1 files changed, 299 insertions, 68 deletions

diff --git a/builtin/repack.c b/builtin/repack.c
index 529e13120d..ede36328a3 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -8,7 +8,6 @@
 #include "path.h"
 #include "run-command.h"
 #include "server-info.h"
-#include "sigchain.h"
 #include "strbuf.h"
 #include "string-list.h"
 #include "strvec.h"
@@ -21,12 +20,14 @@
 #include "pack.h"
 #include "pack-bitmap.h"
 #include "refs.h"
+#include "list-objects-filter-options.h"
 
 #define ALL_INTO_ONE 1
 #define LOOSEN_UNREACHABLE 2
 #define PACK_CRUFT 4
 
 #define DELETE_PACK 1
+#define RETAIN_PACK 2
 
 static int pack_everything;
 static int delta_base_offset = 1;
@@ -51,11 +52,12 @@ struct pack_objects_args {
 	const char *window_memory;
 	const char *depth;
 	const char *threads;
-	const char *max_pack_size;
+	unsigned long max_pack_size;
 	int no_reuse_delta;
 	int no_reuse_object;
 	int quiet;
 	int local;
+	struct list_objects_filter_options filter_options;
 };
 
 static int repack_config(const char *var, const char *value,
@@ -116,11 +118,26 @@ static void pack_mark_for_deletion(struct string_list_item *item)
 	item->util = (void*)((uintptr_t)item->util | DELETE_PACK);
 }
 
+static void pack_unmark_for_deletion(struct string_list_item *item)
+{
+	item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK);
+}
+
 static int pack_is_marked_for_deletion(struct string_list_item *item)
 {
 	return (uintptr_t)item->util & DELETE_PACK;
 }
 
+static void pack_mark_retained(struct string_list_item *item)
+{
+	item->util = (void*)((uintptr_t)item->util | RETAIN_PACK);
+}
+
+static int pack_is_retained(struct string_list_item *item)
+{
+	return (uintptr_t)item->util & RETAIN_PACK;
+}
+
 static void mark_packs_for_deletion_1(struct string_list *names,
 				      struct string_list *list)
 {
@@ -133,17 +150,39 @@ static void mark_packs_for_deletion_1(struct string_list *names,
 		if (len < hexsz)
 			continue;
 		sha1 = item->string + len - hexsz;
-		/*
-		 * Mark this pack for deletion, which ensures that this
-		 * pack won't be included in a MIDX (if `--write-midx`
-		 * was given) and that we will actually delete this pack
-		 * (if `-d` was given).
-		 */
-		if (!string_list_has_string(names, sha1))
+
+		if (pack_is_retained(item)) {
+			pack_unmark_for_deletion(item);
+		} else if (!string_list_has_string(names, sha1)) {
+			/*
+			 * Mark this pack for deletion, which ensures
+			 * that this pack won't be included in a MIDX
+			 * (if `--write-midx` was given) and that we
+			 * will actually delete this pack (if `-d` was
+			 * given).
+			 */
 			pack_mark_for_deletion(item);
+		}
 	}
 }
 
+static void retain_cruft_pack(struct existing_packs *existing,
+			      struct packed_git *cruft)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list_item *item;
+
+	strbuf_addstr(&buf, pack_basename(cruft));
+	strbuf_strip_suffix(&buf, ".pack");
+
+	item = string_list_lookup(&existing->cruft_packs, buf.buf);
+	if (!item)
+		BUG("could not find cruft pack '%s'", pack_basename(cruft));
+
+	pack_mark_retained(item);
+	strbuf_release(&buf);
+}
+
 static void mark_packs_for_deletion(struct existing_packs *existing,
 				    struct string_list *names)
 
@@ -225,6 +264,8 @@ static void collect_pack_filenames(struct existing_packs *existing,
 	}
 
 	string_list_sort(&existing->kept_packs);
+	string_list_sort(&existing->non_kept_packs);
+	string_list_sort(&existing->cruft_packs);
 	strbuf_release(&buf);
 }
 
@@ -242,7 +283,7 @@ static void prepare_pack_objects(struct child_process *cmd,
 	if (args->threads)
 		strvec_pushf(&cmd->args, "--threads=%s", args->threads);
 	if (args->max_pack_size)
-		strvec_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size);
+		strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size);
 	if (args->no_reuse_delta)
 		strvec_pushf(&cmd->args, "--no-reuse-delta");
 	if (args->no_reuse_object)
@@ -315,6 +356,18 @@ static struct generated_pack_data *populate_pack_exts(const char *name)
 	return data;
 }
 
