commit-graph: create options for split files

The split commit-graph feature is now fully implemented, but needs
some more run-time configurability. Allow direct callers to 'git
commit-graph write --split' to specify the values used in the
merge strategy and the expire time.

Update the documentation to specify these values.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-commit-graph.txt

@@ -26,7 +26,7 @@ OPTIONS
 	Use given directory for the location of packfiles and commit-graph
 	file. This parameter exists to specify the location of an alternate
 	that only has the objects directory, not a full `.git` directory. The
-	commit-graph file is expected to be at `<dir>/info/commit-graph` and
+	commit-graph file is expected to be in the `<dir>/info` directory and
 	the packfiles are expected to be in `<dir>/pack`.
 
 
@@ -51,6 +51,25 @@ or `--stdin-packs`.)
 +
 With the `--append` option, include all commits that are present in the
 existing commit-graph file.
++
+With the `--split` option, write the commit-graph as a chain of multiple
+commit-graph files stored in `<dir>/info/commit-graphs`. The new commits
+not already in the commit-graph are added in a new "tip" file. This file
+is merged with the existing file if the following merge conditions are
+met:
++
+* If `--size-multiple=<X>` is not specified, let `X` equal 2. If the new
+tip file would have `N` commits and the previous tip has `M` commits and
+`X` times `N` is greater than  `M`, instead merge the two files into a
+single file.
++
+* If `--max-commits=<M>` is specified with `M` a positive integer, and the
+new tip file would have more than `M` commits, then instead merge the new
+tip with the previous tip.
++
+Finally, if `--expire-time=<datetime>` is not specified, let `datetime`
+be the current time. After writing the split commit-graph, delete all
+unused commit-graph whose modified times are older than `datetime`.
 
 'read'::
 

Documentation/technical/commit-graph.txt

@@ -248,10 +248,11 @@ When writing a set of commits that do not exist in the commit-graph stack of
 height N, we default to creating a new file at level N + 1. We then decide to
 merge with the Nth level if one of two conditions hold:
 
-  1. The expected file size for level N + 1 is at least half the file size for
+  1. `--size-multiple=<X>` is specified or X = 2, and the number of commits in
-     level N.
+     level N is less than X times the number of commits in level N + 1.
 
-  2. Level N + 1 contains more than 64,0000 commits.
+  2. `--max-commits=<C>` is specified with non-zero C and the number of commits
+     in level N + 1 is more than C commits.
 
 This decision cascades down the levels: when we merge a level we create a new
 set of commits that then compares to the next level.

builtin/commit-graph.c

@@ -10,7 +10,7 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph [--object-dir <objdir>]"),
 	N_("git commit-graph read [--object-dir <objdir>]"),
 	N_("git commit-graph verify [--object-dir <objdir>]"),
-	N_("git commit-graph write [--object-dir <objdir>] [--append|--split] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append|--split] [--reachable|--stdin-packs|--stdin-commits] <split options>"),
 	NULL
 };
 
@@ -25,7 +25,7 @@ static const char * const builtin_commit_graph_read_usage[] = {
 };
 
 static const char * const builtin_commit_graph_write_usage[] = {
-	N_("git commit-graph write [--object-dir <objdir>] [--append|--split] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append|--split] [--reachable|--stdin-packs|--stdin-commits] <split options>"),
 	NULL
 };
 
@@ -135,6 +135,7 @@ static int graph_read(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
+static struct split_commit_graph_opts split_opts;
 
 static int graph_write(int argc, const char **argv)
 {
@@ -158,9 +159,19 @@ static int graph_write(int argc, const char **argv)
 			N_("include all commits already in the commit-graph file")),
 		OPT_BOOL(0, "split", &opts.split,
 			N_("allow writing an incremental commit-graph file")),
+		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
+			N_("maximum number of commits in a non-base split commit-graph")),
+		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
+			N_("maximum ratio between two levels of a split commit-graph")),
+		OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
+			N_("maximum number of commits in a non-base split commit-graph")),
 		OPT_END(),
 	};
 
+	split_opts.size_multiple = 2;
+	split_opts.max_commits = 0;
+	split_opts.expire_time = 0;
+
 	argc = parse_options(argc, argv, NULL,
 			     builtin_commit_graph_write_options,
 			     builtin_commit_graph_write_usage, 0);
@@ -176,8 +187,11 @@ static int graph_write(int argc, const char **argv)
 
 	read_replace_refs = 0;
 
