Merge branch 'tb/bloom-improvements'

"git commit-graph write" learned to limit the number of bloom
filters that are computed from scratch with the --max-new-filters
option.

* tb/bloom-improvements:
  commit-graph: introduce 'commitGraph.maxNewFilters'
  builtin/commit-graph.c: introduce '--max-new-filters=<n>'
  commit-graph: rename 'split_commit_graph_opts'
  bloom: encode out-of-bounds filters as non-empty
  bloom/diff: properly short-circuit on max_changes
  bloom: use provided 'struct bloom_filter_settings'
  bloom: split 'get_bloom_filter()' in two
  commit-graph.c: store maximum changed paths
  commit-graph: respect 'commitGraph.readChangedPaths'
  t/helper/test-read-graph.c: prepare repo settings
  commit-graph: pass a 'struct repository *' in more places
  t4216: use an '&&'-chain
  commit-graph: introduce 'get_bloom_filter_settings()'

Documentation/config.txt

@@ -340,6 +340,8 @@ include::config/column.txt[]
 
 include::config/commit.txt[]
 
+include::config/commitgraph.txt[]
+
 include::config/credential.txt[]
 
 include::config/completion.txt[]

Documentation/config/commitgraph.txt

@@ -0,0 +1,8 @@
+commitGraph.maxNewFilters::
+	Specifies the default value for the `--max-new-filters` option of `git
+	commit-graph write` (c.f., linkgit:git-commit-graph[1]).
+
+commitGraph.readChangedPaths::
+	If true, then git will use the changed-path Bloom filters in the
+	commit-graph file (if it exists, and they are present). Defaults to
+	true. See linkgit:git-commit-graph[1] for more information.

Documentation/git-commit-graph.txt

@@ -67,6 +67,13 @@ this option is given, future commit-graph writes will automatically assume
 that this option was intended. Use `--no-changed-paths` to stop storing this
 data.
 +
+With the `--max-new-filters=<n>` option, generate at most `n` new Bloom
+filters (if `--changed-paths` is specified). If `n` is `-1`, no limit is
+enforced. Only commits present in the new layer count against this
+limit. To retroactively compute Bloom filters over earlier layers, it is
+advised to use `--split=replace`.  Overrides the `commitGraph.maxNewFilters`
+configuration.
++
 With the `--split[=<strategy>]` option, write the commit-graph as a
 chain of multiple commit-graph files stored in
 `<dir>/info/commit-graphs`. Commit-graph layers are merged based on the

Documentation/technical/commit-graph-format.txt

@@ -125,7 +125,7 @@ CHUNK DATA:
     * The rest of the chunk is the concatenation of all the computed Bloom
       filters for the commits in lexicographic order.
     * Note: Commits with no changes or more than 512 changes have Bloom filters
-      of length zero.
+      of length one, with either all bits set to zero or one respectively.
     * The BDAT chunk is present if and only if BIDX is present.
 
   Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]

blame.c

@@ -1276,7 +1276,7 @@ static int maybe_changed_path(struct repository *r,
 	if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
 		return 1;
 
-	filter = get_bloom_filter(r, origin->commit, 0);
+	filter = get_bloom_filter(r, origin->commit);
 
 	if (!filter)
 		return 1;
@@ -2892,16 +2892,18 @@ void setup_blame_bloom_data(struct blame_scoreboard *sb,
 			    const char *path)
 {
 	struct blame_bloom_data *bd;
+	struct bloom_filter_settings *bs;
 
 	if (!sb->repo->objects->commit_graph)
 		return;
 
-	if (!sb->repo->objects->commit_graph->bloom_filter_settings)
+	bs = get_bloom_filter_settings(sb->repo);
+	if (!bs)
 		return;
 
 	bd = xmalloc(sizeof(struct blame_bloom_data));
 
-	bd->settings = sb->repo->objects->commit_graph->bloom_filter_settings;
+	bd->settings = bs;
 
 	bd->alloc = 4;
 	bd->nr = 0;

bloom.c

@@ -38,7 +38,7 @@ static int load_bloom_filter_from_graph(struct commit_graph *g,
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
+	/* The commit graph commit 'c' lives in doesn't carry Bloom filters. */
 	if (!g->chunk_bloom_indexes)
 		return 0;
 
@@ -177,15 +177,25 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
 	return strcmp(e1->path, e2->path);
 }
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
+static void init_truncated_large_filter(struct bloom_filter *filter)
+{
+	filter->data = xmalloc(1);
+	filter->data[0] = 0xFF;
+	filter->len = 1;
+}
+
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
-				      int compute_if_not_present)
+						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
+						 enum bloom_filter_computed *computed)
 {
 	struct bloom_filter *filter;
-	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 	int i;
 	struct diff_options diffopt;
-	int max_changes = 512;
+
+	if (computed)
+		*computed = BLOOM_NOT_COMPUTED;
 
 	if (!bloom_filters.slab_size)
 		return NULL;
@@ -194,12 +204,11 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
-		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
+		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
-			r->objects->commit_graph->chunk_bloom_indexes)
 			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
 	}
 
