1 files changed, 360 insertions, 132 deletions

diff --git a/commit-graph.c b/commit-graph.c
index b205e65ed1..6dc777e2f3 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -16,13 +16,32 @@
 #include "hashmap.h"
 #include "replace-object.h"
 #include "progress.h"
+#include "bloom.h"
+#include "commit-slab.h"
+
+void git_test_write_commit_graph_or_die(void)
+{
+	int flags = 0;
+	if (!git_env_bool(GIT_TEST_COMMIT_GRAPH, 0))
+		return;
+
+	if (git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0))
+		flags = COMMIT_GRAPH_WRITE_BLOOM_FILTERS;
+
+	if (write_commit_graph_reachable(the_repository->objects->odb,
+					 flags, NULL))
+		die("failed to write commit-graph under GIT_TEST_COMMIT_GRAPH");
+}
 
 #define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */
 #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
+#define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
+#define MAX_NUM_CHUNKS 7
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -44,30 +63,63 @@
 /* Remember to update object flag allocation in object.h */
 #define REACHABLE       (1u<<15)
 
-char *get_commit_graph_filename(const char *obj_dir)
+/* Keep track of the order in which commits are added to our list. */
+define_commit_slab(commit_pos, int);
+static struct commit_pos commit_pos = COMMIT_SLAB_INIT(1, commit_pos);
+
+static void set_commit_pos(struct repository *r, const struct object_id *oid)
+{
+	static int32_t max_pos;
+	struct commit *commit = lookup_commit(r, oid);
+
+	if (!commit)
+		return; /* should never happen, but be lenient */
+
+	*commit_pos_at(&commit_pos, commit) = max_pos++;
+}
+
+static int commit_pos_cmp(const void *va, const void *vb)
+{
+	const struct commit *a = *(const struct commit **)va;
+	const struct commit *b = *(const struct commit **)vb;
+	return commit_pos_at(&commit_pos, a) -
+	       commit_pos_at(&commit_pos, b);
+}
+
+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;
+
+	/* lower generation 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;
+}
+
+char *get_commit_graph_filename(struct object_directory *obj_dir)
 {
-	char *filename = xstrfmt("%s/info/commit-graph", obj_dir);
-	char *normalized = xmalloc(strlen(filename) + 1);
-	normalize_path_copy(normalized, filename);
-	free(filename);
-	return normalized;
+	return xstrfmt("%s/info/commit-graph", obj_dir->path);
 }
 
-static char *get_split_graph_filename(const char *obj_dir,
+static char *get_split_graph_filename(struct object_directory *odb,
 				      const char *oid_hex)
 {
-	char *filename = xstrfmt("%s/info/commit-graphs/graph-%s.graph",
-				 obj_dir,
-				 oid_hex);
-	char *normalized = xmalloc(strlen(filename) + 1);
-	normalize_path_copy(normalized, filename);
-	free(filename);
-	return normalized;
+	return xstrfmt("%s/info/commit-graphs/graph-%s.graph", odb->path,
+		       oid_hex);
 }
 
-static char *get_chain_filename(const char *obj_dir)
+static char *get_chain_filename(struct object_directory *odb)
 {
-	return xstrfmt("%s/info/commit-graphs/commit-graph-chain", obj_dir);
+	return xstrfmt("%s/info/commit-graphs/commit-graph-chain", odb->path);
 }
 
 static uint8_t oid_version(void)
@@ -78,7 +130,6 @@ static uint8_t oid_version(void)
 static struct commit_graph *alloc_commit_graph(void)
 {
 	struct commit_graph *g = xcalloc(1, sizeof(*g));
-	g->graph_fd = -1;
 
 	return g;
 }
@@ -117,7 +168,8 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st)
 	return 1;
 }
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st)
+struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+						 struct object_directory *odb)
 {
 	void *graph_map;
 	size_t graph_size;
@@ -131,12 +183,13 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st)
 		return NULL;
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
-	ret = parse_commit_graph(graph_map, fd, graph_size);
+	close(fd);
+	ret = parse_commit_graph(graph_map, graph_size);
 
