@@ -540,10 +564,10 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 	 * having to do eight extra binary search iterations).
 	 */
 	for (i = 0; i < 256; i++) {
-		while (count < nr_commits) {
+		while (count < ctx->commits.nr) {
 			if ((*list)->object.oid.hash[0] != i)
 				break;
-			display_progress(progress, ++*progress_cnt);
+			display_progress(ctx->progress, ++ctx->progress_cnt);
 			count++;
 			list++;
 		}
@@ -553,14 +577,12 @@ static void write_graph_chunk_fanout(struct hashfile *f,
 }
 
 static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
-				   struct commit **commits, int nr_commits,
-				   struct progress *progress,
-				   uint64_t *progress_cnt)
+				   struct write_commit_graph_context *ctx)
 {
-	struct commit **list = commits;
+	struct commit **list = ctx->commits.list;
 	int count;
-	for (count = 0; count < nr_commits; count++, list++) {
-		display_progress(progress, ++*progress_cnt);
+	for (count = 0; count < ctx->commits.nr; count++, list++) {
+		display_progress(ctx->progress, ++ctx->progress_cnt);
 		hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
 	}
 }
@@ -572,19 +594,17 @@ static const unsigned char *commit_to_sha1(size_t index, void *table)
 }
 
 static void write_graph_chunk_data(struct hashfile *f, int hash_len,
-				   struct commit **commits, int nr_commits,
-				   struct progress *progress,
-				   uint64_t *progress_cnt)
+				   struct write_commit_graph_context *ctx)
 {
-	struct commit **list = commits;
-	struct commit **last = commits + nr_commits;
+	struct commit **list = ctx->commits.list;
+	struct commit **last = ctx->commits.list + ctx->commits.nr;
 	uint32_t num_extra_edges = 0;
 
 	while (list < last) {
 		struct commit_list *parent;
 		int edge_value;
 		uint32_t packedDate[2];
-		display_progress(progress, ++*progress_cnt);
+		display_progress(ctx->progress, ++ctx->progress_cnt);
 
 		parse_commit_no_graph(*list);
 		hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len);
@@ -595,8 +615,8 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 			edge_value = GRAPH_PARENT_NONE;
 		else {
 			edge_value = sha1_pos(parent->item->object.oid.hash,
-					      commits,
-					      nr_commits,
+					      ctx->commits.list,
+					      ctx->commits.nr,
 					      commit_to_sha1);
 
 			if (edge_value < 0)
@@ -616,8 +636,8 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 			edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges;
 		else {
 			edge_value = sha1_pos(parent->item->object.oid.hash,
-					      commits,
-					      nr_commits,
+					      ctx->commits.list,
+					      ctx->commits.nr,
 					      commit_to_sha1);
 			if (edge_value < 0)
 				BUG("missing parent %s for commit %s",
@@ -649,19 +669,16 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 }
 
 static void write_graph_chunk_extra_edges(struct hashfile *f,
-					  struct commit **commits,
-					  int nr_commits,
-					  struct progress *progress,
-					  uint64_t *progress_cnt)
+					  struct write_commit_graph_context *ctx)
 {
-	struct commit **list = commits;
-	struct commit **last = commits + nr_commits;
+	struct commit **list = ctx->commits.list;
+	struct commit **last = ctx->commits.list + ctx->commits.nr;
 	struct commit_list *parent;
 
 	while (list < last) {
 		int num_parents = 0;
 
-		display_progress(progress, ++*progress_cnt);
+		display_progress(ctx->progress, ++ctx->progress_cnt);
 
 		for (parent = (*list)->parents; num_parents < 3 && parent;
 		     parent = parent->next)
@@ -675,8 +692,8 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 		/* Since num_parents > 2, this initializer is safe. */
 		for (parent = (*list)->parents->next; parent; parent = parent->next) {
 			int edge_value = sha1_pos(parent->item->object.oid.hash,
-						  commits,
-						  nr_commits,
+						  ctx->commits.list,
+						  ctx->commits.nr,
 						  commit_to_sha1);
 
 			if (edge_value < 0)
@@ -700,125 +717,111 @@ static int commit_compare(const void *_a, const void *_b)
 	return oidcmp(a, b);
 }
 