-	if (filter->data)
+	if (filter->data && filter->len)
 		return filter;
 	if (!compute_if_not_present)
 		return NULL;
@@ -207,7 +216,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;
 	diffopt.detect_rename = 0;
-	diffopt.max_changes = max_changes;
+	diffopt.max_changes = settings->max_changed_paths;
 	diff_setup_done(&diffopt);
 
 	/* ensure commit is parsed so we have parent information */
@@ -219,7 +228,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diffopt.num_changes <= max_changes) {
+	if (diff_queued_diff.nr <= settings->max_changed_paths) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
@@ -256,23 +265,41 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 			diff_free_filepair(diff_queued_diff.queue[i]);
 		}
 
-		filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		if (hashmap_get_size(&pathmap) > settings->max_changed_paths) {
+			init_truncated_large_filter(filter);
+			if (computed)
+				*computed |= BLOOM_TRUNC_LARGE;
+			goto cleanup;
+		}
+
+		filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		if (!filter->len) {
+			if (computed)
+				*computed |= BLOOM_TRUNC_EMPTY;
+			filter->len = 1;
+		}
 		filter->data = xcalloc(filter->len, sizeof(unsigned char));
 
 		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
 			struct bloom_key key;
-			fill_bloom_key(e->path, strlen(e->path), &key, &settings);
+			fill_bloom_key(e->path, strlen(e->path), &key, settings);
-			add_key_to_filter(&key, filter, &settings);
+			add_key_to_filter(&key, filter, settings);
 		}
 
+	cleanup:
 		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
 	} else {
 		for (i = 0; i < diff_queued_diff.nr; i++)
 			diff_free_filepair(diff_queued_diff.queue[i]);
-		filter->data = NULL;
+		init_truncated_large_filter(filter);
-		filter->len = 0;
+
+		if (computed)
+			*computed |= BLOOM_TRUNC_LARGE;
 	}
 
+	if (computed)
+		*computed |= BLOOM_COMPUTED;
+
 	free(diff_queued_diff.queue);
 	DIFF_QUEUE_CLEAR(&diff_queued_diff);
 

bloom.h

@@ -28,9 +28,18 @@ struct bloom_filter_settings {
 	 * that contain n*b bits.
 	 */
 	uint32_t bits_per_entry;
+
+	/*
+	 * The maximum number of changed paths per commit
+	 * before declaring a Bloom filter to be too-large.
+	 *
+	 * Not written to the commit-graph file.
+	 */
+	uint32_t max_changed_paths;
 };
 
-#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 }
+#define DEFAULT_BLOOM_MAX_CHANGES 512
+#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
 #define BITS_PER_WORD 8
 #define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
 
@@ -80,9 +89,21 @@ void add_key_to_filter(const struct bloom_key *key,
 
 void init_bloom_filters(void);
 
-struct bloom_filter *get_bloom_filter(struct repository *r,
+enum bloom_filter_computed {
+	BLOOM_NOT_COMPUTED = (1 << 0),
+	BLOOM_COMPUTED     = (1 << 1),
+	BLOOM_TRUNC_LARGE  = (1 << 2),
+	BLOOM_TRUNC_EMPTY  = (1 << 3),
+};
+
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 						 struct commit *c,
-				      int compute_if_not_present);
+						 int compute_if_not_present,
+						 const struct bloom_filter_settings *settings,
+						 enum bloom_filter_computed *computed);
+
+#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
+	(r), (c), 0, NULL, NULL)
 
 int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,

builtin/commit-graph.c

@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -106,7 +108,7 @@ static int graph_verify(int argc, const char **argv)
 	FREE_AND_NULL(graph_name);
 
 	if (open_ok)
-		graph = load_commit_graph_one_fd_st(fd, &st, odb);
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
 	else
 		graph = read_commit_graph_one(the_repository, odb);
 
@@ -119,7 +121,7 @@ static int graph_verify(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
-static struct split_commit_graph_opts split_opts;
+static struct commit_graph_opts write_opts;
 
 static int write_option_parse_split(const struct option *opt, const char *arg,
 				    int unset)
@@ -162,6 +164,35 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
+static int git_commit_graph_write_config(const char *var, const char *value,
+					 void *cb)
+{
+	if (!strcmp(var, "commitgraph.maxnewfilters"))
+		write_opts.max_new_filters = git_config_int(var, value);
+	/*
+	 * No need to fall-back to 'git_default_config', since this was already
+	 * called in 'cmd_commit_graph()'.
+	 */
+	return 0;
+}
+
 static int graph_write(int argc, const char **argv)
 {
 	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
@@ -187,27 +218,33 @@ static int graph_write(int argc, const char **argv)
 		OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
 			N_("enable computation for changed paths")),
 		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
-		OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL,
+		OPT_CALLBACK_F(0, "split", &write_opts.split_flags, NULL,
 			N_("allow writing an incremental commit-graph file"),
 			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
 			write_option_parse_split),
-		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
+		OPT_INTEGER(0, "max-commits", &write_opts.max_commits,
 			N_("maximum number of commits in a non-base split commit-graph")),
-		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
+		OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple,
 			N_("maximum ratio between two levels of a split commit-graph")),
-		OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
+		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
 			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of changed-path Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
 	opts.progress = isatty(2);
 	opts.enable_changed_paths = -1;
-	split_opts.size_multiple = 2;
+	write_opts.size_multiple = 2;
-	split_opts.max_commits = 0;
+	write_opts.max_commits = 0;
-	split_opts.expire_time = 0;
+	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
 
 	trace2_cmd_mode("write");
 
