rocksdb/table/plain/plain_table_builder.h
Peter Dillinger 04db764831 Embed original file number in SST table properties (#8686)
Summary:
I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add
file numbers to external SST files (so that more can share db session
ids for better uniqueness properties), because of forward compatibility.
We would have a version of RocksDB that assumes session IDs are unique
on external SST files and therefore can't really break that invariant in
future files.

This change adds a table property for "orig_file_number" which is
populated by normal SST files and also external SST files generated by
SstFileWriter. SstFileWriter now keeps a db_session_id for life of the
object and increments its own file numbers for embedding in table
properties. (They are arguably "fake" file numbers because these numbers
and not embedded in the file name.)

While updating block_based_table_builder, I removed several unnecessary
fields from Rep, because following the pattern would have created
another unnecessary field.

This change also updates block_based_table_reader to use this new
property when available, which means that for newer SST files, we can
determine the stable/original <db_session_id,file_number> unique
identifier using just the file contents, not the file name. (It's a bit
complicated; detailed comments in block_based_table_reader.)

Also added DB host id to properties listing by sst_dump, which could be
useful in debugging.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686

Test Plan: majorly overhauled StableCacheKeys test for this change

Reviewed By: zhichao-cao

Differential Revision: D30457742

Pulled By: pdillinger

fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-20 20:40:48 -07:00

153 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_NAMESPACE {
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 ImmutableOptions& ioptions, const MutableCFOptions& moptions,
const IntTblPropCollectorFactories* 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, const std::string& db_id = "",
const std::string& db_session_id = "", uint64_t file_number = 0);
// 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 { return status_; }
// Return non-ok iff some error happens during IO.
IOStatus io_status() const override { return io_status_; }
// 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
std::string GetFileChecksum() const override;
// Get file checksum function name
const char* GetFileChecksumFuncName() const override;
private:
Arena arena_;
const ImmutableOptions& 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_;
IOStatus io_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_;
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_NAMESPACE
#endif // ROCKSDB_LITE