thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 16:42:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix more tests

Browse Source
This commit is contained in:
Amos Bird 2021-05-04 20:40:34 +08:00
parent ba17acbd63
commit 718c284437
No known key found for this signature in database
GPG Key ID: 80D430DCBECFEDB4
9 changed files with 101 additions and 85 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/Interpreters/ActionsDAG.cpp
View File

@ -440,7 +440,7 @@ void ActionsDAG::removeUnusedActions(bool allow_remove_inputs)
}
NameSet ActionsDAG::foldActionsByProjection(
const NameSet & required_columns, const Block & projection_block_for_keys, const String & predicate_column_name)
const NameSet & required_columns, const Block & projection_block_for_keys, const String & predicate_column_name, bool add_missing_keys)
{
std::unordered_set<const Node *> visited_nodes;
std::unordered_set<std::string_view> visited_index_names;
@ -457,6 +457,8 @@ NameSet ActionsDAG::foldActionsByProjection(
}
}
if (add_missing_keys)
{
for (const auto & column : required_columns)
{
if (visited_index_names.find(column) == visited_index_names.end())
@ -464,8 +466,8 @@ NameSet ActionsDAG::foldActionsByProjection(
if (const ColumnWithTypeAndName * column_with_type_name = projection_block_for_keys.findByName(column))
{
const auto * node = &addInput(*column_with_type_name);
index.push_back(node);
visited_nodes.insert(node);
index.push_back(node);
visited_index_names.insert(column);
}
else
@ -475,6 +477,7 @@ NameSet ActionsDAG::foldActionsByProjection(
}
}
}
}
while (!stack.empty())
{

5
src/Interpreters/ActionsDAG.h
View File

@ -169,7 +169,10 @@ public:
void removeUnusedActions(const NameSet & required_names);
NameSet foldActionsByProjection(
const NameSet & required_columns, const Block & projection_block_for_keys, const String & predicate_column_name = {});
const NameSet & required_columns,
const Block & projection_block_for_keys,
const String & predicate_column_name = {},
bool add_missing_keys = true);
void reorderAggregationKeysForProjection(const std::unordered_map<std::string_view, size_t> & key_names_pos_map);
void addAggregatesViaProjection(const Block & aggregates);

2
src/Interpreters/ExpressionAnalyzer.cpp
View File

@ -1638,7 +1638,7 @@ void ExpressionAnalysisResult::finalize(const ExpressionActionsChain & chain, si
if (hasWhere())
{
auto where_column_name = query.where()->getColumnName();
where_column_name = query.where()->getColumnName();
remove_where_filter = chain.steps.at(where_step_num)->required_output.find(where_column_name)->second;
}
}

1
src/Interpreters/ExpressionAnalyzer.h
View File

@ -209,6 +209,7 @@ struct ExpressionAnalysisResult
bool has_order_by = false;
bool has_window = false;
String where_column_name;
bool remove_where_filter = false;
bool optimize_read_in_order = false;
bool optimize_aggregation_in_order = false;

