Merge branch 'ds/commit-graph-format-v2' into pu

Introduce version 2 of the commit-graph format to correct
deficiency in the initial version.

cf. <pull.112.v2.git.gitgitgadget@gmail.com> (v2)

* ds/commit-graph-format-v2:
  commit-graph: implement file format version 2
  commit-graph: add --version=<n> option
  commit-graph: create new version flags
  commit-graph: collapse parameters into flags
  commit-graph: return with errors during write

Author: gitster

Documentation/git-commit-graph.txt

@@ -51,6 +51,9 @@ or `--stdin-packs`.)
 +
 With the `--append` option, include all commits that are present in the
 existing commit-graph file.
++
+With the `--version=<n>` option, specify the file format version. Used
+only for testing.
 
 'read'::
 

Documentation/technical/commit-graph-format.txt

@@ -31,13 +31,22 @@ and hash type.
 
 All 4-byte numbers are in network order.
 
+There are two versions available, 1 and 2. These currently differ only in
+the header.
+
 HEADER:
 
+All commit-graph files use the first five bytes for the same purpose.
+
   4-byte signature:
       The signature is: {'C', 'G', 'P', 'H'}
 
   1-byte version number:
-      Currently, the only valid version is 1.
+      Currently, the valid version numbers are 1 and 2.
+
+The remainder of the header changes depending on the version.
+
+Version 1:
 
   1-byte Hash Version (1 = SHA-1)
       We infer the hash length (H) from this value.
@@ -47,6 +56,21 @@ HEADER:
   1-byte (reserved for later use)
      Current clients should ignore this value.
 
+Version 2:
+
+  1-byte number (C) of "chunks"
+
+  1-byte reachability index version number:
+      Currently, the only valid number is 1.
+
+  1-byte (reserved for later use)
+      Current clients expect this value to be zero, and will not
+      try to read the commit-graph file if it is non-zero.
+
+  4-byte format identifier for the hash algorithm:
+      If this identifier does not agree with the repository's current
+      hash algorithm, then the client will not read the commit graph.
+
 CHUNK LOOKUP:
 
   (C + 1) * 12 bytes listing the table of contents for the chunks:

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] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits] [--version=<n>]"),
 	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] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits] [--version=<n>]"),
 	NULL
 };
 
@@ -35,6 +35,7 @@ static struct opts_commit_graph {
 	int stdin_packs;
 	int stdin_commits;
 	int append;
+	int version;
 } opts;
 
 
@@ -116,6 +117,11 @@ static int graph_read(int argc, const char **argv)
 		*(unsigned char*)(graph->data + 5),
 		*(unsigned char*)(graph->data + 6),
 		*(unsigned char*)(graph->data + 7));
+
+	if (*(unsigned char *)(graph->data + 4) == 2)
+		printf("hash algorithm: %X\n",
+		       get_be32(graph->data + 8));
+
 	printf("num_commits: %u\n", graph->num_commits);
 	printf("chunks:");
 
@@ -141,6 +147,8 @@ static int graph_write(int argc, const char **argv)
 	struct string_list *pack_indexes = NULL;
 	struct string_list *commit_hex = NULL;
 	struct string_list lines;
+	int result;
+	int flags = COMMIT_GRAPH_PROGRESS;
 
 	static struct option builtin_commit_graph_write_options[] = {
 		OPT_STRING(0, "object-dir", &opts.obj_dir,
@@ -154,6 +162,8 @@ static int graph_write(int argc, const char **argv)
 			N_("start walk at commits listed by stdin")),
 		OPT_BOOL(0, "append", &opts.append,
 			N_("include all commits already in the commit-graph file")),
+		OPT_INTEGER(0, "version", &opts.version,
+			N_("specify the file format version")),
 		OPT_END(),
 	};
 
@@ -165,14 +175,24 @@ static int graph_write(int argc, const char **argv)
 		die(_("use at most one of --reachable, --stdin-commits, or --stdin-packs"));
 	if (!opts.obj_dir)
 		opts.obj_dir = get_object_directory();
+	if (opts.append)
+		flags |= COMMIT_GRAPH_APPEND;
 
-	read_replace_refs = 0;
+	switch (opts.version) {
+	case 1:
+		flags |= COMMIT_GRAPH_VERSION_1;
+		break;
 
-	if (opts.reachable) {
-		write_commit_graph_reachable(opts.obj_dir, opts.append, 1);
-		return 0;
+	case 2:
+		flags |= COMMIT_GRAPH_VERSION_2;
+		break;
 	}
 
+	read_replace_refs = 0;
+
+	if (opts.reachable)
+		return write_commit_graph_reachable(opts.obj_dir, flags);
+
 	string_list_init(&lines, 0);
 	if (opts.stdin_packs || opts.stdin_commits) {
 		struct strbuf buf = STRBUF_INIT;
@@ -188,14 +208,13 @@ static int graph_write(int argc, const char **argv)
 		UNLEAK(buf);
 	}
 
-	write_commit_graph(opts.obj_dir,
-			   pack_indexes,
-			   commit_hex,
-			   opts.append,
-			   1);
+	result = write_commit_graph(opts.obj_dir,
+				    pack_indexes,
+				    commit_hex,
+				    flags);
 
 	UNLEAK(lines);
-	return 0;
+	return result;
 }
 
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)

builtin/commit.c

@@ -1669,8 +1669,9 @@ int cmd_commit(int argc, const char **argv, const char *prefix)
 		      "new_index file. Check that disk is not full and quota is\n"
 		      "not exceeded, and then \"git restore --staged :/\" to recover."));
 
-	if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0))
-		write_commit_graph_reachable(get_object_directory(), 0, 0);
+	if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
+	    write_commit_graph_reachable(get_object_directory(), 0))
+		return 1;
 
 	repo_rerere(the_repository, 0);
 	run_command_v_opt(argv_gc_auto, RUN_GIT_CMD);

builtin/gc.c

@@ -685,9 +685,10 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		clean_pack_garbage();
 	}
 
-	if (gc_write_commit_graph)
-		write_commit_graph_reachable(get_object_directory(), 0,
-					     !quiet && !daemonized);
+	if (gc_write_commit_graph &&
+	    write_commit_graph_reachable(get_object_directory(),
+					 !quiet && !daemonized ? COMMIT_GRAPH_PROGRESS : 0))
+		return 1;
 
 	if (auto_gc && too_many_loose_objects())
 		warning(_("There are too many unreachable loose objects; "