Merge branch 'ds/maintenance-loose-objects-batchsize'

The job to coalesce loose objects into packfiles in "git
maintenance" now has configurable batch size.

* ds/maintenance-loose-objects-batchsize:
  maintenance: add loose-objects.batchSize config
  maintenance: force progress/no-quiet to children

Author: gitster

Documentation/config/maintenance.adoc

@@ -61,6 +61,11 @@ maintenance.loose-objects.auto::
 	loose objects is at least the value of `maintenance.loose-objects.auto`.
 	The default value is 100.
 
+maintenance.loose-objects.batchSize::
+	This integer config option controls the maximum number of loose objects
+	written into a packfile during the `loose-objects` task. The default is
+	fifty thousand. Use value `0` to indicate no limit.
+
 maintenance.incremental-repack.auto::
 	This integer config option controls how often the `incremental-repack`
 	task should be run as part of `git maintenance run --auto`. If zero,

Documentation/git-maintenance.adoc

@@ -126,13 +126,17 @@ loose-objects::
 	objects that already exist in a pack-file; concurrent Git processes
 	will examine the pack-file for the object data instead of the loose
 	object. Second, it creates a new pack-file (starting with "loose-")
-	containing a batch of loose objects. The batch size is limited to 50
-	thousand objects to prevent the job from taking too long on a
-	repository with many loose objects. The `gc` task writes unreachable
-	objects as loose objects to be cleaned up by a later step only if
-	they are not re-added to a pack-file; for this reason it is not
-	advisable to enable both the `loose-objects` and `gc` tasks at the
-	same time.
+	containing a batch of loose objects.
++
+The batch size defaults to fifty thousand objects to prevent the job from
+taking too long on a repository with many loose objects. Use the
+`maintenance.loose-objects.batchSize` config option to adjust this size,
+including a value of `0` to remove the limit.
++
+The `gc` task writes unreachable objects as loose objects to be cleaned up
+by a later step only if they are not re-added to a pack-file; for this
+reason it is not advisable to enable both the `loose-objects` and `gc`
+tasks at the same time.
 
 incremental-repack::
 	The `incremental-repack` job repacks the object directory

builtin/gc.c

@@ -1029,6 +1029,8 @@ static int run_write_commit_graph(struct maintenance_run_opts *opts)
 
 	if (opts->quiet)
 		strvec_push(&child.args, "--no-progress");
+	else
+		strvec_push(&child.args, "--progress");
 
 	return !!run_command(&child);
 }
@@ -1161,6 +1163,7 @@ static int write_loose_object_to_stdin(const struct object_id *oid,
 
 	fprintf(d->in, "%s\n", oid_to_hex(oid));
 
+	/* If batch_size is INT_MAX, then this will return 0 always. */
 	return ++(d->count) > d->batch_size;
 }
 
@@ -1185,6 +1188,8 @@ static int pack_loose(struct maintenance_run_opts *opts)
 	strvec_push(&pack_proc.args, "pack-objects");
 	if (opts->quiet)
 		strvec_push(&pack_proc.args, "--quiet");
+	else
+		strvec_push(&pack_proc.args, "--no-quiet");
 	strvec_pushf(&pack_proc.args, "%s/pack/loose", r->objects->odb->path);
 
 	pack_proc.in = -1;
@@ -1204,6 +1209,15 @@ static int pack_loose(struct maintenance_run_opts *opts)
 	data.count = 0;
 	data.batch_size = 50000;
 
+	repo_config_get_int(r, "maintenance.loose-objects.batchSize",
+			    &data.batch_size);
+
+	/* If configured as 0, then remove limit. */
+	if (!data.batch_size)
+		data.batch_size = INT_MAX;
+	else if (data.batch_size > 0)
+		data.batch_size--; /* Decrease for equality on limit. */
+
 	for_each_loose_file_in_objdir(r->objects->odb->path,
 				      write_loose_object_to_stdin,
 				      NULL,
@@ -1263,6 +1277,8 @@ static int multi_pack_index_write(struct maintenance_run_opts *opts)
 
 	if (opts->quiet)
 		strvec_push(&child.args, "--no-progress");
+	else
+		strvec_push(&child.args, "--progress");
 
 	if (run_command(&child))
 		return error(_("failed to write multi-pack-index"));
@@ -1279,6 +1295,8 @@ static int multi_pack_index_expire(struct maintenance_run_opts *opts)
 
 	if (opts->quiet)
 		strvec_push(&child.args, "--no-progress");
+	else
+		strvec_push(&child.args, "--progress");
 
 	if (run_command(&child))
 		return error(_("'git multi-pack-index expire' failed"));
@@ -1335,6 +1353,8 @@ static int multi_pack_index_repack(struct maintenance_run_opts *opts)
 
 	if (opts->quiet)
 		strvec_push(&child.args, "--no-progress");
+	else
+		strvec_push(&child.args, "--progress");
 
 	strvec_pushf(&child.args, "--batch-size=%"PRIuMAX,
 				  (uintmax_t)get_auto_pack_size());

t/t7900-maintenance.sh

@@ -306,6 +306,34 @@ test_expect_success 'maintenance.loose-objects.auto' '
 	test_subcommand git prune-packed --quiet <trace-loC
 '
 
+test_expect_success 'maintenance.loose-objects.batchSize' '
+	git init loose-batch &&
+
+	# This creates three objects per commit.
+	test_commit_bulk -C loose-batch 34 &&
+	pack=$(ls loose-batch/.git/objects/pack/pack-*.pack) &&
+	index="${pack%pack}idx" &&
+	rm "$index" &&
+	git -C loose-batch unpack-objects <"$pack" &&
+	git -C loose-batch config maintenance.loose-objects.batchSize 50 &&
+
+	GIT_PROGRESS_DELAY=0 \
+	git -C loose-batch maintenance run --no-quiet --task=loose-objects 2>err &&
+	grep "Enumerating objects: 50, done." err &&
+
+	GIT_PROGRESS_DELAY=0 \
+	git -C loose-batch maintenance run --no-quiet --task=loose-objects 2>err &&
+	grep "Enumerating objects: 50, done." err &&
+
+	GIT_PROGRESS_DELAY=0 \
+	git -C loose-batch maintenance run --no-quiet --task=loose-objects 2>err &&
+	grep "Enumerating objects: 2, done." err &&
+
+	GIT_PROGRESS_DELAY=0 \
+	git -C loose-batch maintenance run --no-quiet --task=loose-objects 2>err &&
+	test_must_be_empty err
+'
+
 test_expect_success 'incremental-repack task' '
 	packDir=.git/objects/pack &&
 	for i in $(test_seq 1 5)