103
src/Interpreters/InterpreterSelectQuery.cpp
View File

@ -397,7 +397,6 @@ InterpreterSelectQuery::InterpreterSelectQuery(
view = nullptr;
}
// TODO Check if we can have prewhere work for projections, also need to allow it in TreeRewriter
if (try_move_to_prewhere && storage && query.where() && !query.prewhere())
{
/// PREWHERE optimization: transfer some condition from WHERE to PREWHERE if enabled and viable
@ -422,6 +421,13 @@ InterpreterSelectQuery::InterpreterSelectQuery(
}
}
if (query.prewhere() && query.where())
{
/// Filter block in WHERE instead to get better performance
query.setExpression(
ASTSelectQuery::Expression::WHERE, makeASTFunction("and", query.prewhere()->clone(), query.where()->clone()));
}
query_analyzer = std::make_unique<SelectQueryExpressionAnalyzer>(
query_ptr, syntax_analyzer_result, context, metadata_snapshot,
NameSet(required_result_column_names.begin(), required_result_column_names.end()),
@ -505,12 +511,6 @@ InterpreterSelectQuery::InterpreterSelectQuery(
query.setExpression(ASTSelectQuery::Expression::WHERE, std::make_shared<ASTLiteral>(0u));
need_analyze_again = true;
}
if (query.prewhere() && query.where())
{
/// Filter block in WHERE instead to get better performance
query.setExpression(ASTSelectQuery::Expression::WHERE, makeASTFunction("and", query.prewhere()->clone(), query.where()->clone()));
need_analyze_again = true;
}
if (need_analyze_again)
{
@ -931,33 +931,6 @@ void InterpreterSelectQuery::executeImpl(QueryPlan & query_plan, const BlockInpu
query_info.projection->aggregate_final = aggregate_final;
}
if (expressions.filter_info)
{
if (!expressions.prewhere_info)
{
const bool does_storage_support_prewhere = !input && !input_pipe && storage && storage->supportsPrewhere();
if (does_storage_support_prewhere && settings.optimize_move_to_prewhere)
{
/// Execute row level filter in prewhere as a part of "move to prewhere" optimization.
expressions.prewhere_info = std::make_shared<PrewhereDAGInfo>(
std::move(expressions.filter_info->actions),
std::move(expressions.filter_info->column_name));
expressions.prewhere_info->prewhere_actions->projectInput(false);
expressions.prewhere_info->remove_prewhere_column = expressions.filter_info->do_remove_column;
expressions.prewhere_info->need_filter = true;
expressions.filter_info = nullptr;
}
}
else
{
/// Add row level security actions to prewhere.
expressions.prewhere_info->row_level_filter_actions = std::move(expressions.filter_info->actions);
expressions.prewhere_info->row_level_column_name = std::move(expressions.filter_info->column_name);
expressions.prewhere_info->row_level_filter_actions->projectInput(false);
expressions.filter_info = nullptr;
}
}
if (options.only_analyze)
{
auto read_nothing = std::make_unique<ReadNothingStep>(source_header);
@ -1543,34 +1516,34 @@ void InterpreterSelectQuery::addEmptySourceToQueryPlan(
}
}
auto read_from_pipe = std::make_unique<ReadFromPreparedSource>(std::move(pipe));
read_from_pipe->setStepDescription("Read from NullSource");
query_plan.addStep(std::move(read_from_pipe));
if (query_info.projection)
{
if (query_info.projection->before_where)
{
auto expression = std::make_shared<ExpressionActions>(
