Skip to content

[chore](be) Reject broadcast joins that finalize build side #63445

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
BiteTheDDDDt merged 1 commit into from
May 21, 2026
Merged

[chore](be) Reject broadcast joins that finalize build side #63445

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions be/src/exec/operator/hashjoin_build_sink.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -774,6 +774,12 @@ Status HashJoinBuildSinkOperatorX::init(const TPlanNode& tnode, RuntimeState* st

Status HashJoinBuildSinkOperatorX::prepare(RuntimeState* state) {
RETURN_IF_ERROR(JoinBuildSinkOperatorX<HashJoinBuildSinkLocalState>::prepare(state));
if (_is_broadcast_join && (_match_all_build || _is_right_semi_anti)) {
return Status::NotSupported(
"Broadcast hash join does not support {} because build-side rows must be "
"finalized exactly once",
to_string(_join_op));
}
_use_shared_hash_table =
_is_broadcast_join && state->enable_share_hash_table_for_broadcast_join();
auto init_keep_column_flags = [&](auto& tuple_descs, auto& output_slot_flags) {
Expand Down
28 changes: 28 additions & 0 deletions be/test/exec/operator/hashjoin_build_sink_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,34 @@ TEST_F(HashJoinBuildSinkTest, Init) {
run_test_block(test_block);
}

TEST_F(HashJoinBuildSinkTest, RejectBroadcastJoinThatRequiresBuildSideFinalize) {
for (const auto join_op : {TJoinOp::RIGHT_OUTER_JOIN, TJoinOp::FULL_OUTER_JOIN,
TJoinOp::RIGHT_SEMI_JOIN, TJoinOp::RIGHT_ANTI_JOIN}) {
auto tnode =
_helper.create_test_plan_node(join_op, {TPrimitiveType::INT}, {false}, {false});
tnode.hash_join_node.__set_is_broadcast_join(true);

auto [probe_operator, sink_operator] = _helper.create_operators(tnode);
ASSERT_TRUE(probe_operator);
ASSERT_TRUE(sink_operator);

auto runtime_state = std::make_unique<MockRuntimeState>();
runtime_state->_query_ctx = _helper.query_ctx.get();
runtime_state->_query_id = _helper.query_ctx->query_id();
runtime_state->resize_op_id_to_local_state(-100);
runtime_state->set_max_operator_id(-100);
runtime_state->set_desc_tbl(_helper.desc_tbl);

auto st = sink_operator->init(tnode, runtime_state.get());
ASSERT_TRUE(st.ok()) << "init failed: " << st.to_string();

st = sink_operator->prepare(runtime_state.get());
ASSERT_TRUE(st.is<ErrorCode::NOT_IMPLEMENTED_ERROR>())
<< "broadcast " << to_string(join_op)
<< " should be rejected, got: " << st.to_string();
}
}

TEST_F(HashJoinBuildSinkTest, Sink) {
auto test_block = [&](TJoinOp::type op_type, const std::vector<TPrimitiveType::type>& key_types,
const std::vector<bool>& left_nullables,
Expand Down
Loading