-struct packed_commit_list {
-	struct commit **list;
-	int nr;
-	int alloc;
-};
-
-struct packed_oid_list {
-	struct object_id *list;
-	int nr;
-	int alloc;
-	struct progress *progress;
-	int progress_done;
-};
-
 static int add_packed_commits(const struct object_id *oid,
 			      struct packed_git *pack,
 			      uint32_t pos,
 			      void *data)
 {
-	struct packed_oid_list *list = (struct packed_oid_list*)data;
+	struct write_commit_graph_context *ctx = (struct write_commit_graph_context*)data;
 	enum object_type type;
 	off_t offset = nth_packed_object_offset(pack, pos);
 	struct object_info oi = OBJECT_INFO_INIT;
 
-	if (list->progress)
-		display_progress(list->progress, ++list->progress_done);
+	if (ctx->progress)
+		display_progress(ctx->progress, ++ctx->progress_done);
 
 	oi.typep = &type;
-	if (packed_object_info(the_repository, pack, offset, &oi) < 0)
+	if (packed_object_info(ctx->r, pack, offset, &oi) < 0)
 		die(_("unable to get type of object %s"), oid_to_hex(oid));
 
 	if (type != OBJ_COMMIT)
 		return 0;
 
-	ALLOC_GROW(list->list, list->nr + 1, list->alloc);
-	oidcpy(&(list->list[list->nr]), oid);
-	list->nr++;
+	ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+	oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid);
+	ctx->oids.nr++;
 
 	return 0;
 }
 
-static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit)
+static void add_missing_parents(struct write_commit_graph_context *ctx, struct commit *commit)
 {
 	struct commit_list *parent;
 	for (parent = commit->parents; parent; parent = parent->next) {
 		if (!(parent->item->object.flags & UNINTERESTING)) {
-			ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc);
-			oidcpy(&oids->list[oids->nr], &(parent->item->object.oid));
-			oids->nr++;
+			ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+			oidcpy(&ctx->oids.list[ctx->oids.nr], &(parent->item->object.oid));
+			ctx->oids.nr++;
 			parent->item->object.flags |= UNINTERESTING;
 		}
 	}
 }
 
-static void close_reachable(struct packed_oid_list *oids, int report_progress)
+static void close_reachable(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit *commit;
-	struct progress *progress = NULL;
 
-	if (report_progress)
-		progress = start_delayed_progress(
-			_("Loading known commits in commit graph"), oids->nr);
-	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, i + 1);
-		commit = lookup_commit(the_repository, &oids->list[i]);
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+					_("Loading known commits in commit graph"),
+					ctx->oids.nr);
+	for (i = 0; i < ctx->oids.nr; i++) {
+		display_progress(ctx->progress, i + 1);
+		commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
 		if (commit)
 			commit->object.flags |= UNINTERESTING;
 	}
-	stop_progress(&progress);
+	stop_progress(&ctx->progress);
 
 	/*
-	 * As this loop runs, oids->nr may grow, but not more
+	 * As this loop runs, ctx->oids.nr may grow, but not more
 	 * than the number of missing commits in the reachable
 	 * closure.
 	 */
-	if (report_progress)
-		progress = start_delayed_progress(
-			_("Expanding reachable commits in commit graph"), oids->nr);
-	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, i + 1);
-		commit = lookup_commit(the_repository, &oids->list[i]);
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+					_("Expanding reachable commits in commit graph"),
+					ctx->oids.nr);
+	for (i = 0; i < ctx->oids.nr; i++) {
+		display_progress(ctx->progress, i + 1);
+		commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
 		if (commit && !parse_commit_no_graph(commit))
-			add_missing_parents(oids, commit);
+			add_missing_parents(ctx, commit);
 	}
-	stop_progress(&progress);
+	stop_progress(&ctx->progress);
 
-	if (report_progress)
-		progress = start_delayed_progress(
-			_("Clearing commit marks in commit graph"), oids->nr);
-	for (i = 0; i < oids->nr; i++) {
-		display_progress(progress, i + 1);
-		commit = lookup_commit(the_repository, &oids->list[i]);
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+					_("Clearing commit marks in commit graph"),
+					ctx->oids.nr);
+	for (i = 0; i < ctx->oids.nr; i++) {
+		display_progress(ctx->progress, i + 1);
+		commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
 		if (commit)
 			commit->object.flags &= ~UNINTERESTING;
 	}
-	stop_progress(&progress);
+	stop_progress(&ctx->progress);
 }
 