-	if (!ret) {
+	if (ret)
+		ret->odb = odb;
+	else
 		munmap(graph_map, graph_size);
-		close(fd);
-	}
 
 	return ret;
 }
@@ -171,8 +224,7 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, int fd,
-					size_t graph_size)
+struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -215,7 +267,6 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 
 	graph->hash_len = the_hash_algo->rawsz;
 	graph->num_chunks = *(unsigned char*)(data + 6);
-	graph->graph_fd = fd;
 	graph->data = graph_map;
 	graph->data_len = graph_size;
 
@@ -280,6 +331,32 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 				chunk_repeated = 1;
 			else
 				graph->chunk_base_graphs = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMINDEXES:
+			if (graph->chunk_bloom_indexes)
+				chunk_repeated = 1;
+			else
+				graph->chunk_bloom_indexes = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_BLOOMDATA:
+			if (graph->chunk_bloom_data)
+				chunk_repeated = 1;
+			else {
+				uint32_t hash_version;
+				graph->chunk_bloom_data = data + chunk_offset;
+				hash_version = get_be32(data + chunk_offset);
+
+				if (hash_version != 1)
+					break;
+
+				graph->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
+				graph->bloom_filter_settings->hash_version = hash_version;
+				graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4);
+				graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
+			}
+			break;
 		}
 
 		if (chunk_repeated) {
@@ -298,6 +375,15 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		last_chunk_offset = chunk_offset;
 	}
 
+	if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
+		init_bloom_filters();
+	} else {
+		/* We need both the bloom chunks to exist together. Else ignore the data */
+		graph->chunk_bloom_indexes = NULL;
+		graph->chunk_bloom_data = NULL;
+		graph->bloom_filter_settings = NULL;
+	}
+
 	hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
 
 	if (verify_commit_graph_lite(graph)) {
@@ -308,7 +394,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 	return graph;
 }
 
-static struct commit_graph *load_commit_graph_one(const char *graph_file)
+static struct commit_graph *load_commit_graph_one(const char *graph_file,
+						  struct object_directory *odb)
 {
 
 	struct stat st;
@@ -319,7 +406,7 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file)
 	if (!open_ok)
 		return NULL;
 
-	g = load_commit_graph_one_fd_st(fd, &st);
+	g = load_commit_graph_one_fd_st(fd, &st, odb);
 
 	if (g)
 		g->filename = xstrdup(graph_file);
@@ -327,15 +414,13 @@ static struct commit_graph *load_commit_graph_one(const char *graph_file)
 	return g;
 }
 
-static struct commit_graph *load_commit_graph_v1(struct repository *r, const char *obj_dir)
+static struct commit_graph *load_commit_graph_v1(struct repository *r,
+						 struct object_directory *odb)
 {
-	char *graph_name = get_commit_graph_filename(obj_dir);
-	struct commit_graph *g = load_commit_graph_one(graph_name);
+	char *graph_name = get_commit_graph_filename(odb);
+	struct commit_graph *g = load_commit_graph_one(graph_name, odb);
 	free(graph_name);
 
-	if (g)
-		g->obj_dir = obj_dir;
-
 	return g;
 }
 
@@ -372,14 +457,15 @@ static int add_graph_to_chain(struct commit_graph *g,
 	return 1;
 }
 
-static struct commit_graph *load_commit_graph_chain(struct repository *r, const char *obj_dir)
+static struct commit_graph *load_commit_graph_chain(struct repository *r,
+						    struct object_directory *odb)
 {
 	struct commit_graph *graph_chain = NULL;
 	struct strbuf line = STRBUF_INIT;
 	struct stat st;
 	struct object_id *oids;
 	int i = 0, valid = 1, count;
-	char *chain_name = get_chain_filename(obj_dir);
+	char *chain_name = get_chain_filename(odb);
 	FILE *fp;
 	int stat_res;
 