+	git_config(git_commit_graph_write_config, &opts);
+
 	argc = parse_options(argc, argv, NULL,
 			     builtin_commit_graph_write_options,
 			     builtin_commit_graph_write_usage, 0);
@@ -232,7 +269,7 @@ static int graph_write(int argc, const char **argv)
 	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		if (write_commit_graph_reachable(odb, flags, &split_opts))
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
 			return 1;
 		return 0;
 	}
@@ -261,7 +298,7 @@ static int graph_write(int argc, const char **argv)
 			       opts.stdin_packs ? &pack_indexes : NULL,
 			       opts.stdin_commits ? &commits : NULL,
 			       flags,
-			       &split_opts))
+			       &write_opts))
 		result = 1;
 
 cleanup:

commit-graph.c

@@ -231,7 +231,8 @@ 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(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb)
 {
 	void *graph_map;
@@ -247,7 +248,7 @@ struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
 	}
 	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
-	ret = parse_commit_graph(graph_map, graph_size);
+	ret = parse_commit_graph(r, graph_map, graph_size);
 
 	if (ret)
 		ret->odb = odb;
@@ -287,7 +288,8 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	return 0;
 }
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size)
 {
 	const unsigned char *data, *chunk_lookup;
 	uint32_t i;
@@ -325,6 +327,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 		return NULL;
 	}
 
+	prepare_repo_settings(r);
+
 	graph = alloc_commit_graph();
 
 	graph->hash_len = the_hash_algo->rawsz;
@@ -401,14 +405,14 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 		case GRAPH_CHUNKID_BLOOMINDEXES:
 			if (graph->chunk_bloom_indexes)
 				chunk_repeated = 1;
-			else
+			else if (r->settings.commit_graph_read_changed_paths)
 				graph->chunk_bloom_indexes = data + chunk_offset;
 			break;
 
 		case GRAPH_CHUNKID_BLOOMDATA:
 			if (graph->chunk_bloom_data)
 				chunk_repeated = 1;
-			else {
+			else if (r->settings.commit_graph_read_changed_paths) {
 				uint32_t hash_version;
 				graph->chunk_bloom_data = data + chunk_offset;
 				hash_version = get_be32(data + chunk_offset);
@@ -420,6 +424,7 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size)
 				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);
+				graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES;
 			}
 			break;
 		}
@@ -452,7 +457,8 @@ free_and_return:
 	return NULL;
 }
 
-static struct commit_graph *load_commit_graph_one(const char *graph_file,
+static struct commit_graph *load_commit_graph_one(struct repository *r,
+						  const char *graph_file,
 						  struct object_directory *odb)
 {
 
@@ -464,7 +470,7 @@ 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, odb);
+	g = load_commit_graph_one_fd_st(r, fd, &st, odb);
 
 	if (g)
 		g->filename = xstrdup(graph_file);
@@ -476,7 +482,7 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r,
 						 struct object_directory *odb)
 {
 	char *graph_name = get_commit_graph_filename(odb);
-	struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+	struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 	free(graph_name);
 
 	return g;
@@ -557,7 +563,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
 		valid = 0;
 		for (odb = r->objects->odb; odb; odb = odb->next) {
 			char *graph_name = get_split_graph_filename(odb, line.buf);
-			struct commit_graph *g = load_commit_graph_one(graph_name, odb);
+			struct commit_graph *g = load_commit_graph_one(r, graph_name, odb);
 
 			free(graph_name);
 
@@ -667,6 +673,17 @@ int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
+{
+	struct commit_graph *g = r->objects->commit_graph;
+	while (g) {
+		if (g->bloom_filter_settings)
+			return g->bloom_filter_settings;
+		g = g->base_graph;
+	}
+	return NULL;
+}
+
 static void close_commit_graph_one(struct commit_graph *g)
 {
 	if (!g)
@@ -952,9 +969,14 @@ struct write_commit_graph_context {
 		 changed_paths:1,
 		 order_by_pack:1;
 
