Files
bitcoin/src/dbwrapper.h
merge-script c8459b6bdc Merge bitcoin/bitcoin#35568: txospenderindex: disable bloom filters to optimize disk usage
6d0ea4cf5b doc: add release notes (Andrew Toth)
a2b1c86903 txospenderindex: disable bloom filters to optimize disk usage (Andrew Toth)

Pull request description:

  LevelDB bloom filters are only consulted on `Get` point reads. This can be verified in https://github.com/bitcoin/bitcoin/blob/master/src/leveldb/table/table.cc#L224-L228. `InternalGet` is the only place that consults the filter, and it is only reached via a `Get` or `Exists` point read. The filters are never consulted for iterator seeks with an iterator created via `NewIterator`.
  txospenderindex only reads via iterator seeks, so building them is wasted effort and space.

  For a db as large as txospenderindex, this results in measurable performance and disk usage.
  On master, a full sync took 4h37m, and the resulting db was 85.0 GiB.
  On this branch, a full sync took 3h57m, and the resulting db was 80.9 GiB.
  So this is a sync speedup of 39 minutes (1.17x), and a disk space reduction of 4.2 GiB.

ACKs for top commit:
  l0rinc:
    ACK 6d0ea4cf5b
  sedited:
    Re-ACK 6d0ea4cf5b
  fjahr:
    Code review ACK 6d0ea4cf5b

Tree-SHA512: fb88b9f9a16ff31562d388e3fd9fd9590c7864dbe6093cd9430ecbce9cdc3f2a8d3fc612aade743d26ad4c6eca1e5dc9b3f1ca28d75caea1209e5c784895405d
2026-07-12 12:39:54 +02:00