-static void compute_generation_numbers(struct packed_commit_list* commits,
-				       int report_progress)
+static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit_list *list = NULL;
-	struct progress *progress = NULL;
 
-	if (report_progress)
-		progress = start_progress(
-			_("Computing commit graph generation numbers"),
-			commits->nr);
-	for (i = 0; i < commits->nr; i++) {
-		display_progress(progress, i + 1);
-		if (commits->list[i]->generation != GENERATION_NUMBER_INFINITY &&
-		    commits->list[i]->generation != GENERATION_NUMBER_ZERO)
+	if (ctx->report_progress)
+		ctx->progress = start_progress(
+					_("Computing commit graph generation numbers"),
+					ctx->commits.nr);
+	for (i = 0; i < ctx->commits.nr; i++) {
+		display_progress(ctx->progress, i + 1);
+		if (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY &&
+		    ctx->commits.list[i]->generation != GENERATION_NUMBER_ZERO)
 			continue;
 
-		commit_list_insert(commits->list[i], &list);
+		commit_list_insert(ctx->commits.list[i], &list);
 		while (list) {
 			struct commit *current = list->item;
 			struct commit_list *parent;
@@ -845,7 +848,7 @@ static void compute_generation_numbers(struct packed_commit_list* commits,
 			}
 		}
 	}
-	stop_progress(&progress);
+	stop_progress(&ctx->progress);
 }
 
 static int add_ref_to_list(const char *refname,
@@ -858,207 +861,187 @@ static int add_ref_to_list(const char *refname,
 	return 0;
 }
 
-void write_commit_graph_reachable(const char *obj_dir, int append,
-				  int report_progress)
+int write_commit_graph_reachable(const char *obj_dir, unsigned int flags)
 {
 	struct string_list list = STRING_LIST_INIT_DUP;
+	int result;
 
 	for_each_ref(add_ref_to_list, &list);
-	write_commit_graph(obj_dir, NULL, &list, append, report_progress);
+	result = write_commit_graph(obj_dir, NULL, &list,
+				    flags);
 
 	string_list_clear(&list, 0);
+	return result;
 }
 
-void write_commit_graph(const char *obj_dir,
-			struct string_list *pack_indexes,
-			struct string_list *commit_hex,
-			int append, int report_progress)
+static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
+				struct string_list *pack_indexes)
 {
-	struct packed_oid_list oids;
-	struct packed_commit_list commits;
-	struct hashfile *f;
-	uint32_t i, count_distinct = 0;
-	char *graph_name;
-	struct lock_file lk = LOCK_INIT;
-	uint32_t chunk_ids[5];
-	uint64_t chunk_offsets[5];
-	int num_chunks;
-	int num_extra_edges;
-	struct commit_list *parent;
-	struct progress *progress = NULL;
-	const unsigned hashsz = the_hash_algo->rawsz;
-	uint64_t progress_cnt = 0;
+	uint32_t i;
 	struct strbuf progress_title = STRBUF_INIT;
-	unsigned long approx_nr_objects;
+	struct strbuf packname = STRBUF_INIT;
+	int dirlen;
 
