Merge branch 'ak/commit-graph-to-slab'

A few fields in "struct commit" that do not have to always be
present have been moved to commit slabs.

* ak/commit-graph-to-slab:
  commit-graph: minimize commit_graph_data_slab access
  commit: move members graph_pos, generation to a slab
  commit-graph: introduce commit_graph_data_slab
  object: drop parsed_object_pool->commit_count

Author: gitster

alloc.c

@@ -99,23 +99,27 @@ void *alloc_object_node(struct repository *r)
 	return obj;
 }
 
-static unsigned int alloc_commit_index(struct repository *r)
+/*
+ * The returned count is to be used as an index into commit slabs,
+ * that are *NOT* maintained per repository, and that is why a single
+ * global counter is used.
+ */
+static unsigned int alloc_commit_index(void)
 {
-	return r->parsed_objects->commit_count++;
+	static unsigned int parsed_commits_count;
+	return parsed_commits_count++;
 }
 
-void init_commit_node(struct repository *r, struct commit *c)
+void init_commit_node(struct commit *c)
 {
 	c->object.type = OBJ_COMMIT;
-	c->index = alloc_commit_index(r);
-	c->graph_pos = COMMIT_NOT_FROM_GRAPH;
-	c->generation = GENERATION_NUMBER_INFINITY;
+	c->index = alloc_commit_index();
 }
 
 void *alloc_commit_node(struct repository *r)
 {
 	struct commit *c = alloc_node(r->parsed_objects->commit_state, sizeof(struct commit));
-	init_commit_node(r, c);
+	init_commit_node(c);
 	return c;
 }
 

alloc.h

@@ -9,7 +9,7 @@ struct repository;
 
 void *alloc_blob_node(struct repository *r);
 void *alloc_tree_node(struct repository *r);
-void init_commit_node(struct repository *r, struct commit *c);
+void init_commit_node(struct commit *c);
 void *alloc_commit_node(struct repository *r);
 void *alloc_tag_node(struct repository *r);
 void *alloc_object_node(struct repository *r);

blame.c

@@ -1272,7 +1272,7 @@ static int maybe_changed_path(struct repository *r,
 	if (!bd)
 		return 1;
 
-	if (origin->commit->generation == GENERATION_NUMBER_INFINITY)
+	if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
 		return 1;
 
 	filter = get_bloom_filter(r, origin->commit, 0);

blob.c

@@ -10,7 +10,7 @@ struct blob *lookup_blob(struct repository *r, const struct object_id *oid)
 	struct object *obj = lookup_object(r, oid);
 	if (!obj)
 		return create_object(r, oid, alloc_blob_node(r));
-	return object_as_type(r, obj, OBJ_BLOB, 0);
+	return object_as_type(obj, OBJ_BLOB, 0);
 }
 
 int parse_blob_buffer(struct blob *item, void *buffer, unsigned long size)

bloom.c

@@ -33,15 +33,16 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 					struct commit *c)
 {
 	uint32_t lex_pos, start_index, end_index;
+	uint32_t graph_pos = commit_graph_position(c);
 
-	while (c->graph_pos < g->num_commits_in_base)
+	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
 	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
-	lex_pos = c->graph_pos - g->num_commits_in_base;
+	lex_pos = graph_pos - g->num_commits_in_base;
 
 	end_index = get_be32(g->chunk_bloom_indexes + 4 * lex_pos);
 
@@ -193,7 +194,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
-		if (c->graph_pos != COMMIT_NOT_FROM_GRAPH &&
+		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
 			r->objects->commit_graph->chunk_bloom_indexes) {
 			if (load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
 				return filter;

builtin/commit-graph.c

@@ -154,7 +154,7 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 			   NULL, 0);
 	if (!result)
 		return error(_("invalid object: %s"), hash);
-	else if (object_as_type(the_repository, result, OBJ_COMMIT, 1))
+	else if (object_as_type(result, OBJ_COMMIT, 1))
 		oidset_insert(commits, &result->oid);
 
 	display_progress(progress, oidset_size(commits));

builtin/fsck.c

@@ -241,7 +241,7 @@ static void mark_unreachable_referents(const struct object_id *oid)
 		enum object_type type = oid_object_info(the_repository,
 							&obj->oid, NULL);
 		if (type > 0)
-			object_as_type(the_repository, obj, type, 0);
+			object_as_type(obj, type, 0);
 	}
 
 	options.walk = mark_used;

commit-graph.c

@@ -87,15 +87,69 @@ static int commit_pos_cmp(const void *va, const void *vb)
 	       commit_pos_at(&commit_pos, b);
 }
 
