pack-objects: create new name-hash algorithm (#5157)

dscho · Git for Windows Build Agent · commit 6b7e02f4fb17 · 2024-10-10T22:50:08.000Z
This is an updated version of gitgitgadget#1785, intended for early consumption into Git for Windows. The idea here is to add a new `--full-name-hash` option to `git pack-objects` and `git repack`. This adjusts the name-hash value used for finding delta bases in such a way that uses the full path name with a lower likelihood of collisions than the default name-hash algorithm. In many repositories with name-hash collisions and many versions of those paths, this can significantly reduce the size of a full repack. It can also help in certain cases of `git push`, but only if the pack is already artificially inflated by name-hash collisions; cases that find "sibling" deltas as better choices become worse with `--full-name-hash`. Thus, this option is currently recommended for full repacks of large repos, and on client machines without reachability bitmaps. Some care is taken to ignore this option when using bitmaps, either writing bitmaps or using a bitmap walk during reads. The bitmap file format contains name-hash values, but no way to indicate which function is used, so compatibility is a concern for bitmaps. Future work could explore this idea. After this PR is merged, then the more-involved `--path-walk` option may be considered.
diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
@@ -16,7 +16,7 @@ SYNOPSIS
 		   [--cruft] [--cruft-expiration=<time>]
 		   [--stdout [--filter=<filter-spec>] | <base-name>]
 		   [--shallow] [--keep-true-parents] [--[no-]sparse]
-		   [--path-walk] < <object-list>
+		   [--path-walk] [--full-name-hash] < <object-list>
 
 
 DESCRIPTION
diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
@@ -11,7 +11,7 @@ SYNOPSIS
 [verse]
 'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [-m]
 	[--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>]
-	[--write-midx] [--path-walk]
+	[--write-midx] [--path-walk] [--full-name-hash]
 
 DESCRIPTION
 -----------
diff --git a/Makefile b/Makefile
@@ -824,6 +824,7 @@ TEST_BUILTINS_OBJS += test-lazy-init-name-hash.o
 TEST_BUILTINS_OBJS += test-match-trees.o
 TEST_BUILTINS_OBJS += test-mergesort.o
 TEST_BUILTINS_OBJS += test-mktemp.o
+TEST_BUILTINS_OBJS += test-name-hash.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-pack-mtimes.o
 TEST_BUILTINS_OBJS += test-parse-options.o
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
@@ -192,7 +192,7 @@ static const char *pack_usage[] = {
 	   "                 [--cruft] [--cruft-expiration=<time>]\n"
 	   "                 [--stdout [--filter=<filter-spec>] | <base-name>]\n"
 	   "                 [--shallow] [--keep-true-parents] [--[no-]sparse]\n"
-	   "                 [--path-walk] < <object-list>"),
+	   "                 [--path-walk] [--full-name-hash] < <object-list>"),
 	NULL
 };
 
@@ -276,6 +276,14 @@ struct configured_exclusion {
 static struct oidmap configured_exclusions;
 
 static struct oidset excluded_by_config;
+static int use_full_name_hash = -1;
+
+static inline uint32_t pack_name_hash_fn(const char *name)
+{
+	if (use_full_name_hash)
+		return pack_full_name_hash(name);
+	return pack_name_hash(name);
+}
 
 /*
  * stats
@@ -1709,7 +1717,7 @@ static int add_object_entry(const struct object_id *oid, enum object_type type,
 		return 0;
 	}
 
-	create_object_entry(oid, type, pack_name_hash(name),
+	create_object_entry(oid, type, pack_name_hash_fn(name),
 			    exclude, name && no_try_delta(name),
 			    found_pack, found_offset);
 	return 1;
@@ -1923,7 +1931,7 @@ static void add_preferred_base_object(const char *name)
 {
 	struct pbase_tree *it;
 	size_t cmplen;
-	unsigned hash = pack_name_hash(name);
+	unsigned hash = pack_name_hash_fn(name);
 
 	if (!num_preferred_base || check_pbase_path(hash))
 		return;
@@ -3644,7 +3652,7 @@ static void show_object_pack_hint(struct object *object, const char *name,
 	 * here using a now in order to perhaps improve the delta selection
 	 * process.
 	 */
-	oe->hash = pack_name_hash(name);
+	oe->hash = pack_name_hash_fn(name);
 	oe->no_try_delta = name && no_try_delta(name);
 
 	stdin_packs_hints_nr++;
@@ -3794,7 +3802,7 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type
 	entry = packlist_find(&to_pack, oid);
 	if (entry) {
 		if (name) {
-			entry->hash = pack_name_hash(name);
+			entry->hash = pack_name_hash_fn(name);
 			entry->no_try_delta = no_try_delta(name);
 		}
 	} else {
@@ -3817,7 +3825,7 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type
 			return;
 		}
 
