1 files changed, 211 insertions, 7 deletions

diff --git a/builtin/repack.c b/builtin/repack.c
index 01440de2d5..5f9bc74adc 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -20,7 +20,7 @@ static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
 static int write_bitmaps = -1;
 static int use_delta_islands;
-static char *packdir, *packtmp;
+static char *packdir, *packtmp_name, *packtmp;
 
 static const char *const git_repack_usage[] = {
 	N_("git repack [<options>]"),
@@ -297,6 +297,142 @@ static void repack_promisor_objects(const struct pack_objects_args *args,
 #define ALL_INTO_ONE 1
 #define LOOSEN_UNREACHABLE 2
 
+struct pack_geometry {
+	struct packed_git **pack;
+	uint32_t pack_nr, pack_alloc;
+	uint32_t split;
+};
+
+static uint32_t geometry_pack_weight(struct packed_git *p)
+{
+	if (open_pack_index(p))
+		die(_("cannot open index for %s"), p->pack_name);
+	return p->num_objects;
+}
+
+static int geometry_cmp(const void *va, const void *vb)
+{
+	uint32_t aw = geometry_pack_weight(*(struct packed_git **)va),
+		 bw = geometry_pack_weight(*(struct packed_git **)vb);
+
+	if (aw < bw)
+		return -1;
+	if (aw > bw)
+		return 1;
+	return 0;
+}
+
+static void init_pack_geometry(struct pack_geometry **geometry_p)
+{
+	struct packed_git *p;
+	struct pack_geometry *geometry;
+
+	*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)
+			continue;
+
+		ALLOC_GROW(geometry->pack,
+			   geometry->pack_nr + 1,
+			   geometry->pack_alloc);
+
+		geometry->pack[geometry->pack_nr] = p;
+		geometry->pack_nr++;
+	}
+
+	QSORT(geometry->pack, geometry->pack_nr, geometry_cmp);
+}
+
+static void split_pack_geometry(struct pack_geometry *geometry, int factor)
+{
+	uint32_t i;
+	uint32_t split;
+	off_t total_size = 0;
+
+	if (!geometry->pack_nr) {
+		geometry->split = geometry->pack_nr;
+		return;
+	}
+
+	/*
+	 * First, count the number of packs (in descending order of size) which
+	 * already form a geometric progression.
+	 */
+	for (i = geometry->pack_nr - 1; i > 0; i--) {
+		struct packed_git *ours = geometry->pack[i];
+		struct packed_git *prev = geometry->pack[i - 1];
+
+		if (unsigned_mult_overflows(factor, geometry_pack_weight(prev)))
+			die(_("pack %s too large to consider in geometric "
+			      "progression"),
+			    prev->pack_name);
+
+		if (geometry_pack_weight(ours) < factor * geometry_pack_weight(prev))
+			break;
+	}
+
+	split = i;
+
+	if (split) {
+		/*
+		 * Move the split one to the right, since the top element in the
+		 * last-compared pair can't be in the progression. Only do this
+		 * when we split in the middle of the array (otherwise if we got
+		 * to the end, then the split is in the right place).
+		 */
+		split++;
+	}
+
+	/*
+	 * Then, anything to the left of 'split' must be in a new pack. But,
+	 * creating that new pack may cause packs in the heavy half to no longer
+	 * form a geometric progression.
+	 *
+	 * Compute an expected size of the new pack, and then determine how many
+	 * packs in the heavy half need to be joined into it (if any) to restore
+	 * the geometric progression.
+	 */
+	for (i = 0; i < split; i++) {
+		struct packed_git *p = geometry->pack[i];
+
+		if (unsigned_add_overflows(total_size, geometry_pack_weight(p)))
+			die(_("pack %s too large to roll up"), p->pack_name);
+		total_size += geometry_pack_weight(p);
+	}
+	for (i = split; i < geometry->pack_nr; i++) {
+		struct packed_git *ours = geometry->pack[i];
+
+		if (unsigned_mult_overflows(factor, total_size))
+			die(_("pack %s too large to roll up"), ours->pack_name);
+
+		if (geometry_pack_weight(ours) < factor * total_size) {
+			if (unsigned_add_overflows(total_size,
+						   geometry_pack_weight(ours)))
+				die(_("pack %s too large to roll up"),
+				    ours->pack_name);
+
+			split++;
+			total_size += geometry_pack_weight(ours);
+		} else
+			break;
+	}
+
+	geometry->split = split;
+}
+
+static void clear_pack_geometry(struct pack_geometry *geometry)
+{
+	if (!geometry)
+		return;
+
+	free(geometry->pack);
+	geometry->pack_nr = 0;
+	geometry->pack_alloc = 0;
+	geometry->split = 0;
+}
+
 int cmd_repack(int argc, const char **argv, const char *prefix)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
@@ -304,6 +440,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct string_list names = STRING_LIST_INIT_DUP;
 	struct string_list rollback = STRING_LIST_INIT_NODUP;
 	struct string_list existing_packs = STRING_LIST_INIT_DUP;
+	struct pack_geometry *geometry = NULL;
 	struct strbuf line = STRBUF_INIT;
 	int i, ext, ret;
 	FILE *out;
@@ -316,6 +453,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	int no_update_server_info = 0;
 	struct pack_objects_args po_args = {NULL};
+	int geometric_factor = 0;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -356,6 +494,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				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_INTEGER('g', "geometric", &geometric_factor,
+			    N_("find a geometric progression with factor <N>")),
 		OPT_END()
 	};
 
