rocksdb/table/plain/plain_table_builder.h
Zhichao Cao 4369f2c7bb Checksum for each SST file and stores in MANIFEST (#6216)
Summary:
In the current code base, RocksDB generate the checksum for each block and verify the checksum at usage. Current PR enable SST file checksum. After a SST file is generated by Flush or Compaction, RocksDB generate the SST file checksum and store the checksum value and checksum method name in the vs_info and MANIFEST as part for the FileMetadata.

Added the enable_sst_file_checksum to Options to enable or disable file checksum. Added sst_file_checksum to Options such that user can plugin their own SST file checksum calculate method via overriding the SstFileChecksum class. The checksum information inlcuding uint32_t checksum value and a checksum name (string).  A new tool is added to LDB such that user can dump out a list of file checksum information from MANIFEST. If user enables the file checksum but does not provide the sst_file_checksum instance, RocksDB will use the default crc32checksum implemented in table/sst_file_checksum_crc32c.h
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6216

Test Plan: Added the testing case in table_test and ldb_cmd_test to verify checksum is correct in different level. Pass make asan_check.

Differential Revision: D19171461

Pulled By: zhichao-cao

fbshipit-source-id: b2e53479eefc5bb0437189eaa1941670e5ba8b87
2020-02-10 15:52:52 -08:00

152 lines
5.2 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).
#pragma once
#ifndef ROCKSDB_LITE
#include <stdint.h>
#include <string>
#include <vector>
#include "db/version_edit.h"
#include "rocksdb/options.h"
#include "rocksdb/status.h"
#include "rocksdb/table.h"
#include "rocksdb/table_properties.h"
#include "table/plain/plain_table_bloom.h"
#include "table/plain/plain_table_index.h"
#include "table/plain/plain_table_key_coding.h"
#include "table/table_builder.h"
namespace rocksdb {
class BlockBuilder;
class BlockHandle;
class WritableFile;
class TableBuilder;
// The builder class of PlainTable. For description of PlainTable format
// See comments of class PlainTableFactory, where instances of
// PlainTableReader are created.
class PlainTableBuilder: public TableBuilder {
public:
// Create a builder that will store the contents of the table it is
// building in *file. Does not close the file. It is up to the
// caller to close the file after calling Finish(). The output file
// will be part of level specified by 'level'. A value of -1 means
// that the caller does not know which level the output file will reside.
PlainTableBuilder(
const ImmutableCFOptions& ioptions, const MutableCFOptions& moptions,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t column_family_id, WritableFileWriter* file,
uint32_t user_key_size, EncodingType encoding_type,
size_t index_sparseness, uint32_t bloom_bits_per_key,
const std::string& column_family_name, uint32_t num_probes = 6,
size_t huge_page_tlb_size = 0, double hash_table_ratio = 0,
bool store_index_in_file = false);
// No copying allowed
PlainTableBuilder(const PlainTableBuilder&) = delete;
void operator=(const PlainTableBuilder&) = delete;
// REQUIRES: Either Finish() or Abandon() has been called.
~PlainTableBuilder();
// Add key,value to the table being constructed.
// REQUIRES: key is after any previously added key according to comparator.
// REQUIRES: Finish(), Abandon() have not been called
void Add(const Slice& key, const Slice& value) override;
// Return non-ok iff some error has been detected.
Status status() const override;
// Finish building the table. Stops using the file passed to the
// constructor after this function returns.
// REQUIRES: Finish(), Abandon() have not been called
Status Finish() override;
// Indicate that the contents of this builder should be abandoned. Stops
// using the file passed to the constructor after this function returns.
// If the caller is not going to call Finish(), it must call Abandon()
// before destroying this builder.
// REQUIRES: Finish(), Abandon() have not been called
void Abandon() override;
// Number of calls to Add() so far.
uint64_t NumEntries() const override;
// Size of the file generated so far. If invoked after a successful
// Finish() call, returns the size of the final generated file.
uint64_t FileSize() const override;
TableProperties GetTableProperties() const override { return properties_; }
bool SaveIndexInFile() const { return store_index_in_file_; }
// Get file checksum
const std::string& GetFileChecksum() const override { return file_checksum_; }
// Get file checksum function name
const char* GetFileChecksumFuncName() const override;
private:
Arena arena_;
const ImmutableCFOptions& ioptions_;
const MutableCFOptions& moptions_;
std::vector<std::unique_ptr<IntTblPropCollector>>
table_properties_collectors_;
BloomBlockBuilder bloom_block_;
std::unique_ptr<PlainTableIndexBuilder> index_builder_;
WritableFileWriter* file_;
uint64_t offset_ = 0;
uint32_t bloom_bits_per_key_;
size_t huge_page_tlb_size_;
Status status_;
TableProperties properties_;
PlainTableKeyEncoder encoder_;
bool store_index_in_file_;
std::vector<uint32_t> keys_or_prefixes_hashes_;
bool closed_ = false; // Either Finish() or Abandon() has been called.
const SliceTransform* prefix_extractor_;
// Store file checksum. If checksum is disabled, its value is "0".
std::string file_checksum_ = kUnknownFileChecksum;
Slice GetPrefix(const Slice& target) const {
assert(target.size() >= 8); // target is internal key
return GetPrefixFromUserKey(GetUserKey(target));
}
Slice GetPrefix(const ParsedInternalKey& target) const {
return GetPrefixFromUserKey(target.user_key);
}
Slice GetUserKey(const Slice& key) const {
return Slice(key.data(), key.size() - 8);
}
Slice GetPrefixFromUserKey(const Slice& user_key) const {
if (!IsTotalOrderMode()) {
return prefix_extractor_->Transform(user_key);
} else {
// Use empty slice as prefix if prefix_extractor is not set.
// In that case,
// it falls back to pure binary search and
// total iterator seek is supported.
return Slice();
}
}
bool IsTotalOrderMode() const { return (prefix_extractor_ == nullptr); }
};
} // namespace rocksdb
#endif // ROCKSDB_LITE