repack: add --keep-pack option

We allow to keep existing packs by having companion .keep files. This
is helpful when a pack is permanently kept. In the next patch, git-gc
just wants to keep a pack temporarily, for one pack-objects
run. git-gc can use --keep-pack for this use case.

A note about why the pack_keep field cannot be reused and
pack_keep_in_core has to be added. This is about the case when
--keep-pack is specified together with either --keep-unreachable or
--unpack-unreachable, but --honor-pack-keep is NOT specified.

In this case, we want to exclude objects from the packs specified on
command line, not from ones with .keep files. If only one bit flag is
used, we have to clear pack_keep on pack files with the .keep file.

But we can't make any assumption about unreachable objects in .keep
packs. If "pack_keep" field is false for .keep packs, we could
potentially pull lots of unreachable objects into the new pack, or
unpack them loose. The safer approach is ignore all packs with either
.keep file or --keep-pack.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 18 insertions, 3 deletions

diff --git a/builtin/repack.c b/builtin/repack.c
index 7bdb40142f..6c636e159e 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -86,7 +86,8 @@ static void remove_pack_on_signal(int signo)
  * have a corresponding .keep or .promisor file. These packs are not to
  * be kept if we are going to pack everything into one file.
  */
-static void get_non_kept_pack_filenames(struct string_list *fname_list)
+static void get_non_kept_pack_filenames(struct string_list *fname_list,
+					const struct string_list *extra_keep)
 {
 	DIR *dir;
 	struct dirent *e;
@@ -97,6 +98,14 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list)
 
 	while ((e = readdir(dir)) != NULL) {
 		size_t len;
+		int i;
+
+		for (i = 0; i < extra_keep->nr; i++)
+			if (!fspathcmp(e->d_name, extra_keep->items[i].string))
+				break;
+		if (extra_keep->nr > 0 && i < extra_keep->nr)
+			continue;
+
 		if (!strip_suffix(e->d_name, ".pack", &len))
 			continue;
 
@@ -148,7 +157,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct string_list rollback = STRING_LIST_INIT_NODUP;
 	struct string_list existing_packs = STRING_LIST_INIT_DUP;
 	struct strbuf line = STRBUF_INIT;
-	int ext, ret, failed;
+	int i, ext, ret, failed;
 	FILE *out;
 
 	/* variables to be filled by option parsing */
@@ -160,6 +169,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	const char *depth = NULL;
 	const char *threads = NULL;
 	const char *max_pack_size = NULL;
+	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	int no_reuse_delta = 0, no_reuse_object = 0;
 	int no_update_server_info = 0;
 	int quiet = 0;
@@ -200,6 +210,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("maximum size of each packfile")),
 		OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects,
 				N_("repack objects in packs marked with .keep")),
+		OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"),
+				N_("do not repack this pack")),
 		OPT_END()
 	};
 
@@ -230,6 +242,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	argv_array_push(&cmd.args, "--keep-true-parents");
 	if (!pack_kept_objects)
 		argv_array_push(&cmd.args, "--honor-pack-keep");
+	for (i = 0; i < keep_pack_list.nr; i++)
+		argv_array_pushf(&cmd.args, "--keep-pack=%s",
+				 keep_pack_list.items[i].string);
 	argv_array_push(&cmd.args, "--non-empty");
 	argv_array_push(&cmd.args, "--all");
 	argv_array_push(&cmd.args, "--reflog");
@@ -254,7 +269,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		argv_array_push(&cmd.args, "--write-bitmap-index");
 
 	if (pack_everything & ALL_INTO_ONE) {
-		get_non_kept_pack_filenames(&existing_packs);
+		get_non_kept_pack_filenames(&existing_packs, &keep_pack_list);
 
 		if (existing_packs.nr && delete_redundant) {
 			if (unpack_unreachable) {