builtin/maintenance: introduce "rerere-gc" task

While git-gc(1) knows to garbage collect the rerere cache,
git-maintenance(1) does not yet have a task for this cleanup. Introduce
a new "rerere-gc" task to plug this gap.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

Documentation/config/maintenance.adoc

@@ -84,6 +84,15 @@ maintenance.reflog-expire.auto::
 	expired reflog entries in the "HEAD" reflog is at least the value of
 	`maintenance.loose-objects.auto`. The default value is 100.
 
+maintenance.rerere-gc.auto::
+	This integer config option controls how often the `rerere-gc` task
+	should be run as part of `git maintenance run --auto`. If zero, then
+	the `rerere-gc` task will not run with the `--auto` option. A negative
+	value will force the task to run every time. Otherwise, any positive
+	value implies the command will run when the "rr-cache" directory exists
+	and has at least one entry, regardless of whether it is stale or not.
+	This heuristic may be refined in the future. The default value is 1.
+
 maintenance.worktree-prune.auto::
 	This integer config option controls how often the `worktree-prune` task
 	should be run as part of `git maintenance run --auto`. If zero, then

Documentation/git-maintenance.adoc

@@ -166,6 +166,10 @@ reflog-expire::
 	The `reflog-expire` task deletes any entries in the reflog older than the
 	expiry threshold. See linkgit:git-reflog[1] for more information.
 
+rerere-gc::
+	The `rerere-gc` task invokes garbage collection for stale entries in
+	the rerere cache. See linkgit:git-rerere[1] for more information.
+
 worktree-prune::
 	The `worktree-prune` task deletes stale or broken worktrees. See
 	linkit:git-worktree[1] for more information.

builtin/gc.c

@@ -16,6 +16,7 @@
 #include "builtin.h"
 #include "abspath.h"
 #include "date.h"
+#include "dir.h"
 #include "environment.h"
 #include "hex.h"
 #include "config.h"
@@ -33,6 +34,7 @@
 #include "pack-objects.h"
 #include "path.h"
 #include "reflog.h"
+#include "rerere.h"
 #include "blob.h"
 #include "tree.h"
 #include "promisor-remote.h"
@@ -393,6 +395,35 @@ static int maintenance_task_rerere_gc(struct maintenance_run_opts *opts UNUSED,
 	return run_command(&rerere_cmd);
 }
 
+static int rerere_gc_condition(struct gc_config *cfg UNUSED)
+{
+	struct strbuf path = STRBUF_INIT;
+	int should_gc = 0, limit = 1;
+	DIR *dir = NULL;
+
+	git_config_get_int("maintenance.rerere-gc.auto", &limit);
+	if (limit <= 0) {
+		should_gc = limit < 0;
+		goto out;
+	}
+
+	/*
+	 * We skip garbage collection in case we either have no "rr-cache"
+	 * directory or when it doesn't contain at least one entry.
+	 */
+	repo_git_path_replace(the_repository, &path, "rr-cache");
+	dir = opendir(path.buf);
+	if (!dir)
+		goto out;
+	should_gc = !!readdir_skip_dot_and_dotdot(dir);
+
+out:
+	strbuf_release(&path);
+	if (dir)
+		closedir(dir);
+	return should_gc;
+}
+
 static int too_many_loose_objects(struct gc_config *cfg)
 {
 	/*
@@ -1511,6 +1542,7 @@ enum maintenance_task_label {
 	TASK_PACK_REFS,
 	TASK_REFLOG_EXPIRE,
 	TASK_WORKTREE_PRUNE,
+	TASK_RERERE_GC,
 
 	/* Leave as final value */
 	TASK__COUNT
@@ -1557,6 +1589,11 @@ static struct maintenance_task tasks[] = {
 		maintenance_task_worktree_prune,
 		worktree_prune_condition,
 	},
+	[TASK_RERERE_GC] = {
+		"rerere-gc",
+		maintenance_task_rerere_gc,
+		rerere_gc_condition,
+	},
 };
 
 static int compare_tasks_by_selection(const void *a_, const void *b_)

t/t7900-maintenance.sh

@@ -564,6 +564,50 @@ test_expect_success 'worktree-prune task honors gc.worktreePruneExpire' '
 	test_path_is_missing .git/worktrees/worktree
 '
 
+test_expect_rerere_gc () {
+	negate=
+	if test "$1" = "!"
+	then
+		negate="!"
+		shift
+	fi
+
+	rm -f "rerere-gc.txt" &&
+	GIT_TRACE2_EVENT="$(pwd)/rerere-gc.txt" "$@" &&
+	test_subcommand $negate git rerere gc <rerere-gc.txt
+}
+
+test_expect_success 'rerere-gc task without --auto always collects garbage' '
+	test_expect_rerere_gc git maintenance run --task=rerere-gc
+'
+
+test_expect_success 'rerere-gc task with --auto only prunes with prunable entries' '
+	test_when_finished "rm -rf .git/rr-cache" &&
+	test_expect_rerere_gc ! git maintenance run --auto --task=rerere-gc &&
+	mkdir .git/rr-cache &&
+	test_expect_rerere_gc ! git maintenance run --auto --task=rerere-gc &&
+	: >.git/rr-cache/entry &&
+	test_expect_rerere_gc git maintenance run --auto --task=rerere-gc
+'
+
+test_expect_success 'rerere-gc task with --auto honors maintenance.rerere-gc.auto' '
+	test_when_finished "rm -rf .git/rr-cache" &&
+
+	# A negative value should always prune.
+	test_expect_rerere_gc git -c maintenance.rerere-gc.auto=-1 maintenance run --auto --task=rerere-gc &&
+
+	# A positive value prunes when there is at least one entry.
+	test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc &&
+	mkdir .git/rr-cache &&
+	test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc &&
+	: >.git/rr-cache/entry-1 &&
+	test_expect_rerere_gc git -c maintenance.rerere-gc.auto=9000 maintenance run --auto --task=rerere-gc &&
+
+	# Zero should never prune.
+	: >.git/rr-cache/entry-1 &&
+	test_expect_rerere_gc ! git -c maintenance.rerere-gc.auto=0 maintenance run --auto --task=rerere-gc
+'
+
 test_expect_success '--auto and --schedule incompatible' '
 	test_must_fail git maintenance run --auto --schedule=daily 2>err &&
 	test_grep "at most one" err