Compute and use generation numbers

Documentation/technical/commit-graph.txt

@@ -77,6 +77,29 @@ in the commit graph. We can treat these commits as having "infinite"
 generation number and walk until reaching commits with known generation
 number.
 
+We use the macro GENERATION_NUMBER_INFINITY = 0xFFFFFFFF to mark commits not
+in the commit-graph file. If a commit-graph file was written by a version
+of Git that did not compute generation numbers, then those commits will
+have generation number represented by the macro GENERATION_NUMBER_ZERO = 0.
+
+Since the commit-graph file is closed under reachability, we can guarantee
+the following weaker condition on all commits:
+
+    If A and B are commits with generation numbers N amd M, respectively,
+    and N < M, then A cannot reach B.
+
+Note how the strict inequality differs from the inequality when we have
+fully-computed generation numbers. Using strict inequality may result in
+walking a few extra commits, but the simplicity in dealing with commits
+with generation number *_INFINITY or *_ZERO is valuable.
+
+We use the macro GENERATION_NUMBER_MAX = 0x3FFFFFFF to for commits whose
+generation numbers are computed to be at least this value. We limit at
+this value since it is the largest value that can be stored in the
+commit-graph file using the 30 bits available to generation numbers. This
+presents another case where a commit can have generation number equal to
+that of a parent.
+
 Design Details
 --------------
 
@@ -98,18 +121,14 @@ Future Work
 - The 'commit-graph' subcommand does not have a "verify" mode that is
   necessary for integration with fsck.
 
-- The file format includes room for precomputed generation numbers. These
-  are not currently computed, so all generation numbers will be marked as
-  0 (or "uncomputed"). A later patch will include this calculation.
-
 - 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:
 
-    - paint_down_to_common()
     - 'log --topo-order'
+    - 'tag --merged'
 
 - Currently, parse_commit_gently() requires filling in the root tree
   object for a commit. This passes through lookup_tree() and consequently

alloc.c

@@ -94,6 +94,7 @@ void *alloc_commit_node(void)
 	c->object.type = OBJ_COMMIT;
 	c->index = alloc_commit_index();
 	c->graph_pos = COMMIT_NOT_FROM_GRAPH;
+	c->generation = GENERATION_NUMBER_INFINITY;
 	return c;
 }
 

builtin/merge.c

@@ -1148,14 +1148,15 @@ int cmd_merge(int argc, const char **argv, const char *prefix)
 	branch = branch_to_free = resolve_refdup("HEAD", 0, &head_oid, NULL);
 	if (branch)
 		skip_prefix(branch, "refs/heads/", &branch);
+
+	init_diff_ui_defaults();
+	git_config(git_merge_config, NULL);
+
 	if (!branch || is_null_oid(&head_oid))
 		head_commit = NULL;
 	else
 		head_commit = lookup_commit_or_die(&head_oid, "HEAD");
 
-	init_diff_ui_defaults();
-	git_config(git_merge_config, NULL);
-
 	if (branch_mergeoptions)
 		parse_branch_merge_options(branch_mergeoptions);
 	argc = parse_options(argc, argv, prefix, builtin_merge_options,

commit-graph.c

@@ -245,6 +245,13 @@ static struct commit_list **insert_parent_or_die(struct commit_graph *g,
 	return &commit_list_insert(c, pptr)->next;
 }
 
+static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, uint32_t pos)
+{
+	const unsigned char *commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * pos;
+	item->graph_pos = pos;
+	item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+}
+
 static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos)
 {
 	uint32_t edge_value;
@@ -262,6 +269,8 @@ static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uin
 	date_low = get_be32(commit_data + g->hash_len + 12);
 	item->date = (timestamp_t)((date_high << 32) | date_low);
 
+	item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+
 	pptr = &item->parents;
 
 	edge_value = get_be32(commit_data + g->hash_len);
@@ -290,31 +299,40 @@ static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uin
 	return 1;
 }
 
