Merge branch 'ns/batch-fsync'

Introduce a filesystem-dependent mechanism to optimize the way the
bits for many loose object files are ensured to hit the disk
platter.

* ns/batch-fsync:
  core.fsyncmethod: performance tests for batch mode
  t/perf: add iteration setup mechanism to perf-lib
  core.fsyncmethod: tests for batch mode
  test-lib-functions: add parsing helpers for ls-files and ls-tree
  core.fsync: use batch mode and sync loose objects by default on Windows
  unpack-objects: use the bulk-checkin infrastructure
  update-index: use the bulk-checkin infrastructure
  builtin/add: add ODB transaction around add_files_to_cache
  cache-tree: use ODB transaction around writing a tree
  core.fsyncmethod: batched disk flushes for loose-objects
  bulk-checkin: rebrand plug/unplug APIs as 'odb transactions'
  bulk-checkin: rename 'state' variable and separate 'plugged' boolean

Documentation/config/core.txt

@@ -628,6 +628,14 @@ core.fsyncMethod::
 * `writeout-only` issues pagecache writeback requests, but depending on the
   filesystem and storage hardware, data added to the repository may not be
   durable in the event of a system crash. This is the default mode on macOS.
+* `batch` enables a mode that uses writeout-only flushes to stage multiple
+  updates in the disk writeback cache and then does a single full fsync of
+  a dummy file to trigger the disk cache flush at the end of the operation.
++
+Currently `batch` mode only applies to loose-object files. Other repository
+data is made durable as if `fsync` was specified. This mode is expected to
+be as safe as `fsync` on macOS for repos stored on HFS+ or APFS filesystems
+and on Windows for repos stored on NTFS or ReFS filesystems.
 
 core.fsyncObjectFiles::
 	This boolean will enable 'fsync()' when writing object files.

builtin/add.c

@@ -141,7 +141,16 @@ int add_files_to_cache(const char *prefix,
 	rev.diffopt.format_callback_data = &data;
 	rev.diffopt.flags.override_submodule_config = 1;
 	rev.max_count = 0; /* do not compare unmerged paths with stage #2 */
+
+	/*
+	 * Use an ODB transaction to optimize adding multiple objects.
+	 * This function is invoked from commands other than 'add', which
+	 * may not have their own transaction active.
+	 */
+	begin_odb_transaction();
 	run_diff_files(&rev, DIFF_RACY_IS_MODIFIED);
+	end_odb_transaction();
+
 	clear_pathspec(&rev.prune_data);
 	return !!data.add_errors;
 }
@@ -665,7 +674,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 		string_list_clear(&only_match_skip_worktree, 0);
 	}
 
-	plug_bulk_checkin();
+	begin_odb_transaction();
 
 	if (add_renormalize)
 		exit_status |= renormalize_tracked_files(&pathspec, flags);
@@ -677,7 +686,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 
 	if (chmod_arg && pathspec.nr)
 		exit_status |= chmod_pathspec(&pathspec, chmod_arg[0], show_only);
-	unplug_bulk_checkin();
+	end_odb_transaction();
 
 finish:
 	if (write_locked_index(&the_index, &lock_file,

builtin/unpack-objects.c

@@ -1,5 +1,6 @@
 #include "builtin.h"
 #include "cache.h"
+#include "bulk-checkin.h"
 #include "config.h"
 #include "object-store.h"
 #include "object.h"
@@ -503,10 +504,12 @@ static void unpack_all(void)
 	if (!quiet)
 		progress = start_progress(_("Unpacking objects"), nr_objects);
 	CALLOC_ARRAY(obj_list, nr_objects);
+	begin_odb_transaction();
 	for (i = 0; i < nr_objects; i++) {
 		unpack_one(i);
 		display_progress(progress, i + 1);
 	}
+	end_odb_transaction();
 	stop_progress(&progress);
 
 	if (delta_list)

builtin/update-index.c

@@ -5,6 +5,7 @@
  */
 #define USE_THE_INDEX_COMPATIBILITY_MACROS
 #include "cache.h"
+#include "bulk-checkin.h"
 #include "config.h"
 #include "lockfile.h"
 #include "quote.h"
@@ -57,6 +58,14 @@ static void report(const char *fmt, ...)
 	if (!verbose)
 		return;
 
+	/*
+	 * It is possible, though unlikely, that a caller could use the verbose
+	 * output to synchronize with addition of objects to the object
+	 * database. The current implementation of ODB transactions leaves
+	 * objects invisible while a transaction is active, so flush the
+	 * transaction here before reporting a change made by update-index.
+	 */
+	flush_odb_transaction();
 	va_start(vp, fmt);
 	vprintf(fmt, vp);
 	putchar('\n');
@@ -1116,6 +1125,12 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 	 */
 	parse_options_start(&ctx, argc, argv, prefix,
 			    options, PARSE_OPT_STOP_AT_NON_OPTION);
+
+	/*
+	 * Allow the object layer to optimize adding multiple objects in
+	 * a batch.
+	 */
+	begin_odb_transaction();
 	while (ctx.argc) {
 		if (parseopt_state != PARSE_OPT_DONE)
 			parseopt_state = parse_options_step(&ctx, options,
@@ -1190,6 +1205,11 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 		strbuf_release(&buf);
 	}
 
+	/*
+	 * By now we have added all of the new objects
+	 */
+	end_odb_transaction();
+
 	if (split_index > 0) {
 		if (git_config_get_split_index() == 0)
 			warning(_("core.splitIndex is set to false; "

bulk-checkin.c

@@ -3,16 +3,21 @@
  */
 #include "cache.h"
 #include "bulk-checkin.h"
+#include "lockfile.h"
 #include "repository.h"
 #include "csum-file.h"
 #include "pack.h"
 #include "strbuf.h"
+#include "string-list.h"
+#include "tmp-objdir.h"
 #include "packfile.h"
 #include "object-store.h"
 