@@ -412,14 +498,12 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, const
 
 		valid = 0;
 		for (odb = r->objects->odb; odb; odb = odb->next) {
-			char *graph_name = get_split_graph_filename(odb->path, line.buf);
-			struct commit_graph *g = load_commit_graph_one(graph_name);
+			char *graph_name = get_split_graph_filename(odb, line.buf);
+			struct commit_graph *g = load_commit_graph_one(graph_name, odb);
 
 			free(graph_name);
 
 			if (g) {
-				g->obj_dir = odb->path;
-
 				if (add_graph_to_chain(g, graph_chain, oids, i)) {
 					graph_chain = g;
 					valid = 1;
@@ -442,23 +526,25 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, const
 	return graph_chain;
 }
 
-struct commit_graph *read_commit_graph_one(struct repository *r, const char *obj_dir)
+struct commit_graph *read_commit_graph_one(struct repository *r,
+					   struct object_directory *odb)
 {
-	struct commit_graph *g = load_commit_graph_v1(r, obj_dir);
+	struct commit_graph *g = load_commit_graph_v1(r, odb);
 
 	if (!g)
-		g = load_commit_graph_chain(r, obj_dir);
+		g = load_commit_graph_chain(r, odb);
 
 	return g;
 }
 
-static void prepare_commit_graph_one(struct repository *r, const char *obj_dir)
+static void prepare_commit_graph_one(struct repository *r,
+				     struct object_directory *odb)
 {
 
 	if (r->objects->commit_graph)
 		return;
 
-	r->objects->commit_graph = read_commit_graph_one(r, obj_dir);
+	r->objects->commit_graph = read_commit_graph_one(r, odb);
 }
 
 /*
@@ -505,7 +591,7 @@ static int prepare_commit_graph(struct repository *r)
 	for (odb = r->objects->odb;
 	     !r->objects->commit_graph && odb;
 	     odb = odb->next)
-		prepare_commit_graph_one(r, odb->path);
+		prepare_commit_graph_one(r, odb);
 	return !!r->objects->commit_graph;
 }
 
@@ -772,7 +858,7 @@ struct packed_oid_list {
 
 struct write_commit_graph_context {
 	struct repository *r;
-	char *obj_dir;
+	struct object_directory *odb;
 	char *graph_name;
 	struct packed_oid_list oids;
 	struct packed_commit_list commits;
@@ -794,9 +880,12 @@ struct write_commit_graph_context {
 	unsigned append:1,
 		 report_progress:1,
 		 split:1,
-		 check_oids:1;
+		 check_oids:1,
+		 changed_paths:1,
+		 order_by_pack:1;
 
 	const struct split_commit_graph_opts *split_opts;
+	size_t total_bloom_filter_data_size;
 };
 
 static void write_graph_chunk_fanout(struct hashfile *f,
@@ -872,7 +961,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -903,7 +992,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -970,7 +1059,7 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 
 			if (edge_value >= 0)
 				edge_value += ctx->new_num_commits_in_base;
-			else {
+			else if (ctx->new_base_graph) {
 				uint32_t pos;
 				if (find_commit_in_graph(parent->item,
 							 ctx->new_base_graph,
@@ -992,6 +1081,59 @@ static void write_graph_chunk_extra_edges(struct hashfile *f,
 	}
 }
 