-	const struct split_commit_graph_opts *split_opts;
+	const struct commit_graph_opts *opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
+
+	int count_bloom_filter_computed;
+	int count_bloom_filter_not_computed;
+	int count_bloom_filter_trunc_empty;
+	int count_bloom_filter_trunc_large;
 };
 
 static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1166,7 +1188,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 	uint32_t cur_pos = 0;
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 		cur_pos += len;
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1185,6 +1207,7 @@ static void trace2_bloom_filter_settings(struct write_commit_graph_context *ctx)
 	jw_object_intmax(&jw, "hash_version", ctx->bloom_settings->hash_version);
 	jw_object_intmax(&jw, "num_hashes", ctx->bloom_settings->num_hashes);
 	jw_object_intmax(&jw, "bits_per_entry", ctx->bloom_settings->bits_per_entry);
+	jw_object_intmax(&jw, "max_changed_paths", ctx->bloom_settings->max_changed_paths);
 	jw_end(&jw);
 
 	trace2_data_json("bloom", ctx->r, "settings", &jw);
@@ -1205,7 +1228,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 	hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
 
 	while (list < last) {
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
 		size_t len = filter ? filter->len : 0;
 
 		display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1270,8 +1293,8 @@ static void close_reachable(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit *commit;
-	enum commit_graph_split_flags flags = ctx->split_opts ?
+	enum commit_graph_split_flags flags = ctx->opts ?
-		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
+		ctx->opts->split_flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
@@ -1375,11 +1398,24 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+	trace2_data_intmax("commit-graph", ctx->r, "filter-computed",
+			   ctx->count_bloom_filter_computed);
+	trace2_data_intmax("commit-graph", ctx->r, "filter-not-computed",
+			   ctx->count_bloom_filter_not_computed);
+	trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-empty",
+			   ctx->count_bloom_filter_trunc_empty);
+	trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large",
+			   ctx->count_bloom_filter_trunc_large);
+}
+
 static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct progress *progress = NULL;
 	struct commit **sorted_commits;
+	int max_new_filters;
 
 	init_bloom_filters();
 
@@ -1396,13 +1432,34 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 	else
 		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
+	max_new_filters = ctx->opts && ctx->opts->max_new_filters >= 0 ?
+		ctx->opts->max_new_filters : ctx->commits.nr;
+
 	for (i = 0; i < ctx->commits.nr; i++) {
+		enum bloom_filter_computed computed = 0;
 		struct commit *c = sorted_commits[i];
-		struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+		struct bloom_filter *filter = get_or_compute_bloom_filter(
-		ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
+			ctx->r,
+			c,
+			ctx->count_bloom_filter_computed < max_new_filters,
+			ctx->bloom_settings,
+			&computed);
+		if (computed & BLOOM_COMPUTED) {
+			ctx->count_bloom_filter_computed++;
+			if (computed & BLOOM_TRUNC_EMPTY)
+				ctx->count_bloom_filter_trunc_empty++;
+			if (computed & BLOOM_TRUNC_LARGE)
+				ctx->count_bloom_filter_trunc_large++;
+		} else if (computed & BLOOM_NOT_COMPUTED)
+			ctx->count_bloom_filter_not_computed++;
+		ctx->total_bloom_filter_data_size += filter
+			? sizeof(unsigned char) * filter->len : 0;
 		display_progress(progress, i + 1);
 	}
 
+	if (trace2_is_enabled())
+		trace2_bloom_filter_write_statistics(ctx);
+
 	free(sorted_commits);
 	stop_progress(&progress);
 }
@@ -1431,7 +1488,7 @@ static int add_ref_to_set(const char *refname,
 
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts)
+				 const struct commit_graph_opts *opts)
 {
 	struct oidset commits = OIDSET_INIT;
 	struct refs_cb_data data;
@@ -1448,7 +1505,7 @@ int write_commit_graph_reachable(struct object_directory *odb,
 	stop_progress(&data.progress);
 
 	result = write_commit_graph(odb, NULL, &commits,
-				    flags, split_opts);
+				    flags, opts);
 
 	oidset_clear(&commits);
 	return result;
@@ -1563,8 +1620,8 @@ 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 ?
+	enum commit_graph_split_flags flags = ctx->opts ?
-		ctx->split_opts->flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
+		ctx->opts->split_flags : COMMIT_GRAPH_SPLIT_UNSPECIFIED;
 
 	ctx->num_extra_edges = 0;
 	if (ctx->report_progress)
@@ -1646,15 +1703,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	int num_chunks = 3;
 	uint64_t chunk_offset;
 	struct object_id file_hash;
-	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
-
-	if (!ctx->bloom_settings) {
-		bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
-							      bloom_settings.bits_per_entry);
-		bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
-							  bloom_settings.num_hashes);
-		ctx->bloom_settings = &bloom_settings;
-	}
 
 	if (ctx->split) {
 		struct strbuf tmp_file = STRBUF_INIT;
@@ -1858,13 +1906,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 	int max_commits = 0;
 	int size_mult = 2;
 
-	if (ctx->split_opts) {
+	if (ctx->opts) {
-		max_commits = ctx->split_opts->max_commits;
+		max_commits = ctx->opts->max_commits;
 
-		if (ctx->split_opts->size_multiple)
+		if (ctx->opts->size_multiple)
-			size_mult = ctx->split_opts->size_multiple;
+			size_mult = ctx->opts->size_multiple;
 