-static struct bulk_checkin_state {
+static int odb_transaction_nesting;
-	unsigned plugged:1;
 
+static struct tmp_objdir *bulk_fsync_objdir;
+
+static struct bulk_checkin_packfile {
 	char *pack_tmp_name;
 	struct hashfile *f;
 	off_t offset;
@@ -21,7 +26,7 @@ static struct bulk_checkin_state {
 	struct pack_idx_entry **written;
 	uint32_t alloc_written;
 	uint32_t nr_written;
-} state;
+} bulk_checkin_packfile;
 
 static void finish_tmp_packfile(struct strbuf *basename,
 				const char *pack_tmp_name,
@@ -39,7 +44,7 @@ static void finish_tmp_packfile(struct strbuf *basename,
 	free(idx_tmp_name);
 }
 
-static void finish_bulk_checkin(struct bulk_checkin_state *state)
+static void flush_bulk_checkin_packfile(struct bulk_checkin_packfile *state)
 {
 	unsigned char hash[GIT_MAX_RAWSZ];
 	struct strbuf packname = STRBUF_INIT;
@@ -80,7 +85,41 @@ clear_exit:
 	reprepare_packed_git(the_repository);
 }
 
-static int already_written(struct bulk_checkin_state *state, struct object_id *oid)
+/*
+ * Cleanup after batch-mode fsync_object_files.
+ */
+static void flush_batch_fsync(void)
+{
+	struct strbuf temp_path = STRBUF_INIT;
+	struct tempfile *temp;
+
+	if (!bulk_fsync_objdir)
+		return;
+
+	/*
+	 * Issue a full hardware flush against a temporary file to ensure
+	 * that all objects are durable before any renames occur. The code in
+	 * fsync_loose_object_bulk_checkin has already issued a writeout
+	 * request, but it has not flushed any writeback cache in the storage
+	 * hardware or any filesystem logs. This fsync call acts as a barrier
+	 * to ensure that the data in each new object file is durable before
+	 * the final name is visible.
+	 */
+	strbuf_addf(&temp_path, "%s/bulk_fsync_XXXXXX", get_object_directory());
+	temp = xmks_tempfile(temp_path.buf);
+	fsync_or_die(get_tempfile_fd(temp), get_tempfile_path(temp));
+	delete_tempfile(&temp);
+	strbuf_release(&temp_path);
+
+	/*
+	 * Make the object files visible in the primary ODB after their data is
+	 * fully durable.
+	 */
+	tmp_objdir_migrate(bulk_fsync_objdir);
+	bulk_fsync_objdir = NULL;
+}
+
+static int already_written(struct bulk_checkin_packfile *state, struct object_id *oid)
 {
 	int i;
 
@@ -112,7 +151,7 @@ static int already_written(struct bulk_checkin_state *state, struct object_id *o
  * status before calling us just in case we ask it to call us again
  * with a new pack.
  */
-static int stream_to_pack(struct bulk_checkin_state *state,
+static int stream_to_pack(struct bulk_checkin_packfile *state,
 			  git_hash_ctx *ctx, off_t *already_hashed_to,
 			  int fd, size_t size, enum object_type type,
 			  const char *path, unsigned flags)
@@ -189,7 +228,7 @@ static int stream_to_pack(struct bulk_checkin_state *state,
 }
 
 /* Lazily create backing packfile for the state */
-static void prepare_to_stream(struct bulk_checkin_state *state,
+static void prepare_to_stream(struct bulk_checkin_packfile *state,
 			      unsigned flags)
 {
 	if (!(flags & HASH_WRITE_OBJECT) || state->f)
@@ -204,7 +243,7 @@ static void prepare_to_stream(struct bulk_checkin_state *state,
 		die_errno("unable to write pack header");
 }
 
-static int deflate_to_pack(struct bulk_checkin_state *state,
+static int deflate_to_pack(struct bulk_checkin_packfile *state,
 			   struct object_id *result_oid,
 			   int fd, size_t size,
 			   enum object_type type, const char *path,
@@ -251,7 +290,7 @@ static int deflate_to_pack(struct bulk_checkin_state *state,
 			BUG("should not happen");
 		hashfile_truncate(state->f, &checkpoint);
 		state->offset = checkpoint.offset;
-		finish_bulk_checkin(state);
+		flush_bulk_checkin_packfile(state);
 		if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
 			return error("cannot seek back");
 	}
@@ -274,25 +313,67 @@ static int deflate_to_pack(struct bulk_checkin_state *state,
 	return 0;
 }
 
+void prepare_loose_object_bulk_checkin(void)
+{
+	/*
+	 * We lazily create the temporary object directory
+	 * the first time an object might be added, since
+	 * callers may not know whether any objects will be
+	 * added at the time they call begin_odb_transaction.
+	 */
+	if (!odb_transaction_nesting || bulk_fsync_objdir)
+		return;
+
+	bulk_fsync_objdir = tmp_objdir_create("bulk-fsync");
+	if (bulk_fsync_objdir)
+		tmp_objdir_replace_primary_odb(bulk_fsync_objdir, 0);
+}
+
+void fsync_loose_object_bulk_checkin(int fd, const char *filename)
+{
+	/*
+	 * If we have an active ODB transaction, we issue a call that
+	 * cleans the filesystem page cache but avoids a hardware flush
+	 * command. Later on we will issue a single hardware flush
+	 * before renaming the objects to their final names as part of
+	 * flush_batch_fsync.
+	 */
+	if (!bulk_fsync_objdir ||
+	    git_fsync(fd, FSYNC_WRITEOUT_ONLY) < 0) {
+		fsync_or_die(fd, filename);
+	}
+}
+
 int index_bulk_checkin(struct object_id *oid,
 		       int fd, size_t size, enum object_type type,
 		       const char *path, unsigned flags)
 {
-	int status = deflate_to_pack(&state, oid, fd, size, type,
+	int status = deflate_to_pack(&bulk_checkin_packfile, oid, fd, size, type,
 				     path, flags);
-	if (!state.plugged)
+	if (!odb_transaction_nesting)
-		finish_bulk_checkin(&state);
+		flush_bulk_checkin_packfile(&bulk_checkin_packfile);
 	return status;
 }
 