-	if (!commit_graph_compatible(the_repository))
-		return;
-
-	oids.nr = 0;
-	approx_nr_objects = approximate_object_count();
-	oids.alloc = approx_nr_objects / 32;
-	oids.progress = NULL;
-	oids.progress_done = 0;
-
-	if (append) {
-		prepare_commit_graph_one(the_repository, obj_dir);
-		if (the_repository->objects->commit_graph)
-			oids.alloc += the_repository->objects->commit_graph->num_commits;
+	strbuf_addf(&packname, "%s/pack/", ctx->obj_dir);
+	dirlen = packname.len;
+	if (ctx->report_progress) {
+		strbuf_addf(&progress_title,
+			    Q_("Finding commits for commit graph in %d pack",
+			       "Finding commits for commit graph in %d packs",
+			       pack_indexes->nr),
+			    pack_indexes->nr);
+		ctx->progress = start_delayed_progress(progress_title.buf, 0);
+		ctx->progress_done = 0;
 	}
-
-	if (oids.alloc < 1024)
-		oids.alloc = 1024;
-	ALLOC_ARRAY(oids.list, oids.alloc);
-
-	if (append && the_repository->objects->commit_graph) {
-		struct commit_graph *commit_graph =
-			the_repository->objects->commit_graph;
-		for (i = 0; i < commit_graph->num_commits; i++) {
-			const unsigned char *hash = commit_graph->chunk_oid_lookup +
-				commit_graph->hash_len * i;
-			hashcpy(oids.list[oids.nr++].hash, hash);
+	for (i = 0; i < pack_indexes->nr; i++) {
+		struct packed_git *p;
+		strbuf_setlen(&packname, dirlen);
+		strbuf_addstr(&packname, pack_indexes->items[i].string);
+		p = add_packed_git(packname.buf, packname.len, 1);
+		if (!p) {
+			error(_("error adding pack %s"), packname.buf);
+			return -1;
 		}
-	}
-
-	if (pack_indexes) {
-		struct strbuf packname = STRBUF_INIT;
-		int dirlen;
-		strbuf_addf(&packname, "%s/pack/", obj_dir);
-		dirlen = packname.len;
-		if (report_progress) {
-			strbuf_addf(&progress_title,
-				    Q_("Finding commits for commit graph in %d pack",
-				       "Finding commits for commit graph in %d packs",
-				       pack_indexes->nr),
-				    pack_indexes->nr);
-			oids.progress = start_delayed_progress(progress_title.buf, 0);
-			oids.progress_done = 0;
+		if (open_pack_index(p)) {
+			error(_("error opening index for %s"), packname.buf);
+			return -1;
 		}
-		for (i = 0; i < pack_indexes->nr; i++) {
-			struct packed_git *p;
-			strbuf_setlen(&packname, dirlen);
-			strbuf_addstr(&packname, pack_indexes->items[i].string);
-			p = add_packed_git(packname.buf, packname.len, 1);
-			if (!p)
-				die(_("error adding pack %s"), packname.buf);
-			if (open_pack_index(p))
-				die(_("error opening index for %s"), packname.buf);
-			for_each_object_in_pack(p, add_packed_commits, &oids,
-						FOR_EACH_OBJECT_PACK_ORDER);
-			close_pack(p);
-			free(p);
-		}
-		stop_progress(&oids.progress);
-		strbuf_reset(&progress_title);
-		strbuf_release(&packname);
+		for_each_object_in_pack(p, add_packed_commits, ctx,
+					FOR_EACH_OBJECT_PACK_ORDER);
+		close_pack(p);
+		free(p);
 	}
 
-	if (commit_hex) {
-		if (report_progress) {
-			strbuf_addf(&progress_title,
-				    Q_("Finding commits for commit graph from %d ref",
-				       "Finding commits for commit graph from %d refs",
-				       commit_hex->nr),
-				    commit_hex->nr);
-			progress = start_delayed_progress(progress_title.buf,
-							  commit_hex->nr);
-		}
-		for (i = 0; i < commit_hex->nr; i++) {
-			const char *end;
-			struct object_id oid;
-			struct commit *result;
+	stop_progress(&ctx->progress);
+	strbuf_reset(&progress_title);
+	strbuf_release(&packname);
 
-			display_progress(progress, i + 1);
-			if (commit_hex->items[i].string &&
-			    parse_oid_hex(commit_hex->items[i].string, &oid, &end))
-				continue;
+	return 0;
+}
 
-			result = lookup_commit_reference_gently(the_repository, &oid, 1);
+static void fill_oids_from_commit_hex(struct write_commit_graph_context *ctx,
+				      struct string_list *commit_hex)
+{
+	uint32_t i;
+	struct strbuf progress_title = STRBUF_INIT;
 
-			if (result) {
-				ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc);
-				oidcpy(&oids.list[oids.nr], &(result->object.oid));
-				oids.nr++;
-			}
-		}
-		stop_progress(&progress);
-		strbuf_reset(&progress_title);
+	if (ctx->report_progress) {
+		strbuf_addf(&progress_title,
+			    Q_("Finding commits for commit graph from %d ref",
+			       "Finding commits for commit graph from %d refs",
+			       commit_hex->nr),
+			    commit_hex->nr);
+		ctx->progress = start_delayed_progress(
+					progress_title.buf,
+					commit_hex->nr);
 	}
+	for (i = 0; i < commit_hex->nr; i++) {
+		const char *end;
+		struct object_id oid;
+		struct commit *result;
 
