Merge branch 'tb/pack-revindex-on-disk'

The on-disk reverse index that allows mapping from the pack offset
to the object name for the object stored at the offset has been
enabled by default.

* tb/pack-revindex-on-disk:
  t: invert `GIT_TEST_WRITE_REV_INDEX`
  config: enable `pack.writeReverseIndex` by default
  pack-revindex: introduce `pack.readReverseIndex`
  pack-revindex: introduce GIT_TEST_REV_INDEX_DIE_ON_DISK
  pack-revindex: make `load_pack_revindex` take a repository
  t5325: mark as leak-free
  pack-write.c: plug a leak in stage_tmp_packfiles()

Documentation/config/pack.txt

@@ -171,9 +171,15 @@ pack.writeBitmapLookupTable::
 	beneficial in repositories that have relatively large bitmap
 	indexes. Defaults to false.
 
+pack.readReverseIndex::
+	When true, git will read any .rev file(s) that may be available
+	(see: linkgit:gitformat-pack[5]). When false, the reverse index
+	will be generated from scratch and stored in memory. Defaults to
+	true.
+
 pack.writeReverseIndex::
 	When true, git will write a corresponding .rev file (see:
 	linkgit:gitformat-pack[5])
 	for each new packfile that it writes in all places except for
 	linkgit:git-fast-import[1] and in the bulk checkin mechanism.
-	Defaults to false.
+	Defaults to true.

builtin/index-pack.c

@@ -1756,12 +1756,13 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	fsck_options.walk = mark_link;
 
 	reset_pack_idx_option(&opts);
+	opts.flags |= WRITE_REV;
 	git_config(git_index_pack_config, &opts);
 	if (prefix && chdir(prefix))
 		die(_("Cannot come back to cwd"));
 
-	if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0))
-		rev_index = 1;
+	if (git_env_bool(GIT_TEST_NO_WRITE_REV_INDEX, 0))
+		rev_index = 0;
 	else
 		rev_index = !!(opts.flags & (WRITE_REV_VERIFY | WRITE_REV));
 

builtin/pack-objects.c

@@ -4294,9 +4294,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	}
 
 	reset_pack_idx_option(&pack_idx_opts);
-	git_config(git_pack_config, NULL);
-	if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0))
 	pack_idx_opts.flags |= WRITE_REV;
+	git_config(git_pack_config, NULL);
+	if (git_env_bool(GIT_TEST_NO_WRITE_REV_INDEX, 0))
+		pack_idx_opts.flags &= ~WRITE_REV;
 
 	progress = isatty(2);
 	argc = parse_options(argc, argv, prefix, pack_objects_options,

ci/run-build-and-tests.sh

@@ -27,7 +27,7 @@ linux-TEST-vars)
 	export GIT_TEST_MULTI_PACK_INDEX=1
 	export GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=1
 	export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master
-	export GIT_TEST_WRITE_REV_INDEX=1
+	export GIT_TEST_NO_WRITE_REV_INDEX=1
 	export GIT_TEST_CHECKOUT_WORKERS=2
 	;;
 linux-clang)

pack-bitmap.c

@@ -465,7 +465,7 @@ static int open_pack_bitmap_1(struct bitmap_index *bitmap_git, struct packed_git
 	return 0;
 }
 
-static int load_reverse_index(struct bitmap_index *bitmap_git)
+static int load_reverse_index(struct repository *r, struct bitmap_index *bitmap_git)
 {
 	if (bitmap_is_midx(bitmap_git)) {
 		uint32_t i;
@@ -479,23 +479,23 @@ static int load_reverse_index(struct bitmap_index *bitmap_git)
 		 * since we will need to make use of them in pack-objects.
 		 */
 		for (i = 0; i < bitmap_git->midx->num_packs; i++) {
-			ret = load_pack_revindex(bitmap_git->midx->packs[i]);
+			ret = load_pack_revindex(r, bitmap_git->midx->packs[i]);
 			if (ret)
 				return ret;
 		}
 		return 0;
 	}
-	return load_pack_revindex(bitmap_git->pack);
+	return load_pack_revindex(r, bitmap_git->pack);
 }
 
-static int load_bitmap(struct bitmap_index *bitmap_git)
+static int load_bitmap(struct repository *r, struct bitmap_index *bitmap_git)
 {
 	assert(bitmap_git->map);
 
 	bitmap_git->bitmaps = kh_init_oid_map();
 	bitmap_git->ext_index.positions = kh_init_oid_pos();
 
-	if (load_reverse_index(bitmap_git))
+	if (load_reverse_index(r, bitmap_git))
 		goto failed;
 
 	if (!(bitmap_git->commits = read_bitmap_1(bitmap_git)) ||
@@ -582,7 +582,7 @@ struct bitmap_index *prepare_bitmap_git(struct repository *r)
 {
 	struct bitmap_index *bitmap_git = xcalloc(1, sizeof(*bitmap_git));
 