+static int has_pack_ext(const struct generated_pack_data *data,
+			const char *ext)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(exts); i++) {
+		if (strcmp(exts[i].name, ext))
+			continue;
+		return !!data->tempfiles[i];
+	}
+	BUG("unknown pack extension: '%s'", ext);
+}
+
 static void repack_promisor_objects(const struct pack_objects_args *args,
 				    struct string_list *names)
 {
@@ -732,6 +785,7 @@ static void midx_included_packs(struct string_list *include,
 
 static int write_midx_included_packs(struct string_list *include,
 				     struct pack_geometry *geometry,
+				     struct string_list *names,
 				     const char *refs_snapshot,
 				     int show_progress, int write_bitmaps)
 {
@@ -761,6 +815,38 @@ static int write_midx_included_packs(struct string_list *include,
 	if (preferred)
 		strvec_pushf(&cmd.args, "--preferred-pack=%s",
 			     pack_basename(preferred));
+	else if (names->nr) {
+		/* The largest pack was repacked, meaning that either
+		 * one or two packs exist depending on whether the
+		 * repository has a cruft pack or not.
+		 *
+		 * Select the non-cruft one as preferred to encourage
+		 * pack-reuse among packs containing reachable objects
+		 * over unreachable ones.
+		 *
+		 * (Note we could write multiple packs here if
+		 * `--max-pack-size` was given, but any one of them
+		 * will suffice, so pick the first one.)
+		 */
+		for_each_string_list_item(item, names) {
+			struct generated_pack_data *data = item->util;
+			if (has_pack_ext(data, ".mtimes"))
+				continue;
+
+			strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack",
+				     item->string);
+			break;
+		}
+	} else {
+		/*
+		 * No packs were kept, and no packs were written. The
+		 * only thing remaining are .keep packs (unless
+		 * --pack-kept-objects was given).
+		 *
+		 * Set the `--preferred-pack` arbitrarily here.
+		 */
+		;
+	}
 
 	if (refs_snapshot)
 		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);
@@ -806,6 +892,153 @@ static void remove_redundant_bitmaps(struct string_list *include,
 	strbuf_release(&path);
 }
 
