Skip to content

Fixed a problem with cardinality estimation for PK joins #907

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
merged 1 commit into from
Jan 10, 2024
Merged

Fixed a problem with cardinality estimation for PK joins #907

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
2 changes: 1 addition & 1 deletion ydb/core/kqp/opt/kqp_statistics_transformer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ void InferStatisticsForKqpTable(const TExprNode::TPtr& input, TTypeAnnotationCon
const auto& tableData = kqpCtx.Tables->ExistingTable(kqpCtx.Cluster, path.Value());
double nRows = tableData.Metadata->RecordsCount;
int nAttrs = tableData.Metadata->Columns.size();
YQL_CLOG(TRACE, CoreDq) << "Infer statistics for table: " << path.Value() << ", nrows: " << nRows << ", nattrs: " << nAttrs;
YQL_CLOG(TRACE, CoreDq) << "Infer statistics for table: " << path.Value() << ", nrows: " << nRows << ", nattrs: " << nAttrs << ", nKeyColumns: " << tableData.Metadata->KeyColumnNames.size();

auto outputStats = TOptimizerStatistics(EStatisticsType::BaseTable, nRows, nAttrs, 0.0, tableData.Metadata->KeyColumnNames);
typeCtx->SetStats(input.Get(), std::make_shared<TOptimizerStatistics>(outputStats));
Expand Down
5 changes: 4 additions & 1 deletion ydb/library/yql/core/yql_cost_function.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,9 +41,11 @@ TOptimizerStatistics NYql::ComputeJoinStats(const TOptimizerStatistics& leftStat

double newCard;
EStatisticsType outputType;
TVector<TString> joinedTableKeys;

if (IsPKJoin(rightStats,rightJoinKeys)) {
newCard = std::max(leftStats.Nrows,rightStats.Nrows);
joinedTableKeys = leftStats.KeyColumns;
if (leftStats.Type == EStatisticsType::BaseTable){
outputType = EStatisticsType::FilteredFactTable;
} else {
Expand All @@ -52,6 +54,7 @@ TOptimizerStatistics NYql::ComputeJoinStats(const TOptimizerStatistics& leftStat
}
else if (IsPKJoin(leftStats,leftJoinKeys)) {
newCard = std::max(leftStats.Nrows,rightStats.Nrows);
joinedTableKeys = rightStats.KeyColumns;
if (rightStats.Type == EStatisticsType::BaseTable){
outputType = EStatisticsType::FilteredFactTable;
} else {
Expand All @@ -69,7 +72,7 @@ TOptimizerStatistics NYql::ComputeJoinStats(const TOptimizerStatistics& leftStat
+ newCard
+ leftStats.Cost + rightStats.Cost;

return TOptimizerStatistics(outputType, newCard, newNCols, cost);
return TOptimizerStatistics(outputType, newCard, newNCols, cost, joinedTableKeys);
}

TOptimizerStatistics NYql::ComputeJoinStats(const TOptimizerStatistics& leftStats, const TOptimizerStatistics& rightStats,
Expand Down
4 changes: 2 additions & 2 deletions ydb/library/yql/dq/opt/dq_opt_stat.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,7 +194,7 @@ void InferStatisticsForFlatMap(const TExprNode::TPtr& input, TTypeAnnotationCont

double selectivity = ComputePredicateSelectivity(flatmap.Lambda().Body(), inputStats);

auto outputStats = TOptimizerStatistics(inputStats->Type, inputStats->Nrows * selectivity, inputStats->Ncols, inputStats->Cost );
auto outputStats = TOptimizerStatistics(inputStats->Type, inputStats->Nrows * selectivity, inputStats->Ncols, inputStats->Cost, inputStats->KeyColumns );

typeCtx->SetStats(input.Get(), std::make_shared<TOptimizerStatistics>(outputStats) );
}
Expand Down Expand Up @@ -235,7 +235,7 @@ void InferStatisticsForFilter(const TExprNode::TPtr& input, TTypeAnnotationConte

double selectivity = ComputePredicateSelectivity(filterBody, inputStats);

auto outputStats = TOptimizerStatistics(inputStats->Type, inputStats->Nrows * selectivity, inputStats->Ncols, inputStats->Cost);
auto outputStats = TOptimizerStatistics(inputStats->Type, inputStats->Nrows * selectivity, inputStats->Ncols, inputStats->Cost, inputStats->KeyColumns);

typeCtx->SetStats(input.Get(), std::make_shared<TOptimizerStatistics>(outputStats) );
}
Expand Down