From 849e20a8c0223c43c3cb9ed83e07bf087896f2a4 Mon Sep 17 00:00:00 2001
From: Shubham Kanodia <shubham.kanodia10@gmail.com>
Date: Tue, 17 Dec 2024 16:05:16 +0530
Subject: [PATCH] maintenance: add prune-remote-refs task

Remote-tracking refs can accumulate in local repositories even as branches
are deleted on remotes, impacting git performance. While git fetch --prune
helps clean these up, it requires a full fetch operation which is expensive
for large repositories.

Add a new maintenance task 'prune-remote-refs' that runs 'git remote prune'
for each configured remote. This provides an automated way to clean up stale
remote-tracking refs without requiring full fetches or manual intervention.
This task is disabled by default.

Signed-off-by: Shubham Kanodia <shubham.kanodia10@gmail.com>
---
 Documentation/git-maintenance.txt | 14 ++++++++++
 builtin/gc.c                      | 42 +++++++++++++++++++++++++++++
 t/t7900-maintenance.sh            | 44 +++++++++++++++++++++++++++++++
 3 files changed, 100 insertions(+)

diff --git a/Documentation/git-maintenance.txt b/Documentation/git-maintenance.txt
index 6e6651309d3253..b71bcc82b830a2 100644
--- a/Documentation/git-maintenance.txt
+++ b/Documentation/git-maintenance.txt
@@ -158,6 +158,20 @@ pack-refs::
 	need to iterate across many references. See linkgit:git-pack-refs[1]
 	for more information.
 
+prune-remote-refs::
+	The `prune-remote-refs` task runs `git remote prune` on each remote
+	repository registered in the local repository. This task helps clean
+	up deleted remote branches, improving the performance of operations
+	that iterate through the refs. See linkgit:git-remote[1] for more
+	information. This task is disabled by default and must be enabled
+	manually.
++
+NOTE: This task is opt-in to prevent unexpected removal of remote refs
+for users of git-maintenance. It is recommended for power users who
+are comfortable with configuring maintenance tasks and understand the
+implications of automatic pruning. For others, running `git remote prune`
+manually might be more appropriate.
+
 OPTIONS
 -------
 --auto::
diff --git a/builtin/gc.c b/builtin/gc.c
index 4ae5196aedfecc..9acf1d2989519f 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -20,6 +20,7 @@
 #include "lockfile.h"
 #include "parse-options.h"
 #include "run-command.h"
+#include "remote.h"
 #include "sigchain.h"
 #include "strvec.h"
 #include "commit.h"
@@ -913,6 +914,40 @@ static int maintenance_opt_schedule(const struct option *opt, const char *arg,
 	return 0;
 }
 
+static int collect_remote(struct remote *remote, void *cb_data)
+{
+	struct string_list *list = cb_data;
+
+	if (!remote->url.nr)
+		return 0;
+
+	string_list_append(list, remote->name);
+	return 0;
+}
+
+static int maintenance_task_prune_remote(struct maintenance_run_opts *opts UNUSED,
+					 struct gc_config *cfg UNUSED)
+{
+	struct string_list_item *item;
+	struct string_list remotes_list = STRING_LIST_INIT_NODUP;
+	struct child_process child = CHILD_PROCESS_INIT;
+	int result = 0;
+
+	for_each_remote(collect_remote, &remotes_list);
+
+	for_each_string_list_item (item, &remotes_list) {
+		const char *remote_name = item->string;
+		child.git_cmd = 1;
+		strvec_pushl(&child.args, "remote", "prune", remote_name, NULL);
+
+		if (run_command(&child))
+			result = error(_("failed to prune '%s'"), remote_name);
+	}
+
+	string_list_clear(&remotes_list, 0);
+	return result;
+}
+
 /* Remember to update object flag allocation in object.h */
 #define SEEN		(1u<<0)
 
@@ -1375,6 +1410,7 @@ enum maintenance_task_label {
 	TASK_GC,
 	TASK_COMMIT_GRAPH,
 	TASK_PACK_REFS,
+	TASK_PRUNE_REMOTE_REFS,
 
 	/* Leave as final value */
 	TASK__COUNT
@@ -1411,6 +1447,10 @@ static struct maintenance_task tasks[] = {
 		maintenance_task_pack_refs,
 		pack_refs_condition,
 	},
+	[TASK_PRUNE_REMOTE_REFS] = {
+		"prune-remote-refs",
+		maintenance_task_prune_remote,
+	},
 };
 
 static int compare_tasks_by_selection(const void *a_, const void *b_)
@@ -1505,6 +1545,8 @@ static void initialize_maintenance_strategy(void)
 		tasks[TASK_LOOSE_OBJECTS].schedule = SCHEDULE_DAILY;
 		tasks[TASK_PACK_REFS].enabled = 1;
 		tasks[TASK_PACK_REFS].schedule = SCHEDULE_WEEKLY;
+		tasks[TASK_PRUNE_REMOTE_REFS].enabled = 0;
+		tasks[TASK_PRUNE_REMOTE_REFS].schedule = SCHEDULE_DAILY;
 	}
 }
 
diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh
index 0ce4ba1cbefbe8..60a0c3f835320b 100755
--- a/t/t7900-maintenance.sh
+++ b/t/t7900-maintenance.sh
@@ -446,6 +446,50 @@ test_expect_success 'pack-refs task' '
 	test_subcommand git pack-refs --all --prune <pack-refs.txt
 '
 
+test_expect_success 'prune-remote-refs task not enabled by default' '
+	git clone . prune-test &&
+	(
+		cd prune-test &&
+		GIT_TRACE2_EVENT="$(pwd)/prune.txt" git maintenance run 2>err &&
+		test_subcommand ! git remote prune origin <prune.txt
+	)
+'
+
+test_expect_success 'prune-remote-refs task cleans stale remote refs' '
+	test_commit initial &&
+
+	# Create two separate remote repos
+	git clone . remote1 &&
+	git clone . remote2 &&
+
+	git clone . prune-test-clean &&
+	(
+		cd prune-test-clean &&
+		git config maintenance.prune-remote-refs.enabled true &&
+
+		# Add both remotes
+		git remote add remote1 "../remote1" &&
+		git remote add remote2 "../remote2" &&
+
+		# Create and push branches to both remotes
+		git branch -f side2 HEAD &&
+		git push remote1 side2 &&
+		git push remote2 side2 &&
+
+		# Rename branches in each remote to simulate a stale branch
+		git -C ../remote1 branch -m side2 side3 &&
+		git -C ../remote2 branch -m side2 side4 &&
+
+		GIT_TRACE2_EVENT="$(pwd)/prune.txt" git maintenance run --task=prune-remote-refs &&
+
+		# Verify pruning happened for both remotes
+		test_subcommand git remote prune remote1 <prune.txt &&
+		test_subcommand git remote prune remote2 <prune.txt &&
+		test_must_fail git rev-parse refs/remotes/remote1/side2 &&
+		test_must_fail git rev-parse refs/remotes/remote2/side2
+	)
+'
+
 test_expect_success '--auto and --schedule incompatible' '
 	test_must_fail git maintenance run --auto --schedule=daily 2>err &&
 	test_grep "at most one" err