+static void write_graph_chunk_bloom_indexes(struct hashfile *f,
+					    struct write_commit_graph_context *ctx)
+{
+	struct commit **list = ctx->commits.list;
+	struct commit **last = ctx->commits.list + ctx->commits.nr;
+	uint32_t cur_pos = 0;
+	struct progress *progress = NULL;
+	int i = 0;
+
+	if (ctx->report_progress)
+		progress = start_delayed_progress(
+			_("Writing changed paths Bloom filters index"),
+			ctx->commits.nr);
+
+	while (list < last) {
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		cur_pos += filter->len;
+		display_progress(progress, ++i);
+		hashwrite_be32(f, cur_pos);
+		list++;
+	}
+
+	stop_progress(&progress);
+}
+
+static void write_graph_chunk_bloom_data(struct hashfile *f,
+					 struct write_commit_graph_context *ctx,
+					 const struct bloom_filter_settings *settings)
+{
+	struct commit **list = ctx->commits.list;
+	struct commit **last = ctx->commits.list + ctx->commits.nr;
+	struct progress *progress = NULL;
+	int i = 0;
+
+	if (ctx->report_progress)
+		progress = start_delayed_progress(
+			_("Writing changed paths Bloom filters data"),
+			ctx->commits.nr);
+
+	hashwrite_be32(f, settings->hash_version);
+	hashwrite_be32(f, settings->num_hashes);
+	hashwrite_be32(f, settings->bits_per_entry);
+
+	while (list < last) {
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		display_progress(progress, ++i);
+		hashwrite(f, filter->data, filter->len * sizeof(unsigned char));
+		list++;
+	}
+
+	stop_progress(&progress);
+}
+
 static int oid_compare(const void *_a, const void *_b)
 {
 	const struct object_id *a = (const struct object_id *)_a;
@@ -1023,6 +1165,8 @@ static int add_packed_commits(const struct object_id *oid,
 	oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid);
 	ctx->oids.nr++;
 
+	set_commit_pos(ctx->r, oid);
+
 	return 0;
 }
 
@@ -1043,6 +1187,8 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit *commit;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1072,8 +1218,9 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 		if (!commit)
 			continue;
 		if (ctx->split) {
-			if (!parse_commit(commit) &&
-			    commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
+			if ((!parse_commit(commit) &&
+			     commit->graph_pos == COMMIT_NOT_FROM_GRAPH) ||
+			    flags == COMMIT_GRAPH_SPLIT_REPLACE)
 				add_missing_parents(ctx, commit);
 		} else if (!parse_commit_no_graph(commit))
 			add_missing_parents(ctx, commit);
@@ -1139,28 +1286,60 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
-static int add_ref_to_list(const char *refname,
-			   const struct object_id *oid,
-			   int flags, void *cb_data)
+static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
-	struct string_list *list = (struct string_list *)cb_data;
+	int i;
+	struct progress *progress = NULL;
+	struct commit **sorted_commits;
 
-	string_list_append(list, oid_to_hex(oid));
+	init_bloom_filters();
+
+	if (ctx->report_progress)
+		progress = start_delayed_progress(
+			_("Computing commit changed paths Bloom filters"),
+			ctx->commits.nr);
+
+	ALLOC_ARRAY(sorted_commits, ctx->commits.nr);
+	COPY_ARRAY(sorted_commits, ctx->commits.list, ctx->commits.nr);
+
+	if (ctx->order_by_pack)
+		QSORT(sorted_commits, ctx->commits.nr, commit_pos_cmp);
+	else
+		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
+
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = sorted_commits[i];
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+		display_progress(progress, i + 1);
+	}
+
+	free(sorted_commits);
+	stop_progress(&progress);
+}
+
+static int add_ref_to_set(const char *refname,
+			  const struct object_id *oid,
+			  int flags, void *cb_data)
+{
+	struct oidset *commits = (struct oidset *)cb_data;
+
+	oidset_insert(commits, oid);
 	return 0;
 }
 
-int write_commit_graph_reachable(const char *obj_dir,
+int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
 				 const struct split_commit_graph_opts *split_opts)
 {
-	struct string_list list = STRING_LIST_INIT_DUP;
+	struct oidset commits = OIDSET_INIT;
 	int result;
 
-	for_each_ref(add_ref_to_list, &list);
-	result = write_commit_graph(obj_dir, NULL, &list,
+	for_each_ref(add_ref_to_set, &commits);
+	result = write_commit_graph(odb, NULL, &commits,
 				    flags, split_opts);
 
-	string_list_clear(&list, 0);
+	oidset_clear(&commits);
 	return result;
 }
 
@@ -1172,7 +1351,7 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
 	struct strbuf packname = STRBUF_INIT;
 	int dirlen;
 
