ClickHouse/dbms/src/Interpreters/MergeJoin.cpp

392 lines
13 KiB
C++
Raw Normal View History

2019-09-09 19:43:37 +00:00
#include <Core/NamesAndTypes.h>
2019-09-13 16:17:37 +00:00
#include <Core/SortCursor.h>
#include <Columns/ColumnNullable.h>
2019-09-09 19:43:37 +00:00
#include <Interpreters/MergeJoin.h>
#include <Interpreters/AnalyzedJoin.h>
2019-09-12 18:06:25 +00:00
#include <Interpreters/sortBlock.h>
2019-09-09 19:43:37 +00:00
#include <DataStreams/materializeBlock.h>
2019-09-12 18:06:25 +00:00
#include <DataStreams/MergeSortingBlockInputStream.h>
2019-09-09 19:43:37 +00:00
namespace DB
{
2019-09-10 14:51:28 +00:00
namespace ErrorCodes
{
extern const int SET_SIZE_LIMIT_EXCEEDED;
2019-09-13 16:17:37 +00:00
extern const int NOT_IMPLEMENTED;
}
struct MergeJoinEqualRange
{
size_t left_start = 0;
size_t right_start = 0;
size_t left_length = 0;
size_t right_length = 0;
bool empty() const { return !left_length && !right_length; }
};
using Range = MergeJoinEqualRange;
class MergeJoinCursor
{
public:
MergeJoinCursor(const Block & block, const SortDescription & desc_)
: impl(SortCursorImpl(block, desc_))
{}
size_t position() const { return impl.pos; }
size_t end() const { return impl.rows; }
2019-09-13 16:17:37 +00:00
bool atEnd() const { return impl.pos >= impl.rows; }
void nextN(size_t num) { impl.pos += num; }
int compareAt(const MergeJoinCursor & rhs, size_t lhs_pos, size_t rhs_pos) const
{
int res = 0;
for (size_t i = 0; i < impl.sort_columns_size; ++i)
{
res = impl.sort_columns[i]->compareAt(lhs_pos, rhs_pos, *(rhs.impl.sort_columns[i]), 1);
if (res)
break;
}
return res;
}
bool sameNext(size_t lhs_pos) const
{
if (impl.isLast())
return false;
for (size_t i = 0; i < impl.sort_columns_size; ++i)
if (impl.sort_columns[i]->compareAt(lhs_pos, lhs_pos + 1, *(impl.sort_columns[i]), 1) != 0)
return false;
return true;
}
size_t getEqualLength()
{
if (atEnd())
return 0;
size_t pos = impl.pos;
for (; pos < impl.rows; ++pos)
if (!sameNext(pos))
break;
return pos - impl.pos + 1;
}
Range getNextEqualRange(MergeJoinCursor & rhs)
{
while (!atEnd() && !rhs.atEnd())
{
int cmp = compareAt(rhs, impl.pos, rhs.impl.pos);
if (cmp < 0)
impl.next();
if (cmp > 0)
rhs.impl.next();
if (!cmp)
{
Range range{impl.pos, rhs.impl.pos, 0, 0};
range.left_length = getEqualLength();
range.right_length = rhs.getEqualLength();
return range;
}
}
return Range{impl.pos, rhs.impl.pos, 0, 0};
}
private:
SortCursorImpl impl;
};
namespace
{
MutableColumns makeMutableColumns(const Block & block, size_t rows_to_reserve = 0)
{
MutableColumns columns;
columns.reserve(block.columns());
for (const auto & src_column : block)
{
columns.push_back(src_column.column->cloneEmpty());
columns.back()->reserve(rows_to_reserve);
}
return columns;
}
void makeSortAndMerge(const Names & keys, SortDescription & sort, SortDescription & merge)
2019-09-13 16:17:37 +00:00
{
NameSet unique_keys;
for (auto & key_name : keys)
{
merge.emplace_back(SortColumnDescription(key_name, 1, 1));
if (!unique_keys.count(key_name))
{
unique_keys.insert(key_name);
sort.emplace_back(SortColumnDescription(key_name, 1, 1));
}
}
2019-09-10 14:51:28 +00:00
}
void copyLeftRange(const Block & block, MutableColumns & columns, size_t start, size_t rows_to_add)
{
for (size_t i = 0; i < block.columns(); ++i)
{
const auto & src_column = block.getByPosition(i).column;
columns[i]->insertRangeFrom(*src_column, start, rows_to_add);
}
}
void copyRightRange(const Block & right_block, const Block & right_columns_to_add, MutableColumns & columns,
size_t row_position, size_t rows_to_add)
{
for (size_t i = 0; i < right_columns_to_add.columns(); ++i)
{
const auto & src_column = right_block.getByName(right_columns_to_add.getByPosition(i).name).column;
auto & dst_column = columns[i];
auto * dst_nullable = typeid_cast<ColumnNullable *>(dst_column.get());
if (dst_nullable && !isColumnNullable(*src_column))
dst_nullable->insertRangeFromNotNullable(*src_column, row_position, rows_to_add);
else
dst_column->insertRangeFrom(*src_column, row_position, rows_to_add);
}
}
void joinEqualsAnyLeft(const Block & right_block, const Block & right_columns_to_add, MutableColumns & right_columns, const Range & range)
{
copyRightRange(right_block, right_columns_to_add, right_columns, range.right_start, range.left_length);
}
void joinEquals(const Block & left_block, const Block & right_block, const Block & right_columns_to_add,
MutableColumns & left_columns, MutableColumns & right_columns, const Range & range, bool is_all)
{
size_t left_rows_to_add = range.left_length;
size_t right_rows_to_add = is_all ? range.right_length : 1;
size_t row_position = range.right_start;
for (size_t right_row = 0; right_row < right_rows_to_add; ++right_row, ++row_position)
{
copyLeftRange(left_block, left_columns, range.left_start, left_rows_to_add);
copyRightRange(right_block, right_columns_to_add, right_columns, row_position, left_rows_to_add);
}
}
void appendNulls(MutableColumns & right_columns, size_t rows_to_add)
{
for (auto & column : right_columns)
for (size_t i = 0; i < rows_to_add; ++i)
column->insertDefault();
}
void joinInequalsLeft(const Block & left_block, MutableColumns & left_columns, MutableColumns & right_columns,
size_t start, size_t end, bool copy_left)
{
if (end <= start)
return;
size_t rows_to_add = end - start;
if (copy_left)
copyLeftRange(left_block, left_columns, start, rows_to_add);
appendNulls(right_columns, rows_to_add);
}
}
2019-09-10 14:51:28 +00:00
MergeJoin::MergeJoin(std::shared_ptr<AnalyzedJoin> table_join_, const Block & right_sample_block)
2019-09-09 19:43:37 +00:00
: table_join(table_join_)
2019-09-18 12:24:35 +00:00
, nullable_right_side(table_join->forceNullableRight())
, is_all(table_join->strictness() == ASTTableJoin::Strictness::All)
, is_inner(isInner(table_join->kind()))
, is_left(isLeft(table_join->kind()))
2019-09-09 19:43:37 +00:00
{
if (!isLeft(table_join->kind()) && !isInner(table_join->kind()))
2019-09-13 16:17:37 +00:00
throw Exception("Partial merge supported for LEFT and INNER JOINs only", ErrorCodes::NOT_IMPLEMENTED);
JoinCommon::extractKeysForJoin(table_join->keyNamesRight(), right_sample_block, right_table_keys, right_columns_to_add);
2019-09-12 14:09:05 +00:00
const NameSet required_right_keys = table_join->requiredRightKeys();
2019-09-12 14:09:05 +00:00
for (const auto & column : right_table_keys)
if (required_right_keys.count(column.name))
right_columns_to_add.insert(ColumnWithTypeAndName{nullptr, column.type, column.name});
JoinCommon::removeLowCardinalityInplace(right_columns_to_add);
2019-09-12 14:09:05 +00:00
JoinCommon::createMissedColumns(right_columns_to_add);
if (nullable_right_side)
JoinCommon::convertColumnsToNullable(right_columns_to_add);
2019-09-12 18:06:25 +00:00
makeSortAndMerge(table_join->keyNamesLeft(), left_sort_description, left_merge_description);
makeSortAndMerge(table_join->keyNamesRight(), right_sort_description, right_merge_description);
2019-09-12 18:06:25 +00:00
}
void MergeJoin::setTotals(const Block & totals_block)
{
totals = totals_block;
mergeRightBlocks();
2019-09-09 19:43:37 +00:00
}
2019-09-13 16:17:37 +00:00
void MergeJoin::mergeRightBlocks()
{
const size_t max_merged_block_size = 128 * 1024 * 1024;
if (right_blocks.empty())
return;
2019-09-13 16:17:37 +00:00
Blocks unsorted_blocks;
unsorted_blocks.reserve(right_blocks.size());
for (const auto & block : right_blocks)
unsorted_blocks.push_back(block);
/// TODO: there should be no splitted keys by blocks for RIGHT|FULL JOIN
MergeSortingBlocksBlockInputStream stream(unsorted_blocks, right_sort_description, max_merged_block_size);
right_blocks.clear();
while (Block block = stream.read())
right_blocks.push_back(block);
}
2019-09-12 18:06:25 +00:00
bool MergeJoin::addJoinedBlock(const Block & src_block)
2019-09-09 19:43:37 +00:00
{
Block block = materializeBlock(src_block);
JoinCommon::removeLowCardinalityInplace(block);
2019-09-12 18:06:25 +00:00
sortBlock(block, right_sort_description);
2019-09-10 14:51:28 +00:00
std::unique_lock lock(rwlock);
right_blocks.push_back(block);
right_blocks_row_count += block.rows();
right_blocks_bytes += block.bytes();
return table_join->sizeLimits().check(right_blocks_row_count, right_blocks_bytes, "JOIN", ErrorCodes::SET_SIZE_LIMIT_EXCEEDED);
2019-09-09 19:43:37 +00:00
}
2019-09-10 14:51:28 +00:00
void MergeJoin::joinBlock(Block & block)
2019-09-09 19:43:37 +00:00
{
JoinCommon::checkTypesOfKeys(block, table_join->keyNamesLeft(), right_table_keys, table_join->keyNamesRight());
materializeBlockInplace(block);
JoinCommon::removeLowCardinalityInplace(block);
2019-09-12 18:06:25 +00:00
sortBlock(block, left_sort_description);
std::shared_lock lock(rwlock);
2019-09-11 18:03:21 +00:00
size_t rows_to_reserve = is_left ? block.rows() : 0;
MutableColumns left_columns = makeMutableColumns(block, (is_all ? rows_to_reserve : 0));
MutableColumns right_columns = makeMutableColumns(right_columns_to_add, rows_to_reserve);
MergeJoinCursor left_cursor(block, left_merge_description);
size_t left_key_tail = 0;
2019-09-13 16:17:37 +00:00
if (is_left)
{
2019-09-13 16:17:37 +00:00
for (auto it = right_blocks.begin(); it != right_blocks.end(); ++it)
{
if (left_cursor.atEnd())
break;
leftJoin(left_cursor, block, *it, left_columns, right_columns, left_key_tail);
2019-09-13 16:17:37 +00:00
}
2019-09-11 18:03:21 +00:00
left_cursor.nextN(left_key_tail);
joinInequalsLeft(block, left_columns, right_columns, left_cursor.position(), left_cursor.end(), is_all);
//left_cursor.nextN(left_cursor.end() - left_cursor.position());
changeLeftColumns(block, std::move(left_columns));
addRightColumns(block, std::move(right_columns));
2019-09-13 16:17:37 +00:00
}
else if (is_inner)
2019-09-13 16:17:37 +00:00
{
2019-09-13 17:23:32 +00:00
for (auto it = right_blocks.begin(); it != right_blocks.end(); ++it)
{
if (left_cursor.atEnd())
break;
innerJoin(left_cursor, block, *it, left_columns, right_columns, left_key_tail);
2019-09-13 17:23:32 +00:00
}
left_cursor.nextN(left_key_tail);
changeLeftColumns(block, std::move(left_columns));
addRightColumns(block, std::move(right_columns));
2019-09-13 16:17:37 +00:00
}
2019-09-10 14:51:28 +00:00
}
void MergeJoin::leftJoin(MergeJoinCursor & left_cursor, const Block & left_block, const Block & right_block,
MutableColumns & left_columns, MutableColumns & right_columns, size_t & left_key_tail)
2019-09-10 14:51:28 +00:00
{
2019-09-13 16:17:37 +00:00
MergeJoinCursor right_cursor(right_block, right_merge_description);
while (!left_cursor.atEnd() && !right_cursor.atEnd())
{
size_t left_position = left_cursor.position(); /// save inequal position
2019-09-13 16:17:37 +00:00
Range range = left_cursor.getNextEqualRange(right_cursor);
joinInequalsLeft(left_block, left_columns, right_columns, left_position, range.left_start, is_all);
2019-09-13 16:17:37 +00:00
if (range.empty())
break;
if (is_all)
joinEquals(left_block, right_block, right_columns_to_add, left_columns, right_columns, range, is_all);
else
joinEqualsAnyLeft(right_block, right_columns_to_add, right_columns, range);
2019-09-13 16:17:37 +00:00
right_cursor.nextN(range.right_length);
/// Do not run over last left keys for ALL JOIN (cause of possible duplicates in next right block)
if (is_all && right_cursor.atEnd())
{
left_key_tail = range.left_length;
break;
}
2019-09-13 16:17:37 +00:00
left_cursor.nextN(range.left_length);
}
2019-09-10 14:51:28 +00:00
}
2019-09-09 19:43:37 +00:00
2019-09-13 17:23:32 +00:00
void MergeJoin::innerJoin(MergeJoinCursor & left_cursor, const Block & left_block, const Block & right_block,
MutableColumns & left_columns, MutableColumns & right_columns, size_t & left_key_tail)
2019-09-13 17:23:32 +00:00
{
MergeJoinCursor right_cursor(right_block, right_merge_description);
while (!left_cursor.atEnd() && !right_cursor.atEnd())
{
Range range = left_cursor.getNextEqualRange(right_cursor);
if (range.empty())
break;
joinEquals(left_block, right_block, right_columns_to_add, left_columns, right_columns, range, is_all);
2019-09-13 17:23:32 +00:00
right_cursor.nextN(range.right_length);
/// Do not run over last left keys for ALL JOIN (cause of possible duplicates in next right block)
if (is_all && right_cursor.atEnd())
{
left_key_tail = range.left_length;
break;
}
2019-09-13 17:23:32 +00:00
left_cursor.nextN(range.left_length);
}
}
void MergeJoin::changeLeftColumns(Block & block, MutableColumns && columns)
2019-09-12 18:06:25 +00:00
{
if (is_left && !is_all)
return;
block.setColumns(std::move(columns));
2019-09-13 16:17:37 +00:00
}
2019-09-12 18:06:25 +00:00
void MergeJoin::addRightColumns(Block & block, MutableColumns && right_columns)
2019-09-13 16:17:37 +00:00
{
for (size_t i = 0; i < right_columns_to_add.columns(); ++i)
{
const auto & column = right_columns_to_add.getByPosition(i);
block.insert(ColumnWithTypeAndName{std::move(right_columns[i]), column.type, column.name});
}
}
2019-09-12 18:06:25 +00:00
2019-09-09 19:43:37 +00:00
}