-		entry = create_object_entry(oid, type, pack_name_hash(name),
+		entry = create_object_entry(oid, type, pack_name_hash_fn(name),
 					    0, name && no_try_delta(name),
 					    pack, offset);
 	}
@@ -4739,6 +4747,8 @@ int cmd_pack_objects(int argc,
 		OPT_STRING_LIST(0, "uri-protocol", &uri_protocols,
 				N_("protocol"),
 				N_("exclude any configured uploadpack.blobpackfileuri with this protocol")),
+		OPT_BOOL(0, "full-name-hash", &use_full_name_hash,
+			 N_("(EXPERIMENTAL!) optimize delta compression across identical path names over time")),
 		OPT_END(),
 	};
 
@@ -4917,6 +4927,11 @@ int cmd_pack_objects(int argc,
 	if (pack_to_stdout || !rev_list_all)
 		write_bitmap_index = 0;
 
+	if (write_bitmap_index && use_full_name_hash > 0)
+		die(_("currently, the --full-name-hash option is incompatible with --write-bitmap-index"));
+	if (use_full_name_hash < 0)
+		use_full_name_hash = git_env_bool("GIT_TEST_FULL_NAME_HASH", 0);
+
 	if (use_delta_islands)
 		strvec_push(&rp, "--topo-order");
 
diff --git a/builtin/repack.c b/builtin/repack.c
@@ -41,7 +41,7 @@ static char *packdir, *packtmp_name, *packtmp;
 static const char *const git_repack_usage[] = {
 	N_("git repack [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [-m]\n"
 	   "[--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>]\n"
-	   "[--write-midx] [--path-walk]"),
+	   "[--write-midx] [--path-walk] [--full-name-hash]"),
 	NULL
 };
 
@@ -61,6 +61,7 @@ struct pack_objects_args {
 	int quiet;
 	int local;
 	int path_walk;
+	int full_name_hash;
 	struct list_objects_filter_options filter_options;
 };
 
@@ -311,6 +312,8 @@ static void prepare_pack_objects(struct child_process *cmd,
 		strvec_pushf(&cmd->args, "--no-reuse-object");
 	if (args->path_walk)
 		strvec_pushf(&cmd->args, "--path-walk");
+	if (args->full_name_hash)
+		strvec_pushf(&cmd->args, "--full-name-hash");
 	if (args->local)
 		strvec_push(&cmd->args,  "--local");
 	if (args->quiet)
@@ -1210,6 +1213,8 @@ int cmd_repack(int argc,
 				N_("pass --no-reuse-object to git-pack-objects")),
 		OPT_BOOL(0, "path-walk", &po_args.path_walk,
 				N_("pass --path-walk to git-pack-objects")),
+		OPT_BOOL(0, "full-name-hash", &po_args.full_name_hash,
+				N_("(EXPERIMENTAL!) pass --full-name-hash to git-pack-objects")),
 		OPT_NEGBIT('n', NULL, &run_update_server_info,
 				N_("do not run git-update-server-info"), 1),
 		OPT__QUIET(&po_args.quiet, N_("be quiet")),
diff --git a/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh
@@ -26,6 +26,7 @@ linux-TEST-vars)
 	export GIT_TEST_CHECKOUT_WORKERS=2
 	export GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL=1
 	export GIT_TEST_PACK_PATH_WALK=1
+	export GIT_TEST_FULL_NAME_HASH=1
 	;;
 linux-clang)
 	export GIT_TEST_DEFAULT_HASH=sha1
diff --git a/pack-objects.h b/pack-objects.h
@@ -219,6 +219,27 @@ static inline uint32_t pack_name_hash(const char *name)
 	return hash;
 }
 
