1 files changed, 337 insertions, 1 deletions

diff --git a/builtin/gc.c b/builtin/gc.c
index 090959350e..3629a82299 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -29,6 +29,8 @@
 #include "tree.h"
 #include "promisor-remote.h"
 #include "refs.h"
+#include "remote.h"
+#include "object-store.h"
 
 #define FAILED_RUN "failed to run %s"
 
@@ -737,9 +739,15 @@ static int dfs_on_ref(const char *refname,
 	commit = lookup_commit(the_repository, oid);
 	if (!commit)
 		return 0;
-	if (parse_commit(commit))
+	if (parse_commit(commit) ||
+	    commit_graph_position(commit) != COMMIT_NOT_FROM_GRAPH)
 		return 0;
 
+	data->num_not_in_graph++;
+
+	if (data->num_not_in_graph >= data->limit)
+		return 1;
+
 	commit_list_append(commit, &stack);
 
 	while (!result && stack) {
@@ -807,6 +815,10 @@ static int run_write_commit_graph(struct maintenance_run_opts *opts)
 
 static int maintenance_task_commit_graph(struct maintenance_run_opts *opts)
 {
+	prepare_repo_settings(the_repository);
+	if (!the_repository->settings.core_commit_graph)
+		return 0;
+
 	close_object_store(the_repository->objects);
 	if (run_write_commit_graph(opts)) {
 		error(_("failed to write commit-graph"));
@@ -816,6 +828,51 @@ static int maintenance_task_commit_graph(struct maintenance_run_opts *opts)
 	return 0;
 }
 
+static int fetch_remote(const char *remote, struct maintenance_run_opts *opts)
+{
+	struct child_process child = CHILD_PROCESS_INIT;
+
+	child.git_cmd = 1;
+	strvec_pushl(&child.args, "fetch", remote, "--prune", "--no-tags",
+		     "--no-write-fetch-head", "--recurse-submodules=no",
+		     "--refmap=", NULL);
+
+	if (opts->quiet)
+		strvec_push(&child.args, "--quiet");
+
+	strvec_pushf(&child.args, "+refs/heads/*:refs/prefetch/%s/*", remote);
+
+	return !!run_command(&child);
+}
+
+static int append_remote(struct remote *remote, void *cbdata)
+{
+	struct string_list *remotes = (struct string_list *)cbdata;
+
+	string_list_append(remotes, remote->name);
+	return 0;
+}
+
+static int maintenance_task_prefetch(struct maintenance_run_opts *opts)
+{
+	int result = 0;
+	struct string_list_item *item;
+	struct string_list remotes = STRING_LIST_INIT_DUP;
+
+	if (for_each_remote(append_remote, &remotes)) {
+		error(_("failed to fill remotes"));
+		result = 1;
+		goto cleanup;
+	}
+
+	for_each_string_list_item(item, &remotes)
+		result |= fetch_remote(item->string, opts);
+
+cleanup:
+	string_list_clear(&remotes, 0);
+	return result;
+}
+
 static int maintenance_task_gc(struct maintenance_run_opts *opts)
 {
 	struct child_process child = CHILD_PROCESS_INIT;
@@ -834,6 +891,268 @@ static int maintenance_task_gc(struct maintenance_run_opts *opts)
 	return run_command(&child);
 }
 