+static int finish_pack_objects_cmd(struct child_process *cmd,
+				   struct string_list *names,
+				   int local)
+{
+	FILE *out;
+	struct strbuf line = STRBUF_INIT;
+
+	out = xfdopen(cmd->out, "r");
+	while (strbuf_getline_lf(&line, out) != EOF) {
+		struct string_list_item *item;
+
+		if (line.len != the_hash_algo->hexsz)
+			die(_("repack: Expecting full hex object ID lines only "
+			      "from pack-objects."));
+		/*
+		 * Avoid putting packs written outside of the repository in the
+		 * list of names.
+		 */
+		if (local) {
+			item = string_list_append(names, line.buf);
+			item->util = populate_pack_exts(line.buf);
+		}
+	}
+	fclose(out);
+
+	strbuf_release(&line);
+
+	return finish_command(cmd);
+}
+
+static int write_filtered_pack(const struct pack_objects_args *args,
+			       const char *destination,
+			       const char *pack_prefix,
+			       struct existing_packs *existing,
+			       struct string_list *names)
+{
+	struct child_process cmd = CHILD_PROCESS_INIT;
+	struct string_list_item *item;
+	FILE *in;
+	int ret;
+	const char *caret;
+	const char *scratch;
+	int local = skip_prefix(destination, packdir, &scratch);
+
+	prepare_pack_objects(&cmd, args, destination);
+
+	strvec_push(&cmd.args, "--stdin-packs");
+
+	if (!pack_kept_objects)
+		strvec_push(&cmd.args, "--honor-pack-keep");
+	for_each_string_list_item(item, &existing->kept_packs)
+		strvec_pushf(&cmd.args, "--keep-pack=%s", item->string);
+
+	cmd.in = -1;
+
+	ret = start_command(&cmd);
+	if (ret)
+		return ret;
+
+	/*
+	 * Here 'names' contains only the pack(s) that were just
+	 * written, which is exactly the packs we want to keep. Also
+	 * 'existing_kept_packs' already contains the packs in
+	 * 'keep_pack_list'.
+	 */
+	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->non_kept_packs)
+		fprintf(in, "%s.pack\n", item->string);
+	for_each_string_list_item(item, &existing->cruft_packs)
+		fprintf(in, "%s.pack\n", item->string);
+	caret = pack_kept_objects ? "" : "^";
+	for_each_string_list_item(item, &existing->kept_packs)
+		fprintf(in, "%s%s.pack\n", caret, item->string);
+	fclose(in);
+
+	return finish_pack_objects_cmd(&cmd, names, local);
+}
+
+static int existing_cruft_pack_cmp(const void *va, const void *vb)
+{
+	struct packed_git *a = *(struct packed_git **)va;
+	struct packed_git *b = *(struct packed_git **)vb;
+
+	if (a->pack_size < b->pack_size)
+		return -1;
+	if (a->pack_size > b->pack_size)
+		return 1;
+	return 0;
+}
+
+static void collapse_small_cruft_packs(FILE *in, size_t max_size,
+				       struct existing_packs *existing)
+{
+	struct packed_git **existing_cruft, *p;
+	struct strbuf buf = STRBUF_INIT;
+	size_t total_size = 0;
+	size_t existing_cruft_nr = 0;
+	size_t i;
+
+	ALLOC_ARRAY(existing_cruft, existing->cruft_packs.nr);
+
+	for (p = get_all_packs(the_repository); p; p = p->next) {
+		if (!(p->is_cruft && p->pack_local))
+			continue;
+
+		strbuf_reset(&buf);
+		strbuf_addstr(&buf, pack_basename(p));
+		strbuf_strip_suffix(&buf, ".pack");
+
+		if (!string_list_has_string(&existing->cruft_packs, buf.buf))
+			continue;
+
+		if (existing_cruft_nr >= existing->cruft_packs.nr)
+			BUG("too many cruft packs (found %"PRIuMAX", but knew "
+			    "of %"PRIuMAX")",
+			    (uintmax_t)existing_cruft_nr + 1,
+			    (uintmax_t)existing->cruft_packs.nr);
+		existing_cruft[existing_cruft_nr++] = p;
+	}
+
+	QSORT(existing_cruft, existing_cruft_nr, existing_cruft_pack_cmp);
+
+	for (i = 0; i < existing_cruft_nr; i++) {
+		size_t proposed;
+
+		p = existing_cruft[i];
+		proposed = st_add(total_size, p->pack_size);
+
+		if (proposed <= max_size) {
+			total_size = proposed;
+			fprintf(in, "-%s\n", pack_basename(p));
+		} else {
+			retain_cruft_pack(existing, p);
+			fprintf(in, "%s\n", pack_basename(p));
+		}
+	}
+
+	for (i = 0; i < existing->non_kept_packs.nr; i++)
+		fprintf(in, "-%s.pack\n",
+			existing->non_kept_packs.items[i].string);
+
+	strbuf_release(&buf);
+	free(existing_cruft);
+}
+
 static int write_cruft_pack(const struct pack_objects_args *args,
 			    const char *destination,
 			    const char *pack_prefix,
@@ -814,9 +1047,8 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 			    struct existing_packs *existing)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
-	struct strbuf line = STRBUF_INIT;
 	struct string_list_item *item;
-	FILE *in, *out;
+	FILE *in;
 	int ret;
 	const char *scratch;
 	int local = skip_prefix(destination, packdir, &scratch);
@@ -853,35 +1085,30 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 	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->non_kept_packs)
-		fprintf(in, "-%s.pack\n", item->string);
-	for_each_string_list_item(item, &existing->cruft_packs)
-		fprintf(in, "-%s.pack\n", item->string);
+	if (args->max_pack_size && !cruft_expiration) {
+		collapse_small_cruft_packs(in, args->max_pack_size, existing);
+	} else {
+		for_each_string_list_item(item, &existing->non_kept_packs)
+			fprintf(in, "-%s.pack\n", item->string);
+		for_each_string_list_item(item, &existing->cruft_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) {
-		struct string_list_item *item;
-
-		if (line.len != the_hash_algo->hexsz)
-			die(_("repack: Expecting full hex object ID lines only "
-			      "from pack-objects."));
-		/*
-		 * avoid putting packs written outside of the repository in the
-		 * list of names
-		 */
-		if (local) {
-			item = string_list_append(names, line.buf);
-			item->util = populate_pack_exts(line.buf);
-		}
-	}
-	fclose(out);
-
-	strbuf_release(&line);
+	return finish_pack_objects_cmd(&cmd, names, local);
+}
 
-	return finish_command(&cmd);
+static const char *find_pack_prefix(const char *packdir, const char *packtmp)
+{
+	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++;
+	return pack_prefix;
 }
 
 int cmd_repack(int argc, const char **argv, const char *prefix)
@@ -891,10 +1118,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct string_list names = STRING_LIST_INIT_DUP;
 	struct existing_packs existing = EXISTING_PACKS_INIT;
 	struct pack_geometry geometry = { 0 };
-	struct strbuf line = STRBUF_INIT;
 	struct tempfile *refs_snapshot = NULL;
 	int i, ext, ret;
-	FILE *out;
 	int show_progress;
 
