ClickHouse/src/Storages/MergeTree/MergeTreeDataPartCompact.h
Azat Khuzhin 22e44ced8a Add column modification time into system.parts_columns
This can be useful to obtain at least some time for the part after
mutations, since mutations will change the modification time of all
parts.

Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2023-07-03 13:34:05 +02:00

80 lines
3.1 KiB
C++

#pragma once
#include <Storages/MergeTree/IMergeTreeDataPart.h>
namespace DB
{
/** In compact format all columns are stored in one file (`data.bin`).
* Data is split in granules and columns are serialized sequentially in one granule.
* Granules are written one by one in data file.
* Marks are also stored in single file (`data.mrk3`).
* In compact format one mark is an array of marks for every column and a number of rows in granule.
* Format of other data part files is not changed.
* It's considered to store only small parts in compact format (up to 10M).
* NOTE: Compact parts aren't supported for tables with non-adaptive granularity.
* NOTE: In compact part compressed and uncompressed size of single column is unknown.
*/
class MergeTreeDataPartCompact : public IMergeTreeDataPart
{
public:
static constexpr auto DATA_FILE_NAME = "data";
static constexpr auto DATA_FILE_NAME_WITH_EXTENSION = "data.bin";
MergeTreeDataPartCompact(
const MergeTreeData & storage_,
const String & name_,
const MergeTreePartInfo & info_,
const MutableDataPartStoragePtr & data_part_storage_,
const IMergeTreeDataPart * parent_part_ = nullptr);
MergeTreeReaderPtr getReader(
const NamesAndTypesList & columns,
const StorageMetadataPtr & metadata_snapshot,
const MarkRanges & mark_ranges,
UncompressedCache * uncompressed_cache,
MarkCache * mark_cache,
const AlterConversionsPtr & alter_conversions,
const MergeTreeReaderSettings & reader_settings_,
const ValueSizeMap & avg_value_size_hints,
const ReadBufferFromFileBase::ProfileCallback & profile_callback) const override;
MergeTreeWriterPtr getWriter(
const NamesAndTypesList & columns_list,
const StorageMetadataPtr & metadata_snapshot,
const std::vector<MergeTreeIndexPtr> & indices_to_recalc,
const CompressionCodecPtr & default_codec_,
const MergeTreeWriterSettings & writer_settings,
const MergeTreeIndexGranularity & computed_index_granularity) override;
bool isStoredOnDisk() const override { return true; }
bool isStoredOnRemoteDisk() const override;
bool isStoredOnRemoteDiskWithZeroCopySupport() const override;
bool hasColumnFiles(const NameAndTypePair & column) const override;
std::optional<time_t> getColumnModificationTime(const String & column_name) const override;
String getFileNameForColumn(const NameAndTypePair & /* column */) const override { return DATA_FILE_NAME; }
~MergeTreeDataPartCompact() override;
protected:
static void loadIndexGranularityImpl(
MergeTreeIndexGranularity & index_granularity_, const MergeTreeIndexGranularityInfo & index_granularity_info_,
size_t columns_count, const IDataPartStorage & data_part_storage_);
private:
void checkConsistency(bool require_part_metadata) const override;
/// Loads marks index granularity into memory
void loadIndexGranularity() override;
/// Compact parts doesn't support per column size, only total size
void calculateEachColumnSizes(ColumnSizeByName & each_columns_size, ColumnSize & total_size) const override;
};
}