-	if (!open_bitmap(r, bitmap_git) && !load_bitmap(bitmap_git))
+	if (!open_bitmap(r, bitmap_git) && !load_bitmap(r, bitmap_git))
 		return bitmap_git;
 
 	free_bitmap_index(bitmap_git);
@@ -591,9 +591,10 @@ struct bitmap_index *prepare_bitmap_git(struct repository *r)
 
 struct bitmap_index *prepare_midx_bitmap_git(struct multi_pack_index *midx)
 {
+	struct repository *r = the_repository;
 	struct bitmap_index *bitmap_git = xcalloc(1, sizeof(*bitmap_git));
 
-	if (!open_midx_bitmap_1(bitmap_git, midx) && !load_bitmap(bitmap_git))
+	if (!open_midx_bitmap_1(bitmap_git, midx) && !load_bitmap(r, bitmap_git))
 		return bitmap_git;
 
 	free_bitmap_index(bitmap_git);
@@ -1594,7 +1595,7 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
 	 * from disk. this is the point of no return; after this the rev_list
 	 * becomes invalidated and we must perform the revwalk through bitmaps
 	 */
-	if (load_bitmap(bitmap_git) < 0)
+	if (load_bitmap(revs->repo, bitmap_git) < 0)
 		goto cleanup;
 
 	object_array_clear(&revs->pending);
@@ -1744,6 +1745,7 @@ int reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
 				       uint32_t *entries,
 				       struct bitmap **reuse_out)
 {
+	struct repository *r = the_repository;
 	struct packed_git *pack;
 	struct bitmap *result = bitmap_git->result;
 	struct bitmap *reuse;
@@ -1754,7 +1756,7 @@ int reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
 
 	assert(result);
 
-	load_reverse_index(bitmap_git);
+	load_reverse_index(r, bitmap_git);
 
 	if (bitmap_is_midx(bitmap_git))
 		pack = bitmap_git->midx->packs[midx_preferred_pack(bitmap_git)];
@@ -2134,11 +2136,12 @@ int rebuild_bitmap(const uint32_t *reposition,
 uint32_t *create_bitmap_mapping(struct bitmap_index *bitmap_git,
 				struct packing_data *mapping)
 {
+	struct repository *r = the_repository;
 	uint32_t i, num_objects;
 	uint32_t *reposition;
 
 	if (!bitmap_is_midx(bitmap_git))
-		load_reverse_index(bitmap_git);
+		load_reverse_index(r, bitmap_git);
 	else if (load_midx_revindex(bitmap_git->midx) < 0)
 		BUG("rebuild_existing_bitmaps: missing required rev-cache "
 		    "extension");

pack-revindex.c

@@ -207,6 +207,9 @@ static int load_revindex_from_disk(char *revindex_name,
 	size_t revindex_size;
 	struct revindex_header *hdr;
 
+	if (git_env_bool(GIT_TEST_REV_INDEX_DIE_ON_DISK, 0))
+		die("dying as requested by '%s'", GIT_TEST_REV_INDEX_DIE_ON_DISK);
+
 	fd = git_open(revindex_name);
 
 	if (fd < 0) {
@@ -285,12 +288,15 @@ cleanup:
 	return ret;
 }
 
-int load_pack_revindex(struct packed_git *p)
+int load_pack_revindex(struct repository *r, struct packed_git *p)
 {
 	if (p->revindex || p->revindex_data)
 		return 0;
 
-	if (!load_pack_revindex_from_disk(p))
+	prepare_repo_settings(r);
+
+	if (r->settings.pack_read_reverse_index &&
+	    !load_pack_revindex_from_disk(p))
 		return 0;
 	else if (!create_pack_revindex_in_memory(p))
 		return 0;
@@ -358,7 +364,7 @@ int offset_to_pack_pos(struct packed_git *p, off_t ofs, uint32_t *pos)
 {
 	unsigned lo, hi;
 
-	if (load_pack_revindex(p) < 0)
+	if (load_pack_revindex(the_repository, p) < 0)
 		return -1;
 
 	lo = 0;

pack-revindex.h

@@ -34,11 +34,13 @@
 #define RIDX_SIGNATURE 0x52494458 /* "RIDX" */
 #define RIDX_VERSION 1
 
-#define GIT_TEST_WRITE_REV_INDEX "GIT_TEST_WRITE_REV_INDEX"
+#define GIT_TEST_NO_WRITE_REV_INDEX "GIT_TEST_NO_WRITE_REV_INDEX"
 #define GIT_TEST_REV_INDEX_DIE_IN_MEMORY "GIT_TEST_REV_INDEX_DIE_IN_MEMORY"
+#define GIT_TEST_REV_INDEX_DIE_ON_DISK "GIT_TEST_REV_INDEX_DIE_ON_DISK"
 
 struct packed_git;
 struct multi_pack_index;
+struct repository;
 