+define_commit_slab(commit_graph_data_slab, struct commit_graph_data);
+static struct commit_graph_data_slab commit_graph_data_slab =
+	COMMIT_SLAB_INIT(1, commit_graph_data_slab);
+
+uint32_t commit_graph_position(const struct commit *c)
+{
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	return data ? data->graph_pos : COMMIT_NOT_FROM_GRAPH;
+}
+
+uint32_t commit_graph_generation(const struct commit *c)
+{
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	if (!data)
+		return GENERATION_NUMBER_INFINITY;
+	else if (data->graph_pos == COMMIT_NOT_FROM_GRAPH)
+		return GENERATION_NUMBER_INFINITY;
+
+	return data->generation;
+}
+
+static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
+{
+	unsigned int i, nth_slab;
+	struct commit_graph_data *data =
+		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
+
+	if (data)
+		return data;
+
+	nth_slab = c->index / commit_graph_data_slab.slab_size;
+	data = commit_graph_data_slab_at(&commit_graph_data_slab, c);
+
+	/*
+	 * commit-slab initializes elements with zero, overwrite this with
+	 * COMMIT_NOT_FROM_GRAPH for graph_pos.
+	 *
+	 * We avoid initializing generation with checking if graph position
+	 * is not COMMIT_NOT_FROM_GRAPH.
+	 */
+	for (i = 0; i < commit_graph_data_slab.slab_size; i++) {
+		commit_graph_data_slab.slab[nth_slab][i].graph_pos =
+			COMMIT_NOT_FROM_GRAPH;
+	}
+
+	return data;
+}
+
 static int commit_gen_cmp(const void *va, const void *vb)
 {
 	const struct commit *a = *(const struct commit **)va;
 	const struct commit *b = *(const struct commit **)vb;
 
+	uint32_t generation_a = commit_graph_generation(a);
+	uint32_t generation_b = commit_graph_generation(b);
 	/* lower generation commits first */
-	if (a->generation < b->generation)
+	if (generation_a < generation_b)
 		return -1;
-	else if (a->generation > b->generation)
+	else if (generation_a > generation_b)
 		return 1;
 
 	/* use date as a heuristic when generations are equal */
@@ -670,22 +724,25 @@ static struct commit_list **insert_parent_or_die(struct repository *r,
 	c = lookup_commit(r, &oid);
 	if (!c)
 		die(_("could not find commit %s"), oid_to_hex(&oid));
-	c->graph_pos = pos;
+	commit_graph_data_at(c)->graph_pos = pos;
 	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;
+	struct commit_graph_data *graph_data;
 	uint32_t lex_index;
 
 	while (pos < g->num_commits_in_base)
 		g = g->base_graph;
 
 	lex_index = pos - g->num_commits_in_base;
 	commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * lex_index;
-	item->graph_pos = pos;
-	item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+
+	graph_data = commit_graph_data_at(item);
+	graph_data->graph_pos = pos;
+	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
 }
 
 static inline void set_commit_tree(struct commit *c, struct tree *t)
@@ -701,6 +758,7 @@ static int fill_commit_in_graph(struct repository *r,
 	uint32_t *parent_data_ptr;
 	uint64_t date_low, date_high;
 	struct commit_list **pptr;
+	struct commit_graph_data *graph_data;
 	const unsigned char *commit_data;
 	uint32_t lex_index;
 
@@ -714,7 +772,8 @@ static int fill_commit_in_graph(struct repository *r,
 	 * Store the "full" position, but then use the
 	 * "local" position for the rest of the calculation.
 	 */
-	item->graph_pos = pos;
+	graph_data = commit_graph_data_at(item);
+	graph_data->graph_pos = pos;
 	lex_index = pos - g->num_commits_in_base;
 
 	commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index;
@@ -727,7 +786,7 @@ static int fill_commit_in_graph(struct repository *r,
 	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;
+	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
 
 	pptr = &item->parents;
 
@@ -759,8 +818,9 @@ static int fill_commit_in_graph(struct repository *r,
 
 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;
+	uint32_t graph_pos = commit_graph_position(item);
+	if (graph_pos != COMMIT_NOT_FROM_GRAPH) {
+		*pos = graph_pos;
 		return 1;
 	} else {
 		struct commit_graph *cur_g = g;
@@ -815,12 +875,13 @@ static struct tree *load_tree_for_commit(struct repository *r,
 {
 	struct object_id oid;
 	const unsigned char *commit_data;
+	uint32_t graph_pos = commit_graph_position(c);
 
-	while (c->graph_pos < g->num_commits_in_base)
+	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
 	commit_data = g->chunk_commit_data +
-			GRAPH_DATA_WIDTH * (c->graph_pos - g->num_commits_in_base);
+			GRAPH_DATA_WIDTH * (graph_pos - g->num_commits_in_base);
 
 	hashcpy(oid.hash, commit_data);
 	set_commit_tree(c, lookup_tree(r, &oid));
@@ -834,7 +895,7 @@ static struct tree *get_commit_tree_in_graph_one(struct repository *r,
 {
 	if (c->maybe_tree)
 		return c->maybe_tree;
-	if (c->graph_pos == COMMIT_NOT_FROM_GRAPH)
+	if (commit_graph_position(c) == COMMIT_NOT_FROM_GRAPH)
 		BUG("get_commit_tree_in_graph_one called from non-commit-graph commit");
 
 	return load_tree_for_commit(r, g, (struct commit *)c);
@@ -1020,7 +1081,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 		else
 			packedDate[0] = 0;
 