-void plug_bulk_checkin(void)
+void begin_odb_transaction(void)
 {
-	state.plugged = 1;
+	odb_transaction_nesting += 1;
 }
 
-void unplug_bulk_checkin(void)
+void flush_odb_transaction(void)
 {
-	state.plugged = 0;
+	flush_batch_fsync();
-	if (state.f)
+	flush_bulk_checkin_packfile(&bulk_checkin_packfile);
-		finish_bulk_checkin(&state);
+}
+
+void end_odb_transaction(void)
+{
+	odb_transaction_nesting -= 1;
+	if (odb_transaction_nesting < 0)
+		BUG("Unbalanced ODB transaction nesting");
+
+	if (odb_transaction_nesting)
+		return;
+
+	flush_odb_transaction();
 }

bulk-checkin.h

@@ -6,11 +6,34 @@
 
 #include "cache.h"
 
+void prepare_loose_object_bulk_checkin(void);
+void fsync_loose_object_bulk_checkin(int fd, const char *filename);
+
 int index_bulk_checkin(struct object_id *oid,
 		       int fd, size_t size, enum object_type type,
 		       const char *path, unsigned flags);
 
-void plug_bulk_checkin(void);
+/*
-void unplug_bulk_checkin(void);
+ * Tell the object database to optimize for adding
+ * multiple objects. end_odb_transaction must be called
+ * to make new objects visible. Transactions can be nested,
+ * and objects are only visible after the outermost transaction
+ * is complete or the transaction is flushed.
+ */
+void begin_odb_transaction(void);
+
+/*
+ * Make any objects that are currently part of a pending object
+ * database transaction visible. It is valid to call this function
+ * even if no transaction is active.
+ */
+void flush_odb_transaction(void);
+
+/*
+ * Tell the object database to make any objects from the
+ * current transaction visible if this is the final nested
+ * transaction.
+ */
+void end_odb_transaction(void);
 
 #endif

cache-tree.c

@@ -3,6 +3,7 @@
 #include "tree.h"
 #include "tree-walk.h"
 #include "cache-tree.h"
+#include "bulk-checkin.h"
 #include "object-store.h"
 #include "replace-object.h"
 #include "promisor-remote.h"
@@ -474,8 +475,10 @@ int cache_tree_update(struct index_state *istate, int flags)
 
 	trace_performance_enter();
 	trace2_region_enter("cache_tree", "update", the_repository);
+	begin_odb_transaction();
 	i = update_one(istate->cache_tree, istate->cache, istate->cache_nr,
 		       "", 0, &skip, flags);
+	end_odb_transaction();
 	trace2_region_leave("cache_tree", "update", the_repository);
 	trace_performance_leave("cache_tree_update");
 	if (i < 0)

cache.h

@@ -1031,6 +1031,10 @@ enum fsync_component {
 			      FSYNC_COMPONENT_INDEX | \
 			      FSYNC_COMPONENT_REFERENCE)
 
+#ifndef FSYNC_COMPONENTS_PLATFORM_DEFAULT
+#define FSYNC_COMPONENTS_PLATFORM_DEFAULT FSYNC_COMPONENTS_DEFAULT
+#endif
+
 /*
  * A bitmask indicating which components of the repo should be fsynced.
  */
@@ -1040,7 +1044,8 @@ extern int use_fsync;
 
 enum fsync_method {
 	FSYNC_METHOD_FSYNC,
-	FSYNC_METHOD_WRITEOUT_ONLY
+	FSYNC_METHOD_WRITEOUT_ONLY,
+	FSYNC_METHOD_BATCH,
 };
 
 extern enum fsync_method fsync_method;
@@ -1766,6 +1771,11 @@ void fsync_or_die(int fd, const char *);
 int fsync_component(enum fsync_component component, int fd);
 void fsync_component_or_die(enum fsync_component component, int fd, const char *msg);
 
+static inline int batch_fsync_enabled(enum fsync_component component)
+{
+	return (fsync_components & component) && (fsync_method == FSYNC_METHOD_BATCH);
+}
+
 ssize_t read_in_full(int fd, void *buf, size_t count);
 ssize_t write_in_full(int fd, const void *buf, size_t count);
 ssize_t pread_in_full(int fd, void *buf, size_t count, off_t offset);

compat/mingw.h

@@ -332,6 +332,9 @@ int mingw_getpagesize(void);
 int win32_fsync_no_flush(int fd);
 #define fsync_no_flush win32_fsync_no_flush
 