-		flags = ctx->split_opts->flags;
+		flags = ctx->opts->split_flags;
 	}
 
 	g = ctx->r->objects->commit_graph;
@@ -2042,8 +2090,8 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	size_t dirnamelen;
 	timestamp_t expire_time = time(NULL);
 
-	if (ctx->split_opts && ctx->split_opts->expire_time)
+	if (ctx->opts && ctx->opts->expire_time)
-		expire_time = ctx->split_opts->expire_time;
+		expire_time = ctx->opts->expire_time;
 	if (!ctx->split) {
 		char *chain_file_name = get_commit_graph_chain_filename(ctx->odb);
 		unlink(chain_file_name);
@@ -2094,12 +2142,13 @@ int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts)
+		       const struct commit_graph_opts *opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
 	int res = 0;
 	int replace = 0;
+	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
 	if (!commit_graph_compatible(the_repository))
 		return 0;
@@ -2110,9 +2159,17 @@ int write_commit_graph(struct object_directory *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->split_opts = split_opts;
+	ctx->opts = opts;
 	ctx->total_bloom_filter_data_size = 0;
 
+	bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
+						      bloom_settings.bits_per_entry);
+	bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
+						  bloom_settings.num_hashes);
+	bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+							 bloom_settings.max_changed_paths);
+	ctx->bloom_settings = &bloom_settings;
+
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;
 	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
@@ -2150,15 +2207,15 @@ int write_commit_graph(struct object_directory *odb,
 			}
 		}
 
-		if (ctx->split_opts)
+		if (ctx->opts)
-			replace = ctx->split_opts->flags & COMMIT_GRAPH_SPLIT_REPLACE;
+			replace = ctx->opts->split_flags & COMMIT_GRAPH_SPLIT_REPLACE;
 	}
 
 	ctx->approx_nr_objects = approximate_object_count();
 	ctx->oids.alloc = ctx->approx_nr_objects / 32;
 
-	if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
+	if (ctx->split && opts && ctx->oids.alloc > opts->max_commits)
-		ctx->oids.alloc = split_opts->max_commits;
+		ctx->oids.alloc = opts->max_commits;
 
 	if (ctx->append) {
 		prepare_commit_graph_one(ctx->r, ctx->odb);

commit-graph.h

@@ -76,11 +76,13 @@ struct commit_graph {
 	struct bloom_filter_settings *bloom_filter_settings;
 };
 
-struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st,
+struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
+						 int fd, struct stat *st,
 						 struct object_directory *odb);
 struct commit_graph *read_commit_graph_one(struct repository *r,
 					   struct object_directory *odb);
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 /*
  * Return 1 if and only if the repository has a commit-graph
@@ -88,6 +90,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
  */
 int generation_numbers_enabled(struct repository *r);
 
+struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r);
+
 enum commit_graph_write_flags {
 	COMMIT_GRAPH_WRITE_APPEND     = (1 << 0),
 	COMMIT_GRAPH_WRITE_PROGRESS   = (1 << 1),
@@ -102,11 +106,12 @@ enum commit_graph_split_flags {
 	COMMIT_GRAPH_SPLIT_REPLACE          = 2
 };
 
-struct split_commit_graph_opts {
+struct commit_graph_opts {
 	int size_multiple;
 	int max_commits;
 	timestamp_t expire_time;
-	enum commit_graph_split_flags flags;
+	enum commit_graph_split_flags split_flags;
+	int max_new_filters;
 };
 
 /*
@@ -117,12 +122,12 @@ struct split_commit_graph_opts {
  */
 int write_commit_graph_reachable(struct object_directory *odb,
 				 enum commit_graph_write_flags flags,
-				 const struct split_commit_graph_opts *split_opts);
+				 const struct commit_graph_opts *opts);
 int write_commit_graph(struct object_directory *odb,
 		       struct string_list *pack_indexes,
 		       struct oidset *commits,
 		       enum commit_graph_write_flags flags,
-		       const struct split_commit_graph_opts *split_opts);
+		       const struct commit_graph_opts *opts);
 
 #define COMMIT_GRAPH_VERIFY_SHALLOW	(1 << 0)
 

diff.h

@@ -287,8 +287,6 @@ struct diff_options {
 
 	/* If non-zero, then stop computing after this many changes. */
 	int max_changes;
-	/* For internal use only. */
-	int num_changes;
 
 	int ita_invisible_in_index;
 /* white-space error highlighting */

fuzz-commit-graph.c

@@ -1,7 +1,8 @@
 #include "commit-graph.h"
 #include "repository.h"
 
