Skip to content

[Improvement](pipeline) Use hash shuffle for 1-phase Agg/Analytic ope… #34122

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
yiguolei merged 1 commit into from
Apr 26, 2024
Merged

[Improvement](pipeline) Use hash shuffle for 1-phase Agg/Analytic ope… #34122

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
11 changes: 7 additions & 4 deletions be/src/pipeline/exec/aggregation_sink_operator.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -616,7 +616,7 @@ void AggSinkLocalState::_init_hash_method(const vectorized::VExprContextSPtrs& p
}

AggSinkOperatorX::AggSinkOperatorX(ObjectPool* pool, int operator_id, const TPlanNode& tnode,
const DescriptorTbl& descs)
const DescriptorTbl& descs, bool require_bucket_distribution)
: DataSinkOperatorX<AggSinkLocalState>(operator_id, tnode.node_id),
_intermediate_tuple_id(tnode.agg_node.intermediate_tuple_id),
_intermediate_tuple_desc(nullptr),
Expand All @@ -629,9 +629,12 @@ AggSinkOperatorX::AggSinkOperatorX(ObjectPool* pool, int operator_id, const TPla
_limit(tnode.limit),
_have_conjuncts((tnode.__isset.vconjunct && !tnode.vconjunct.nodes.empty()) ||
(tnode.__isset.conjuncts && !tnode.conjuncts.empty())),
_partition_exprs(tnode.__isset.distribute_expr_lists ? tnode.distribute_expr_lists[0]
: std::vector<TExpr> {}),
_is_colocate(tnode.agg_node.__isset.is_colocate && tnode.agg_node.is_colocate),
_partition_exprs(require_bucket_distribution ? (tnode.__isset.distribute_expr_lists
? tnode.distribute_expr_lists[0]
: std::vector<TExpr> {})
: tnode.agg_node.grouping_exprs),
_is_colocate(tnode.agg_node.__isset.is_colocate && tnode.agg_node.is_colocate &&
require_bucket_distribution),
_agg_fn_output_row_descriptor(descs, tnode.row_tuples, tnode.nullable_tuples) {}

Status AggSinkOperatorX::init(const TPlanNode& tnode, RuntimeState* state) {
Expand Down
2 changes: 1 addition & 1 deletion be/src/pipeline/exec/aggregation_sink_operator.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ class AggSinkLocalState : public PipelineXSinkLocalState<AggSharedState> {
class AggSinkOperatorX final : public DataSinkOperatorX<AggSinkLocalState> {
public:
AggSinkOperatorX(ObjectPool* pool, int operator_id, const TPlanNode& tnode,
const DescriptorTbl& descs);
const DescriptorTbl& descs, bool require_bucket_distribution);
~AggSinkOperatorX() override = default;
Status init(const TDataSink& tsink) override {
return Status::InternalError("{} should not init with TPlanNode",
Expand Down
6 changes: 4 additions & 2 deletions be/src/pipeline/exec/partitioned_aggregation_sink_operator.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,9 +122,11 @@ void PartitionedAggSinkLocalState::update_profile(RuntimeProfile* child_profile)

PartitionedAggSinkOperatorX::PartitionedAggSinkOperatorX(ObjectPool* pool, int operator_id,
const TPlanNode& tnode,
const DescriptorTbl& descs)
const DescriptorTbl& descs,
bool require_bucket_distribution)
: DataSinkOperatorX<PartitionedAggSinkLocalState>(operator_id, tnode.node_id) {
_agg_sink_operator = std::make_unique<AggSinkOperatorX>(pool, operator_id, tnode, descs);
_agg_sink_operator = std::make_unique<AggSinkOperatorX>(pool, operator_id, tnode, descs,
require_bucket_distribution);
}

Status PartitionedAggSinkOperatorX::init(const TPlanNode& tnode, RuntimeState* state) {
Expand Down
2 changes: 1 addition & 1 deletion be/src/pipeline/exec/partitioned_aggregation_sink_operator.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,7 +308,7 @@ class PartitionedAggSinkLocalState
class PartitionedAggSinkOperatorX : public DataSinkOperatorX<PartitionedAggSinkLocalState> {
public:
PartitionedAggSinkOperatorX(ObjectPool* pool, int operator_id, const TPlanNode& tnode,
const DescriptorTbl& descs);
const DescriptorTbl& descs, bool require_bucket_distribution);
~PartitionedAggSinkOperatorX() override = default;
Status init(const TDataSink& tsink) override {
return Status::InternalError("{} should not init with TPlanNode",
Expand Down
10 changes: 8 additions & 2 deletions be/src/pipeline/pipeline_x/pipeline_x_fragment_context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1024,14 +1024,16 @@ Status PipelineXFragmentContext::_create_operator(ObjectPool* pool, const TPlanN
DataSinkOperatorXPtr sink;
if (_runtime_state->enable_agg_spill() && !tnode.agg_node.grouping_exprs.empty()) {
sink.reset(new PartitionedAggSinkOperatorX(pool, next_sink_operator_id(), tnode,
descs));
descs, _require_bucket_distribution));
} else {
sink.reset(new AggSinkOperatorX(pool, next_sink_operator_id(), tnode, descs));
sink.reset(new AggSinkOperatorX(pool, next_sink_operator_id(), tnode, descs,
_require_bucket_distribution));
}
sink->set_dests_id({op->operator_id()});
RETURN_IF_ERROR(cur_pipe->set_sink(sink));
RETURN_IF_ERROR(cur_pipe->sink_x()->init(tnode, _runtime_state.get()));
}
_require_bucket_distribution = true;
break;
}
case TPlanNodeType::HASH_JOIN_NODE: {
Expand Down Expand Up @@ -1096,6 +1098,7 @@ Status PipelineXFragmentContext::_create_operator(ObjectPool* pool, const TPlanN
_pipeline_parent_map.push(op->node_id(), cur_pipe);
_pipeline_parent_map.push(op->node_id(), build_side_pipe);
}
_require_bucket_distribution = true;
break;
}
case TPlanNodeType::CROSS_JOIN_NODE: {
Expand Down Expand Up @@ -1201,6 +1204,7 @@ Status PipelineXFragmentContext::_create_operator(ObjectPool* pool, const TPlanN
sink->set_dests_id({op->operator_id()});
RETURN_IF_ERROR(cur_pipe->set_sink(sink));
RETURN_IF_ERROR(cur_pipe->sink_x()->init(tnode, _runtime_state.get()));
_require_bucket_distribution = true;
break;
}
case TPlanNodeType::INTERSECT_NODE: {
Expand Down Expand Up @@ -1258,6 +1262,8 @@ Status PipelineXFragmentContext::_create_operator(ObjectPool* pool, const TPlanN
print_plan_node_type(tnode.node_type));
}

_require_bucket_distribution = true;

return Status::OK();
}
// NOLINTEND(readability-function-cognitive-complexity)
Expand Down
2 changes: 2 additions & 0 deletions be/src/pipeline/pipeline_x/pipeline_x_fragment_context.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,6 +239,8 @@ class PipelineXFragmentContext : public PipelineFragmentContext {

// Total instance num running on all BEs
int _total_instances = -1;

bool _require_bucket_distribution = false;
};

} // namespace pipeline
Expand Down