-	if (!pack_indexes && !commit_hex) {
-		if (report_progress)
-			oids.progress = start_delayed_progress(
-				_("Finding commits for commit graph among packed objects"),
-				approx_nr_objects);
-		for_each_packed_object(add_packed_commits, &oids,
-				       FOR_EACH_OBJECT_PACK_ORDER);
-		if (oids.progress_done < approx_nr_objects)
-			display_progress(oids.progress, approx_nr_objects);
-		stop_progress(&oids.progress);
-	}
-
-	close_reachable(&oids, report_progress);
-
-	if (report_progress)
-		progress = start_delayed_progress(
-			_("Counting distinct commits in commit graph"),
-			oids.nr);
-	display_progress(progress, 0); /* TODO: Measure QSORT() progress */
-	QSORT(oids.list, oids.nr, commit_compare);
-	count_distinct = 1;
-	for (i = 1; i < oids.nr; i++) {
-		display_progress(progress, i + 1);
-		if (!oideq(&oids.list[i - 1], &oids.list[i]))
-			count_distinct++;
-	}
-	stop_progress(&progress);
-
-	if (count_distinct >= GRAPH_EDGE_LAST_MASK)
-		die(_("the commit graph format cannot write %d commits"), count_distinct);
-
-	commits.nr = 0;
-	commits.alloc = count_distinct;
-	ALLOC_ARRAY(commits.list, commits.alloc);
-
-	num_extra_edges = 0;
-	if (report_progress)
-		progress = start_delayed_progress(
-			_("Finding extra edges in commit graph"),
-			oids.nr);
-	for (i = 0; i < oids.nr; i++) {
-		int num_parents = 0;
-		display_progress(progress, i + 1);
-		if (i > 0 && oideq(&oids.list[i - 1], &oids.list[i]))
+		display_progress(ctx->progress, i + 1);
+		if (commit_hex->items[i].string &&
+		    parse_oid_hex(commit_hex->items[i].string, &oid, &end))
 			continue;
 
-		commits.list[commits.nr] = lookup_commit(the_repository, &oids.list[i]);
-		parse_commit_no_graph(commits.list[commits.nr]);
+		result = lookup_commit_reference_gently(ctx->r, &oid, 1);
 
-		for (parent = commits.list[commits.nr]->parents;
+		if (result) {
+			ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+			oidcpy(&ctx->oids.list[ctx->oids.nr], &(result->object.oid));
+			ctx->oids.nr++;
+		}
+	}
+	stop_progress(&ctx->progress);
+	strbuf_release(&progress_title);
+}
+
+static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx)
+{
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+			_("Finding commits for commit graph among packed objects"),
+			ctx->approx_nr_objects);
+	for_each_packed_object(add_packed_commits, ctx,
+			       FOR_EACH_OBJECT_PACK_ORDER);
+	if (ctx->progress_done < ctx->approx_nr_objects)
+		display_progress(ctx->progress, ctx->approx_nr_objects);
+	stop_progress(&ctx->progress);
+}
+
+static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
+{
+	uint32_t i, count_distinct = 1;
+
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+			_("Counting distinct commits in commit graph"),
+			ctx->oids.nr);
+	display_progress(ctx->progress, 0); /* TODO: Measure QSORT() progress */
+	QSORT(ctx->oids.list, ctx->oids.nr, commit_compare);
+
+	for (i = 1; i < ctx->oids.nr; i++) {
+		display_progress(ctx->progress, i + 1);
+		if (!oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i]))
+			count_distinct++;
+	}
+	stop_progress(&ctx->progress);
+
+	return count_distinct;
+}
+
+static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
+{
+	uint32_t i;
+	struct commit_list *parent;
+
+	ctx->num_extra_edges = 0;
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+			_("Finding extra edges in commit graph"),
+			ctx->oids.nr);
+	for (i = 0; i < ctx->oids.nr; i++) {
+		int num_parents = 0;
+		display_progress(ctx->progress, i + 1);
+		if (i > 0 && oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i]))
+			continue;
+
+		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
+		parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
+
+		for (parent = ctx->commits.list[ctx->commits.nr]->parents;
 		     parent; parent = parent->next)
 			num_parents++;
 
 		if (num_parents > 2)
-			num_extra_edges += num_parents - 1;
+			ctx->num_extra_edges += num_parents - 1;
 
-		commits.nr++;
+		ctx->commits.nr++;
 	}
-	num_chunks = num_extra_edges ? 4 : 3;
-	stop_progress(&progress);
+	stop_progress(&ctx->progress);
+}
 