+#define FSYNC_COMPONENTS_PLATFORM_DEFAULT (FSYNC_COMPONENTS_DEFAULT | FSYNC_COMPONENT_LOOSE_OBJECT)
+#define FSYNC_METHOD_DEFAULT (FSYNC_METHOD_BATCH)
+
 struct rlimit {
 	unsigned int rlim_cur;
 };

config.c

@@ -1342,7 +1342,7 @@ static const struct fsync_component_name {
 
 static enum fsync_component parse_fsync_components(const char *var, const char *string)
 {
-	enum fsync_component current = FSYNC_COMPONENTS_DEFAULT;
+	enum fsync_component current = FSYNC_COMPONENTS_PLATFORM_DEFAULT;
 	enum fsync_component positive = 0, negative = 0;
 
 	while (string) {
@@ -1688,6 +1688,8 @@ static int git_default_core_config(const char *var, const char *value, void *cb)
 			fsync_method = FSYNC_METHOD_FSYNC;
 		else if (!strcmp(value, "writeout-only"))
 			fsync_method = FSYNC_METHOD_WRITEOUT_ONLY;
+		else if (!strcmp(value, "batch"))
+			fsync_method = FSYNC_METHOD_BATCH;
 		else
 			warning(_("ignoring unknown core.fsyncMethod value '%s'"), value);
 

git-compat-util.h

@@ -1324,11 +1324,13 @@ __attribute__((format (printf, 3, 4))) NORETURN
 void BUG_fl(const char *file, int line, const char *fmt, ...);
 #define BUG(...) BUG_fl(__FILE__, __LINE__, __VA_ARGS__)
 
+#ifndef FSYNC_METHOD_DEFAULT
 #ifdef __APPLE__
 #define FSYNC_METHOD_DEFAULT FSYNC_METHOD_WRITEOUT_ONLY
 #else
 #define FSYNC_METHOD_DEFAULT FSYNC_METHOD_FSYNC
 #endif
+#endif
 
 enum fsync_action {
 	FSYNC_WRITEOUT_ONLY,

object-file.c

@@ -1893,7 +1893,9 @@ static void close_loose_object(int fd, const char *filename)
 	if (the_repository->objects->odb->will_destroy)
 		goto out;
 
-	if (fsync_object_files > 0)
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		fsync_loose_object_bulk_checkin(fd, filename);
+	else if (fsync_object_files > 0)
 		fsync_or_die(fd, filename);
 	else
 		fsync_component_or_die(FSYNC_COMPONENT_LOOSE_OBJECT, fd,
@@ -1961,6 +1963,9 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 	static struct strbuf tmp_file = STRBUF_INIT;
 	static struct strbuf filename = STRBUF_INIT;
 
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		prepare_loose_object_bulk_checkin();
+
 	loose_object_path(the_repository, &filename, oid);
 
 	fd = create_tmpfile(&tmp_file, filename.buf);

t/lib-unique-files.sh

@@ -0,0 +1,34 @@
+# Helper to create files with unique contents
+
+# Create multiple files with unique contents within this test run. Takes the
+# number of directories, the number of files in each directory, and the base
+# directory.
+#
+# test_create_unique_files 2 3 my_dir -- Creates 2 directories with 3 files
+#					 each in my_dir, all with contents
+#					 different from previous invocations
+#					 of this command in this run.
+
+test_create_unique_files () {
+	test "$#" -ne 3 && BUG "3 param"
+
+	local dirs="$1" &&
+	local files="$2" &&
+	local basedir="$3" &&
+	local counter="0" &&
+	local i &&
+	local j &&
+	test_tick &&
+	local basedata="$basedir$test_tick" &&
+	rm -rf "$basedir" &&
+	for i in $(test_seq $dirs)
+	do
+		local dir="$basedir/dir$i" &&
+		mkdir -p "$dir" &&
+		for j in $(test_seq $files)
+		do
+			counter=$((counter + 1)) &&
+			echo "$basedata.$counter">"$dir/file$j.txt"
+		done
+	done
+}

t/perf/p0008-odb-fsync.sh

@@ -0,0 +1,82 @@
+#!/bin/sh
+#
+# This test measures the performance of adding new files to the object
+# database. The test was originally added to measure the effect of the
+# core.fsyncMethod=batch mode, which is why we are testing different values of
+# that setting explicitly and creating a lot of unique objects.
+
+test_description="Tests performance of adding things to the object database"
+
+. ./perf-lib.sh
+
+. $TEST_DIRECTORY/lib-unique-files.sh
+
+test_perf_fresh_repo
+test_checkout_worktree
+
+dir_count=10
+files_per_dir=50
+total_files=$((dir_count * files_per_dir))
+
+populate_files () {
+	test_create_unique_files $dir_count $files_per_dir files
+}
+
+setup_repo () {
+	(rm -rf .git || 1) &&
+	git init &&
+	test_commit first &&
+	populate_files
+}
+
+test_perf_fsync_cfgs () {
+	local method &&
+	local cfg &&
+	for method in none fsync batch writeout-only
+	do
+		case $method in
+		none)
+			cfg="-c core.fsync=none"
+			;;
+		*)
+			cfg="-c core.fsync=loose-object -c core.fsyncMethod=$method"
+		esac &&
+
+		# Set GIT_TEST_FSYNC=1 explicitly since fsync is normally
+		# disabled by t/test-lib.sh.
+		if ! test_perf "$1 (fsyncMethod=$method)" \
+						--setup "$2" \
+						"GIT_TEST_FSYNC=1 git $cfg $3"
+		then
+			break
+		fi
+	done
+}
+
+test_perf_fsync_cfgs "add $total_files files" \
+	"setup_repo" \
+	"add -- files"
+
+test_perf_fsync_cfgs "stash $total_files files" \
+	"setup_repo" \
+	"stash push -u -- files"
+
+test_perf_fsync_cfgs "unpack $total_files files" \
+	"
+	setup_repo &&
+	git -c core.fsync=none add -- files &&
+	git -c core.fsync=none commit -q -m second &&
+	echo HEAD | git pack-objects -q --stdout --revs >test_pack.pack &&
+	setup_repo
+	" \
+	"unpack-objects -q <test_pack.pack"
+
+test_perf_fsync_cfgs "commit $total_files files" \
+	"
+	setup_repo &&
+	git -c core.fsync=none add -- files &&
+	populate_files
+	" \
+	"commit -q -a -m test"
+
+test_done