-	if (opts.reachable)
+	if (opts.reachable) {
-		return write_commit_graph_reachable(opts.obj_dir, flags);
+		if (write_commit_graph_reachable(opts.obj_dir, flags, &split_opts))
+			return 1;
+		return 0;
+	}
 
 	string_list_init(&lines, 0);
 	if (opts.stdin_packs || opts.stdin_commits) {
@@ -197,7 +211,8 @@ static int graph_write(int argc, const char **argv)
 	if (write_commit_graph(opts.obj_dir,
 			       pack_indexes,
 			       commit_hex,
-			       flags))
+			       flags,
+			       &split_opts))
 		result = 1;
 
 	UNLEAK(lines);

builtin/commit.c

@@ -1670,7 +1670,7 @@ int cmd_commit(int argc, const char **argv, const char *prefix)
 		      "not exceeded, and then \"git reset HEAD\" to recover."));
 
 	if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
-	    write_commit_graph_reachable(get_object_directory(), 0))
+	    write_commit_graph_reachable(get_object_directory(), 0, NULL))
 		return 1;
 
 	repo_rerere(the_repository, 0);

builtin/gc.c

@@ -666,7 +666,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 
 	if (gc_write_commit_graph &&
 	    write_commit_graph_reachable(get_object_directory(),
-					 !quiet && !daemonized ? COMMIT_GRAPH_PROGRESS : 0))
+					 !quiet && !daemonized ? COMMIT_GRAPH_PROGRESS : 0,
+					 NULL))
 		return 1;
 
 	if (auto_gc && too_many_loose_objects())

commit-graph.c

@@ -768,6 +768,8 @@ struct write_commit_graph_context {
 	unsigned append:1,
 		 report_progress:1,
 		 split:1;
+
+	const struct split_commit_graph_opts *split_opts;
 };
 
 static void write_graph_chunk_fanout(struct hashfile *f,
@@ -1116,14 +1118,15 @@ static int add_ref_to_list(const char *refname,
 	return 0;
 }
 
-int write_commit_graph_reachable(const char *obj_dir, unsigned int flags)
+int write_commit_graph_reachable(const char *obj_dir, unsigned int flags,
+				 const struct split_commit_graph_opts *split_opts)
 {
 	struct string_list list = STRING_LIST_INIT_DUP;
 	int result;
 
 	for_each_ref(add_ref_to_list, &list);
 	result = write_commit_graph(obj_dir, NULL, &list,
-				    flags);
+				    flags, split_opts);
 
 	string_list_clear(&list, 0);
 	return result;
@@ -1498,20 +1501,25 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	return 0;
 }
 
-static int split_strategy_max_commits = 64000;
-static float split_strategy_size_mult = 2.0f;
-
 static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 {
 	struct commit_graph *g = ctx->r->objects->commit_graph;
 	uint32_t num_commits = ctx->commits.nr;
 	uint32_t i;
 
+	int max_commits = 0;
+	int size_mult = 2;
+
+	if (ctx->split_opts) {
+		max_commits = ctx->split_opts->max_commits;
+		size_mult = ctx->split_opts->size_multiple;
+	}
+
 	g = ctx->r->objects->commit_graph;
 	ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
 
-	while (g && (g->num_commits <= split_strategy_size_mult * num_commits ||
+	while (g && (g->num_commits <= size_mult * num_commits ||
-		     num_commits > split_strategy_max_commits)) {
+		    (max_commits && num_commits > max_commits))) {
 		if (strcmp(g->obj_dir, ctx->obj_dir))
 			break;
 
@@ -1675,7 +1683,10 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 	DIR *dir;
 	struct dirent *de;
 	size_t dirnamelen;
-	time_t expire_time = time(NULL);
+	timestamp_t expire_time = time(NULL);
+
+	if (ctx->split_opts && ctx->split_opts->expire_time)
+		expire_time -= ctx->split_opts->expire_time;
 
 	strbuf_addstr(&path, ctx->obj_dir);
 	strbuf_addstr(&path, "/info/commit-graphs");
@@ -1719,7 +1730,8 @@ static void expire_commit_graphs(struct write_commit_graph_context *ctx)
 int write_commit_graph(const char *obj_dir,
 		       struct string_list *pack_indexes,
 		       struct string_list *commit_hex,
-		       unsigned int flags)
+		       unsigned int flags,
+		       const struct split_commit_graph_opts *split_opts)
 {
 	struct write_commit_graph_context *ctx;
 	uint32_t i, count_distinct = 0;
@@ -1734,6 +1746,7 @@ int write_commit_graph(const char *obj_dir,
 	ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0;
 	ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0;
 	ctx->split = flags & COMMIT_GRAPH_SPLIT ? 1 : 0;
+	ctx->split_opts = split_opts;
 