-struct commit_graph *parse_commit_graph(void *graph_map, size_t graph_size);
+struct commit_graph *parse_commit_graph(struct repository *r,
+					void *graph_map, size_t graph_size);
 
 int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
 
@@ -10,7 +11,7 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
 	struct commit_graph *g;
 
 	initialize_the_repository();
-	g = parse_commit_graph((void *)data, size);
+	g = parse_commit_graph(the_repository, (void *)data, size);
 	repo_clear(the_repository);
 	free_commit_graph(g);
 

line-log.c

@@ -1159,7 +1159,7 @@ static int bloom_filter_check(struct rev_info *rev,
 		return 1;
 
 	if (!rev->bloom_filter_settings ||
-	    !(filter = get_bloom_filter(rev->repo, commit, 0)))
+	    !(filter = get_bloom_filter(rev->repo, commit)))
 		return 1;
 
 	if (!range)

repo-settings.c

@@ -17,9 +17,12 @@ void prepare_repo_settings(struct repository *r)
 
 	if (!repo_config_get_bool(r, "core.commitgraph", &value))
 		r->settings.core_commit_graph = value;
+	if (!repo_config_get_bool(r, "commitgraph.readchangedpaths", &value))
+		r->settings.commit_graph_read_changed_paths = value;
 	if (!repo_config_get_bool(r, "gc.writecommitgraph", &value))
 		r->settings.gc_write_commit_graph = value;
 	UPDATE_DEFAULT_BOOL(r->settings.core_commit_graph, 1);
+	UPDATE_DEFAULT_BOOL(r->settings.commit_graph_read_changed_paths, 1);
 	UPDATE_DEFAULT_BOOL(r->settings.gc_write_commit_graph, 1);
 
 	if (!repo_config_get_int(r, "index.version", &value))

repository.h

@@ -30,6 +30,7 @@ struct repo_settings {
 	int initialized;
 
 	int core_commit_graph;
+	int commit_graph_read_changed_paths;
 	int gc_write_commit_graph;
 	int fetch_write_commit_graph;
 

revision.c

@@ -681,10 +681,7 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 
 	repo_parse_commit(revs->repo, revs->commits->item);
 
-	if (!revs->repo->objects->commit_graph)
+	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
-		return;
-
-	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
 	if (!revs->bloom_filter_settings)
 		return;
 
@@ -755,7 +752,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 	if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
 		return -1;
 
-	filter = get_bloom_filter(revs->repo, commit, 0);
+	filter = get_bloom_filter(revs->repo, commit);
 
 	if (!filter) {
 		count_bloom_filter_not_present++;

t/helper/test-bloom.c

@@ -39,7 +39,9 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 	struct bloom_filter *filter;
 	setup_git_directory();
 	c = lookup_commit(the_repository, commit_oid);
-	filter = get_bloom_filter(the_repository, c, 1);
+	filter = get_or_compute_bloom_filter(the_repository, c, 1,
+					     &settings,
+					     NULL);
 	print_bloom_filter(filter);
 }
 

t/helper/test-read-graph.c

@@ -12,11 +12,12 @@ int cmd__read_graph(int argc, const char **argv)
 	setup_git_directory();
 	odb = the_repository->objects->odb;
 
+	prepare_repo_settings(the_repository);
+
 	graph = read_commit_graph_one(the_repository, odb);
 	if (!graph)
 		return 1;
 
-
 	printf("header: %08x %d %d %d %d\n",
 		ntohl(*(uint32_t*)graph->data),
 		*(unsigned char*)(graph->data + 4),

t/t0095-bloom.sh

@@ -71,8 +71,8 @@ test_expect_success 'get bloom filters for commit with no changes' '
 	git init &&
 	git commit --allow-empty -m "c0" &&
 	cat >expect <<-\EOF &&
-	Filter_Length:0
+	Filter_Length:1
-	Filter_Data:
+	Filter_Data:00|
 	EOF
 	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
 	test_cmp expect actual
@@ -107,8 +107,8 @@ test_expect_success EXPENSIVE 'get bloom filter for commit with 513 changes' '
 	git add bigDir &&
 	git commit -m "commit with 513 changes" &&
 	cat >expect <<-\EOF &&
-	Filter_Length:0
+	Filter_Length:1
-	Filter_Data:
+	Filter_Data:ff|
 	EOF
 	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
 	test_cmp expect actual

t/t4216-log-bloom.sh

@@ -30,6 +30,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	rm file_to_be_deleted &&
 	git add . &&
 	git commit -m "file removed" &&
+	git commit --allow-empty -m "empty" &&
 	git commit-graph write --reachable --changed-paths &&
 
 	test_oid_cache <<-EOF
@@ -37,6 +38,7 @@ test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
 	oid_version sha256:2
 	EOF
 '
+
 graph_read_expect () {
 	NUM_CHUNKS=5
 	cat >expect <<- EOF
@@ -49,7 +51,7 @@ graph_read_expect () {
 }
 
 test_expect_success 'commit-graph write wrote out the bloom chunks' '
-	graph_read_expect 15
+	graph_read_expect 16
 '
 