query_info.projection->before_where, ExpressionActionsSettings::fromContext(context_));
pipe.addSimpleTransform(
[&expression](const Block & header) { return std::make_shared<ExpressionTransform>(header, expression); });
auto where_step = std::make_unique<FilterStep>(
query_plan.getCurrentDataStream(),
query_info.projection->before_where,
query_info.projection->where_column_name,
query_info.projection->remove_where_filter);
where_step->setStepDescription("WHERE");
query_plan.addStep(std::move(where_step));
}
if (query_info.projection->desc->type == ProjectionDescription::Type::Aggregate)
{
if (query_info.projection->before_aggregation)
{
auto expression = std::make_shared<ExpressionActions>(
query_info.projection->before_aggregation, ExpressionActionsSettings::fromContext(context_));
pipe.addSimpleTransform(
[&expression](const Block & header) { return std::make_shared<ExpressionTransform>(header, expression); });
}
}
auto expression_before_aggregation
= std::make_unique<ExpressionStep>(query_plan.getCurrentDataStream(), query_info.projection->before_aggregation);
expression_before_aggregation->setStepDescription("Before GROUP BY");
query_plan.addStep(std::move(expression_before_aggregation));
}
auto read_from_pipe = std::make_unique<ReadFromPreparedSource>(std::move(pipe));
read_from_pipe->setStepDescription("Read from NullSource");
query_plan.addStep(std::move(read_from_pipe));
if (query_info.projection && query_info.projection->desc->type == ProjectionDescription::Type::Aggregate)
{
executeMergeAggregatedImpl(
query_plan,
query_info.projection->aggregate_overflow_row,
@ -1581,9 +1554,39 @@ void InterpreterSelectQuery::addEmptySourceToQueryPlan(
query_info.projection->aggregate_descriptions);
}
}
}
void InterpreterSelectQuery::addPrewhereAliasActions()
{
const Settings & settings = context->getSettingsRef();
auto & expressions = analysis_result;
if (expressions.filter_info)
{
if (!expressions.prewhere_info)
{
const bool does_storage_support_prewhere = !input && !input_pipe && storage && storage->supportsPrewhere();
if (does_storage_support_prewhere && settings.optimize_move_to_prewhere)
{
/// Execute row level filter in prewhere as a part of "move to prewhere" optimization.
expressions.prewhere_info = std::make_shared<PrewhereDAGInfo>(
std::move(expressions.filter_info->actions),
std::move(expressions.filter_info->column_name));
expressions.prewhere_info->prewhere_actions->projectInput(false);
expressions.prewhere_info->remove_prewhere_column = expressions.filter_info->do_remove_column;
expressions.prewhere_info->need_filter = true;
expressions.filter_info = nullptr;
}
}
else
{
/// Add row level security actions to prewhere.
expressions.prewhere_info->row_level_filter_actions = std::move(expressions.filter_info->actions);
expressions.prewhere_info->row_level_column_name = std::move(expressions.filter_info->column_name);
expressions.prewhere_info->row_level_filter_actions->projectInput(false);
expressions.filter_info = nullptr;
}
}
auto & prewhere_info = analysis_result.prewhere_info;
auto & columns_to_remove_after_prewhere = analysis_result.columns_to_remove_after_prewhere;