-	strbuf_addf(&packname, "%s/pack/", ctx->obj_dir);
+	strbuf_addf(&packname, "%s/pack/", ctx->odb->path);
 	dirlen = packname.len;
 	if (ctx->report_progress) {
 		strbuf_addf(&progress_title,
@@ -1209,39 +1388,46 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
 	return 0;
 }
 
-static int fill_oids_from_commit_hex(struct write_commit_graph_context *ctx,
-				     struct string_list *commit_hex)
+static int fill_oids_from_commits(struct write_commit_graph_context *ctx,
+				  struct oidset *commits)
 {
-	uint32_t i;
+	uint32_t i = 0;
 	struct strbuf progress_title = STRBUF_INIT;
+	struct oidset_iter iter;
+	struct object_id *oid;
+
+	if (!oidset_size(commits))
+		return 0;
 
 	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);
+			       oidset_size(commits)),
+			    oidset_size(commits));
 		ctx->progress = start_delayed_progress(
 					progress_title.buf,
-					commit_hex->nr);
+					oidset_size(commits));
 	}
-	for (i = 0; i < commit_hex->nr; i++) {
-		const char *end;
-		struct object_id oid;
+
+	oidset_iter_init(commits, &iter);
+	while ((oid = oidset_iter_next(&iter))) {
 		struct commit *result;
 
-		display_progress(ctx->progress, i + 1);
-		if (!parse_oid_hex(commit_hex->items[i].string, &oid, &end) &&
-		    (result = lookup_commit_reference_gently(ctx->r, &oid, 1))) {
+		display_progress(ctx->progress, ++i);
+
+		result = lookup_commit_reference_gently(ctx->r, oid, 1);
+		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++;
 		} else if (ctx->check_oids) {
 			error(_("invalid commit object id: %s"),
-			    commit_hex->items[i].string);
+			      oid_to_hex(oid));
 			return -1;
 		}
 	}
+
 	stop_progress(&ctx->progress);
 	strbuf_release(&progress_title);
 
@@ -1293,6 +1479,8 @@ static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
 static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 {
 	uint32_t i;
+	enum commit_graph_split_flags flags = ctx->split_opts ?
+		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1309,11 +1497,14 @@ static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
 		ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc);
 		ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
 
-		if (ctx->split &&
+		if (ctx->split && flags != COMMIT_GRAPH_SPLIT_REPLACE &&
 		    ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
 			continue;
 
-		parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
+		if (ctx->split && flags == COMMIT_GRAPH_SPLIT_REPLACE)
+			parse_commit(ctx->commits.list[ctx->commits.nr]);
+		else
+			parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
 
 		num_parents = commit_list_count(ctx->commits.list[ctx->commits.nr]->parents);
 		if (num_parents > 2)
@@ -1356,22 +1547,23 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int fd;
 	struct hashfile *f;
 	struct lock_file lk = LOCK_INIT;
-	uint32_t chunk_ids[6];
-	uint64_t chunk_offsets[6];
+	uint32_t chunk_ids[MAX_NUM_CHUNKS + 1];
+	uint64_t chunk_offsets[MAX_NUM_CHUNKS + 1];
 	const unsigned hashsz = the_hash_algo->rawsz;
 	struct strbuf progress_title = STRBUF_INIT;
 	int num_chunks = 3;
 	struct object_id file_hash;
+	const struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
 
 		strbuf_addf(&tmp_file,
 			    "%s/info/commit-graphs/tmp_graph_XXXXXX",
-			    ctx->obj_dir);
+			    ctx->odb->path);
 		ctx->graph_name = strbuf_detach(&tmp_file, NULL);
 	} else {
-		ctx->graph_name = get_commit_graph_filename(ctx->obj_dir);
+		ctx->graph_name = get_commit_graph_filename(ctx->odb);
 	}
 
 	if (safe_create_leading_directories(ctx->graph_name)) {
@@ -1382,13 +1574,13 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	}
 
 	if (ctx->split) {
-		char *lock_name = get_chain_filename(ctx->obj_dir);
+		char *lock_name = get_chain_filename(ctx->odb);
 
 		hold_lock_file_for_update(&lk, lock_name, LOCK_DIE_ON_ERROR);
 
 		fd = git_mkstemp_mode(ctx->graph_name, 0444);
 		if (fd < 0) {
-			error(_("unable to create '%s'"), ctx->graph_name);
+			error(_("unable to create temporary graph layer"));
 			return -1;
 		}
 