 /*
  * load_pack_revindex populates the revindex's internal data-structures for the
@@ -47,7 +49,7 @@ struct multi_pack_index;
  * If a '.rev' file is present it is mmap'd, and pointers are assigned into it
  * (instead of using the in-memory variant).
  */
-int load_pack_revindex(struct packed_git *p);
+int load_pack_revindex(struct repository *r, struct packed_git *p);
 
 /*
  * load_midx_revindex loads the '.rev' file corresponding to the given

pack-write.c

@@ -570,6 +570,8 @@ void stage_tmp_packfiles(struct strbuf *name_buffer,
 		rename_tmp_packfile(name_buffer, rev_tmp_name, "rev");
 	if (mtimes_tmp_name)
 		rename_tmp_packfile(name_buffer, mtimes_tmp_name, "mtimes");
+
+	free((char *)rev_tmp_name);
 }
 
 void write_promisor_file(const char *promisor_name, struct ref **sought, int nr_sought)

packfile.c

@@ -2154,7 +2154,7 @@ int for_each_object_in_pack(struct packed_git *p,
 	int r = 0;
 
 	if (flags & FOR_EACH_OBJECT_PACK_ORDER) {
-		if (load_pack_revindex(p))
+		if (load_pack_revindex(the_repository, p))
 			return -1;
 	}
 

repo-settings.c

@@ -63,6 +63,7 @@ void prepare_repo_settings(struct repository *r)
 	repo_cfg_bool(r, "core.multipackindex", &r->settings.core_multi_pack_index, 1);
 	repo_cfg_bool(r, "index.sparse", &r->settings.sparse_index, 0);
 	repo_cfg_bool(r, "index.skiphash", &r->settings.index_skip_hash, r->settings.index_skip_hash);
+	repo_cfg_bool(r, "pack.readreverseindex", &r->settings.pack_read_reverse_index, 1);
 
 	/*
 	 * The GIT_TEST_MULTI_PACK_INDEX variable is special in that

repository.h

@@ -37,6 +37,7 @@ struct repo_settings {
 	int fetch_write_commit_graph;
 	int command_requires_full_index;
 	int sparse_index;
+	int pack_read_reverse_index;
 
 	struct fsmonitor_settings *fsmonitor; /* lazily loaded */
 

t/README

@@ -475,7 +475,7 @@ GIT_TEST_DEFAULT_HASH=<hash-algo> specifies which hash algorithm to
 use in the test scripts. Recognized values for <hash-algo> are "sha1"
 and "sha256".
 
-GIT_TEST_WRITE_REV_INDEX=<boolean>, when true enables the
+GIT_TEST_NO_WRITE_REV_INDEX=<boolean>, when true disables the
 'pack.writeReverseIndex' setting.
 
 GIT_TEST_SPARSE_INDEX=<boolean>, when true enables index writes to use the

t/perf/p5312-pack-bitmaps-revs.sh

@@ -12,8 +12,7 @@ test_lookup_pack_bitmap () {
 	test_perf_large_repo
 
 	test_expect_success 'setup bitmap config' '
-		git config pack.writebitmaps true &&
-		git config pack.writeReverseIndex true
+		git config pack.writebitmaps true
 	'
 
 	# we need to create the tag up front such that it is covered by the repack and

t/t5325-reverse-index.sh

@@ -1,17 +1,20 @@
 #!/bin/sh
 
 test_description='on-disk reverse index'
+
+TEST_PASSES_SANITIZE_LEAK=true
 . ./test-lib.sh
 
 # The below tests want control over the 'pack.writeReverseIndex' setting
 # themselves to assert various combinations of it with other options.
-sane_unset GIT_TEST_WRITE_REV_INDEX
+sane_unset GIT_TEST_NO_WRITE_REV_INDEX
 
 packdir=.git/objects/pack
 
 test_expect_success 'setup' '
 	test_commit base &&
 
+	test_config pack.writeReverseIndex false &&
 	pack=$(git pack-objects --all $packdir/pack) &&
 	rev=$packdir/pack-$pack.rev &&
 
@@ -94,6 +97,17 @@ test_expect_success 'reverse index is not generated when available on disk' '
 		--batch-check="%(objectsize:disk)" <tip
 '
 
+test_expect_success 'reverse index is ignored when pack.readReverseIndex is false' '
+	test_index_pack true &&
+	test_path_is_file $rev &&
+
+	test_config pack.readReverseIndex false &&
+
+	git rev-parse HEAD >tip &&
+	GIT_TEST_REV_INDEX_DIE_ON_DISK=1 git cat-file \
+		--batch-check="%(objectsize:disk)" <tip
+'
+
 test_expect_success 'revindex in-memory vs on-disk' '
 	git init repo &&
 	test_when_finished "rm -fr repo" &&