t/perf/p4220-log-grep-engines.sh

@@ -36,7 +36,8 @@ do
 		else
 			prereq=""
 		fi
-		test_perf $prereq "$engine log$GIT_PERF_4220_LOG_OPTS --grep='$pattern'" "
+		test_perf "$engine log$GIT_PERF_4220_LOG_OPTS --grep='$pattern'" \
+			--prereq "$prereq" "
 			git -c grep.patternType=$engine log --pretty=format:%h$GIT_PERF_4220_LOG_OPTS --grep='$pattern' >'out.$engine' || :
 		"
 	done

t/perf/p4221-log-grep-engines-fixed.sh

@@ -26,7 +26,8 @@ do
 		else
 			prereq=""
 		fi
-		test_perf $prereq "$engine log$GIT_PERF_4221_LOG_OPTS --grep='$pattern'" "
+		test_perf "$engine log$GIT_PERF_4221_LOG_OPTS --grep='$pattern'" \
+			--prereq "$prereq" "
 			git -c grep.patternType=$engine log --pretty=format:%h$GIT_PERF_4221_LOG_OPTS --grep='$pattern' >'out.$engine' || :
 		"
 	done

t/perf/p5302-pack-index.sh

@@ -26,9 +26,8 @@ test_expect_success 'set up thread-counting tests' '
 	done
 '
 
-test_perf PERF_EXTRA 'index-pack 0 threads' '
+test_perf 'index-pack 0 threads' --prereq PERF_EXTRA \
-	rm -rf repo.git &&
+	--setup 'rm -rf repo.git && git init --bare repo.git' '
-	git init --bare repo.git &&
 	GIT_DIR=repo.git git index-pack --threads=1 --stdin < $PACK
 '
 
@@ -36,17 +35,15 @@ for t in $threads
 do
 	THREADS=$t
 	export THREADS
-	test_perf PERF_EXTRA "index-pack $t threads" '
+	test_perf "index-pack $t threads" --prereq PERF_EXTRA \
-		rm -rf repo.git &&
+		--setup 'rm -rf repo.git && git init --bare repo.git' '
-		git init --bare repo.git &&
 		GIT_DIR=repo.git GIT_FORCE_THREADS=1 \
 		git index-pack --threads=$THREADS --stdin <$PACK
 	'
 done
 
-test_perf 'index-pack default number of threads' '
+test_perf 'index-pack default number of threads' \
-	rm -rf repo.git &&
+	--setup 'rm -rf repo.git && git init --bare repo.git' '
-	git init --bare repo.git &&
 	GIT_DIR=repo.git git index-pack --stdin < $PACK
 '
 

t/perf/p7519-fsmonitor.sh

@@ -60,18 +60,6 @@ then
 	esac
 fi
 
-if test -n "$GIT_PERF_7519_DROP_CACHE"
-then
-	# When using GIT_PERF_7519_DROP_CACHE, GIT_PERF_REPEAT_COUNT must be 1 to
-	# generate valid results. Otherwise the caching that happens for the nth
-	# run will negate the validity of the comparisons.
-	if test "$GIT_PERF_REPEAT_COUNT" -ne 1
-	then
-		echo "warning: Setting GIT_PERF_REPEAT_COUNT=1" >&2
-		GIT_PERF_REPEAT_COUNT=1
-	fi
-fi
-
 trace_start () {
 	if test -n "$GIT_PERF_7519_TRACE"
 	then
@@ -175,10 +163,10 @@ setup_for_fsmonitor_hook () {
 
 test_perf_w_drop_caches () {
 	if test -n "$GIT_PERF_7519_DROP_CACHE"; then
-		test-tool drop-caches
+		test_perf "$1" --setup "test-tool drop-caches" "$2"
-	fi
+	else
-
 		test_perf "$@"
+	fi
 }
 
 test_fsmonitor_suite () {

t/perf/p7820-grep-engines.sh

@@ -49,13 +49,15 @@ do
 		fi
 		if ! test_have_prereq PERF_GREP_ENGINES_THREADS
 		then
-			test_perf $prereq "$engine grep$GIT_PERF_7820_GREP_OPTS '$pattern'" "
+			test_perf "$engine grep$GIT_PERF_7820_GREP_OPTS '$pattern'" \
+				--prereq "$prereq" "
 				git -c grep.patternType=$engine grep$GIT_PERF_7820_GREP_OPTS -- '$pattern' >'out.$engine' || :
 			"
 		else
 			for threads in $GIT_PERF_GREP_THREADS
 			do
-				test_perf PTHREADS,$prereq "$engine grep$GIT_PERF_7820_GREP_OPTS '$pattern' with $threads threads" "
+				test_perf "$engine grep$GIT_PERF_7820_GREP_OPTS '$pattern' with $threads threads"
+					--prereq PTHREADS,$prereq "
 					git -c grep.patternType=$engine -c grep.threads=$threads grep$GIT_PERF_7820_GREP_OPTS -- '$pattern' >'out.$engine.$threads' || :
 				"
 			done

