1 files changed, 197 insertions, 35 deletions
diff --git a/builtin/repack.c b/builtin/repack.c
index d1a563d5b6..c957b2959f 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -18,12 +18,21 @@
 #include "pack-bitmap.h"
 #include "refs.h"
 
+#define ALL_INTO_ONE 1
+#define LOOSEN_UNREACHABLE 2
+#define PACK_CRUFT 4
+
+#define DELETE_PACK 1
+#define CRUFT_PACK 2
+
+static int pack_everything;
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
 static int write_bitmaps = -1;
 static int use_delta_islands;
 static int run_update_server_info = 1;
 static char *packdir, *packtmp_name, *packtmp;
+static char *cruft_expiration;
 
 static const char *const git_repack_usage[] = {
 	N_("git repack [<options>]"),
@@ -35,9 +44,21 @@ static const char incremental_bitmap_conflict_error[] = N_(
 "--no-write-bitmap-index or disable the pack.writebitmaps configuration."
 );
 
+struct pack_objects_args {
+	const char *window;
+	const char *window_memory;
+	const char *depth;
+	const char *threads;
+	const char *max_pack_size;
+	int no_reuse_delta;
+	int no_reuse_object;
+	int quiet;
+	int local;
+};
 
 static int repack_config(const char *var, const char *value, void *cb)
 {
+	struct pack_objects_args *cruft_po_args = cb;
 	if (!strcmp(var, "repack.usedeltabaseoffset")) {
 		delta_base_offset = git_config_bool(var, value);
 		return 0;
@@ -59,6 +80,14 @@ static int repack_config(const char *var, const char *value, void *cb)
 		run_update_server_info = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "repack.cruftwindow"))
+		return git_config_string(&cruft_po_args->window, var, value);
+	if (!strcmp(var, "repack.cruftwindowmemory"))
+		return git_config_string(&cruft_po_args->window_memory, var, value);
+	if (!strcmp(var, "repack.cruftdepth"))
+		return git_config_string(&cruft_po_args->depth, var, value);
+	if (!strcmp(var, "repack.cruftthreads"))
+		return git_config_string(&cruft_po_args->threads, var, value);
 	return git_default_config(var, value, cb);
 }
 
@@ -131,12 +160,19 @@ static void collect_pack_filenames(struct string_list *fname_nonkept_list,
 		fname = xmemdupz(e->d_name, len);
 
 		if ((extra_keep->nr > 0 && i < extra_keep->nr) ||
-		    (file_exists(mkpath("%s/%s.keep", packdir, fname))))
+		    (file_exists(mkpath("%s/%s.keep", packdir, fname)))) {
 			string_list_append_nodup(fname_kept_list, fname);
-		else
-			string_list_append_nodup(fname_nonkept_list, fname);
+		} else {
+			struct string_list_item *item;
+			item = string_list_append_nodup(fname_nonkept_list,
+							fname);
+			if (file_exists(mkpath("%s/%s.mtimes", packdir, fname)))
+				item->util = (void*)(uintptr_t)CRUFT_PACK;
+		}
 	}
 	closedir(dir);
+
+	string_list_sort(fname_kept_list);
 }
 
 static void remove_redundant_pack(const char *dir_name, const char *base_name)
@@ -151,18 +187,6 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name)
 	strbuf_release(&buf);
 }
 
-struct pack_objects_args {
-	const char *window;
-	const char *window_memory;
-	const char *depth;
-	const char *threads;
-	const char *max_pack_size;
-	int no_reuse_delta;
-	int no_reuse_object;
-	int quiet;
-	int local;
-};
-
 static void prepare_pack_objects(struct child_process *cmd,
 				 const struct pack_objects_args *args)
 {
@@ -217,6 +241,7 @@ static struct {
 } exts[] = {
 	{".pack"},
 	{".rev", 1},
+	{".mtimes", 1},
 	{".bitmap", 1},
 	{".promisor", 1},
 	{".idx"},
@@ -304,9 +329,6 @@ static void repack_promisor_objects(const struct pack_objects_args *args,
 		die(_("could not finish pack-objects to repack promisor objects"));
 }
 
-#define ALL_INTO_ONE 1
-#define LOOSEN_UNREACHABLE 2
-
 struct pack_geometry {
 	struct packed_git **pack;
 	uint32_t pack_nr, pack_alloc;
@@ -332,16 +354,39 @@ static int geometry_cmp(const void *va, const void *vb)
 	return 0;
 }
 
-static void init_pack_geometry(struct pack_geometry **geometry_p)
+static void init_pack_geometry(struct pack_geometry **geometry_p,
+			       struct string_list *existing_kept_packs)
 {
 	struct packed_git *p;
 	struct pack_geometry *geometry;
+	struct strbuf buf = STRBUF_INIT;
 
