From 866e5b1634824afda66137b5744b89ec79a46577 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 17 Sep 2024 15:24:02 -0400 Subject: [PATCH] pack-objects: add GIT_TEST_FULL_NAME_HASH Add a new environment variable to opt-in to the --full-name-hash option in 'git pack-objects'. This allows for extra testing of the feature without repeating all of the test scenarios. 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. Signed-off-by: Derrick Stolee --- builtin/pack-objects.c | 6 ++++-- ci/run-build-and-tests.sh | 1 + t/README | 4 ++++ t/t5510-fetch.sh | 7 ++++++- t/t5616-partial-clone.sh | 26 ++++++++++++++++++++++++-- t/t6020-bundle-misc.sh | 6 +++++- 6 files changed, 44 insertions(+), 6 deletions(-) diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 919be27b2ac8c6..f1fba6afe37d32 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -266,7 +266,7 @@ struct configured_exclusion { static struct oidmap configured_exclusions; static struct oidset excluded_by_config; -static int use_full_name_hash; +static int use_full_name_hash = -1; static inline uint32_t pack_name_hash_fn(const char *name) { @@ -4554,8 +4554,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (pack_to_stdout || !rev_list_all) write_bitmap_index = 0; - if (write_bitmap_index && use_full_name_hash) + 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/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh index e520f809434017..f7a2d655773165 100755 --- a/ci/run-build-and-tests.sh +++ b/ci/run-build-and-tests.sh @@ -25,6 +25,7 @@ linux-TEST-vars) export GIT_TEST_NO_WRITE_REV_INDEX=1 export GIT_TEST_CHECKOUT_WORKERS=2 export GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL=1 + export GIT_TEST_FULL_NAME_HASH=1 ;; linux-clang) export GIT_TEST_DEFAULT_HASH=sha1 diff --git a/t/README b/t/README index cd884fdcd4dfe2..87285a29151cc1 100644 --- a/t/README +++ b/t/README @@ -488,6 +488,10 @@ 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=, when true, sets the default name-hash +function in 'git pack-objects' to be the one used by the --full-name-hash +option. + GIT_TEST_FSCACHE= exercises the uncommon fscache code path which adds a cache below mingw's lstat and dirent implementations. diff --git a/t/t5510-fetch.sh b/t/t5510-fetch.sh index 3b3991ab8678a5..bb4bb04ba2d41e 100755 --- a/t/t5510-fetch.sh +++ b/t/t5510-fetch.sh @@ -1061,7 +1061,12 @@ 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="$ad" && test_bundle_object_count --thin twoside-boundary.bdl 3 ' diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh index 2da7291e37997a..436f99adbb2605 100755 --- a/t/t5616-partial-clone.sh +++ b/t/t5616-partial-clone.sh @@ -515,7 +515,18 @@ test_expect_success 'fetch lazy-fetches only to resolve deltas' ' # Exercise to make sure it works. Git will not fetch anything from the # promisor remote other than for the big tree (because it needs to # resolve the delta). - GIT_TRACE_PACKET="$(pwd)/trace" git -C client \ + # + # TODO: the --full-name-hash option is disabled here, since this test + # is fundamentally broken! When GIT_TEST_FULL_NAME_HASH=1, 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" withot 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="$(pwd)/trace" \ + GIT_TEST_FULL_NAME_HASH=0 \ + git -C client \ fetch "file://$(pwd)/server" main && # Verify the assumption that the client needed to fetch the delta base @@ -534,7 +545,18 @@ 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="$(pwd)/trace" git -C client \ + # + # TODO: the --full-name-hash option is disabled here, since this test + # is fundamentally broken! When GIT_TEST_FULL_NAME_HASH=1, the server + # recognizes delta bases in a different way and then sends a _blob_ to + # the client with a delta base that the client does not have! This is + # because the client is cloned from "promisor-server" with tree:0 but + # is now fetching from "server" withot any filter. This is violating the + # promise to the server that all reachable objects exist and could be + # used as delta bases! + GIT_TRACE_PACKET="$(pwd)/trace" \ + GIT_TEST_FULL_NAME_HASH=0 \ + git -C client \ fetch "file://$(pwd)/server" main && # Verify that protocol version 2 was used. diff --git a/t/t6020-bundle-misc.sh b/t/t6020-bundle-misc.sh index 34b5cd62c201d9..553a20d10e98ce 100755 --- a/t/t6020-bundle-misc.sh +++ b/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 the --full-name-hash option is used, then one fewer + # delta base is found and this counts a different number + # of objects after performing --fix-thin. + GIT_TEST_FULL_NAME_HASH=0 \ + git bundle create since.bdl \ --since "Thu Apr 7 15:27:00 2005 -0700" \ --all &&