t/perf/perf-lib.sh

@@ -189,19 +189,39 @@ exit $ret' >&3 2>&4
 }
 
 test_wrapper_ () {
-	test_wrapper_func_=$1; shift
+	local test_wrapper_func_="$1"; shift
+	local test_title_="$1"; shift
 	test_start_
-	test "$#" = 3 && { test_prereq=$1; shift; } || test_prereq=
+	test_prereq=
-	test "$#" = 2 ||
+	test_perf_setup_=
-	BUG "not 2 or 3 parameters to test-expect-success"
+	while test $# != 0
+	do
+		case $1 in
+		--prereq)
+			test_prereq=$2
+			shift
+			;;
+		--setup)
+			test_perf_setup_=$2
+			shift
+			;;
+		*)
+			break
+			;;
+		esac
+		shift
+	done
+	test "$#" = 1 || BUG "test_wrapper_ needs 2 positional parameters"
 	export test_prereq
-	if ! test_skip "$@"
+	export test_perf_setup_
+
+	if ! test_skip "$test_title_" "$@"
 	then
 		base=$(basename "$0" .sh)
 		echo "$test_count" >>"$perf_results_dir"/$base.subtests
 		echo "$1" >"$perf_results_dir"/$base.$test_count.descr
 		base="$perf_results_dir"/"$PERF_RESULTS_PREFIX$(basename "$0" .sh)"."$test_count"
-		"$test_wrapper_func_" "$@"
+		"$test_wrapper_func_" "$test_title_" "$@"
 	fi
 
 	test_finish_
@@ -214,6 +234,16 @@ test_perf_ () {
 		echo "perf $test_count - $1:"
 	fi
 	for i in $(test_seq 1 $GIT_PERF_REPEAT_COUNT); do
+		if test -n "$test_perf_setup_"
+		then
+			say >&3 "setup: $test_perf_setup_"
+			if ! test_eval_ $test_perf_setup_
+			then
+				test_failure_ "$test_perf_setup_"
+				break
+			fi
+
+		fi
 		say >&3 "running: $2"
 		if test_run_perf_ "$2"
 		then
@@ -237,11 +267,24 @@ test_perf_ () {
 	rm test_time.*
 }
 
+# Usage: test_perf 'title' [options] 'perf-test'
+#	Run the performance test script specified in perf-test with
+#	optional prerequisite and setup steps.
+# Options:
+#	--prereq prerequisites: Skip the test if prequisites aren't met
+#	--setup "setup-steps": Run setup steps prior to each measured iteration
+#
 test_perf () {
 	test_wrapper_ test_perf_ "$@"
 }
 
 test_size_ () {
+	if test -n "$test_perf_setup_"
+	then
+		say >&3 "setup: $test_perf_setup_"
+		test_eval_ $test_perf_setup_
+	fi
+
 	say >&3 "running: $2"
 	if test_eval_ "$2" 3>"$base".result; then
 		test_ok_ "$1"
@@ -250,6 +293,14 @@ test_size_ () {
 	fi
 }
 
+# Usage: test_size 'title' [options] 'size-test'
+#	Run the size test script specified in size-test with optional
+#	prerequisites and setup steps. Returns the numeric value
+#	returned by size-test.
+# Options:
+#	--prereq prerequisites: Skip the test if prequisites aren't met
+#	--setup "setup-steps": Run setup steps prior to the size measurement
+
 test_size () {
 	test_wrapper_ test_size_ "$@"
 }

t/t3700-add.sh

@@ -8,6 +8,8 @@ test_description='Test of git add, including the -- option.'
 TEST_PASSES_SANITIZE_LEAK=true
 . ./test-lib.sh
 
+. $TEST_DIRECTORY/lib-unique-files.sh
+
 # Test the file mode "$1" of the file "$2" in the index.
 test_mode_in_index () {
 	case "$(git ls-files -s "$2")" in
@@ -34,6 +36,32 @@ test_expect_success \
     'Test that "git add -- -q" works' \
     'touch -- -q && git add -- -q'
 
+BATCH_CONFIGURATION='-c core.fsync=loose-object -c core.fsyncmethod=batch'
+
+test_expect_success 'git add: core.fsyncmethod=batch' "
+	test_create_unique_files 2 4 files_base_dir1 &&
+	GIT_TEST_FSYNC=1 git $BATCH_CONFIGURATION add -- ./files_base_dir1/ &&
+	git ls-files --stage files_base_dir1/ |
+	test_parse_ls_files_stage_oids >added_files_oids &&
+
+	# We created 2 subdirs with 4 files each (8 files total) above
+	test_line_count = 8 added_files_oids &&
+	git cat-file --batch-check='%(objectname)' <added_files_oids >added_files_actual &&
+	test_cmp added_files_oids added_files_actual
+"
+
+test_expect_success 'git update-index: core.fsyncmethod=batch' "
+	test_create_unique_files 2 4 files_base_dir2 &&
+	find files_base_dir2 ! -type d -print | xargs git $BATCH_CONFIGURATION update-index --add -- &&
+	git ls-files --stage files_base_dir2 |
+	test_parse_ls_files_stage_oids >added_files2_oids &&
+
+	# We created 2 subdirs with 4 files each (8 files total) above
+	test_line_count = 8 added_files2_oids &&
+	git cat-file --batch-check='%(objectname)' <added_files2_oids >added_files2_actual &&
+	test_cmp added_files2_oids added_files2_actual
+"
+
 test_expect_success \
 	'git add: Test that executable bit is not used if core.filemode=0' \
 	'git config core.filemode 0 &&

t/t3903-stash.sh

@@ -9,6 +9,7 @@ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
 export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 
 . ./test-lib.sh
+. $TEST_DIRECTORY/lib-unique-files.sh
 
 test_expect_success 'usage on cmd and subcommand invalid option' '
 	test_expect_code 129 git stash --invalid-option 2>usage &&
@@ -1410,6 +1411,25 @@ test_expect_success 'stash handles skip-worktree entries nicely' '
 	git rev-parse --verify refs/stash:A.t
 '
 
