Merge branch 'nd/repack-keep-pack'

"git gc" in a large repository takes a lot of time as it considers
to repack all objects into one pack by default.  The command has
been taught to pretend as if the largest existing packfile is
marked with ".keep" so that it is left untouched while objects in
other packs and loose ones are repacked.

* nd/repack-keep-pack:
  pack-objects: show some progress when counting kept objects
  gc --auto: exclude base pack if not enough mem to "repack -ad"
  gc: handle a corner case in gc.bigPackThreshold
  gc: add gc.bigPackThreshold config
  gc: add --keep-largest-pack option
  repack: add --keep-pack option
  t7700: have closing quote of a test at the beginning of line

1 files changed, 63 insertions, 20 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 24b1c6c5dd..0bfd33ea27 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -30,6 +30,7 @@
 #include "list.h"
 #include "packfile.h"
 #include "object-store.h"
+#include "dir.h"
 
 static const char *pack_usage[] = {
 	N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"),
@@ -45,7 +46,7 @@ static const char *pack_usage[] = {
 static struct packing_data to_pack;
 
 static struct pack_idx_entry **written_list;
-static uint32_t nr_result, nr_written;
+static uint32_t nr_result, nr_written, nr_seen;
 
 static int non_empty;
 static int reuse_delta = 1, reuse_object = 1;
@@ -55,7 +56,8 @@ static int pack_loose_unreachable;
 static int local;
 static int have_non_local_packs;
 static int incremental;
-static int ignore_packed_keep;
+static int ignore_packed_keep_on_disk;
+static int ignore_packed_keep_in_core;
 static int allow_ofs_delta;
 static struct pack_idx_option pack_idx_opts;
 static const char *base_name;
@@ -80,7 +82,7 @@ static uint16_t write_bitmap_options;
 static int exclude_promisor_objects;
 
 static unsigned long delta_cache_size = 0;
-static unsigned long max_delta_cache_size = 256 * 1024 * 1024;
+static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
 static unsigned long cache_max_small_delta_size = 1000;
 
 static unsigned long window_memory_limit = 0;
@@ -982,13 +984,16 @@ static int want_found_object(int exclude, struct packed_git *p)
 	 * Otherwise, we signal "-1" at the end to tell the caller that we do
 	 * not know either way, and it needs to check more packs.
 	 */
-	if (!ignore_packed_keep &&
+	if (!ignore_packed_keep_on_disk &&
+	    !ignore_packed_keep_in_core &&
 	    (!local || !have_non_local_packs))
 		return 1;
 
 	if (local && !p->pack_local)
 		return 0;
-	if (ignore_packed_keep && p->pack_local && p->pack_keep)
+	if (p->pack_local &&
+	    ((ignore_packed_keep_on_disk && p->pack_keep) ||
+	     (ignore_packed_keep_in_core && p->pack_keep_in_core)))
 		return 0;
 
 	/* we don't know yet; keep looking for more packs */
@@ -1091,6 +1096,8 @@ static int add_object_entry(const struct object_id *oid, enum object_type type,
 	off_t found_offset = 0;
 	uint32_t index_pos;
 
+	display_progress(progress_state, ++nr_seen);
+
 	if (have_duplicate_entry(oid, exclude, &index_pos))
 		return 0;
 
@@ -1106,8 +1113,6 @@ static int add_object_entry(const struct object_id *oid, enum object_type type,
 	create_object_entry(oid, type, pack_name_hash(name),
 			    exclude, name && no_try_delta(name),
 			    index_pos, found_pack, found_offset);
-
-	display_progress(progress_state, nr_result);
 	return 1;
 }
 
@@ -1118,6 +1123,8 @@ static int add_object_entry_from_bitmap(const struct object_id *oid,
 {
 	uint32_t index_pos;
 
+	display_progress(progress_state, ++nr_seen);
+
 	if (have_duplicate_entry(oid, 0, &index_pos))
 		return 0;
 
@@ -1125,8 +1132,6 @@ static int add_object_entry_from_bitmap(const struct object_id *oid,
 		return 0;
 
 	create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset);
-
-	display_progress(progress_state, nr_result);
 	return 1;
 }
 
@@ -1711,6 +1716,10 @@ static void get_object_details(void)
 	uint32_t i;
 	struct object_entry **sorted_by_offset;
 
+	if (progress)
+		progress_state = start_progress(_("Counting objects"),
+						to_pack.nr_objects);
+
 	sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *));
 	for (i = 0; i < to_pack.nr_objects; i++)
 		sorted_by_offset[i] = to_pack.objects + i;
@@ -1721,7 +1730,9 @@ static void get_object_details(void)
 		check_object(entry);
 		if (big_file_threshold < entry->size)
 			entry->no_try_delta = 1;
+		display_progress(progress_state, i + 1);
 	}
+	stop_progress(&progress_state);
 