+static int find_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t *pos)
+{
+	if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) {
+		*pos = item->graph_pos;
+		return 1;
+	} else {
+		return bsearch_graph(g, &(item->object.oid), pos);
+	}
+}
+
 int parse_commit_in_graph(struct commit *item)
 {
+	uint32_t pos;
+
 	if (!core_commit_graph)
 		return 0;
 	if (item->object.parsed)
 		return 1;
-
 	prepare_commit_graph();
-	if (commit_graph) {
-		uint32_t pos;
-		int found;
-		if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) {
-			pos = item->graph_pos;
-			found = 1;
-		} else {
-			found = bsearch_graph(commit_graph, &(item->object.oid), &pos);
-		}
-
-		if (found)
-			return fill_commit_in_graph(item, commit_graph, pos);
-	}
-
+	if (commit_graph && find_commit_in_graph(item, commit_graph, &pos))
+		return fill_commit_in_graph(item, commit_graph, pos);
 	return 0;
 }
 
+void load_commit_graph_info(struct commit *item)
+{
+	uint32_t pos;
+	if (!core_commit_graph)
+		return;
+	prepare_commit_graph();
+	if (commit_graph && find_commit_in_graph(item, commit_graph, &pos))
+		fill_commit_graph_info(item, commit_graph, pos);
+}
+
 static struct tree *load_tree_for_commit(struct commit_graph *g, struct commit *c)
 {
 	struct object_id oid;
@@ -437,6 +455,8 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 		else
 			packedDate[0] = 0;
 
+		packedDate[0] |= htonl((*list)->generation << 2);
+
 		packedDate[1] = htonl((*list)->date);
 		hashwrite(f, packedDate, 8);
 
@@ -569,6 +589,45 @@ static void close_reachable(struct packed_oid_list *oids)
 	}
 }
 
+static void compute_generation_numbers(struct packed_commit_list* commits)
+{
+	int i;
+	struct commit_list *list = NULL;
+
+	for (i = 0; i < commits->nr; i++) {
+		if (commits->list[i]->generation != GENERATION_NUMBER_INFINITY &&
+		    commits->list[i]->generation != GENERATION_NUMBER_ZERO)
+			continue;
+
+		commit_list_insert(commits->list[i], &list);
+		while (list) {
+			struct commit *current = list->item;
+			struct commit_list *parent;
+			int all_parents_computed = 1;
+			uint32_t max_generation = 0;
+
+			for (parent = current->parents; parent; parent = parent->next) {
+				if (parent->item->generation == GENERATION_NUMBER_INFINITY ||
+				    parent->item->generation == GENERATION_NUMBER_ZERO) {
+					all_parents_computed = 0;
+					commit_list_insert(parent->item, &list);
+					break;
+				} else if (parent->item->generation > max_generation) {
+					max_generation = parent->item->generation;
+				}
+			}
+
+			if (all_parents_computed) {
+				current->generation = max_generation + 1;
+				pop_commit(&list);
+
+				if (current->generation > GENERATION_NUMBER_MAX)
+					current->generation = GENERATION_NUMBER_MAX;
+			}
+		}
+	}
+}
+
 void write_commit_graph(const char *obj_dir,
 			const char **pack_indexes,
 			int nr_packs,
@@ -692,6 +751,8 @@ void write_commit_graph(const char *obj_dir,
 	if (commits.nr >= GRAPH_PARENT_MISSING)
 		die(_("too many commits to write graph"));
 
+	compute_generation_numbers(&commits);
+
 	graph_name = get_commit_graph_filename(obj_dir);
 	fd = hold_lock_file_for_update(&lk, graph_name, 0);
 

commit-graph.h

@@ -17,6 +17,14 @@ char *get_commit_graph_filename(const char *obj_dir);
  */
 int parse_commit_in_graph(struct commit *item);
 
+/*
+ * It is possible that we loaded commit contents from the commit buffer,
+ * but we also want to ensure the commit-graph content is correctly
+ * checked and filled. Fill the graph_pos and generation members of
+ * the given commit.
+ */
+void load_commit_graph_info(struct commit *item);
+
 struct tree *get_commit_tree_in_graph(const struct commit *c);
 
 struct commit_graph {

commit.c

@@ -331,7 +331,7 @@ const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep)
 	return ret;
 }
 
-int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size)
+int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size, int check_graph)
 {
 	const char *tail = buffer;
 	const char *bufptr = buffer;
@@ -386,6 +386,9 @@ int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long s
 	}
 	item->date = parse_commit_date(bufptr, tail);
 