 	*geometry_p = xcalloc(1, sizeof(struct pack_geometry));
 	geometry = *geometry_p;
 
 	for (p = get_all_packs(the_repository); p; p = p->next) {
-		if (!pack_kept_objects && p->pack_keep)
+		if (!pack_kept_objects) {
+			/*
+			 * Any pack that has its pack_keep bit set will appear
+			 * in existing_kept_packs below, but this saves us from
+			 * doing a more expensive check.
+			 */
+			if (p->pack_keep)
+				continue;
+
+			/*
+			 * The pack may be kept via the --keep-pack option;
+			 * check 'existing_kept_packs' to determine whether to
+			 * ignore it.
+			 */
+			strbuf_reset(&buf);
+			strbuf_addstr(&buf, pack_basename(p));
+			strbuf_strip_suffix(&buf, ".pack");
+
+			if (string_list_has_string(existing_kept_packs, buf.buf))
+				continue;
+		}
+		if (p->is_cruft)
 			continue;
 
 		ALLOC_GROW(geometry->pack,
@@ -353,6 +398,7 @@ static void init_pack_geometry(struct pack_geometry **geometry_p)
 	}
 
 	QSORT(geometry->pack, geometry->pack_nr, geometry_cmp);
+	strbuf_release(&buf);
 }
 
 static void split_pack_geometry(struct pack_geometry *geometry, int factor)
@@ -548,9 +594,20 @@ static void midx_included_packs(struct string_list *include,
 
 			string_list_insert(include, strbuf_detach(&buf, NULL));
 		}
+
+		for_each_string_list_item(item, existing_nonkept_packs) {
+			if (!((uintptr_t)item->util & CRUFT_PACK)) {
+				/*
+				 * no need to check DELETE_PACK, since we're not
+				 * doing an ALL_INTO_ONE repack
+				 */
+				continue;
+			}
+			string_list_insert(include, xstrfmt("%s.idx", item->string));
+		}
 	} else {
 		for_each_string_list_item(item, existing_nonkept_packs) {
-			if (item->util)
+			if ((uintptr_t)item->util & DELETE_PACK)
 				continue;
 			string_list_insert(include, xstrfmt("%s.idx", item->string));
 		}
@@ -604,6 +661,67 @@ static int write_midx_included_packs(struct string_list *include,
 	return finish_command(&cmd);
 }
 
+static int write_cruft_pack(const struct pack_objects_args *args,
+			    const char *pack_prefix,
+			    struct string_list *names,
+			    struct string_list *existing_packs,
+			    struct string_list *existing_kept_packs)
+{
+	struct child_process cmd = CHILD_PROCESS_INIT;
+	struct strbuf line = STRBUF_INIT;
+	struct string_list_item *item;
+	FILE *in, *out;
+	int ret;
+
+	prepare_pack_objects(&cmd, args);
+
+	strvec_push(&cmd.args, "--cruft");
+	if (cruft_expiration)
+		strvec_pushf(&cmd.args, "--cruft-expiration=%s",
+			     cruft_expiration);
+
+	strvec_push(&cmd.args, "--honor-pack-keep");
+	strvec_push(&cmd.args, "--non-empty");
+	strvec_push(&cmd.args, "--max-pack-size=0");
+
+	cmd.in = -1;
+
+	ret = start_command(&cmd);
+	if (ret)
+		return ret;
+
+	/*
+	 * names has a confusing double use: it both provides the list
+	 * of just-written new packs, and accepts the name of the cruft
+	 * pack we are writing.
+	 *
+	 * By the time it is read here, it contains only the pack(s)
+	 * that were just written, which is exactly the set of packs we
+	 * want to consider kept.
+	 */
+	in = xfdopen(cmd.in, "w");
+	for_each_string_list_item(item, names)
+		fprintf(in, "%s-%s.pack\n", pack_prefix, item->string);
+	for_each_string_list_item(item, existing_packs)
+		fprintf(in, "-%s.pack\n", item->string);
+	for_each_string_list_item(item, existing_kept_packs)
+		fprintf(in, "%s.pack\n", item->string);
+	fclose(in);
+
+	out = xfdopen(cmd.out, "r");
+	while (strbuf_getline_lf(&line, out) != EOF) {
+		if (line.len != the_hash_algo->hexsz)
+			die(_("repack: Expecting full hex object ID lines only "
+			      "from pack-objects."));
+		string_list_append(names, line.buf);
+	}
+	fclose(out);
+
+	strbuf_release(&line);
+
+	return finish_command(&cmd);
+}
+
 int cmd_repack(int argc, const char **argv, const char *prefix)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
@@ -620,12 +738,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int show_progress;
 
 	/* variables to be filled by option parsing */
-	int pack_everything = 0;
 	int delete_redundant = 0;
 	const char *unpack_unreachable = NULL;
 	int keep_unreachable = 0;
 	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	struct pack_objects_args po_args = {NULL};
+	struct pack_objects_args cruft_po_args = {NULL};
 	int geometric_factor = 0;
 	int write_midx = 0;
 
