Merge branch 'dk/gc-idx-wo-pack' into maint

Having a leftover .idx file without corresponding .pack file in
the repository hurts performance; "git gc" learned to prune them.

We may want to do the same for .bitmap (and notice but not prune
.keep) without corresponding .pack, but that can be a separate
topic.

* dk/gc-idx-wo-pack:
  gc: remove garbage .idx files from pack dir
  t5304: test cleaning pack garbage
  prepare_packed_git(): refactor garbage reporting in pack directory

2 files changed, 45 insertions, 2 deletions

diff --git a/builtin/count-objects.c b/builtin/count-objects.c
index ad0c79954a..ba9291944f 100644
--- a/builtin/count-objects.c
+++ b/builtin/count-objects.c
@@ -15,9 +15,31 @@ static int verbose;
 static unsigned long loose, packed, packed_loose;
 static off_t loose_size;
 
-static void real_report_garbage(const char *desc, const char *path)
+static const char *bits_to_msg(unsigned seen_bits)
+{
+	switch (seen_bits) {
+	case 0:
+		return "no corresponding .idx or .pack";
+	case PACKDIR_FILE_GARBAGE:
+		return "garbage found";
+	case PACKDIR_FILE_PACK:
+		return "no corresponding .idx";
+	case PACKDIR_FILE_IDX:
+		return "no corresponding .pack";
+	case PACKDIR_FILE_PACK|PACKDIR_FILE_IDX:
+	default:
+		return NULL;
+	}
+}
+
+static void real_report_garbage(unsigned seen_bits, const char *path)
 {
 	struct stat st;
+	const char *desc = bits_to_msg(seen_bits);
+
+	if (!desc)
+		return;
+
 	if (!stat(path, &st))
 		size_garbage += st.st_size;
 	warning("%s: %s", desc, path);
@@ -27,7 +49,7 @@ static void real_report_garbage(const char *desc, const char *path)
 static void loose_garbage(const char *path)
 {
 	if (verbose)
-		report_garbage("garbage found", path);
+		report_garbage(PACKDIR_FILE_GARBAGE, path);
 }
 
 static int count_loose(const unsigned char *sha1, const char *path, void *data)
diff --git a/builtin/gc.c b/builtin/gc.c
index cb13ab72c3..42258fe348 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -46,6 +46,22 @@ static struct argv_array rerere = ARGV_ARRAY_INIT;
 static struct tempfile pidfile;
 static struct lock_file log_lock;
 
+static struct string_list pack_garbage = STRING_LIST_INIT_DUP;
+
+static void clean_pack_garbage(void)
+{
+	int i;
+	for (i = 0; i < pack_garbage.nr; i++)
+		unlink_or_warn(pack_garbage.items[i].string);
+	string_list_clear(&pack_garbage, 0);
+}
+
+static void report_pack_garbage(unsigned seen_bits, const char *path)
+{
+	if (seen_bits == PACKDIR_FILE_IDX)
+		string_list_append(&pack_garbage, path);
+}
+
 static void git_config_date_string(const char *key, const char **output)
 {
 	if (git_config_get_string_const(key, output))
@@ -416,6 +432,11 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 	if (run_command_v_opt(rerere.argv, RUN_GIT_CMD))
 		return error(FAILED_RUN, rerere.argv[0]);
 
+	report_garbage = report_pack_garbage;
+	reprepare_packed_git();
+	if (pack_garbage.nr > 0)
+		clean_pack_garbage();
+
 	if (auto_gc && too_many_loose_objects())
 		warning(_("There are too many unreachable loose objects; "
 			"run 'git prune' to remove them."));