+static inline uint32_t pack_full_name_hash(const char *name)
+{
+	const uint32_t bigp = 1234572167U;
+	uint32_t c, hash = bigp;
+
+	if (!name)
+		return 0;
+
+	/*
+	 * Do the simplest thing that will resemble pseudo-randomness: add
+	 * random multiples of a large prime number with a binary shift.
+	 * The goal is not to be cryptographic, but to be generally
+	 * uniformly distributed.
+	 */
+	while ((c = *name++) != 0) {
+		hash += c * bigp;
+		hash = (hash >> 5) | (hash << 27);
+	}
+	return hash;
+}
+
 static inline enum object_type oe_type(const struct object_entry *e)
 {
 	return e->type_valid ? e->type_ : OBJ_BAD;
diff --git a/t/README b/t/README
@@ -495,6 +495,10 @@ a test and then fails then the whole test run will abort. This can help to make
 sure the expected tests are executed and not silently skipped when their
 dependency breaks or is simply not present in a new environment.
 
+GIT_TEST_FULL_NAME_HASH=<boolean>, when true, sets the default name-hash
+function in 'git pack-objects' to be the one used by the --full-name-hash
+option.
+
 Naming Tests
 ------------
 
diff --git a/t/helper/test-name-hash.c b/t/helper/test-name-hash.c
@@ -0,0 +1,24 @@
+/*
+ * test-name-hash.c: Read a list of paths over stdin and report on their
+ * name-hash and full name-hash.
+ */
+
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "pack-objects.h"
+#include "strbuf.h"
+
+int cmd__name_hash(int argc UNUSED, const char **argv UNUSED)
+{
+	struct strbuf line = STRBUF_INIT;
+
+	while (!strbuf_getline(&line, stdin)) {
+		uint32_t name_hash = pack_name_hash(line.buf);
+		uint32_t full_hash = pack_full_name_hash(line.buf);
+
+		printf("%10"PRIu32"\t%10"PRIu32"\t%s\n", name_hash, full_hash, line.buf);
+	}
+
+	strbuf_release(&line);
+	return 0;
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
@@ -44,6 +44,7 @@ static struct test_cmd cmds[] = {
 	{ "match-trees", cmd__match_trees },
 	{ "mergesort", cmd__mergesort },
 	{ "mktemp", cmd__mktemp },
+	{ "name-hash", cmd__name_hash },
 	{ "online-cpus", cmd__online_cpus },
 	{ "pack-mtimes", cmd__pack_mtimes },
 	{ "parse-options", cmd__parse_options },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
@@ -37,6 +37,7 @@ int cmd__lazy_init_name_hash(int argc, const char **argv);
 int cmd__match_trees(int argc, const char **argv);
 int cmd__mergesort(int argc, const char **argv);
 int cmd__mktemp(int argc, const char **argv);
+int cmd__name_hash(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__pack_mtimes(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);
diff --git a/t/perf/p5313-pack-objects.sh b/t/perf/p5313-pack-objects.sh
@@ -38,6 +38,14 @@ test_size 'thin pack size with --path-walk' '
 	test_file_size out
 '
 
+test_perf 'thin pack with --full-name-hash' '
+	git pack-objects --thin --stdout --revs --sparse --full-name-hash <in-thin >out
+'
+
+test_size 'thin pack size with --full-name-hash' '
+	test_file_size out
+'
+
 test_perf 'big pack' '
 	git pack-objects --stdout --no-reuse-delta --revs \
 		--sparse <in-big >out
@@ -56,6 +64,14 @@ test_size 'big pack size with --path-walk' '
 	test_file_size out
 '
 
+test_perf 'big pack with --full-name-hash' '
+	git pack-objects --stdout --revs --sparse --full-name-hash <in-big >out
+'
+
+test_size 'big pack size with --full-name-hash' '
+	test_file_size out
+'
+
 test_perf 'repack' '
 	git repack -adf
 '
@@ -74,4 +90,13 @@ test_size 'repack size with --path-walk' '
 	test_file_size "$pack"
 '
 
