pack-objects: add GIT_TEST_NAME_HASH_VERSION

Add a new environment variable to opt-in to differen values of the
--name-hash-version=<n> option in 'git pack-objects'. This allows for
extra testing of the feature without repeating all of the test
scenarios. Unlike many GIT_TEST_* variables, we are choosing to not add
this to the linux-TEST-vars CI build as that test run is already
overloaded. The behavior exposed by this test variable is of low risk
and should be sufficient to allow manual testing when an issue arises.

But this option isn't free. There are a few tests that change behavior
with the variable enabled.

First, there are a few tests that are very sensitive to certain delta
bases being picked. These are both involving the generation of thin
bundles and then counting their objects via 'git index-pack --fix-thin'
which pulls the delta base into the new packfile. For these tests,
disable the option as a decent long-term option.

Second, there are two tests in t5616-partial-clone.sh that I believe are
actually broken scenarios. While the client is set up to clone the
'promisor-server' repo via a treeless partial clone filter (tree:0),
that filter does not translate to the 'server' repo. Thus, fetching from
these repos causes the server to think that the client has all reachable
trees and blobs from the commits advertised as 'haves'. This leads the
server to providing a thin pack assuming those objects as delta bases.
Changing the name-hash algorithm presents new delta bases and thus
breaks the expectations of these tests. An alternative could be to set
up 'server' as a promisor server with the correct filter enabled. This
may also point out more issues with partial clone being set up as a
remote-based filtering mechanism and not a repository-wide setting. For
now, do the minimal change to make the test work by disabling the test
variable.

Third, there are some tests that compare the exact output of a 'git
pack-objects' process when using bitmaps. The warning that ignores the
--name-hash-version=2 and forces version 1 causes these tests to fail.
Disable the environment variable to get around this issue.

Signed-off-by: Derrick Stolee <[email protected]>

Author: derrickstolee

builtin/pack-objects.c

@@ -266,7 +266,7 @@ struct configured_exclusion {
 static struct oidmap configured_exclusions;
 
 static struct oidset excluded_by_config;
-static int name_hash_version = 1;
+static int name_hash_version = -1;
 
 static void validate_name_hash_version(void)
 {
@@ -4609,6 +4609,9 @@ int cmd_pack_objects(int argc,
 	if (pack_to_stdout || !rev_list_all)
 		write_bitmap_index = 0;
 
+	if (name_hash_version < 0)
+		name_hash_version = (int)git_env_ulong("GIT_TEST_NAME_HASH_VERSION", 1);
+
 	validate_name_hash_version();
 	if (write_bitmap_index && name_hash_version != 1) {
 		warning(_("currently, --write-bitmap-index requires --name-hash-version=1"));

t/README

@@ -492,6 +492,10 @@ 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_NAME_HASH_VERSION=<int>, when set, causes 'git pack-objects' to
+assume '--name-hash-version=<n>'.
+
+
 Naming Tests
 ------------
 

t/t5300-pack-object.sh

@@ -675,15 +675,18 @@ do
 done
 
 test_expect_success 'valid and invalid --name-hash-versions' '
+	sane_unset GIT_TEST_NAME_HASH_VERSION &&
+
 	# Valid values are hard to verify other than "do not fail".
 	# Performance tests will be more valuable to validate these versions.
-	for value in 1 2
+	# Negative values are converted to version 1.
+	for value in -1 1 2
 	do
 		git pack-objects base --all --name-hash-version=$value || return 1
 	done &&
 
 	# Invalid values have clear post-conditions.
-	for value in -1 0 3
+	for value in 0 3
 	do
 		test_must_fail git pack-objects base --all --name-hash-version=$value 2>err &&
 		test_grep "invalid --name-hash-version option" err || return 1

t/t5310-pack-bitmaps.sh

@@ -420,7 +420,10 @@ test_bitmap_cases () {
 			cat >expect <<-\EOF &&
 			error: missing value for '\''pack.preferbitmaptips'\''
 			EOF
-			git repack -adb 2>actual &&
+
+			# Disable name hash version adjustment due to stderr comparison.
+			GIT_TEST_NAME_HASH_VERSION=1 \
+				git repack -adb 2>actual &&
 			test_cmp expect actual
 		)
 	'

t/t5333-pseudo-merge-bitmaps.sh

@@ -209,6 +209,10 @@ test_expect_success 'bitmapPseudoMerge.stableThreshold creates stable groups' '
 '
 
 test_expect_success 'out of order thresholds are rejected' '
+	# Disable this option to avoid stderr message
+	GIT_TEST_NAME_HASH_VERSION=1 &&
+	export GIT_TEST_NAME_HASH_VERSION &&
+
 	test_must_fail git \
 		-c bitmapPseudoMerge.test.pattern="refs/*" \
 		-c bitmapPseudoMerge.test.threshold=1.month.ago \