 	if (ctx->split) {
 		struct commit_graph *g;
@@ -1761,8 +1774,8 @@ int write_commit_graph(const char *obj_dir,
 	ctx->approx_nr_objects = approximate_object_count();
 	ctx->oids.alloc = ctx->approx_nr_objects / 32;
 
-	if (ctx->split && ctx->oids.alloc > split_strategy_max_commits)
+	if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
-		ctx->oids.alloc = split_strategy_max_commits;
+		ctx->oids.alloc = split_opts->max_commits;
 
 	if (ctx->append) {
 		prepare_commit_graph_one(ctx->r, ctx->obj_dir);

commit-graph.h

@@ -75,17 +75,25 @@ int generation_numbers_enabled(struct repository *r);
 #define COMMIT_GRAPH_PROGRESS   (1 << 1)
 #define COMMIT_GRAPH_SPLIT      (1 << 2)
 
+struct split_commit_graph_opts {
+	int size_multiple;
+	int max_commits;
+	timestamp_t expire_time;
+};
+
 /*
  * The write_commit_graph* methods return zero on success
  * and a negative value on failure. Note that if the repository
  * is not compatible with the commit-graph feature, then the
  * methods will return 0 without writing a commit-graph.
  */
-int write_commit_graph_reachable(const char *obj_dir, unsigned int flags);
+int write_commit_graph_reachable(const char *obj_dir, unsigned int flags,
+				 const struct split_commit_graph_opts *split_opts);
 int write_commit_graph(const char *obj_dir,
 		       struct string_list *pack_indexes,
 		       struct string_list *commit_hex,
-		       unsigned int flags);
+		       unsigned int flags,
+		       const struct split_commit_graph_opts *split_opts);
 
 int verify_commit_graph(struct repository *r, struct commit_graph *g);
 

t/t5324-split-commit-graph.sh

@@ -169,4 +169,51 @@ test_expect_success 'create fork and chain across alternate' '
 
 graph_git_behavior 'alternate: commit 13 vs 6' commits/13 commits/6
 
+test_expect_success 'test merge stragety constants' '
+	git clone . merge-2 &&
+	(
+		cd merge-2 &&
+		git config core.commitGraph true &&
+		test_line_count = 2 $graphdir/commit-graph-chain &&
+		test_commit 14 &&
+		git commit-graph write --reachable --split --size-multiple=2 &&
+		test_line_count = 3 $graphdir/commit-graph-chain
+
+	) &&
+	git clone . merge-10 &&
+	(
+		cd merge-10 &&
+		git config core.commitGraph true &&
+		test_line_count = 2 $graphdir/commit-graph-chain &&
+		test_commit 14 &&
+		git commit-graph write --reachable --split --size-multiple=10 &&
+		test_line_count = 1 $graphdir/commit-graph-chain &&
+		ls $graphdir/graph-*.graph >graph-files &&
+		test_line_count = 1 graph-files
+	) &&
+	git clone . merge-10-expire &&
+	(
+		cd merge-10-expire &&
+		git config core.commitGraph true &&
+		test_line_count = 2 $graphdir/commit-graph-chain &&
+		test_commit 15 &&
+		git commit-graph write --reachable --split --size-multiple=10 --expire-time=1980-01-01 &&
+		test_line_count = 1 $graphdir/commit-graph-chain &&
+		ls $graphdir/graph-*.graph >graph-files &&
+		test_line_count = 3 graph-files
+	) &&
+	git clone --no-hardlinks . max-commits &&
+	(
+		cd max-commits &&
+		git config core.commitGraph true &&
+		test_line_count = 2 $graphdir/commit-graph-chain &&
+		test_commit 16 &&
+		test_commit 17 &&
+		git commit-graph write --reachable --split --max-commits=1 &&
+		test_line_count = 1 $graphdir/commit-graph-chain &&
+		ls $graphdir/graph-*.graph >graph-files &&
+		test_line_count = 1 graph-files
+	)
+'
+
 test_done