+
+BATCH_CONFIGURATION='-c core.fsync=loose-object -c core.fsyncmethod=batch'
+
+test_expect_success 'stash with core.fsyncmethod=batch' "
+	test_create_unique_files 2 4 files_base_dir &&
+	GIT_TEST_FSYNC=1 git $BATCH_CONFIGURATION stash push -u -- ./files_base_dir/ &&
+
+	# The files were untracked, so use the third parent,
+	# which contains the untracked files
+	git ls-tree -r stash^3 -- ./files_base_dir/ |
+	test_parse_ls_tree_oids >stashed_files_oids &&
+
+	# We created 2 dirs with 4 files each (8 files total) above
+	test_line_count = 8 stashed_files_oids &&
+	git cat-file --batch-check='%(objectname)' <stashed_files_oids >stashed_files_actual &&
+	test_cmp stashed_files_oids stashed_files_actual
+"
+
+
 test_expect_success 'git stash succeeds despite directory/file change' '
 	test_create_repo directory_file_switch_v1 &&
 	(

t/t5300-pack-object.sh

@@ -161,22 +161,27 @@ test_expect_success 'pack-objects with bogus arguments' '
 '
 
 check_unpack () {
+	local packname="$1" &&
+	local object_list="$2" &&
+	local git_config="$3" &&
 	test_when_finished "rm -rf git2" &&
-	git init --bare git2 &&
+	git $git_config init --bare git2 &&
-	git -C git2 unpack-objects -n <"$1".pack &&
+	(
-	git -C git2 unpack-objects <"$1".pack &&
+		git $git_config -C git2 unpack-objects -n <"$packname".pack &&
-	(cd .git && find objects -type f -print) |
+		git $git_config -C git2 unpack-objects <"$packname".pack &&
-	while read path
+		git $git_config -C git2 cat-file --batch-check="%(objectname)"
-	do
+	) <"$object_list" >current &&
-		cmp git2/$path .git/$path || {
+	cmp "$object_list" current
-			echo $path differs.
-			return 1
-		}
-	done
 }
 
 test_expect_success 'unpack without delta' '
-	check_unpack test-1-${packname_1}
+	check_unpack test-1-${packname_1} obj-list
+'
+
+BATCH_CONFIGURATION='-c core.fsync=loose-object -c core.fsyncmethod=batch'
+
+test_expect_success 'unpack without delta (core.fsyncmethod=batch)' '
+	check_unpack test-1-${packname_1} obj-list "$BATCH_CONFIGURATION"
 '
 
 test_expect_success 'pack with REF_DELTA' '
@@ -185,7 +190,11 @@ test_expect_success 'pack with REF_DELTA' '
 '
 
 test_expect_success 'unpack with REF_DELTA' '
-	check_unpack test-2-${packname_2}
+	check_unpack test-2-${packname_2} obj-list
+'
+
+test_expect_success 'unpack with REF_DELTA (core.fsyncmethod=batch)' '
+       check_unpack test-2-${packname_2} obj-list "$BATCH_CONFIGURATION"
 '
 
 test_expect_success 'pack with OFS_DELTA' '
@@ -195,7 +204,11 @@ test_expect_success 'pack with OFS_DELTA' '
 '
 
 test_expect_success 'unpack with OFS_DELTA' '
-	check_unpack test-3-${packname_3}
+	check_unpack test-3-${packname_3} obj-list
+'
+
+test_expect_success 'unpack with OFS_DELTA (core.fsyncmethod=batch)' '
+       check_unpack test-3-${packname_3} obj-list "$BATCH_CONFIGURATION"
 '
 
 test_expect_success 'compare delta flavors' '

t/t5317-pack-objects-filter-objects.sh

@@ -10,9 +10,6 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 # Test blob:none filter.
 
 test_expect_success 'setup r1' '
-	echo "{print \$1}" >print_1.awk &&
-	echo "{print \$2}" >print_2.awk &&
-
 	git init r1 &&
 	for n in 1 2 3 4 5
 	do
@@ -22,10 +19,13 @@ test_expect_success 'setup r1' '
 	done
 '
 
+parse_verify_pack_blob_oid () {
+	awk '{print $1}' -
+}
+
 test_expect_success 'verify blob count in normal packfile' '
-	git -C r1 ls-files -s file.1 file.2 file.3 file.4 file.5 \
+	git -C r1 ls-files -s file.1 file.2 file.3 file.4 file.5 |
-		>ls_files_result &&
+	test_parse_ls_files_stage_oids |
-	awk -f print_2.awk ls_files_result |
 	sort >expected &&
 
 	git -C r1 pack-objects --revs --stdout >all.pack <<-EOF &&
@@ -35,7 +35,7 @@ test_expect_success 'verify blob count in normal packfile' '
 
 	git -C r1 verify-pack -v ../all.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -54,12 +54,12 @@ test_expect_success 'verify blob:none packfile has no blobs' '
 test_expect_success 'verify normal and blob:none packfiles have same commits/trees' '
 	git -C r1 verify-pack -v ../all.pack >verify_result &&
 	grep -E "commit|tree" verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >expected &&
 
 	git -C r1 verify-pack -v ../filter.pack >verify_result &&
 	grep -E "commit|tree" verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -123,8 +123,8 @@ test_expect_success 'setup r2' '
 '
 
 test_expect_success 'verify blob count in normal packfile' '
-	git -C r2 ls-files -s large.1000 large.10000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 large.10000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r2 pack-objects --revs --stdout >all.pack <<-EOF &&
@@ -134,7 +134,7 @@ test_expect_success 'verify blob count in normal packfile' '
 
 	git -C r2 verify-pack -v ../all.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -161,8 +161,8 @@ test_expect_success 'verify blob:limit=1000' '
 '
 