@@ -1406,6 +1598,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
 		num_chunks++;
 	}
+	if (ctx->changed_paths) {
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMINDEXES;
+		num_chunks++;
+		chunk_ids[num_chunks] = GRAPH_CHUNKID_BLOOMDATA;
+		num_chunks++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
 		num_chunks++;
@@ -1424,6 +1622,15 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 						4 * ctx->num_extra_edges;
 		num_chunks++;
 	}
+	if (ctx->changed_paths) {
+		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
+						sizeof(uint32_t) * ctx->commits.nr;
+		num_chunks++;
+
+		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
+						sizeof(uint32_t) * 3 + ctx->total_bloom_filter_data_size;
+		num_chunks++;
+	}
 	if (ctx->num_commit_graphs_after > 1) {
 		chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
 						hashsz * (ctx->num_commit_graphs_after - 1);
@@ -1461,6 +1668,10 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	write_graph_chunk_data(f, hashsz, ctx);
 	if (ctx->num_extra_edges)
 		write_graph_chunk_extra_edges(f, ctx);
+	if (ctx->changed_paths) {
+		write_graph_chunk_bloom_indexes(f, ctx);
+		write_graph_chunk_bloom_data(f, ctx, &bloom_settings);
+	}
 	if (ctx->num_commit_graphs_after > 1 &&
 	    write_graph_chunk_base(f, ctx)) {
 		return -1;
@@ -1470,7 +1681,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 
 	if (ctx->split && ctx->base_graph_name && ctx->num_commit_graphs_after > 1) {
 		char *new_base_hash = xstrdup(oid_to_hex(&ctx->new_base_graph->oid));
-		char *new_base_name = get_split_graph_filename(ctx->new_base_graph->obj_dir, new_base_hash);
+		char *new_base_name = get_split_graph_filename(ctx->new_base_graph->odb, new_base_hash);
 
 		free(ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2]);
 		free(ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2]);
@@ -1494,8 +1705,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 		}
 
 		if (ctx->base_graph_name) {
-			const char *dest = ctx->commit_graph_filenames_after[
-						ctx->num_commit_graphs_after - 2];
+			const char *dest;
+			int idx = ctx->num_commit_graphs_after - 1;
+			if (ctx->num_commit_graphs_after > 1)
+				idx--;
+
+			dest = ctx->commit_graph_filenames_after[idx];
 
 			if (strcmp(ctx->base_graph_name, dest)) {
 				result = rename(ctx->base_graph_name, dest);
@@ -1506,12 +1721,12 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 				}
 			}
 		} else {
-			char *graph_name = get_commit_graph_filename(ctx->obj_dir);
+			char *graph_name = get_commit_graph_filename(ctx->odb);
 			unlink(graph_name);
 		}
 
 		ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1] = xstrdup(oid_to_hex(&file_hash));
-		final_graph_name = get_split_graph_filename(ctx->obj_dir,
+		final_graph_name = get_split_graph_filename(ctx->odb,
 					ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1]);
 		ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 1] = final_graph_name;
 
@@ -1535,6 +1750,7 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 {
 	struct commit_graph *g;
 	uint32_t num_commits;
+	enum commit_graph_split_flags flags = COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 	uint32_t i;
 
 	int max_commits = 0;
@@ -1545,30 +1761,42 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 
 		if (ctx->split_opts->size_multiple)
 			size_mult = ctx->split_opts->size_multiple;
+
+		flags = ctx->split_opts->flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
 	num_commits = ctx->commits.nr;
-	ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
-
-	while (g && (g->num_commits <= size_mult * num_commits ||
-		    (max_commits && num_commits > max_commits))) {
-		if (strcmp(g->obj_dir, ctx->obj_dir))
-			break;
+	if (flags == COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->num_commit_graphs_after = 1;
+	else
+		ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
+
+	if (flags != COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED &&
+	    flags != COMMIT_GRAPH_SPLIT_REPLACE) {
+		while (g && (g->num_commits <= size_mult * num_commits ||
+			    (max_commits && num_commits > max_commits))) {
+			if (g->odb != ctx->odb)
+				break;
 
