rocksdb/table/block_based/index_reader_common.h
Yu Zhang 9f7877f246 Add support to strip / pad timestamp when creating / reading a block based table (#11495)
Summary:
Add support to strip timestamp in block based table builder and pad timestamp in block based table reader.

On the write path, use the per column family option `AdvancedColumnFamilyOptions.persist_user_defined_timestamps` to indicate whether user-defined timestamps should be stripped for all block based tables created for the column family.

On the read path, added a per table `TableReadOption.user_defined_timestamps_persisted` to flag whether the user keys in the table contains user defined timestamps.

This patch is mostly passing the related flags down to the block building/parsing level with the exception of handling the `first_internal_key` in `IndexValue`, which is included in the `IndexBuilder` level.  The value part of range deletion entries should have a similar handling, I haven't decided where to best fit this piece of logic, I will do it in a follow up.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11495

Test Plan:
Existing test `BlockBasedTableReaderTest` is parameterized to run with:
1) different UDT test modes: kNone, kNormal, kStripUserDefinedTimestamp
2) all four index types, when index type is `kTwoLevelIndexSearch`, also enables partitioned filters
3) parallel vs non-parallel compression
4) enable/disable compression dictionary.

Also added tests for API `BlockBasedTableReader::NewIterator`.

`PartitionedFilterBlockTest` is parameterized to run with different UDT test modes:kNone, kNormal, kStripUserDefinedTimestamp.

```
make all check
./block_based_table_reader_test
./partitioned_filter_block_test
```

Reviewed By: ltamasi

Differential Revision: D46344577

Pulled By: jowlyzhang

fbshipit-source-id: 93ac8542b19319d1298712b8bed908c8831ba675
2023-06-01 11:10:03 -07:00

92 lines
3.3 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#pragma once
#include "table/block_based/block_based_table_reader.h"
#include "table/block_based/reader_common.h"
namespace ROCKSDB_NAMESPACE {
// Encapsulates common functionality for the various index reader
// implementations. Provides access to the index block regardless of whether
// it is owned by the reader or stored in the cache, or whether it is pinned
// in the cache or not.
class BlockBasedTable::IndexReaderCommon : public BlockBasedTable::IndexReader {
public:
IndexReaderCommon(const BlockBasedTable* t,
CachableEntry<Block>&& index_block)
: table_(t), index_block_(std::move(index_block)) {
assert(table_ != nullptr);
}
protected:
static Status ReadIndexBlock(const BlockBasedTable* table,
FilePrefetchBuffer* prefetch_buffer,
const ReadOptions& read_options, bool use_cache,
GetContext* get_context,
BlockCacheLookupContext* lookup_context,
CachableEntry<Block>* index_block);
const BlockBasedTable* table() const { return table_; }
const InternalKeyComparator* internal_comparator() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return &table_->get_rep()->internal_comparator;
}
bool index_has_first_key() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return table_->get_rep()->index_has_first_key;
}
bool index_key_includes_seq() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return table_->get_rep()->index_key_includes_seq;
}
bool index_value_is_full() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return table_->get_rep()->index_value_is_full;
}
bool cache_index_blocks() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return table_->get_rep()->table_options.cache_index_and_filter_blocks;
}
bool user_defined_timestamps_persisted() const {
assert(table_ != nullptr);
assert(table_->get_rep() != nullptr);
return table_->get_rep()->user_defined_timestamps_persisted;
}
Status GetOrReadIndexBlock(bool no_io, GetContext* get_context,
BlockCacheLookupContext* lookup_context,
CachableEntry<Block>* index_block,
const ReadOptions& read_options) const;
size_t ApproximateIndexBlockMemoryUsage() const {
assert(!index_block_.GetOwnValue() || index_block_.GetValue() != nullptr);
return index_block_.GetOwnValue()
? index_block_.GetValue()->ApproximateMemoryUsage()
: 0;
}
private:
const BlockBasedTable* table_;
CachableEntry<Block> index_block_;
};
} // namespace ROCKSDB_NAMESPACE