builtin/repack.c: pass --refs-snapshot when writing bitmaps

To prevent the race described in an earlier patch, generate and pass a
reference snapshot to the multi-pack bitmap code, if we are writing one
from `git repack`.

This patch is mostly limited to creating a temporary file, and then
calling for_each_ref(). Except we try to minimize duplicates, since
doing so can drastically reduce the size in network-of-forks style
repositories. In the kernel's fork network (the repository containing
all objects from the kernel and all its forks), deduplicating the
references drops the snapshot size from 934 MB to just 12 MB.

But since we're handling duplicates in this way, we have to make sure
that we preferred references (those listed in pack.preferBitmapTips)
before non-preferred ones (to avoid recording an object which is pointed
at by a preferred tip as non-preferred).

We accomplish this by doing separate passes over the references: first
visiting each prefix in pack.preferBitmapTips, and then over the rest of
the references.

Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

builtin/repack.c

@@ -15,6 +15,8 @@
 #include "promisor-remote.h"
 #include "shallow.h"
 #include "pack.h"
+#include "pack-bitmap.h"
+#include "refs.h"
 
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
@@ -453,6 +455,68 @@ static void clear_pack_geometry(struct pack_geometry *geometry)
 	geometry->split = 0;
 }
 
+struct midx_snapshot_ref_data {
+	struct tempfile *f;
+	struct oidset seen;
+	int preferred;
+};
+
+static int midx_snapshot_ref_one(const char *refname,
+				 const struct object_id *oid,
+				 int flag, void *_data)
+{
+	struct midx_snapshot_ref_data *data = _data;
+	struct object_id peeled;
+
+	if (!peel_iterated_oid(oid, &peeled))
+		oid = &peeled;
+
+	if (oidset_insert(&data->seen, oid))
+		return 0; /* already seen */
+
+	if (oid_object_info(the_repository, oid, NULL) != OBJ_COMMIT)
+		return 0;
+
+	fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "",
+		oid_to_hex(oid));
+
+	return 0;
+}
+
+static void midx_snapshot_refs(struct tempfile *f)
+{
+	struct midx_snapshot_ref_data data;
+	const struct string_list *preferred = bitmap_preferred_tips(the_repository);
+
+	data.f = f;
+	data.preferred = 0;
+	oidset_init(&data.seen, 0);
+
+	if (!fdopen_tempfile(f, "w"))
+		 die(_("could not open tempfile %s for writing"),
+		     get_tempfile_path(f));
+
+	if (preferred) {
+		struct string_list_item *item;
+
+		data.preferred = 1;
+		for_each_string_list_item(item, preferred)
+			for_each_ref_in(item->string, midx_snapshot_ref_one, &data);
+		data.preferred = 0;
+	}
+
+	for_each_ref(midx_snapshot_ref_one, &data);
+
+	if (close_tempfile_gently(f)) {
+		int save_errno = errno;
+		delete_tempfile(&f);
+		errno = save_errno;
+		die_errno(_("could not close refs snapshot tempfile"));
+	}
+
+	oidset_clear(&data.seen);
+}
+
 static void midx_included_packs(struct string_list *include,
 				struct string_list *existing_nonkept_packs,
 				struct string_list *existing_kept_packs,
@@ -488,6 +552,7 @@ static void midx_included_packs(struct string_list *include,
 
 static int write_midx_included_packs(struct string_list *include,
 				     struct pack_geometry *geometry,
+				     const char *refs_snapshot,
 				     int show_progress, int write_bitmaps)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
@@ -517,6 +582,9 @@ static int write_midx_included_packs(struct string_list *include,
 		strvec_pushf(&cmd.args, "--preferred-pack=%s",
 			     pack_basename(largest));
 
+	if (refs_snapshot)
+		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);
+
 	ret = start_command(&cmd);
 	if (ret)
 		return ret;
@@ -539,6 +607,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct string_list existing_kept_packs = STRING_LIST_INIT_DUP;
 	struct pack_geometry *geometry = NULL;
 	struct strbuf line = STRBUF_INIT;
+	struct tempfile *refs_snapshot = NULL;
 	int i, ext, ret;
 	FILE *out;
 	int show_progress = isatty(2);
@@ -627,6 +696,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx)
 		die(_(incremental_bitmap_conflict_error));
 
+	if (write_midx && write_bitmaps) {
+		struct strbuf path = STRBUF_INIT;
+
+		strbuf_addf(&path, "%s/%s_XXXXXX", get_object_directory(),
+			    "bitmap-ref-tips");
+
+		refs_snapshot = xmks_tempfile(path.buf);
+		midx_snapshot_refs(refs_snapshot);
+
+		strbuf_release(&path);
+	}
+
 	if (geometric_factor) {
 		if (pack_everything)
 			die(_("--geometric is incompatible with -A, -a"));
@@ -809,6 +890,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				    &existing_kept_packs, &names, geometry);
 
 		ret = write_midx_included_packs(&include, geometry,
+						refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL,
 						show_progress, write_bitmaps > 0);
 
 		string_list_clear(&include, 0);

t/t7700-repack.sh

@@ -330,4 +330,46 @@ test_expect_success 'cleans up MIDX when appropriate' '
 	)
 '
 
+test_expect_success '--write-midx with preferred bitmap tips' '
+	git init midx-preferred-tips &&
+	test_when_finished "rm -fr midx-preferred-tips" &&
+	(
+		cd midx-preferred-tips &&
+
+		test_commit_bulk --message="%s" 103 &&
+
+		git log --format="%H" >commits.raw &&
+		sort <commits.raw >commits &&
+
+		git log --format="create refs/tags/%s/%s %H" HEAD >refs &&
+		git update-ref --stdin <refs &&
+
+		git repack --write-midx --write-bitmap-index &&
+		test_path_is_file $midx &&
+		test_path_is_file $midx-$(midx_checksum $objdir).bitmap &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >before &&
+		test_line_count = 1 before &&
+
+		rm -fr $midx-$(midx_checksum $objdir).bitmap &&
+		rm -fr $midx-$(midx_checksum $objdir).rev &&
+		rm -fr $midx &&
+
+		# instead of constructing the snapshot ourselves (c.f., the test
+		# "write a bitmap with --refs-snapshot (preferred tips)" in
+		# t5326), mark the missing commit as preferred by adding it to
+		# the pack.preferBitmapTips configuration.
+		git for-each-ref --format="%(refname:rstrip=1)" \
+			--points-at="$(cat before)" >missing &&
+		git config pack.preferBitmapTips "$(cat missing)" &&
+		git repack --write-midx --write-bitmap-index &&
+
+		test-tool bitmap list-commits | sort >bitmaps &&
+		comm -13 bitmaps commits >after &&
+
+		! test_cmp before after
+	)
+'
+
 test_done