mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 13:41:46 +00:00
04db764831
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
138 lines
4.8 KiB
C++
138 lines
4.8 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 <limits>
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include "db/version_edit.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/table.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "table/table_builder.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class CuckooTableBuilder: public TableBuilder {
|
|
public:
|
|
CuckooTableBuilder(
|
|
WritableFileWriter* file, double max_hash_table_ratio,
|
|
uint32_t max_num_hash_func, uint32_t max_search_depth,
|
|
const Comparator* user_comparator, uint32_t cuckoo_block_size,
|
|
bool use_module_hash, bool identity_as_first_hash,
|
|
uint64_t (*get_slice_hash)(const Slice&, uint32_t, uint64_t),
|
|
uint32_t column_family_id, const std::string& column_family_name,
|
|
const std::string& db_id = "", const std::string& db_session_id = "",
|
|
uint64_t file_number = 0);
|
|
// No copying allowed
|
|
CuckooTableBuilder(const CuckooTableBuilder&) = delete;
|
|
void operator=(const CuckooTableBuilder&) = delete;
|
|
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
~CuckooTableBuilder() {}
|
|
|
|
// 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_; }
|
|
|
|
// Get file checksum
|
|
std::string GetFileChecksum() const override;
|
|
|
|
// Get file checksum function name
|
|
const char* GetFileChecksumFuncName() const override;
|
|
|
|
private:
|
|
struct CuckooBucket {
|
|
CuckooBucket()
|
|
: vector_idx(kMaxVectorIdx), make_space_for_key_call_id(0) {}
|
|
uint32_t vector_idx;
|
|
// This number will not exceed kvs_.size() + max_num_hash_func_.
|
|
// We assume number of items is <= 2^32.
|
|
uint32_t make_space_for_key_call_id;
|
|
};
|
|
static const uint32_t kMaxVectorIdx = port::kMaxInt32;
|
|
|
|
bool MakeSpaceForKey(const autovector<uint64_t>& hash_vals,
|
|
const uint32_t call_id,
|
|
std::vector<CuckooBucket>* buckets, uint64_t* bucket_id);
|
|
Status MakeHashTable(std::vector<CuckooBucket>* buckets);
|
|
|
|
inline bool IsDeletedKey(uint64_t idx) const;
|
|
inline Slice GetKey(uint64_t idx) const;
|
|
inline Slice GetUserKey(uint64_t idx) const;
|
|
inline Slice GetValue(uint64_t idx) const;
|
|
|
|
uint32_t num_hash_func_;
|
|
WritableFileWriter* file_;
|
|
const double max_hash_table_ratio_;
|
|
const uint32_t max_num_hash_func_;
|
|
const uint32_t max_search_depth_;
|
|
const uint32_t cuckoo_block_size_;
|
|
uint64_t hash_table_size_;
|
|
bool is_last_level_file_;
|
|
bool has_seen_first_key_;
|
|
bool has_seen_first_value_;
|
|
uint64_t key_size_;
|
|
uint64_t value_size_;
|
|
// A list of fixed-size key-value pairs concatenating into a string.
|
|
// Use GetKey(), GetUserKey(), and GetValue() to retrieve a specific
|
|
// key / value given an index
|
|
std::string kvs_;
|
|
std::string deleted_keys_;
|
|
// Number of key-value pairs stored in kvs_ + number of deleted keys
|
|
uint64_t num_entries_;
|
|
// Number of keys that contain value (non-deletion op)
|
|
uint64_t num_values_;
|
|
Status status_;
|
|
IOStatus io_status_;
|
|
TableProperties properties_;
|
|
const Comparator* ucomp_;
|
|
bool use_module_hash_;
|
|
bool identity_as_first_hash_;
|
|
uint64_t (*get_slice_hash_)(const Slice& s, uint32_t index,
|
|
uint64_t max_num_buckets);
|
|
std::string largest_user_key_ = "";
|
|
std::string smallest_user_key_ = "";
|
|
|
|
bool closed_; // Either Finish() or Abandon() has been called.
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
#endif // ROCKSDB_LITE
|