builtin/repack.c: allow configuring cruft pack generation

In servers which set the pack.window configuration to a large value, we
can wind up spending quite a lot of time finding new bases when breaking
delta chains between reachable and unreachable objects while generating
a cruft pack.

Introduce a handful of `repack.cruft*` configuration variables to
control the parameters used by pack-objects when generating a cruft
pack.

Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

Documentation/config/repack.txt

@@ -30,3 +30,12 @@ repack.updateServerInfo::
 	If set to false, linkgit:git-repack[1] will not run
 	linkgit:git-update-server-info[1]. Defaults to true. Can be overridden
 	when true by the `-n` option of linkgit:git-repack[1].
+
+repack.cruftWindow::
+repack.cruftWindowMemory::
+repack.cruftDepth::
+repack.cruftThreads::
+	Parameters used by linkgit:git-pack-objects[1] when generating
+	a cruft pack and the respective parameters are not given over
+	the command line. See similarly named `pack.*` configuration
+	variables for defaults and meaning.

builtin/repack.c

@@ -41,9 +41,21 @@ static const char incremental_bitmap_conflict_error[] = N_(
 "--no-write-bitmap-index or disable the pack.writebitmaps configuration."
 );
 
+struct pack_objects_args {
+	const char *window;
+	const char *window_memory;
+	const char *depth;
+	const char *threads;
+	const char *max_pack_size;
+	int no_reuse_delta;
+	int no_reuse_object;
+	int quiet;
+	int local;
+};
 
 static int repack_config(const char *var, const char *value, void *cb)
 {
+	struct pack_objects_args *cruft_po_args = cb;
 	if (!strcmp(var, "repack.usedeltabaseoffset")) {
 		delta_base_offset = git_config_bool(var, value);
 		return 0;
@@ -65,6 +77,14 @@ static int repack_config(const char *var, const char *value, void *cb)
 		run_update_server_info = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "repack.cruftwindow"))
+		return git_config_string(&cruft_po_args->window, var, value);
+	if (!strcmp(var, "repack.cruftwindowmemory"))
+		return git_config_string(&cruft_po_args->window_memory, var, value);
+	if (!strcmp(var, "repack.cruftdepth"))
+		return git_config_string(&cruft_po_args->depth, var, value);
+	if (!strcmp(var, "repack.cruftthreads"))
+		return git_config_string(&cruft_po_args->threads, var, value);
 	return git_default_config(var, value, cb);
 }
 
@@ -157,18 +177,6 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name)
 	strbuf_release(&buf);
 }
 
-struct pack_objects_args {
-	const char *window;
-	const char *window_memory;
-	const char *depth;
-	const char *threads;
-	const char *max_pack_size;
-	int no_reuse_delta;
-	int no_reuse_object;
-	int quiet;
-	int local;
-};
-
 static void prepare_pack_objects(struct child_process *cmd,
 				 const struct pack_objects_args *args)
 {
@@ -692,6 +700,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int keep_unreachable = 0;
 	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	struct pack_objects_args po_args = {NULL};
+	struct pack_objects_args cruft_po_args = {NULL};
 	int geometric_factor = 0;
 	int write_midx = 0;
 
@@ -746,7 +755,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		OPT_END()
 	};
 
-	git_config(repack_config, NULL);
+	git_config(repack_config, &cruft_po_args);
 
 	argc = parse_options(argc, argv, prefix, builtin_repack_options,
 				git_repack_usage, 0);
@@ -921,7 +930,19 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		if (*pack_prefix == '/')
 			pack_prefix++;
 
-		ret = write_cruft_pack(&po_args, pack_prefix, &names,
+		if (!cruft_po_args.window)
+			cruft_po_args.window = po_args.window;
+		if (!cruft_po_args.window_memory)
+			cruft_po_args.window_memory = po_args.window_memory;
+		if (!cruft_po_args.depth)
+			cruft_po_args.depth = po_args.depth;
+		if (!cruft_po_args.threads)
+			cruft_po_args.threads = po_args.threads;
+
+		cruft_po_args.local = po_args.local;
+		cruft_po_args.quiet = po_args.quiet;
+
+		ret = write_cruft_pack(&cruft_po_args, pack_prefix, &names,
 				       &existing_nonkept_packs,
 				       &existing_kept_packs);
 		if (ret)

t/t5329-pack-objects-cruft.sh

@@ -565,4 +565,87 @@ test_expect_success 'cruft repack ignores pack.packSizeLimit' '
 	)
 '
 
+test_expect_success 'cruft repack respects repack.cruftWindow' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+
+		GIT_TRACE2_EVENT=$(pwd)/event.trace \
+		git -c pack.window=1 -c repack.cruftWindow=2 repack \
+		       --cruft --window=3 &&
+
+		grep "pack-objects.*--window=2.*--cruft" event.trace
+	)
+'
+
+test_expect_success 'cruft repack respects --window by default' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+
+		GIT_TRACE2_EVENT=$(pwd)/event.trace \
+		git -c pack.window=2 repack --cruft --window=3 &&
+
+		grep "pack-objects.*--window=3.*--cruft" event.trace
+	)
+'
+
+test_expect_success 'cruft repack respects --quiet' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+		GIT_PROGRESS_DELAY=0 git repack --cruft --quiet 2>err &&
+		test_must_be_empty err
+	)
+'
+
+test_expect_success 'cruft --local drops unreachable objects' '
+	git init alternate &&
+	git init repo &&
+	test_when_finished "rm -fr alternate repo" &&
+
+	test_commit -C alternate base &&
+	# Pack all objects in alterate so that the cruft repack in "repo" sees
+	# the object it dropped due to `--local` as packed. Otherwise this
+	# object would not appear packed anywhere (since it is not packed in
+	# alternate and likewise not part of the cruft pack in the other repo
+	# because of `--local`).
+	git -C alternate repack -ad &&
+
+	(
+		cd repo &&
+
+		object="$(git -C ../alternate rev-parse HEAD:base.t)" &&
+		git -C ../alternate cat-file -p $object >contents &&
+
+		# Write some reachable objects and two unreachable ones: one
+		# that the alternate has and another that is unique.
+		test_commit other &&
+		git hash-object -w -t blob contents &&
+		cruft="$(echo cruft | git hash-object -w -t blob --stdin)" &&
+
+		( cd ../alternate/.git/objects && pwd ) \
+		       >.git/objects/info/alternates &&
+
+		test_path_is_file $objdir/$(test_oid_to_path $cruft) &&
+		test_path_is_file $objdir/$(test_oid_to_path $object) &&
+
+		git repack -d --cruft --local &&
+
+		test-tool pack-mtimes "$(basename $(ls $packdir/pack-*.mtimes))" \
+		       >objects &&
+		! grep $object objects &&
+		grep $cruft objects
+	)
+'
+
 test_done