+test_perf 'repack with --full-name-hash' '
+	git repack -adf --full-name-hash
+'
+
+test_size 'repack size with --full-name-hash' '
+	pack=$(ls .git/objects/pack/pack-*.pack) &&
+	test_file_size "$pack"
+'
+
 test_done
diff --git a/t/perf/p5314-name-hash.sh b/t/perf/p5314-name-hash.sh
@@ -0,0 +1,41 @@
+#!/bin/sh
+
+test_description='Tests pack performance using bitmaps'
+. ./perf-lib.sh
+
+GIT_TEST_PASSING_SANITIZE_LEAK=0
+export GIT_TEST_PASSING_SANITIZE_LEAK
+
+test_perf_large_repo
+
+test_size 'paths at head' '
+	git ls-tree -r --name-only HEAD >path-list &&
+	wc -l <path-list
+'
+
+test_size 'number of distinct name-hashes' '
+	cat path-list | test-tool name-hash >name-hashes &&
+	cat name-hashes | awk "{ print \$1; }" | sort -n | uniq -c >name-hash-count &&
+	wc -l <name-hash-count
+'
+
+test_size 'number of distinct full-name-hashes' '
+	cat name-hashes | awk "{ print \$2; }" | sort -n | uniq -c >full-name-hash-count &&
+	wc -l <full-name-hash-count
+'
+
+test_size 'maximum multiplicity of name-hashes' '
+	cat name-hash-count | \
+		sort -nr | \
+		head -n 1 | \
+		awk "{ print \$1; }"
+'
+
+test_size 'maximum multiplicity of fullname-hashes' '
+	cat full-name-hash-count | \
+		sort -nr | \
+		head -n 1 | \
+		awk "{ print \$1; }"
+'
+
+test_done
diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh
@@ -695,4 +695,19 @@ test_expect_success '--path-walk thin pack' '
 	git -C server index-pack --fix-thin --stdin <out.pack
 '
 
+# The following test is not necessarily a permanent choice, but since we do not
+# have a "name hash version" bit in the .bitmap file format, we cannot write the
+# full-name hash values into the .bitmap file without risking breakage later.
+#
+# TODO: Make these compatible in the future and replace this test with the
+# expected behavior when both are specified.
+test_expect_success '--full-name-hash and --write-bitmap-index are incompatible' '
+	test_must_fail git pack-objects base --all \
+		--full-name-hash --write-bitmap-index 2>err &&
+	grep incompatible err &&
+
+	# --stdout option silently removes --write-bitmap-index
+	git pack-objects --stdout --all --full-name-hash --write-bitmap-index >out
+'
+
 test_done
diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh
@@ -27,6 +27,32 @@ has_any () {
 	grep -Ff "$1" "$2"
 }
 
+# Since name-hash values are stored in the .bitmap files, add a test
+# that checks that the name-hash calculations are stable across versions.
+# Not exhaustive, but these hashing algorithms would be hard to change
+# without causing deviations here.
+test_expect_success 'name-hash value stability' '
+	cat >names <<-\EOF &&
+	first
+	second
+	third
+	one-long-enough-for-collisions
+	two-long-enough-for-collisions
+	EOF
+
+	test-tool name-hash <names >out &&
+
+	cat >expect <<-\EOF &&
+	2582249472	3109209818	first
+	2289942528	3781118409	second
+	2300837888	3028707182	third
+	2544516325	3241327563	one-long-enough-for-collisions
+	2544516325	4207880830	two-long-enough-for-collisions
+	EOF
+
+	test_cmp expect out
+'
+
 test_bitmap_cases () {
 	writeLookupTable=false
 	for i in "$@"
diff --git a/t/t5510-fetch.sh b/t/t5510-fetch.sh
@@ -1080,7 +1080,12 @@ test_expect_success 'all boundary commits are excluded' '
 	test_tick &&
 	git merge otherside &&
 	ad=$(git log --no-walk --format=%ad HEAD) &&
-	git bundle create twoside-boundary.bdl main --since="$ad" &&
+
+	# If the --full-name-hash function is used here, then no delta
+	# pair is found and the bundle does not expand to three objects
+	# when fixing the thin object.
+	GIT_TEST_FULL_NAME_HASH=0 \
+		git bundle create twoside-boundary.bdl main --since="$ad" &&
 	test_bundle_object_count --thin twoside-boundary.bdl 3
 '
 
diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh
diff --git a/t/t6020-bundle-misc.sh b/t/t6020-bundle-misc.sh
diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh
diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh
