thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-23 08:02:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Optimize Count() Cond.

Browse Source 
Follow up https://github.com/yandex/ClickHouse/pull/6028
This commit is contained in:
Amos Bird 2019-08-05 22:15:15 +08:00
parent 7388454eb2
commit a7db425592
1 changed files with 23 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
dbms/src/Interpreters/ExpressionAnalyzer.cpp
View File

@ -982,6 +982,18 @@ void ExpressionAnalyzer::getAggregateInfo(Names & key_names, AggregateDescriptio
aggregates = aggregate_descriptions;
}
struct ColumnExt
{
size_t compressed_size;
size_t type_size;
size_t uncompressed_size;
String name;
bool operator<(const ColumnExt & that) const
{
return std::tie(compressed_size, type_size, uncompressed_size) < std::tie(that.compressed_size, that.type_size, that.uncompressed_size);
}
};
void ExpressionAnalyzer::collectUsedColumns()
{
/** Calculate which columns are required to execute the expression.
@ -1040,23 +1052,23 @@ void ExpressionAnalyzer::collectUsedColumns()
/// You need to read at least one column to find the number of rows.
if (select_query && required.empty())
{
/// We will find a column with minimum compressed size. Because it is the column that is cheapest to read.
size_t min_data_compressed = 0;
String min_column_name;
/// We will find a column with minimum <compressed_size, type_size, uncompressed_size>.
/// Because it is the column that is cheapest to read.
std::vector<ColumnExt> columns;
if (storage)
{
auto column_sizes = storage->getColumnSizes();
for (auto & [column_name, column_size] : column_sizes)
for (auto & source_column : source_columns)
{
if (min_data_compressed == 0 || min_data_compressed > column_size.data_compressed)
{
min_data_compressed = column_size.data_compressed;
min_column_name = column_name;
}
auto c = column_sizes.find(source_column.name);
if (c == column_sizes.end())
continue;
size_t type_size = source_column.type->haveMaximumSizeOfValue() ? source_column.type->getMaximumSizeOfValueInMemory() : 100;
columns.emplace_back(ColumnExt{c->second.data_compressed, type_size, c->second.data_uncompressed, source_column.name});
}
}
if (min_data_compressed > 0)
required.insert(min_column_name);
if (columns.size())
required.insert(std::min_element(columns.begin(), columns.end())->name);
else
/// If we have no information about columns sizes, choose a column of minimum size of its data type.
required.insert(ExpressionActions::getSmallestColumn(source_columns));