@@ -382,8 +522,16 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (write_bitmaps && !(pack_everything & ALL_INTO_ONE))
 		die(_(incremental_bitmap_conflict_error));
 
+	if (geometric_factor) {
+		if (pack_everything)
+			die(_("--geometric is incompatible with -A, -a"));
+		init_pack_geometry(&geometry);
+		split_pack_geometry(geometry, geometric_factor);
+	}
+
 	packdir = mkpathdup("%s/pack", get_object_directory());
-	packtmp = mkpathdup("%s/.tmp-%d-pack", packdir, (int)getpid());
+	packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid());
+	packtmp = mkpathdup("%s/%s", packdir, packtmp_name);
 
 	sigchain_push_common(remove_pack_on_signal);
 
@@ -396,9 +544,21 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		strvec_pushf(&cmd.args, "--keep-pack=%s",
 			     keep_pack_list.items[i].string);
 	strvec_push(&cmd.args, "--non-empty");
-	strvec_push(&cmd.args, "--all");
-	strvec_push(&cmd.args, "--reflog");
-	strvec_push(&cmd.args, "--indexed-objects");
+	if (!geometry) {
+		/*
+		 * We need to grab all reachable objects, including those that
+		 * are reachable from reflogs and the index.
+		 *
+		 * When repacking into a geometric progression of packs,
+		 * however, we ask 'git pack-objects --stdin-packs', and it is
+		 * not about packing objects based on reachability but about
+		 * repacking all the objects in specified packs and loose ones
+		 * (indeed, --stdin-packs is incompatible with these options).
+		 */
+		strvec_push(&cmd.args, "--all");
+		strvec_push(&cmd.args, "--reflog");
+		strvec_push(&cmd.args, "--indexed-objects");
+	}
 	if (has_promisor_remote())
 		strvec_push(&cmd.args, "--exclude-promisor-objects");
 	if (write_bitmaps > 0)
@@ -414,6 +574,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		repack_promisor_objects(&po_args, &names);
 
 		if (existing_packs.nr && delete_redundant) {
+			for_each_string_list_item(item, &names) {
+				strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack",
+					     packtmp_name, item->string);
+			}
 			if (unpack_unreachable) {
 				strvec_pushf(&cmd.args,
 					     "--unpack-unreachable=%s",
@@ -429,17 +593,37 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				strvec_push(&cmd.env_array, "GIT_REF_PARANOIA=1");
 			}
 		}
+	} else if (geometry) {
+		strvec_push(&cmd.args, "--stdin-packs");
+		strvec_push(&cmd.args, "--unpacked");
 	} else {
 		strvec_push(&cmd.args, "--unpacked");
 		strvec_push(&cmd.args, "--incremental");
 	}
 
-	cmd.no_stdin = 1;
+	if (geometry)
+		cmd.in = -1;
+	else
+		cmd.no_stdin = 1;
 
 	ret = start_command(&cmd);
 	if (ret)
 		return ret;
 
+	if (geometry) {
+		FILE *in = xfdopen(cmd.in, "w");
+		/*
+		 * The resulting pack should contain all objects in packs that
+		 * are going to be rolled up, but exclude objects in packs which
+		 * are being left alone.
+		 */
+		for (i = 0; i < geometry->split; i++)
+			fprintf(in, "%s\n", pack_basename(geometry->pack[i]));
+		for (i = geometry->split; i < geometry->pack_nr; i++)
+			fprintf(in, "^%s\n", pack_basename(geometry->pack[i]));
+		fclose(in);
+	}
+
 	out = xfdopen(cmd.out, "r");
 	while (strbuf_getline_lf(&line, out) != EOF) {
 		if (line.len != the_hash_algo->hexsz)
@@ -507,6 +691,25 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			if (!string_list_has_string(&names, sha1))
 				remove_redundant_pack(packdir, item->string);
 		}
+
+		if (geometry) {
+			struct strbuf buf = STRBUF_INIT;
+
+			uint32_t i;
+			for (i = 0; i < geometry->split; i++) {
+				struct packed_git *p = geometry->pack[i];
+				if (string_list_has_string(&names,
+							   hash_to_hex(p->hash)))
+					continue;
+
+				strbuf_reset(&buf);
+				strbuf_addstr(&buf, pack_basename(p));
+				strbuf_strip_suffix(&buf, ".pack");
+
+				remove_redundant_pack(packdir, buf.buf);
+			}
+			strbuf_release(&buf);
+		}
 		if (!po_args.quiet && isatty(2))
 			opts |= PRUNE_PACKED_VERBOSE;
 		prune_packed_objects(opts);
@@ -523,11 +726,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	remove_temporary_files();
 
 	if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0))
-		write_midx_file(get_object_directory(), 0);
+		write_midx_file(get_object_directory(), NULL, 0);
 
 	string_list_clear(&names, 0);
 	string_list_clear(&rollback, 0);
 	string_list_clear(&existing_packs, 0);
+	clear_pack_geometry(geometry);
 	strbuf_release(&line);
 
 	return 0;