maintenance: create auto condition for loose-objects

The loose-objects task deletes loose objects that already exist in a
pack-file, then place the remaining loose objects into a new pack-file.
If this step runs all the time, then we risk creating pack-files with
very few objects with every 'git commit' process. To prevent
overwhelming the packs directory with small pack-files, place a minimum
number of objects to justify the task.

The 'maintenance.loose-objects.auto' config option specifies a minimum
number of loose objects to justify the task to run under the '--auto'
option. This defaults to 100 loose objects. Setting the value to zero
will prevent the step from running under '--auto' while a negative value
will force it to run every time.

Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: derrickstolee

Documentation/config/maintenance.txt

@@ -14,3 +14,12 @@ maintenance.commit-graph.auto::
 	reachable commits that are not in the commit-graph file is at least
 	the value of `maintenance.commit-graph.auto`. The default value is
 	100.
+
+maintenance.loose-objects.auto::
+	This integer config option controls how often the `loose-objects` task
+	should be run as part of `git maintenance run --auto`. If zero, then
+	the `loose-objects` task will not run with the `--auto` option. A
+	negative value will force the task to run every time. Otherwise, a
+	positive value implies the command should run when the number of
+	loose objects is at least the value of `maintenance.loose-objects.auto`.
+	The default value is 100.

builtin/gc.c

@@ -899,6 +899,35 @@ struct write_loose_object_data {
 	int batch_size;
 };
 
+static int loose_object_auto_limit = 100;
+
+static int loose_object_count(const struct object_id *oid,
+			       const char *path,
+			       void *data)
+{
+	int *count = (int*)data;
+	if (++(*count) >= loose_object_auto_limit)
+		return 1;
+	return 0;
+}
+
+static int loose_object_auto_condition(void)
+{
+	int count = 0;
+
+	git_config_get_int("maintenance.loose-objects.auto",
+			   &loose_object_auto_limit);
+
+	if (!loose_object_auto_limit)
+		return 0;
+	if (loose_object_auto_limit < 0)
+		return 1;
+
+	return for_each_loose_file_in_objdir(the_repository->objects->odb->path,
+					     loose_object_count,
+					     NULL, NULL, &count);
+}
+
 static int bail_on_loose(const struct object_id *oid,
 			 const char *path,
 			 void *data)
@@ -1009,6 +1038,7 @@ static struct maintenance_task tasks[] = {
 	[TASK_LOOSE_OBJECTS] = {
 		"loose-objects",
 		maintenance_task_loose_objects,
+		loose_object_auto_condition,
 	},
 	[TASK_GC] = {
 		"gc",

t/t7900-maintenance.sh

@@ -127,4 +127,26 @@ test_expect_success 'loose-objects task' '
 	test_cmp packs-between packs-after
 '
 
+test_expect_success 'maintenance.loose-objects.auto' '
+	git repack -adk &&
+	GIT_TRACE2_EVENT="$(pwd)/trace-lo1.txt" \
+		git -c maintenance.loose-objects.auto=1 maintenance \
+		run --auto --task=loose-objects 2>/dev/null &&
+	test_subcommand ! git prune-packed --quiet <trace-lo1.txt &&
+	printf data-A | git hash-object -t blob --stdin -w &&
+	GIT_TRACE2_EVENT="$(pwd)/trace-loA" \
+		git -c maintenance.loose-objects.auto=2 \
+		maintenance run --auto --task=loose-objects 2>/dev/null &&
+	test_subcommand ! git prune-packed --quiet <trace-loA &&
+	printf data-B | git hash-object -t blob --stdin -w &&
+	GIT_TRACE2_EVENT="$(pwd)/trace-loB" \
+		git -c maintenance.loose-objects.auto=2 \
+		maintenance run --auto --task=loose-objects 2>/dev/null &&
+	test_subcommand git prune-packed --quiet <trace-loB &&
+	GIT_TRACE2_EVENT="$(pwd)/trace-loC" \
+		git -c maintenance.loose-objects.auto=2 \
+		maintenance run --auto --task=loose-objects 2>/dev/null &&
+	test_subcommand git prune-packed --quiet <trace-loC
+'
+
 test_done