@@ -635,6 +753,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		OPT_BIT('A', NULL, &pack_everything,
 				N_("same as -a, and turn unreachable objects loose"),
 				   LOOSEN_UNREACHABLE | ALL_INTO_ONE),
+		OPT_BIT(0, "cruft", &pack_everything,
+				N_("same as -a, pack unreachable cruft objects separately"),
+				   PACK_CRUFT),
+		OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
+				N_("with -C, expire objects older than this")),
 		OPT_BOOL('d', NULL, &delete_redundant,
 				N_("remove redundant packs, and run git-prune-packed")),
 		OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
@@ -675,7 +798,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		OPT_END()
 	};
 
-	git_config(repack_config, NULL);
+	git_config(repack_config, &cruft_po_args);
 
 	argc = parse_options(argc, argv, prefix, builtin_repack_options,
 				git_repack_usage, 0);
@@ -687,6 +810,15 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	    (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
 		die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A");
 
+	if (pack_everything & PACK_CRUFT) {
+		pack_everything |= ALL_INTO_ONE;
+
+		if (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))
+			die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-A");
+		if (keep_unreachable)
+			die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-k");
+	}
+
 	if (write_bitmaps < 0) {
 		if (!write_midx &&
 		    (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository()))
@@ -714,17 +846,20 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		strbuf_release(&path);
 	}
 
+	packdir = mkpathdup("%s/pack", get_object_directory());
+	packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid());
+	packtmp = mkpathdup("%s/%s", packdir, packtmp_name);
+
+	collect_pack_filenames(&existing_nonkept_packs, &existing_kept_packs,
+			       &keep_pack_list);
+
 	if (geometric_factor) {
 		if (pack_everything)
 			die(_("options '%s' and '%s' cannot be used together"), "--geometric", "-A/-a");
-		init_pack_geometry(&geometry);
+		init_pack_geometry(&geometry, &existing_kept_packs);
 		split_pack_geometry(geometry, geometric_factor);
 	}
 
-	packdir = mkpathdup("%s/pack", get_object_directory());
-	packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid());
-	packtmp = mkpathdup("%s/%s", packdir, packtmp_name);
-
 	sigchain_push_common(remove_pack_on_signal);
 
 	prepare_pack_objects(&cmd, &po_args);
@@ -764,13 +899,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (use_delta_islands)
 		strvec_push(&cmd.args, "--delta-islands");
 
-	collect_pack_filenames(&existing_nonkept_packs, &existing_kept_packs,
-			       &keep_pack_list);
-
 	if (pack_everything & ALL_INTO_ONE) {
 		repack_promisor_objects(&po_args, &names);
 
-		if (existing_nonkept_packs.nr && delete_redundant) {
+		if (existing_nonkept_packs.nr && delete_redundant &&
+		    !(pack_everything & PACK_CRUFT)) {
 			for_each_string_list_item(item, &names) {
 				strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack",
 					     packtmp_name, item->string);
@@ -832,6 +965,35 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (!names.nr && !po_args.quiet)
 		printf_ln(_("Nothing new to pack."));
 
+	if (pack_everything & PACK_CRUFT) {
+		const char *pack_prefix;
+		if (!skip_prefix(packtmp, packdir, &pack_prefix))
+			die(_("pack prefix %s does not begin with objdir %s"),
+			    packtmp, packdir);
+		if (*pack_prefix == '/')
+			pack_prefix++;
+
+		if (!cruft_po_args.window)
+			cruft_po_args.window = po_args.window;
+		if (!cruft_po_args.window_memory)
+			cruft_po_args.window_memory = po_args.window_memory;
+		if (!cruft_po_args.depth)
+			cruft_po_args.depth = po_args.depth;
+		if (!cruft_po_args.threads)
+			cruft_po_args.threads = po_args.threads;
+
+		cruft_po_args.local = po_args.local;
+		cruft_po_args.quiet = po_args.quiet;
+
+		ret = write_cruft_pack(&cruft_po_args, pack_prefix, &names,
+				       &existing_nonkept_packs,
+				       &existing_kept_packs);
+		if (ret)
+			return ret;
+	}
+
+	string_list_sort(&names);
+
 	for_each_string_list_item(item, &names) {
 		item->util = (void *)(uintptr_t)populate_pack_exts(item->string);
 	}
@@ -872,7 +1034,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 
 	if (delete_redundant && pack_everything & ALL_INTO_ONE) {
 		const int hexsz = the_hash_algo->hexsz;
-		string_list_sort(&names);
 		for_each_string_list_item(item, &existing_nonkept_packs) {
 			char *sha1;
 			size_t len = strlen(item->string);
@@ -885,7 +1046,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			 * was given) and that we will actually delete this pack
 			 * (if `-d` was given).
 			 */
-			item->util = (void*)(intptr_t)!string_list_has_string(&names, sha1);
+			if (!string_list_has_string(&names, sha1))
+				item->util = (void*)(uintptr_t)((size_t)item->util | DELETE_PACK);
 		}
 	}
 
@@ -909,7 +1071,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (delete_redundant) {
 		int opts = 0;
 		for_each_string_list_item(item, &existing_nonkept_packs) {
-			if (!item->util)
+			if (!((uintptr_t)item->util & DELETE_PACK))
 				continue;
 			remove_redundant_pack(packdir, item->string);
 		}