+	if (check_graph)
+		load_commit_graph_info(item);
+
 	return 0;
 }
 
@@ -412,7 +415,7 @@ int parse_commit_gently(struct commit *item, int quiet_on_missing)
 		return error("Object %s not a commit",
 			     oid_to_hex(&item->object.oid));
 	}
-	ret = parse_commit_buffer(item, buffer, size);
+	ret = parse_commit_buffer(item, buffer, size, 0);
 	if (save_commit_buffer && !ret) {
 		set_commit_buffer(item, buffer, size);
 		return 0;
@@ -640,6 +643,24 @@ static int compare_commits_by_author_date(const void *a_, const void *b_,
 	return 0;
 }
 
+int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, void *unused)
+{
+	const struct commit *a = a_, *b = b_;
+
+	/* newer commits first */
+	if (a->generation < b->generation)
+		return 1;
+	else if (a->generation > b->generation)
+		return -1;
+
+	/* use date as a heuristic when generations are equal */
+	if (a->date < b->date)
+		return 1;
+	else if (a->date > b->date)
+		return -1;
+	return 0;
+}
+
 int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused)
 {
 	const struct commit *a = a_, *b = b_;
@@ -787,11 +808,14 @@ static int queue_has_nonstale(struct prio_queue *queue)
 }
 
 /* all input commits in one and twos[] must have been parsed! */
-static struct commit_list *paint_down_to_common(struct commit *one, int n, struct commit **twos)
+static struct commit_list *paint_down_to_common(struct commit *one, int n,
+						struct commit **twos,
+						int min_generation)
 {
-	struct prio_queue queue = { compare_commits_by_commit_date };
+	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
 	struct commit_list *result = NULL;
 	int i;
+	uint32_t last_gen = GENERATION_NUMBER_INFINITY;
 
 	one->object.flags |= PARENT1;
 	if (!n) {
@@ -810,6 +834,15 @@ static struct commit_list *paint_down_to_common(struct commit *one, int n, struc
 		struct commit_list *parents;
 		int flags;
 
+		if (commit->generation > last_gen)
+			BUG("bad generation skip %8x > %8x at %s",
+			    commit->generation, last_gen,
+			    oid_to_hex(&commit->object.oid));
+		last_gen = commit->generation;
+
+		if (commit->generation < min_generation)
+			break;
+
 		flags = commit->object.flags & (PARENT1 | PARENT2 | STALE);
 		if (flags == (PARENT1 | PARENT2)) {
 			if (!(commit->object.flags & RESULT)) {
@@ -858,7 +891,7 @@ static struct commit_list *merge_bases_many(struct commit *one, int n, struct co
 			return NULL;
 	}
 
-	list = paint_down_to_common(one, n, twos);
+	list = paint_down_to_common(one, n, twos, 0);
 
 	while (list) {
 		struct commit *commit = pop_commit(&list);
@@ -916,6 +949,7 @@ static int remove_redundant(struct commit **array, int cnt)
 		parse_commit(array[i]);
 	for (i = 0; i < cnt; i++) {
 		struct commit_list *common;
+		uint32_t min_generation = array[i]->generation;
 
 		if (redundant[i])
 			continue;
@@ -924,8 +958,12 @@ static int remove_redundant(struct commit **array, int cnt)
 				continue;
 			filled_index[filled] = j;
 			work[filled++] = array[j];
+
+			if (array[j]->generation < min_generation)
+				min_generation = array[j]->generation;
 		}
-		common = paint_down_to_common(array[i], filled, work);
+		common = paint_down_to_common(array[i], filled, work,
+					      min_generation);
 		if (array[i]->object.flags & PARENT2)
 			redundant[i] = 1;
 		for (j = 0; j < filled; j++)
@@ -1035,14 +1073,21 @@ int in_merge_bases_many(struct commit *commit, int nr_reference, struct commit *
 {
 	struct commit_list *bases;
 	int ret = 0, i;
+	uint32_t min_generation = GENERATION_NUMBER_INFINITY;
 
 	if (parse_commit(commit))
 		return ret;
-	for (i = 0; i < nr_reference; i++)
+	for (i = 0; i < nr_reference; i++) {
 		if (parse_commit(reference[i]))
 			return ret;
+		if (reference[i]->generation < min_generation)
+			min_generation = reference[i]->generation;
+	}
+
+	if (commit->generation > min_generation)
+		return ret;
 
-	bases = paint_down_to_common(commit, nr_reference, reference);
+	bases = paint_down_to_common(commit, nr_reference, reference, commit->generation);
 	if (commit->object.flags & PARENT2)
 		ret = 1;
 	clear_commit_marks(commit, all_flags);