t/t5510-fetch.sh

@@ -1062,7 +1062,12 @@ 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 a different 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_NAME_HASH_VERSION=1 \
+		git bundle create twoside-boundary.bdl main --since="$ad" &&
 	test_bundle_object_count --thin twoside-boundary.bdl 3
 '
 

t/t5616-partial-clone.sh

@@ -516,7 +516,18 @@ test_expect_success 'fetch lazy-fetches only to resolve deltas' '
 	# Exercise to make sure it works. Git will not fetch anything from the
 	# promisor remote other than for the big tree (because it needs to
 	# resolve the delta).
-	GIT_TRACE_PACKET="$(pwd)/trace" git -C client \
+	#
+	# TODO: the --full-name-hash option is disabled here, since this test
+	# is fundamentally broken! When GIT_TEST_NAME_HASH_VERSION=2, the server
+	# recognizes delta bases in a different way and then sends a _blob_ to
+	# the client with a delta base that the client does not have! This is
+	# because the client is cloned from "promisor-server" with tree:0 but
+	# is now fetching from "server" without any filter. This is violating the
+	# promise to the server that all reachable objects exist and could be
+	# used as delta bases!
+	GIT_TRACE_PACKET="$(pwd)/trace" \
+		GIT_TEST_NAME_HASH_VERSION=1 \
+		git -C client \
 		fetch "file://$(pwd)/server" main &&
 
 	# Verify the assumption that the client needed to fetch the delta base
@@ -535,7 +546,18 @@ test_expect_success 'fetch lazy-fetches only to resolve deltas, protocol v2' '
 	# Exercise to make sure it works. Git will not fetch anything from the
 	# promisor remote other than for the big blob (because it needs to
 	# resolve the delta).
-	GIT_TRACE_PACKET="$(pwd)/trace" git -C client \
+	#
+	# TODO: the --full-name-hash option is disabled here, since this test
+	# is fundamentally broken! When GIT_TEST_NAME_HASH_VERSION=2, the server
+	# recognizes delta bases in a different way and then sends a _blob_ to
+	# the client with a delta base that the client does not have! This is
+	# because the client is cloned from "promisor-server" with tree:0 but
+	# is now fetching from "server" without any filter. This is violating the
+	# promise to the server that all reachable objects exist and could be
+	# used as delta bases!
+	GIT_TRACE_PACKET="$(pwd)/trace" \
+		GIT_TEST_NAME_HASH_VERSION=1 \
+		git -C client \
 		fetch "file://$(pwd)/server" main &&
 
 	# Verify that protocol version 2 was used.

t/t6020-bundle-misc.sh

@@ -247,7 +247,11 @@ test_expect_success 'create bundle with --since option' '
 	EOF
 	test_cmp expect actual &&
 
-	git bundle create since.bdl \
+	# If a different name hash function is used, then one fewer
+	# delta base is found and this counts a different number
+	# of objects after performing --fix-thin.
+	GIT_TEST_NAME_HASH_VERSION=1 \
+		git bundle create since.bdl \
 		--since "Thu Apr 7 15:27:00 2005 -0700" \
 		--all &&
 

t/t7406-submodule-update.sh

@@ -1094,7 +1094,9 @@ test_expect_success 'submodule update --quiet passes quietness to fetch with a s
 	) &&
 	git clone super4 super5 &&
 	(cd super5 &&
-	 git submodule update --quiet --init --depth=1 submodule3 >out 2>err &&
+	 # This test var can mess with the stderr output checked in this test.
+	 GIT_TEST_NAME_HASH_VERSION=1 \
+		git submodule update --quiet --init --depth=1 submodule3 >out 2>err &&
 	 test_must_be_empty out &&
 	 test_must_be_empty err
 	) &&

t/t7700-repack.sh

@@ -309,7 +309,10 @@ test_expect_success 'no bitmaps created if .keep files present' '
 	keep=${pack%.pack}.keep &&
 	test_when_finished "rm -f \"\$keep\"" &&
 	>"$keep" &&
-	git -C bare.git repack -ad 2>stderr &&
+
+	# Disable --name-hash-version test due to stderr comparison.
+	GIT_TEST_NAME_HASH_VERSION=1 \
+		git -C bare.git repack -ad 2>stderr &&
 	test_must_be_empty stderr &&
 	find bare.git/objects/pack/ -type f -name "*.bitmap" >actual &&
 	test_must_be_empty actual
@@ -320,7 +323,10 @@ test_expect_success 'auto-bitmaps do not complain if unavailable' '
 	blob=$(test-tool genrandom big $((1024*1024)) |
 	       git -C bare.git hash-object -w --stdin) &&
 	git -C bare.git update-ref refs/tags/big $blob &&
-	git -C bare.git repack -ad 2>stderr &&
+
+	# Disable --name-hash-version test due to stderr comparison.
+	GIT_TEST_NAME_HASH_VERSION=1 \
+		git -C bare.git repack -ad 2>stderr &&
 	test_must_be_empty stderr &&
 	find bare.git/objects/pack -type f -name "*.bitmap" >actual &&
 	test_must_be_empty actual