-		num_commits += g->num_commits;
-		g = g->base_graph;
+			num_commits += g->num_commits;
+			g = g->base_graph;
 
-		ctx->num_commit_graphs_after--;
+			ctx->num_commit_graphs_after--;
+		}
 	}
 
-	ctx->new_base_graph = g;
+	if (flags != COMMIT_GRAPH_SPLIT_REPLACE)
+		ctx->new_base_graph = g;
+	else if (ctx->num_commit_graphs_after != 1)
+		BUG("split_graph_merge_strategy: num_commit_graphs_after "
+		    "should be 1 with --split=replace");
 
 	if (ctx->num_commit_graphs_after == 2) {
-		char *old_graph_name = get_commit_graph_filename(g->obj_dir);
+		char *old_graph_name = get_commit_graph_filename(g->odb);
 
 		if (!strcmp(g->filename, old_graph_name) &&
-		    strcmp(g->obj_dir, ctx->obj_dir)) {
+		    g->odb != ctx->odb) {
 			ctx->num_commit_graphs_after = 1;
 			ctx->new_base_graph = NULL;
 		}
@@ -1576,8 +1804,8 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 		free(old_graph_name);
 	}
 
-	ALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
-	ALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
+	CALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
+	CALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
 
 	for (i = 0; i < ctx->num_commit_graphs_after &&
 		    i < ctx->num_commit_graphs_before; i++)
@@ -1663,19 +1891,15 @@ static void merge_commit_graphs(struct write_commit_graph_context *ctx)
 {
 	struct commit_graph *g = ctx->r->objects->commit_graph;
 	uint32_t current_graph_number = ctx->num_commit_graphs_before;
-	struct strbuf progress_title = STRBUF_INIT;
 
 	while (g && current_graph_number >= ctx->num_commit_graphs_after) {
 		current_graph_number--;
 
-		if (ctx->report_progress) {
-			strbuf_addstr(&progress_title, _("Merging commit-graph"));
-			ctx->progress = start_delayed_progress(progress_title.buf, 0);
-		}
+		if (ctx->report_progress)
+			ctx->progress = start_delayed_progress(_("Merging commit-graph"), 0);
 
 		merge_commit_graph(ctx, g);
 		stop_progress(&ctx->progress);
-		strbuf_release(&progress_title);
 
 		g = g->base_graph;
 	}
@@ -1717,15 +1941,15 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	timestamp_t expire_time = time(NULL);
 
 	if (ctx->split_opts && ctx->split_opts->expire_time)
-		expire_time -= ctx->split_opts->expire_time;
+		expire_time = ctx->split_opts->expire_time;
 	if (!ctx->split) {
-		char *chain_file_name = get_chain_filename(ctx->obj_dir);
+		char *chain_file_name = get_chain_filename(ctx->odb);
 		unlink(chain_file_name);
 		free(chain_file_name);
 		ctx->num_commit_graphs_after = 0;
 	}
 
-	strbuf_addstr(&path, ctx->obj_dir);
+	strbuf_addstr(&path, ctx->odb->path);
 	strbuf_addstr(&path, "/info/commit-graphs");
 	dir = opendir(path.buf);
 