 	/*
 	 * This must happen in a second pass, since we rely on the delta
@@ -2675,7 +2686,7 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs)
 		struct object_id oid;
 		struct object *o;
 
-		if (!p->pack_local || p->pack_keep)
+		if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
 			continue;
 		if (open_pack_index(p))
 			die("cannot open pack index");
@@ -2738,7 +2749,8 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid)
 					get_packed_git(the_repository);
 
 	while (p) {
-		if ((!p->pack_local || p->pack_keep) &&
+		if ((!p->pack_local || p->pack_keep ||
+				p->pack_keep_in_core) &&
 			find_pack_entry_one(oid->hash, p)) {
 			last_found = p;
 			return 1;
@@ -2781,7 +2793,7 @@ static void loosen_unused_packed_objects(struct rev_info *revs)
 	struct object_id oid;
 
 	for (p = get_packed_git(the_repository); p; p = p->next) {
-		if (!p->pack_local || p->pack_keep)
+		if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
 			continue;
 
 		if (open_pack_index(p))
@@ -2807,7 +2819,8 @@ static int pack_options_allow_reuse(void)
 {
 	return pack_to_stdout &&
 	       allow_ofs_delta &&
-	       !ignore_packed_keep &&
+	       !ignore_packed_keep_on_disk &&
+	       !ignore_packed_keep_in_core &&
 	       (!local || !have_non_local_packs) &&
 	       !incremental;
 }
@@ -2916,6 +2929,32 @@ static void get_object_list(int ac, const char **av)
 	oid_array_clear(&recent_objects);
 }
 
+static void add_extra_kept_packs(const struct string_list *names)
+{
+	struct packed_git *p;
+
+	if (!names->nr)
+		return;
+
+	for (p = get_packed_git(the_repository); p; p = p->next) {
+		const char *name = basename(p->pack_name);
+		int i;
+
+		if (!p->pack_local)
+			continue;
+
+		for (i = 0; i < names->nr; i++)
+			if (!fspathcmp(name, names->items[i].string))
+				break;
+
+		if (i < names->nr) {
+			p->pack_keep_in_core = 1;
+			ignore_packed_keep_in_core = 1;
+			continue;
+		}
+	}
+}
+
 static int option_parse_index_version(const struct option *opt,
 				      const char *arg, int unset)
 {
@@ -2955,6 +2994,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	struct argv_array rp = ARGV_ARRAY_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
 	int rev_list_index = 0;
+	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	struct option pack_objects_options[] = {
 		OPT_SET_INT('q', "quiet", &progress,
 			    N_("do not show progress meter"), 0),
@@ -3019,8 +3059,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			 N_("create thin packs")),
 		OPT_BOOL(0, "shallow", &shallow,
 			 N_("create packs suitable for shallow fetches")),
-		OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep,
+		OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk,
 			 N_("ignore packs that have companion .keep file")),
+		OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"),
+				N_("ignore this pack")),
 		OPT_INTEGER(0, "compression", &pack_compression_level,
 			    N_("pack compression level")),
 		OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents,
@@ -3148,19 +3190,20 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (progress && all_progress_implied)
 		progress = 2;
 
-	if (ignore_packed_keep) {
+	add_extra_kept_packs(&keep_pack_list);
+	if (ignore_packed_keep_on_disk) {
 		struct packed_git *p;
 		for (p = get_packed_git(the_repository); p; p = p->next)
 			if (p->pack_local && p->pack_keep)
 				break;
 		if (!p) /* no keep-able packs found */
-			ignore_packed_keep = 0;
+			ignore_packed_keep_on_disk = 0;
 	}
 	if (local) {
 		/*
-		 * unlike ignore_packed_keep above, we do not want to
-		 * unset "local" based on looking at packs, as it
-		 * also covers non-local objects
+		 * unlike ignore_packed_keep_on_disk above, we do not
+		 * want to unset "local" based on looking at packs, as
+		 * it also covers non-local objects
 		 */
 		struct packed_git *p;
 		for (p = get_packed_git(the_repository); p; p = p->next) {
@@ -3172,7 +3215,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	}
 
 	if (progress)
-		progress_state = start_progress(_("Counting objects"), 0);
+		progress_state = start_progress(_("Enumerating objects"), 0);
 	if (!use_internal_rev_list)
 		read_object_list_from_stdin();
 	else {