295 lines
8.1 KiB
C++

// Copyright (c) 2012-present The Bitcoin Core developers
// Distributed under the MIT software license, see the accompanying
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
#ifndef BITCOIN_DBWRAPPER_H
#define BITCOIN_DBWRAPPER_H
#include <attributes.h>
#include <serialize.h>
#include <span.h>
#include <streams.h>
#include <util/byte_units.h>
#include <util/check.h>
#include <util/fs.h>
#include <util/obfuscation.h>
#include <cstddef>
#include <cstdint>
#include <exception>
#include <memory>
#include <optional>
#include <span>
#include <stdexcept>
#include <string>
namespace leveldb {
class Env;
} // namespace leveldb
static const size_t DBWRAPPER_PREALLOC_KEY_SIZE = 64;
static const size_t DBWRAPPER_PREALLOC_VALUE_SIZE = 1024;
static const size_t DBWRAPPER_MAX_FILE_SIZE{32_MiB};
//! User-controlled performance and debug options.
struct DBOptions {
//! Compact database on startup.
bool force_compact = false;
};
//! Application-specific storage settings.
struct DBParams {
//! Location in the filesystem where leveldb data will be stored.
fs::path path;
//! Configures various leveldb cache settings.
uint64_t cache_bytes;
//! If true, use leveldb's memory environment.
bool memory_only = false;
//! If true, remove all existing data.
bool wipe_data = false;
//! If true, store data obfuscated via simple XOR. If false, XOR with a
//! zero'd byte array.
bool obfuscate = false;
//! If true, build a LevelDB bloom filter to accelerate point lookups.
bool bloom_filter = true;
//! Passed-through options.
DBOptions options{};
//! If non-null, use this as the leveldb::Env instead of the default.
//! Caller retains ownership.
leveldb::Env* testing_env = nullptr;
//! Maximum LevelDB SST file size. Larger values reduce the frequency
//! of compactions but increase their duration.
size_t max_file_size = DBWRAPPER_MAX_FILE_SIZE;
};
class dbwrapper_error : public std::runtime_error
{
public:
explicit dbwrapper_error(const std::string& msg) : std::runtime_error(msg) {}
};
class CDBWrapper;
/** These should be considered an implementation detail of the specific database.
*/
namespace dbwrapper_private {
/** Work around circular dependency, as well as for testing in dbwrapper_tests.
* Database obfuscation should be considered an implementation detail of the
* specific database.
*/
const Obfuscation& GetObfuscation(const CDBWrapper&);
}; // namespace dbwrapper_private
bool DestroyDB(const std::string& path_str);
/** Batch of changes queued to be written to a CDBWrapper */
class CDBBatch
{
friend class CDBWrapper;
private:
const CDBWrapper &parent;
struct WriteBatchImpl;
const std::unique_ptr<WriteBatchImpl> m_impl_batch;
DataStream m_key_scratch{};
DataStream m_value_scratch{};
void WriteImpl(std::span<const std::byte> key, DataStream& value);
void EraseImpl(std::span<const std::byte> key);
public:
/**
* @param[in] _parent CDBWrapper that this batch is to be submitted to
*/
explicit CDBBatch(const CDBWrapper& _parent);
~CDBBatch();
void Clear();
template <typename K, typename V>
void Write(const K& key, const V& value)
{
ScopedDataStreamUsage scoped_key{m_key_scratch}, scoped_value{m_value_scratch};
m_key_scratch << key;
m_value_scratch << value;
WriteImpl(m_key_scratch, m_value_scratch);
}
template <typename K>
void Erase(const K& key)
{
ScopedDataStreamUsage scoped_key{m_key_scratch};
m_key_scratch << key;
EraseImpl(m_key_scratch);
}
size_t ApproximateSize() const;
};
class CDBIterator
{
public:
struct IteratorImpl;
private:
const CDBWrapper &parent;
const std::unique_ptr<IteratorImpl> m_impl_iter;
DataStream m_scratch{};
void SeekImpl(std::span<const std::byte> key);
std::span<const std::byte> GetKeyImpl() const;
std::span<const std::byte> GetValueImpl() const;
public:
/**
* @param[in] _parent Parent CDBWrapper instance.
* @param[in] _piter The original leveldb iterator.
*/
CDBIterator(const CDBWrapper& _parent, std::unique_ptr<IteratorImpl> _piter);
~CDBIterator();
bool Valid() const;
void SeekToFirst();
template<typename K> void Seek(const K& key) {
ScopedDataStreamUsage scoped_scratch{m_scratch};
m_scratch << key;
SeekImpl(m_scratch);
}
void Next();
template<typename K> bool GetKey(K& key) {
try {
SpanReader ssKey{GetKeyImpl()};
ssKey >> key;
} catch (const std::exception&) {
return false;
}
return true;
}
template<typename V> bool GetValue(V& value) {
try {
ScopedDataStreamUsage scoped_scratch{m_scratch};
m_scratch.write(GetValueImpl());
dbwrapper_private::GetObfuscation(parent)(m_scratch);
m_scratch >> value;
} catch (const std::exception&) {
return false;
}
return true;
}
};
struct LevelDBContext;
class CDBWrapper
{
friend const Obfuscation& dbwrapper_private::GetObfuscation(const CDBWrapper&);
private:
//! holds all leveldb-specific fields of this class
std::unique_ptr<LevelDBContext> m_db_context;
//! the name of this database
std::string m_name;
//! optional XOR-obfuscation of the database
Obfuscation m_obfuscation;
//! obfuscation key storage key, null-prefixed to avoid collisions
inline static const std::string OBFUSCATION_KEY{"\000obfuscate_key", 14}; // explicit size to avoid truncation at leading \0
std::optional<std::string> ReadImpl(std::span<const std::byte> key) const;
bool ExistsImpl(std::span<const std::byte> key) const;
size_t EstimateSizeImpl(std::span<const std::byte> key1, std::span<const std::byte> key2) const;
auto& DBContext() const LIFETIMEBOUND { return *Assert(m_db_context); }
public:
CDBWrapper(const DBParams& params);
~CDBWrapper();
CDBWrapper(const CDBWrapper&) = delete;
CDBWrapper& operator=(const CDBWrapper&) = delete;
template <typename K, typename V>
bool Read(const K& key, V& value) const
{
DataStream ssKey{};
ssKey.reserve(DBWRAPPER_PREALLOC_KEY_SIZE);
ssKey << key;
std::optional<std::string> strValue{ReadImpl(ssKey)};
if (!strValue) {
return false;
}
try {
std::span ssValue{MakeWritableByteSpan(*strValue)};
m_obfuscation(ssValue);
SpanReader{ssValue} >> value;
} catch (const std::exception&) {
return false;
}
return true;
}
template <typename K, typename V>
void Write(const K& key, const V& value, bool fSync = false)
{
CDBBatch batch(*this);
batch.Write(key, value);
WriteBatch(batch, fSync);
}
template <typename K>
bool Exists(const K& key) const
{
DataStream ssKey{};
ssKey.reserve(DBWRAPPER_PREALLOC_KEY_SIZE);
ssKey << key;
return ExistsImpl(ssKey);
}
template <typename K>
void Erase(const K& key, bool fSync = false)
{
CDBBatch batch(*this);
batch.Erase(key);
WriteBatch(batch, fSync);
}
void WriteBatch(CDBBatch& batch, bool fSync = false);
//! Perform a blocking full compaction of the underlying LevelDB.
void CompactFull();
//! Return a LevelDB property value, if available.
std::optional<std::string> GetProperty(const std::string& property) const;
// Get an estimate of LevelDB memory usage (in bytes).
size_t DynamicMemoryUsage() const;
CDBIterator* NewIterator();
/**
* Return true if the database managed by this class contains no entries.
*/
bool IsEmpty();
template<typename K>
size_t EstimateSize(const K& key_begin, const K& key_end) const
{
DataStream ssKey1{}, ssKey2{};
ssKey1.reserve(DBWRAPPER_PREALLOC_KEY_SIZE);
ssKey2.reserve(DBWRAPPER_PREALLOC_KEY_SIZE);
ssKey1 << key_begin;
ssKey2 << key_end;
return EstimateSizeImpl(ssKey1, ssKey2);
}
};
#endif // BITCOIN_DBWRAPPER_H