 	/* variables to be filled by option parsing */
@@ -907,6 +1132,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int write_midx = 0;
 	const char *cruft_expiration = NULL;
 	const char *expire_to = NULL;
+	const char *filter_to = NULL;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -919,6 +1145,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				   PACK_CRUFT),
 		OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
 				N_("with --cruft, expire objects older than this")),
+		OPT_MAGNITUDE(0, "max-cruft-size", &cruft_po_args.max_pack_size,
+				N_("with --cruft, limit the size of new cruft packs")),
 		OPT_BOOL('d', NULL, &delete_redundant,
 				N_("remove redundant packs, and run git-prune-packed")),
 		OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
@@ -946,8 +1174,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("limits the maximum delta depth")),
 		OPT_STRING(0, "threads", &po_args.threads, N_("n"),
 				N_("limits the maximum number of threads")),
-		OPT_STRING(0, "max-pack-size", &po_args.max_pack_size, N_("bytes"),
+		OPT_MAGNITUDE(0, "max-pack-size", &po_args.max_pack_size,
 				N_("maximum size of each packfile")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&po_args.filter_options),
 		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"),
@@ -958,9 +1187,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			   N_("write a multi-pack index of the resulting packs")),
 		OPT_STRING(0, "expire-to", &expire_to, N_("dir"),
 			   N_("pack prefix to store a pack containing pruned objects")),
+		OPT_STRING(0, "filter-to", &filter_to, N_("dir"),
+			   N_("pack prefix to store a pack containing filtered out objects")),
 		OPT_END()
 	};
 
+	list_objects_filter_init(&po_args.filter_options);
+
 	git_config(repack_config, &cruft_po_args);
 
 	argc = parse_options(argc, argv, prefix, builtin_repack_options,
@@ -969,19 +1202,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (delete_redundant && repository_format_precious_objects)
 		die(_("cannot delete packs in a precious-objects repo"));
 
-	if (keep_unreachable &&
-	    (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
-		die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A");
+	die_for_incompatible_opt3(unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE), "-A",
+				  keep_unreachable, "-k/--keep-unreachable",
+				  pack_everything & PACK_CRUFT, "--cruft");
 
-	if (pack_everything & PACK_CRUFT) {
+	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()))
@@ -1101,6 +1328,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		strvec_push(&cmd.args, "--incremental");
 	}
 
+	if (po_args.filter_options.choice)
+		strvec_pushf(&cmd.args, "--filter=%s",
+			     expand_list_objects_filter_spec(&po_args.filter_options));
+	else if (filter_to)
+		die(_("option '%s' can only be used along with '%s'"), "--filter-to", "--filter");
+
 	if (geometry.split_factor)
 		cmd.in = -1;
 	else
@@ -1124,18 +1357,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		fclose(in);
 	}
 
-	out = xfdopen(cmd.out, "r");
-	while (strbuf_getline_lf(&line, out) != EOF) {
-		struct string_list_item *item;
-
-		if (line.len != the_hash_algo->hexsz)
-			die(_("repack: Expecting full hex object ID lines only from pack-objects."));
-		item = string_list_append(&names, line.buf);
-		item->util = populate_pack_exts(item->string);
-	}
-	strbuf_release(&line);
-	fclose(out);
-	ret = finish_command(&cmd);
+	ret = finish_pack_objects_cmd(&cmd, &names, 1);
 	if (ret)
 		goto cleanup;
 
@@ -1143,12 +1365,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		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++;
+		const char *pack_prefix = find_pack_prefix(packdir, packtmp);
 
 		if (!cruft_po_args.window)
 			cruft_po_args.window = po_args.window;
@@ -1203,6 +1420,19 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		}
 	}
 
+	if (po_args.filter_options.choice) {
+		if (!filter_to)
+			filter_to = packtmp;
+
+		ret = write_filtered_pack(&po_args,
+					  filter_to,
+					  find_pack_prefix(packdir, packtmp),
+					  &existing,
+					  &names);
+		if (ret)
+			goto cleanup;
+	}
+
 	string_list_sort(&names);
 
 	close_object_store(the_repository->objects);
@@ -1248,7 +1478,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		struct string_list include = STRING_LIST_INIT_NODUP;
 		midx_included_packs(&include, &existing, &names, &geometry);
 
-		ret = write_midx_included_packs(&include, &geometry,
+		ret = write_midx_included_packs(&include, &geometry, &names,
 						refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL,
 						show_progress, write_bitmaps > 0);
 
@@ -1295,6 +1525,7 @@ cleanup:
 	string_list_clear(&names, 1);
 	existing_packs_release(&existing);
 	free_pack_geometry(&geometry);
+	list_objects_filter_release(&po_args.filter_options);
 
 	return ret;
 }