+static int prune_packed(struct maintenance_run_opts *opts)
+{
+	struct child_process child = CHILD_PROCESS_INIT;
+
+	child.git_cmd = 1;
+	strvec_push(&child.args, "prune-packed");
+
+	if (opts->quiet)
+		strvec_push(&child.args, "--quiet");
+
+	return !!run_command(&child);
+}
+
+struct write_loose_object_data {
+	FILE *in;
+	int count;
+	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)
+{
+	return 1;
+}
+
+static int write_loose_object_to_stdin(const struct object_id *oid,
+				       const char *path,
+				       void *data)
+{
+	struct write_loose_object_data *d = (struct write_loose_object_data *)data;
+
+	fprintf(d->in, "%s\n", oid_to_hex(oid));
+
+	return ++(d->count) > d->batch_size;
+}
+
+static int pack_loose(struct maintenance_run_opts *opts)
+{
+	struct repository *r = the_repository;
+	int result = 0;
+	struct write_loose_object_data data;
+	struct child_process pack_proc = CHILD_PROCESS_INIT;
+
+	/*
+	 * Do not start pack-objects process
+	 * if there are no loose objects.
+	 */
+	if (!for_each_loose_file_in_objdir(r->objects->odb->path,
+					   bail_on_loose,
+					   NULL, NULL, NULL))
+		return 0;
+
+	pack_proc.git_cmd = 1;
+
+	strvec_push(&pack_proc.args, "pack-objects");
+	if (opts->quiet)
+		strvec_push(&pack_proc.args, "--quiet");
+	strvec_pushf(&pack_proc.args, "%s/pack/loose", r->objects->odb->path);
+
+	pack_proc.in = -1;
+
+	if (start_command(&pack_proc)) {
+		error(_("failed to start 'git pack-objects' process"));
+		return 1;
+	}
+
+	data.in = xfdopen(pack_proc.in, "w");
+	data.count = 0;
+	data.batch_size = 50000;
+
+	for_each_loose_file_in_objdir(r->objects->odb->path,
+				      write_loose_object_to_stdin,
+				      NULL,
+				      NULL,
+				      &data);
+
+	fclose(data.in);
+
+	if (finish_command(&pack_proc)) {
+		error(_("failed to finish 'git pack-objects' process"));
+		result = 1;
+	}
+
+	return result;
+}
+
+static int maintenance_task_loose_objects(struct maintenance_run_opts *opts)
+{
+	return prune_packed(opts) || pack_loose(opts);
+}
+
+static int incremental_repack_auto_condition(void)
+{
+	struct packed_git *p;
+	int enabled;
+	int incremental_repack_auto_limit = 10;
+	int count = 0;
+
+	if (git_config_get_bool("core.multiPackIndex", &enabled) ||
+	    !enabled)
+		return 0;
+
+	git_config_get_int("maintenance.incremental-repack.auto",
+			   &incremental_repack_auto_limit);
+
+	if (!incremental_repack_auto_limit)
+		return 0;
+	if (incremental_repack_auto_limit < 0)
+		return 1;
+
+	for (p = get_packed_git(the_repository);
+	     count < incremental_repack_auto_limit && p;
+	     p = p->next) {
+		if (!p->multi_pack_index)
+			count++;
+	}
+
+	return count >= incremental_repack_auto_limit;
+}
+
+static int multi_pack_index_write(struct maintenance_run_opts *opts)
+{
+	struct child_process child = CHILD_PROCESS_INIT;
+
+	child.git_cmd = 1;
+	strvec_pushl(&child.args, "multi-pack-index", "write", NULL);
+
+	if (opts->quiet)
+		strvec_push(&child.args, "--no-progress");
+
+	if (run_command(&child))
+		return error(_("failed to write multi-pack-index"));
+
+	return 0;
+}
+
+static int multi_pack_index_expire(struct maintenance_run_opts *opts)
+{
+	struct child_process child = CHILD_PROCESS_INIT;
+
+	child.git_cmd = 1;
+	strvec_pushl(&child.args, "multi-pack-index", "expire", NULL);
+
+	if (opts->quiet)
+		strvec_push(&child.args, "--no-progress");
+
+	close_object_store(the_repository->objects);
+
+	if (run_command(&child))
+		return error(_("'git multi-pack-index expire' failed"));
+
+	return 0;
+}
+
+#define TWO_GIGABYTES (INT32_MAX)
+
+static off_t get_auto_pack_size(void)
+{
+	/*
+	 * The "auto" value is special: we optimize for
+	 * one large pack-file (i.e. from a clone) and
+	 * expect the rest to be small and they can be
+	 * repacked quickly.
+	 *
+	 * The strategy we select here is to select a
+	 * size that is one more than the second largest
+	 * pack-file. This ensures that we will repack
+	 * at least two packs if there are three or more
+	 * packs.
+	 */
+	off_t max_size = 0;
+	off_t second_largest_size = 0;
+	off_t result_size;
+	struct packed_git *p;
+	struct repository *r = the_repository;
+
+	reprepare_packed_git(r);
+	for (p = get_all_packs(r); p; p = p->next) {
+		if (p->pack_size > max_size) {
+			second_largest_size = max_size;
+			max_size = p->pack_size;
+		} else if (p->pack_size > second_largest_size)
+			second_largest_size = p->pack_size;
+	}
+
+	result_size = second_largest_size + 1;
+
+	/* But limit ourselves to a batch size of 2g */
+	if (result_size > TWO_GIGABYTES)
+		result_size = TWO_GIGABYTES;
+
+	return result_size;
+}
+
+static int multi_pack_index_repack(struct maintenance_run_opts *opts)
+{
+	struct child_process child = CHILD_PROCESS_INIT;
+
+	child.git_cmd = 1;
+	strvec_pushl(&child.args, "multi-pack-index", "repack", NULL);
+
+	if (opts->quiet)
+		strvec_push(&child.args, "--no-progress");
+
+	strvec_pushf(&child.args, "--batch-size=%"PRIuMAX,
+				  (uintmax_t)get_auto_pack_size());
+
+	close_object_store(the_repository->objects);
+
+	if (run_command(&child))
+		return error(_("'git multi-pack-index repack' failed"));
+
+	return 0;
+}
+
+static int maintenance_task_incremental_repack(struct maintenance_run_opts *opts)
+{
+	prepare_repo_settings(the_repository);
+	if (!the_repository->settings.core_multi_pack_index) {
+		warning(_("skipping incremental-repack task because core.multiPackIndex is disabled"));
+		return 0;
+	}
+
+	if (multi_pack_index_write(opts))
+		return 1;
+	if (multi_pack_index_expire(opts))
+		return 1;
+	if (multi_pack_index_repack(opts))
+		return 1;
+	return 0;
+}
+
 typedef int maintenance_task_fn(struct maintenance_run_opts *opts);
 
 /*
@@ -854,6 +1173,9 @@ struct maintenance_task {
 };
 
 enum maintenance_task_label {
+	TASK_PREFETCH,
+	TASK_LOOSE_OBJECTS,
+	TASK_INCREMENTAL_REPACK,
 	TASK_GC,
 	TASK_COMMIT_GRAPH,
 
@@ -862,6 +1184,20 @@ enum maintenance_task_label {
 };
 
 static struct maintenance_task tasks[] = {
+	[TASK_PREFETCH] = {
+		"prefetch",
+		maintenance_task_prefetch,
+	},
+	[TASK_LOOSE_OBJECTS] = {
+		"loose-objects",
+		maintenance_task_loose_objects,
+		loose_object_auto_condition,
+	},
+	[TASK_INCREMENTAL_REPACK] = {
+		"incremental-repack",
+		maintenance_task_incremental_repack,
+		incremental_repack_auto_condition,
+	},
 	[TASK_GC] = {
 		"gc",
 		maintenance_task_gc,