 test_expect_success 'verify blob:limit=1001' '
-	git -C r2 ls-files -s large.1000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r2 pack-objects --revs --stdout --filter=blob:limit=1001 >filter.pack <<-EOF &&
@@ -172,15 +172,15 @@ test_expect_success 'verify blob:limit=1001' '
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify blob:limit=10001' '
-	git -C r2 ls-files -s large.1000 large.10000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 large.10000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r2 pack-objects --revs --stdout --filter=blob:limit=10001 >filter.pack <<-EOF &&
@@ -190,15 +190,15 @@ test_expect_success 'verify blob:limit=10001' '
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify blob:limit=1k' '
-	git -C r2 ls-files -s large.1000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r2 pack-objects --revs --stdout --filter=blob:limit=1k >filter.pack <<-EOF &&
@@ -208,15 +208,15 @@ test_expect_success 'verify blob:limit=1k' '
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify explicitly specifying oversized blob in input' '
-	git -C r2 ls-files -s large.1000 large.10000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 large.10000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	echo HEAD >objects &&
@@ -226,15 +226,15 @@ test_expect_success 'verify explicitly specifying oversized blob in input' '
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify blob:limit=1m' '
-	git -C r2 ls-files -s large.1000 large.10000 >ls_files_result &&
+	git -C r2 ls-files -s large.1000 large.10000 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r2 pack-objects --revs --stdout --filter=blob:limit=1m >filter.pack <<-EOF &&
@@ -244,7 +244,7 @@ test_expect_success 'verify blob:limit=1m' '
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -253,12 +253,12 @@ test_expect_success 'verify blob:limit=1m' '
 test_expect_success 'verify normal and blob:limit packfiles have same commits/trees' '
 	git -C r2 verify-pack -v ../all.pack >verify_result &&
 	grep -E "commit|tree" verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >expected &&
 
 	git -C r2 verify-pack -v ../filter.pack >verify_result &&
 	grep -E "commit|tree" verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -289,9 +289,8 @@ test_expect_success 'setup r3' '
 '
 
 test_expect_success 'verify blob count in normal packfile' '
-	git -C r3 ls-files -s sparse1 sparse2 dir1/sparse1 dir1/sparse2 \
+	git -C r3 ls-files -s sparse1 sparse2 dir1/sparse1 dir1/sparse2 |
-		>ls_files_result &&
+	test_parse_ls_files_stage_oids |
-	awk -f print_2.awk ls_files_result |
 	sort >expected &&
 
 	git -C r3 pack-objects --revs --stdout >all.pack <<-EOF &&
@@ -301,7 +300,7 @@ test_expect_success 'verify blob count in normal packfile' '
 
 	git -C r3 verify-pack -v ../all.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -342,9 +341,8 @@ test_expect_success 'setup r4' '
 '
 
 test_expect_success 'verify blob count in normal packfile' '
-	git -C r4 ls-files -s pattern sparse1 sparse2 dir1/sparse1 dir1/sparse2 \
+	git -C r4 ls-files -s pattern sparse1 sparse2 dir1/sparse1 dir1/sparse2 |
-		>ls_files_result &&
+	test_parse_ls_files_stage_oids |
-	awk -f print_2.awk ls_files_result |
 	sort >expected &&
 
 	git -C r4 pack-objects --revs --stdout >all.pack <<-EOF &&
@@ -354,19 +352,19 @@ test_expect_success 'verify blob count in normal packfile' '
 
 	git -C r4 verify-pack -v ../all.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify sparse:oid=OID' '
-	git -C r4 ls-files -s dir1/sparse1 dir1/sparse2 >ls_files_result &&
+	git -C r4 ls-files -s dir1/sparse1 dir1/sparse2 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r4 ls-files -s pattern >staged &&
-	oid=$(awk -f print_2.awk staged) &&
+	oid=$(test_parse_ls_files_stage_oids <staged) &&
 	git -C r4 pack-objects --revs --stdout --filter=sparse:oid=$oid >filter.pack <<-EOF &&
 	HEAD
 	EOF
@@ -374,15 +372,15 @@ test_expect_success 'verify sparse:oid=OID' '
 
 	git -C r4 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
 '
 
 test_expect_success 'verify sparse:oid=oid-ish' '
-	git -C r4 ls-files -s dir1/sparse1 dir1/sparse2 >ls_files_result &&
+	git -C r4 ls-files -s dir1/sparse1 dir1/sparse2 |
-	awk -f print_2.awk ls_files_result |
+	test_parse_ls_files_stage_oids |
 	sort >expected &&
 
 	git -C r4 pack-objects --revs --stdout --filter=sparse:oid=main:pattern >filter.pack <<-EOF &&
@@ -392,7 +390,7 @@ test_expect_success 'verify sparse:oid=oid-ish' '
 
 	git -C r4 verify-pack -v ../filter.pack >verify_result &&
 	grep blob verify_result |
-	awk -f print_1.awk |
+	parse_verify_pack_blob_oid |
 	sort >observed &&
 
 	test_cmp expected observed
@@ -402,9 +400,8 @@ test_expect_success 'verify sparse:oid=oid-ish' '
 # This models previously omitted objects that we did not receive.
 
 test_expect_success 'setup r1 - delete loose blobs' '
-	git -C r1 ls-files -s file.1 file.2 file.3 file.4 file.5 \
+	git -C r1 ls-files -s file.1 file.2 file.3 file.4 file.5 |
-		>ls_files_result &&
+	test_parse_ls_files_stage_oids |
-	awk -f print_2.awk ls_files_result |
 	sort >expected &&
 
 	for id in `cat expected | sed "s|..|&/|"`

t/test-lib-functions.sh

@@ -1782,6 +1782,16 @@ test_oid_to_path () {
 	echo "${1%$basename}/$basename"
 }
 
+# Parse oids from git ls-files --staged output
+test_parse_ls_files_stage_oids () {
+	awk '{print $2}' -
+}
+
+# Parse oids from git ls-tree output
+test_parse_ls_tree_oids () {
+	awk '{print $3}' -
+}
+
 # Choose a port number based on the test script's number and store it in
 # the given variable name, unless that variable already contains a number.
 test_set_port () {