26
src/Storages/MergeTree/MergeTreeData.cpp
View File

@ -3923,14 +3923,16 @@ bool MergeTreeData::getQueryProcessingStageWithAggregateProjection(
{
if (analysis_result.before_where)
{
candidate.where_column_name = analysis_result.where_column_name;
candidate.remove_where_filter = analysis_result.remove_where_filter;
candidate.before_where = analysis_result.before_where->clone();
std::cerr << fmt::format("before_where_actions = \n{}", candidate.before_where->dumpDAG()) << std::endl;
required_columns = candidate.before_where->foldActionsByProjection(
required_columns,
projection.sample_block_for_keys,
query_ptr->as<const ASTSelectQuery &>().where()->getColumnName());
candidate.where_column_name);
std::cerr << fmt::format("before_where_actions = \n{}", candidate.before_where->dumpDAG()) << std::endl;
std::cerr << fmt::format("where_required_columns = \n{}", fmt::join(required_columns, ", ")) << std::endl;
if (required_columns.empty())
return false;
@ -3947,13 +3949,16 @@ bool MergeTreeData::getQueryProcessingStageWithAggregateProjection(
candidate.prewhere_info->need_filter = prewhere_info->need_filter;
auto prewhere_actions = prewhere_info->prewhere_actions->clone();
// If there is a before_where action, prewhere_action only requires columns to evaluate the prewhere expression.
// Else it should provide all columns to later actions.
NameSet prewhere_required_columns = analysis_result.before_where ? NameSet{} : required_columns;
auto prewhere_required_columns = required_columns;
// required_columns should not contain columns generated by prewhere
for (const auto & column : prewhere_actions->getResultColumns())
required_columns.erase(column.name);
std::cerr << fmt::format("prewhere_actions = \n{}", prewhere_actions->dumpDAG()) << std::endl;
// Prewhere_action should not add missing keys.
prewhere_required_columns = prewhere_actions->foldActionsByProjection(
prewhere_required_columns, projection.sample_block_for_keys, prewhere_info->prewhere_column_name);
prewhere_required_columns, projection.sample_block_for_keys, prewhere_info->prewhere_column_name, false);
std::cerr << fmt::format("prewhere_actions = \n{}", prewhere_actions->dumpDAG()) << std::endl;
std::cerr << fmt::format("prewhere_required_columns = \n{}", fmt::join(prewhere_required_columns, ", ")) << std::endl;
if (prewhere_required_columns.empty())
return false;
candidate.prewhere_info->prewhere_actions = std::make_shared<ExpressionActions>(prewhere_actions, actions_settings);
@ -3962,21 +3967,23 @@ bool MergeTreeData::getQueryProcessingStageWithAggregateProjection(
{
auto row_level_filter_actions = prewhere_info->row_level_filter_actions->clone();
prewhere_required_columns = row_level_filter_actions->foldActionsByProjection(
prewhere_required_columns, projection.sample_block_for_keys, prewhere_info->row_level_column_name);
prewhere_required_columns, projection.sample_block_for_keys, prewhere_info->row_level_column_name, false);
std::cerr << fmt::format("row_level_filter_required_columns = \n{}", fmt::join(prewhere_required_columns, ", "))
<< std::endl;
if (prewhere_required_columns.empty())
return false;
candidate.prewhere_info->row_level_filter
= std::make_shared<ExpressionActions>(row_level_filter_actions, actions_settings);
}
// TODO wait for alias analysis to be moved into expression analyzer
if (prewhere_info->alias_actions)
{
auto alias_actions = prewhere_info->alias_actions->clone();
std::cerr << fmt::format("alias_actions = \n{}", alias_actions->dumpDAG()) << std::endl;
prewhere_required_columns
= alias_actions->foldActionsByProjection(prewhere_required_columns, projection.sample_block_for_keys);
= alias_actions->foldActionsByProjection(prewhere_required_columns, projection.sample_block_for_keys, {}, false);
std::cerr << fmt::format("alias_actions = \n{}", alias_actions->dumpDAG()) << std::endl;
std::cerr << fmt::format("alias_required_columns = \n{}", fmt::join(prewhere_required_columns, ", ")) << std::endl;
if (prewhere_required_columns.empty())
return false;
candidate.prewhere_info->alias_actions = std::make_shared<ExpressionActions>(alias_actions, actions_settings);
@ -4033,8 +4040,7 @@ bool MergeTreeData::getQueryProcessingStageWithAggregateProjection(
std::cerr << fmt::format("before_aggregation = \n{}", candidate.before_aggregation->dumpDAG()) << std::endl;
auto required_columns = candidate.before_aggregation->foldActionsByProjection(keys, projection.sample_block_for_keys);
std::cerr << fmt::format("before_aggregation = \n{}", candidate.before_aggregation->dumpDAG()) << std::endl;
std::cerr << fmt::format("keys = {}", fmt::join(required_columns, ", ")) << std::endl;
std::cerr << fmt::format("aggregate_required_columns = \n{}", fmt::join(required_columns, ", ")) << std::endl;
if (required_columns.empty())
continue;

2
src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp
View File

@ -201,7 +201,7 @@ QueryPlanPtr MergeTreeDataSelectExecutor::read(
auto where_step = std::make_unique<FilterStep>(
plan->getCurrentDataStream(),
query_info.projection->before_where,
given_select.where()->getColumnName(),
query_info.projection->where_column_name,
query_info.projection->remove_where_filter);
where_step->setStepDescription("WHERE");

1
src/Storages/SelectQueryInfo.h
View File

@ -126,6 +126,7 @@ struct ProjectionCandidate
const ProjectionDescription * desc;
PrewhereInfoPtr prewhere_info;
ActionsDAGPtr before_where;
String where_column_name;
bool remove_where_filter = false;
ActionsDAGPtr before_aggregation;
Names required_columns;

1
tests/queries/0_stateless/01710_projections.reference
View File

@ -1,5 +1,4 @@
2020-10-24 00:00:00 0 -0.2906208323366036
2020-10-24 00:00:00 0 -5.350401006920782
2020-10-24 00:00:00 1000 -0.3856164567802157 1.2352100180287104
2020-10-24 00:00:00 1.3619605237696326 0.16794469697335793 0.7637956767025532 0.8899329799574005 0.6227685185389797 0.30795997278638165 0.7637956767025532
2020-10-24 00:00:00 19 -1.9455094931672063 0.7759802460082872 0.6 0