-		packedDate[0] |= htonl((*list)->generation << 2);
+		packedDate[0] |= htonl(commit_graph_data_at(*list)->generation << 2);
 
 		packedDate[1] = htonl((*list)->date);
 		hashwrite(f, packedDate, 8);
@@ -1219,7 +1280,7 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 			continue;
 		if (ctx->split) {
 			if ((!parse_commit(commit) &&
-			     commit->graph_pos == COMMIT_NOT_FROM_GRAPH) ||
+			     commit_graph_position(commit) == COMMIT_NOT_FROM_GRAPH) ||
 			    flags == COMMIT_GRAPH_SPLIT_REPLACE)
 				add_missing_parents(ctx, commit);
 		} else if (!parse_commit_no_graph(commit))
@@ -1251,9 +1312,11 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 					_("Computing commit graph generation numbers"),
 					ctx->commits.nr);
 	for (i = 0; i < ctx->commits.nr; i++) {
+		uint32_t generation = commit_graph_data_at(ctx->commits.list[i])->generation;
+
 		display_progress(ctx->progress, i + 1);
-		if (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY &&
-		    ctx->commits.list[i]->generation != GENERATION_NUMBER_ZERO)
+		if (generation != GENERATION_NUMBER_INFINITY &&
+		    generation != GENERATION_NUMBER_ZERO)
 			continue;
 
 		commit_list_insert(ctx->commits.list[i], &list);
@@ -1264,22 +1327,26 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 			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) {
+				generation = commit_graph_data_at(parent->item)->generation;
+
+				if (generation == GENERATION_NUMBER_INFINITY ||
+				    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;
+				} else if (generation > max_generation) {
+					max_generation = generation;
 				}
 			}
 
 			if (all_parents_computed) {
-				current->generation = max_generation + 1;
+				struct commit_graph_data *data = commit_graph_data_at(current);
+
+				data->generation = max_generation + 1;
 				pop_commit(&list);
 
-				if (current->generation > GENERATION_NUMBER_MAX)
-					current->generation = GENERATION_NUMBER_MAX;
+				if (data->generation > GENERATION_NUMBER_MAX)
+					data->generation = GENERATION_NUMBER_MAX;
 			}
 		}
 	}
@@ -1458,7 +1525,7 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
 			if (ctx->split) {
 				struct commit *c = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
-				if (!c || c->graph_pos != COMMIT_NOT_FROM_GRAPH)
+				if (!c || commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
 					continue;
 			}
 
@@ -1492,7 +1559,7 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
 		if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE &&
-		    ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
+		    commit_graph_position(ctx->commits.list[ctx->commits.nr]) != COMMIT_NOT_FROM_GRAPH)
 			continue;
 
 		if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE)
@@ -2241,6 +2308,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 		struct commit *graph_commit, *odb_commit;
 		struct commit_list *graph_parents, *odb_parents;
 		uint32_t max_generation = 0;
+		uint32_t generation;
 
 		display_progress(progress, i + 1);
 		hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
@@ -2279,8 +2347,9 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 					     oid_to_hex(&graph_parents->item->object.oid),
 					     oid_to_hex(&odb_parents->item->object.oid));
 
-			if (graph_parents->item->generation > max_generation)
-				max_generation = graph_parents->item->generation;
+			generation = commit_graph_generation(graph_parents->item);
+			if (generation > max_generation)
+				max_generation = generation;
 
 			graph_parents = graph_parents->next;
 			odb_parents = odb_parents->next;
@@ -2290,7 +2359,7 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 			graph_report(_("commit-graph parent list for commit %s terminates early"),
 				     oid_to_hex(&cur_oid));
 
-		if (!graph_commit->generation) {
+		if (!commit_graph_generation(graph_commit)) {
 			if (generation_zero == GENERATION_NUMBER_EXISTS)
 				graph_report(_("commit-graph has generation number zero for commit %s, but non-zero elsewhere"),
 					     oid_to_hex(&cur_oid));
@@ -2310,10 +2379,11 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 		if (max_generation == GENERATION_NUMBER_MAX)
 			max_generation--;
 
-		if (graph_commit->generation != max_generation + 1)
+		generation = commit_graph_generation(graph_commit);
+		if (generation != max_generation + 1)
 			graph_report(_("commit-graph generation for commit %s is %u != %u"),
 				     oid_to_hex(&cur_oid),
-				     graph_commit->generation,
+				     generation,
 				     max_generation + 1);
 
 		if (graph_commit->date != odb_commit->date)