 # Turn off any inherited trace2 settings for this test.
@@ -58,14 +60,14 @@ sane_unset GIT_TRACE2_PERF_BRIEF
 sane_unset GIT_TRACE2_CONFIG_PARAMS
 
 setup () {
-	rm "$TRASH_DIRECTORY/trace.perf"
+	rm -f "$TRASH_DIRECTORY/trace.perf" &&
 	git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
 	GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
 }
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":${2:-0},\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -95,7 +97,9 @@ do
 		      "--ancestry-path side..master"
 	do
 		test_expect_success "git log option: $option for path: $path" '
-			test_bloom_filters_used "$option -- $path"
+			test_bloom_filters_used "$option -- $path" &&
+			test_config commitgraph.readChangedPaths false &&
+			test_bloom_filters_not_used "$option -- $path"
 		'
 	done
 done
@@ -139,8 +143,11 @@ test_expect_success 'setup - add commit-graph to the chain without Bloom filters
 	test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
 '
 
-test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
+test_expect_success 'use Bloom filters even if the latest graph does not have Bloom filters' '
-	test_bloom_filters_not_used "-- A/B"
+	# Ensure that the number of empty filters is equal to the number of
+	# filters in the latest graph layer to prove that they are loaded (and
+	# ignored).
+	test_bloom_filters_used "-- A/B" 3
 '
 
 test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
@@ -151,7 +158,7 @@ test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
 
 test_bloom_filters_used_when_some_filters_are_missing () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"maybe\":6,\"definitely_not\":8"
+	bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"maybe\":6,\"definitely_not\":9"
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom
@@ -169,31 +176,230 @@ test_expect_success 'persist filter settings' '
 		GIT_TEST_BLOOM_SETTINGS_NUM_HASHES=9 \
 		GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY=15 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2.txt &&
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15,\"max_changed_paths\":512" trace2.txt &&
 	GIT_TRACE2_EVENT="$(pwd)/trace2-auto.txt" \
 		GIT_TRACE2_EVENT_NESTING=5 \
 		git commit-graph write --reachable --changed-paths &&
-	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt
+	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15,\"max_changed_paths\":512" trace2-auto.txt
 '
 
+test_max_changed_paths () {
+	grep "\"max_changed_paths\":$1" $2
+}
+
+test_filter_not_computed () {
+	grep "\"key\":\"filter-not-computed\",\"value\":\"$1\"" $2
+}
+
+test_filter_computed () {
+	grep "\"key\":\"filter-computed\",\"value\":\"$1\"" $2
+}
+
+test_filter_trunc_empty () {
+	grep "\"key\":\"filter-trunc-empty\",\"value\":\"$1\"" $2
+}
+
+test_filter_trunc_large () {
+	grep "\"key\":\"filter-trunc-large\",\"value\":\"$1\"" $2
+}
+
 test_expect_success 'correctly report changes over limit' '
-	git init 513changes &&
+	git init limits &&
 	(
-		cd 513changes &&
+		cd limits &&
-		for i in $(test_seq 1 513)
+		mkdir d &&
+		mkdir d/e &&
+
+		for i in $(test_seq 1 2)
 		do
-			echo $i >file$i.txt || return 1
+			printf $i >d/file$i.txt &&
+			printf $i >d/e/file$i.txt || return 1
 		done &&
-		git add . &&
+
+		mkdir mode &&
+		printf bash >mode/script.sh &&
+
+		mkdir foo &&
+		touch foo/bar &&
+		touch foo.txt &&
+
+		git add d foo foo.txt mode &&
 		git commit -m "files" &&
+
+		# Commit has 7 file and 4 directory adds
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace" \
 			git commit-graph write --reachable --changed-paths &&
-		for i in $(test_seq 1 513)
+		test_max_changed_paths 10 trace &&
+		test_filter_computed 1 trace &&
+		test_filter_trunc_large 1 trace &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
 		do
-			git -c core.commitGraph=false log -- file$i.txt >expect &&
+			git -c commitGraph.readChangedPaths=false log \
-			git log -- file$i.txt >actual &&
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# Make a variety of path changes
+		printf new1 >d/e/file1.txt &&
+		printf new2 >d/file2.txt &&
+		rm d/e/file2.txt &&
+		rm -r foo &&
+		printf text >foo &&
+		mkdir f &&
+		printf new1 >f/file1.txt &&
+
+		# including a mode-only change (counts as modified)
+		git update-index --chmod=+x mode/script.sh &&
+
+		git add foo d f &&
+		git commit -m "complicated" &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-edit" \
+			git commit-graph write --reachable --changed-paths &&
+		test_max_changed_paths 10 trace-edit &&
+		test_filter_computed 2 trace-edit &&
+		test_filter_trunc_large 2 trace-edit &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
+			test_cmp expect actual || return 1
+		done &&
+
+		# start from scratch and rebuild
+		rm -f .git/objects/info/commit-graph &&
+		GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=11 \
+			GIT_TRACE2_EVENT="$(pwd)/trace-update" \
+			git commit-graph write --reachable --changed-paths &&
+		test_max_changed_paths 11 trace-update &&
+		test_filter_computed 2 trace-update &&
+		test_filter_trunc_large 0 trace-update &&
+
+		for path in $(git ls-tree -r --name-only HEAD)
+		do
+			git -c commitGraph.readChangedPaths=false log \
+				-- $path >expect &&
+			git log -- $path >actual &&
 			test_cmp expect actual || return 1
 		done
 	)
 '
 