-	if (commits.nr >= GRAPH_EDGE_LAST_MASK)
-		die(_("too many commits to write graph"));
+static int write_commit_graph_file(struct write_commit_graph_context *ctx)
+{
+	uint32_t i;
+	struct hashfile *f;
+	struct lock_file lk = LOCK_INIT;
+	uint32_t chunk_ids[5];
+	uint64_t chunk_offsets[5];
+	const unsigned hashsz = the_hash_algo->rawsz;
+	struct strbuf progress_title = STRBUF_INIT;
+	int num_chunks = ctx->num_extra_edges ? 4 : 3;
 
-	compute_generation_numbers(&commits, report_progress);
-
-	graph_name = get_commit_graph_filename(obj_dir);
-	if (safe_create_leading_directories(graph_name)) {
-		UNLEAK(graph_name);
-		die_errno(_("unable to create leading directories of %s"),
-			  graph_name);
+	ctx->graph_name = get_commit_graph_filename(ctx->obj_dir);
+	if (safe_create_leading_directories(ctx->graph_name)) {
+		UNLEAK(ctx->graph_name);
+		error(_("unable to create leading directories of %s"),
+			ctx->graph_name);
+		return -1;
 	}
 
-	hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR);
+	hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR);
 	f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
 
 	hashwrite_be32(f, GRAPH_SIGNATURE);
@@ -1071,7 +1054,7 @@ void write_commit_graph(const char *obj_dir,
 	chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT;
 	chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
 	chunk_ids[2] = GRAPH_CHUNKID_DATA;
-	if (num_extra_edges)
+	if (ctx->num_extra_edges)
 		chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES;
 	else
 		chunk_ids[3] = 0;
@@ -1079,9 +1062,9 @@ void write_commit_graph(const char *obj_dir,
 
 	chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
 	chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
-	chunk_offsets[2] = chunk_offsets[1] + hashsz * commits.nr;
-	chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * commits.nr;
-	chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges;
+	chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr;
+	chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr;
+	chunk_offsets[4] = chunk_offsets[3] + 4 * ctx->num_extra_edges;
 
 	for (i = 0; i <= num_chunks; i++) {
 		uint32_t chunk_write[3];
@@ -1092,31 +1075,113 @@ void write_commit_graph(const char *obj_dir,
 		hashwrite(f, chunk_write, 12);
 	}
 
-	if (report_progress) {
+	if (ctx->report_progress) {
 		strbuf_addf(&progress_title,
 			    Q_("Writing out commit graph in %d pass",
 			       "Writing out commit graph in %d passes",
 			       num_chunks),
 			    num_chunks);
-		progress = start_delayed_progress(
+		ctx->progress = start_delayed_progress(
 			progress_title.buf,
-			num_chunks * commits.nr);
+			num_chunks * ctx->commits.nr);
 	}
-	write_graph_chunk_fanout(f, commits.list, commits.nr, progress, &progress_cnt);
-	write_graph_chunk_oids(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
-	write_graph_chunk_data(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
-	if (num_extra_edges)
-		write_graph_chunk_extra_edges(f, commits.list, commits.nr, progress, &progress_cnt);
-	stop_progress(&progress);
+	write_graph_chunk_fanout(f, ctx);
+	write_graph_chunk_oids(f, hashsz, ctx);
+	write_graph_chunk_data(f, hashsz, ctx);
+	if (ctx->num_extra_edges)
+		write_graph_chunk_extra_edges(f, ctx);
+	stop_progress(&ctx->progress);
 	strbuf_release(&progress_title);
 
-	close_commit_graph(the_repository);
+	close_commit_graph(ctx->r);
 	finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
 	commit_lock_file(&lk);
 