@@ -1764,35 +1988,30 @@ out:
 	strbuf_release(&path);
 }
 
-int write_commit_graph(const char *obj_dir,
+int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
-		       struct string_list *commit_hex,
+		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
 		       const struct split_commit_graph_opts *split_opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
-	size_t len;
 	int res = 0;
+	int replace = 0;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
 
 	ctx = xcalloc(1, sizeof(struct write_commit_graph_context));
 	ctx->r = the_repository;
-
-	/* normalize object dir with no trailing slash */
-	ctx->obj_dir = xmallocz(strlen(obj_dir) + 1);
-	normalize_path_copy(ctx->obj_dir, obj_dir);
-	len = strlen(ctx->obj_dir);
-	if (len && ctx->obj_dir[len - 1] == '/')
-		ctx->obj_dir[len - 1] = 0;
-
+	ctx->odb = odb;
 	ctx->append = flags & COMMIT_GRAPH_WRITE_APPEND ? 1 : 0;
 	ctx->report_progress = flags & COMMIT_GRAPH_WRITE_PROGRESS ? 1 : 0;
 	ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
 	ctx->check_oids = flags & COMMIT_GRAPH_WRITE_CHECK_OIDS ? 1 : 0;
 	ctx->split_opts = split_opts;
+	ctx->changed_paths = flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS ? 1 : 0;
+	ctx->total_bloom_filter_data_size = 0;
 
 	if (ctx->split) {
 		struct commit_graph *g;
@@ -1815,6 +2034,9 @@ int write_commit_graph(const char *obj_dir,
 				g = g->base_graph;
 			}
 		}
+
+		if (ctx->split_opts)
+			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
@@ -1824,7 +2046,7 @@ int write_commit_graph(const char *obj_dir,
 		ctx->oids.alloc = split_opts->max_commits;
 
 	if (ctx->append) {
-		prepare_commit_graph_one(ctx->r, ctx->obj_dir);
+		prepare_commit_graph_one(ctx->r, ctx->odb);
 		if (ctx->r->objects->commit_graph)
 			ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits;
 	}
@@ -1842,17 +2064,20 @@ int write_commit_graph(const char *obj_dir,
 	}
 
 	if (pack_indexes) {
+		ctx->order_by_pack = 1;
 		if ((res = fill_oids_from_packs(ctx, pack_indexes)))
 			goto cleanup;
 	}
 
-	if (commit_hex) {
-		if ((res = fill_oids_from_commit_hex(ctx, commit_hex)))
+	if (commits) {
+		if ((res = fill_oids_from_commits(ctx, commits)))
 			goto cleanup;
 	}
 
-	if (!pack_indexes && !commit_hex)
+	if (!pack_indexes && !commits) {
+		ctx->order_by_pack = 1;
 		fill_oids_from_all_packs(ctx);
+	}
 
 	close_reachable(ctx);
 
@@ -1875,18 +2100,22 @@ int write_commit_graph(const char *obj_dir,
 		goto cleanup;
 	}
 
-	if (!ctx->commits.nr)
+	if (!ctx->commits.nr && !replace)
 		goto cleanup;
 
 	if (ctx->split) {
 		split_graph_merge_strategy(ctx);
 
-		merge_commit_graphs(ctx);
+		if (!replace)
+			merge_commit_graphs(ctx);
 	} else
 		ctx->num_commit_graphs_after = 1;
 
 	compute_generation_numbers(ctx);
 
+	if (ctx->changed_paths)
+		compute_bloom_filters(ctx);
+
 	res = write_commit_graph_file(ctx);
 
 	if (ctx->split)
@@ -1898,7 +2127,6 @@ cleanup:
 	free(ctx->graph_name);
 	free(ctx->commits.list);
 	free(ctx->oids.list);
-	free(ctx->obj_dir);
 
 	if (ctx->commit_graph_filenames_after) {
 		for (i = 0; i < ctx->num_commit_graphs_after; i++) {
@@ -2107,12 +2335,12 @@ void free_commit_graph(struct commit_graph *g)
 {
 	if (!g)
 		return;
-	if (g->graph_fd >= 0) {
+	if (g->data) {
 		munmap((void *)g->data, g->data_len);
 		g->data = NULL;
-		close(g->graph_fd);
 	}
 	free(g->filename);
+	free(g->bloom_filter_settings);
 	free(g);
 }