+test_expect_success 'correctly report commits with no changed paths' '
+	git init empty &&
+	test_when_finished "rm -fr empty" &&
+	(
+		cd empty &&
+
+		git commit --allow-empty -m "initial commit" &&
+
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --changed-paths &&
+		test_filter_computed 1 trace.event &&
+		test_filter_not_computed 0 trace.event &&
+		test_filter_trunc_empty 1 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success 'Bloom generation is limited by --max-new-filters' '
+	(
+		cd limits &&
+		test_commit c2 filter &&
+		test_commit c3 filter &&
+		test_commit c4 no-filter &&
+
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --split=replace \
+				--changed-paths --max-new-filters=2 &&
+
+		test_filter_computed 2 trace.event &&
+		test_filter_not_computed 3 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success 'Bloom generation backfills previously-skipped filters' '
+	# Check specifying commitGraph.maxNewFilters over "git config" works.
+	test_config -C limits commitGraph.maxNewFilters 1 &&
+	(
+		cd limits &&
+
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --changed-paths \
+				--split=replace &&
+		test_filter_computed 1 trace.event &&
+		test_filter_not_computed 4 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success '--max-new-filters overrides configuration' '
+	git init override &&
+	test_when_finished "rm -fr override" &&
+	test_config -C override commitGraph.maxNewFilters 2 &&
+	(
+		cd override &&
+		test_commit one &&
+		test_commit two &&
+
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable --changed-paths \
+				--max-new-filters=1 &&
+		test_filter_computed 1 trace.event &&
+		test_filter_not_computed 1 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
+test_expect_success 'Bloom generation backfills empty commits' '
+	git init empty &&
+	test_when_finished "rm -fr empty" &&
+	(
+		cd empty &&
+		for i in $(test_seq 1 6)
+		do
+			git commit --allow-empty -m "$i"
+		done &&
+
+		# Generate Bloom filters for empty commits 1-6, two at a time.
+		for i in $(test_seq 1 3)
+		do
+			rm -f trace.event &&
+			GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+				git commit-graph write --reachable \
+					--changed-paths --max-new-filters=2 &&
+			test_filter_computed 2 trace.event &&
+			test_filter_not_computed 4 trace.event &&
+			test_filter_trunc_empty 2 trace.event &&
+			test_filter_trunc_large 0 trace.event
+		done &&
+
+		# Finally, make sure that once all commits have filters, that
+		# none are subsequently recomputed.
+		rm -f trace.event &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.event" \
+			git commit-graph write --reachable \
+				--changed-paths --max-new-filters=2 &&
+		test_filter_computed 0 trace.event &&
+		test_filter_not_computed 6 trace.event &&
+		test_filter_trunc_empty 0 trace.event &&
+		test_filter_trunc_large 0 trace.event
+	)
+'
+
 test_done

t/t5324-split-commit-graph.sh

@@ -427,4 +427,17 @@ done <<\EOF
 0600 -r--------
 EOF
 
+test_expect_success '--split=replace with partial Bloom data' '
+	rm -rf $graphdir $infodir/commit-graph &&
+	git reset --hard commits/3 &&
+	git rev-list -1 HEAD~2 >a &&
+	git rev-list -1 HEAD~1 >b &&
+	git commit-graph write --split=no-merge --stdin-commits --changed-paths <a &&
+	git commit-graph write --split=no-merge --stdin-commits <b &&
+	git commit-graph write --split=replace --stdin-commits --changed-paths <c &&
+	ls $graphdir/graph-*.graph >graph-files &&
+	test_line_count = 1 graph-files &&
+	verify_chain_files_exist $graphdir
+'
+
 test_done

tree-diff.c

@@ -434,7 +434,7 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		if (diff_can_quit_early(opt))
 			break;
 
-		if (opt->max_changes && opt->num_changes > opt->max_changes)
+		if (opt->max_changes && diff_queued_diff.nr > opt->max_changes)
 			break;
 
 		if (opt->pathspec.nr) {
@@ -521,7 +521,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 
 			/* t↓ */
 			update_tree_entry(&t);
-			opt->num_changes++;
 		}
 
 		/* t > p[imin] */
@@ -539,7 +538,6 @@ static struct combine_diff_path *ll_diff_tree_paths(
 		skip_emit_tp:
 			/* ∀ pi=p[imin]  pi↓ */
 			update_tp_entries(tp, nparent);
-			opt->num_changes++;
 		}
 	}
 
@@ -557,7 +555,6 @@ struct combine_diff_path *diff_tree_paths(
 	const struct object_id **parents_oid, int nparent,
 	struct strbuf *base, struct diff_options *opt)
 {
-	opt->num_changes = 0;
 	p = ll_diff_tree_paths(p, oid, parents_oid, nparent, base, opt);
 
 	/*