-	free(graph_name);
-	free(commits.list);
-	free(oids.list);
+	return 0;
+}
+
+int write_commit_graph(const char *obj_dir,
+		       struct string_list *pack_indexes,
+		       struct string_list *commit_hex,
+		       unsigned int flags)
+{
+	struct write_commit_graph_context *ctx;
+	uint32_t i, count_distinct = 0;
+	int res = 0;
+
+	if (!commit_graph_compatible(the_repository))
+		return 0;
+
+	ctx = xcalloc(1, sizeof(struct write_commit_graph_context));
+	ctx->r = the_repository;
+	ctx->obj_dir = obj_dir;
+	ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0;
+	ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0;
+
+	ctx->approx_nr_objects = approximate_object_count();
+	ctx->oids.alloc = ctx->approx_nr_objects / 32;
+
+	if (ctx->append) {
+		prepare_commit_graph_one(ctx->r, ctx->obj_dir);
+		if (ctx->r->objects->commit_graph)
+			ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits;
+	}
+
+	if (ctx->oids.alloc < 1024)
+		ctx->oids.alloc = 1024;
+	ALLOC_ARRAY(ctx->oids.list, ctx->oids.alloc);
+
+	if (ctx->append && ctx->r->objects->commit_graph) {
+		struct commit_graph *g = ctx->r->objects->commit_graph;
+		for (i = 0; i < g->num_commits; i++) {
+			const unsigned char *hash = g->chunk_oid_lookup + g->hash_len * i;
+			hashcpy(ctx->oids.list[ctx->oids.nr++].hash, hash);
+		}
+	}
+
+	if (pack_indexes) {
+		if ((res = fill_oids_from_packs(ctx, pack_indexes)))
+			goto cleanup;
+	}
+
+	if (commit_hex)
+		fill_oids_from_commit_hex(ctx, commit_hex);
+
+	if (!pack_indexes && !commit_hex)
+		fill_oids_from_all_packs(ctx);
+
+	close_reachable(ctx);
+
+	count_distinct = count_distinct_commits(ctx);
+
+	if (count_distinct >= GRAPH_EDGE_LAST_MASK) {
+		error(_("the commit graph format cannot write %d commits"), count_distinct);
+		res = -1;
+		goto cleanup;
+	}
+
+	ctx->commits.alloc = count_distinct;
+	ALLOC_ARRAY(ctx->commits.list, ctx->commits.alloc);
+
+	copy_oids_to_commits(ctx);
+
+	if (ctx->commits.nr >= GRAPH_EDGE_LAST_MASK) {
+		error(_("too many commits to write graph"));
+		res = -1;
+		goto cleanup;
+	}
+
+	compute_generation_numbers(ctx);
+
+	res = write_commit_graph_file(ctx);
+
+cleanup:
+	free(ctx->graph_name);
+	free(ctx->commits.list);
+	free(ctx->oids.list);
+	free(ctx);
+
+	return res;
 }
 
 #define VERIFY_COMMIT_GRAPH_ERROR_HASH 2

commit-graph.h

@@ -65,12 +65,20 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
  */
 int generation_numbers_enabled(struct repository *r);
 
-void write_commit_graph_reachable(const char *obj_dir, int append,
-				  int report_progress);
-void write_commit_graph(const char *obj_dir,
-			struct string_list *pack_indexes,
-			struct string_list *commit_hex,
-			int append, int report_progress);
+#define COMMIT_GRAPH_APPEND     (1 << 0)
+#define COMMIT_GRAPH_PROGRESS   (1 << 1)
+
+/*
+ * The write_commit_graph* methods return zero on success
+ * and a negative value on failure. Note that if the repository
+ * is not compatible with the commit-graph feature, then the
+ * methods will return 0 without writing a commit-graph.
+ */
+int write_commit_graph_reachable(const char *obj_dir, unsigned int flags);
+int write_commit_graph(const char *obj_dir,
+		       struct string_list *pack_indexes,
+		       struct string_list *commit_hex,
+		       unsigned int flags);
 
 int verify_commit_graph(struct repository *r, struct commit_graph *g);
 

commit.c

@@ -449,7 +449,7 @@ int parse_commit_buffer(struct repository *r, struct commit *item, const void *b
 	item->date = parse_commit_date(bufptr, tail);
 
 	if (check_graph)
-		load_commit_graph_info(the_repository, item);
+		load_commit_graph_info(r, item);
 
 	return 0;
 }

t/t5318-commit-graph.sh

@@ -23,6 +23,14 @@ test_expect_success 'write graph with no packs' '
 	test_path_is_file info/commit-graph
 '
 
+test_expect_success 'close with correct error on bad input' '
+	cd "$TRASH_DIRECTORY/full" &&
+	echo doesnotexist >in &&
+	{ git commit-graph write --stdin-packs <in 2>stderr; ret=$?; } &&
+	test "$ret" = 1 &&
+	test_i18ngrep "error adding pack" stderr
+'
+
 test_expect_success 'create commits and repack' '
 	cd "$TRASH_DIRECTORY/full" &&
 	for i in $(test_seq 3)