1d6e8d64ee
This change implements support for Zstd-based compression in LevelDB. Building up from the Snappy compression (which has been supported since inception), this change adds Zstd as an alternate compression algorithm. We are implementing this to provide alternative options for users who might have different performance and efficiency requirements. For instance, the Zstandard website (https://facebook.github.io/zstd/) claims that the Zstd algorithm can achieve around 30% higher compression ratios than Snappy, with relatively smaller (~10%) slowdowns in de/compression speeds. Benchmarking results: $ blaze-bin/third_party/leveldb/db_bench LevelDB: version 1.23 Date: Thu Feb 2 18:50:06 2023 CPU: 56 * Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz CPUCache: 35840 KB Keys: 16 bytes each Values: 100 bytes each (50 bytes after compression) Entries: 1000000 RawSize: 110.6 MB (estimated) FileSize: 62.9 MB (estimated) ------------------------------------------------ fillseq : 2.613 micros/op; 42.3 MB/s fillsync : 3924.432 micros/op; 0.0 MB/s (1000 ops) fillrandom : 3.609 micros/op; 30.7 MB/s overwrite : 4.508 micros/op; 24.5 MB/s readrandom : 6.136 micros/op; (864322 of 1000000 found) readrandom : 5.446 micros/op; (864083 of 1000000 found) readseq : 0.180 micros/op; 613.3 MB/s readreverse : 0.321 micros/op; 344.7 MB/s compact : 827043.000 micros/op; readrandom : 4.603 micros/op; (864105 of 1000000 found) readseq : 0.169 micros/op; 656.3 MB/s readreverse : 0.315 micros/op; 350.8 MB/s fill100K : 854.009 micros/op; 111.7 MB/s (1000 ops) crc32c : 1.227 micros/op; 3184.0 MB/s (4K per op) snappycomp : 3.610 micros/op; 1081.9 MB/s (output: 55.2%) snappyuncomp : 0.691 micros/op; 5656.3 MB/s zstdcomp : 15.731 micros/op; 248.3 MB/s (output: 44.1%) zstduncomp : 4.218 micros/op; 926.2 MB/s PiperOrigin-RevId: 509957778
219 lines
5.3 KiB
C++
219 lines
5.3 KiB
C++
// Copyright (c) 2018 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.
|
|
|
|
#ifndef STORAGE_LEVELDB_PORT_PORT_STDCXX_H_
|
|
#define STORAGE_LEVELDB_PORT_PORT_STDCXX_H_
|
|
|
|
// port/port_config.h availability is automatically detected via __has_include
|
|
// in newer compilers. If LEVELDB_HAS_PORT_CONFIG_H is defined, it overrides the
|
|
// configuration detection.
|
|
#if defined(LEVELDB_HAS_PORT_CONFIG_H)
|
|
|
|
#if LEVELDB_HAS_PORT_CONFIG_H
|
|
#include "port/port_config.h"
|
|
#endif // LEVELDB_HAS_PORT_CONFIG_H
|
|
|
|
#elif defined(__has_include)
|
|
|
|
#if __has_include("port/port_config.h")
|
|
#include "port/port_config.h"
|
|
#endif // __has_include("port/port_config.h")
|
|
|
|
#endif // defined(LEVELDB_HAS_PORT_CONFIG_H)
|
|
|
|
#if HAVE_CRC32C
|
|
#include <crc32c/crc32c.h>
|
|
#endif // HAVE_CRC32C
|
|
#if HAVE_SNAPPY
|
|
#include <snappy.h>
|
|
#endif // HAVE_SNAPPY
|
|
#if HAVE_ZSTD
|
|
#include <zstd.h>
|
|
#endif // HAVE_ZSTD
|
|
|
|
#include <cassert>
|
|
#include <condition_variable> // NOLINT
|
|
#include <cstddef>
|
|
#include <cstdint>
|
|
#include <mutex> // NOLINT
|
|
#include <string>
|
|
|
|
#include "port/thread_annotations.h"
|
|
|
|
namespace leveldb {
|
|
namespace port {
|
|
|
|
class CondVar;
|
|
|
|
// Thinly wraps std::mutex.
|
|
class LOCKABLE Mutex {
|
|
public:
|
|
Mutex() = default;
|
|
~Mutex() = default;
|
|
|
|
Mutex(const Mutex&) = delete;
|
|
Mutex& operator=(const Mutex&) = delete;
|
|
|
|
void Lock() EXCLUSIVE_LOCK_FUNCTION() { mu_.lock(); }
|
|
void Unlock() UNLOCK_FUNCTION() { mu_.unlock(); }
|
|
void AssertHeld() ASSERT_EXCLUSIVE_LOCK() {}
|
|
|
|
private:
|
|
friend class CondVar;
|
|
std::mutex mu_;
|
|
};
|
|
|
|
// Thinly wraps std::condition_variable.
|
|
class CondVar {
|
|
public:
|
|
explicit CondVar(Mutex* mu) : mu_(mu) { assert(mu != nullptr); }
|
|
~CondVar() = default;
|
|
|
|
CondVar(const CondVar&) = delete;
|
|
CondVar& operator=(const CondVar&) = delete;
|
|
|
|
void Wait() {
|
|
std::unique_lock<std::mutex> lock(mu_->mu_, std::adopt_lock);
|
|
cv_.wait(lock);
|
|
lock.release();
|
|
}
|
|
void Signal() { cv_.notify_one(); }
|
|
void SignalAll() { cv_.notify_all(); }
|
|
|
|
private:
|
|
std::condition_variable cv_;
|
|
Mutex* const mu_;
|
|
};
|
|
|
|
inline bool Snappy_Compress(const char* input, size_t length,
|
|
std::string* output) {
|
|
#if HAVE_SNAPPY
|
|
output->resize(snappy::MaxCompressedLength(length));
|
|
size_t outlen;
|
|
snappy::RawCompress(input, length, &(*output)[0], &outlen);
|
|
output->resize(outlen);
|
|
return true;
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)output;
|
|
#endif // HAVE_SNAPPY
|
|
|
|
return false;
|
|
}
|
|
|
|
inline bool Snappy_GetUncompressedLength(const char* input, size_t length,
|
|
size_t* result) {
|
|
#if HAVE_SNAPPY
|
|
return snappy::GetUncompressedLength(input, length, result);
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)result;
|
|
return false;
|
|
#endif // HAVE_SNAPPY
|
|
}
|
|
|
|
inline bool Snappy_Uncompress(const char* input, size_t length, char* output) {
|
|
#if HAVE_SNAPPY
|
|
return snappy::RawUncompress(input, length, output);
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)output;
|
|
return false;
|
|
#endif // HAVE_SNAPPY
|
|
}
|
|
|
|
inline bool Zstd_Compress(const char* input, size_t length,
|
|
std::string* output) {
|
|
#if HAVE_ZSTD
|
|
// Get the MaxCompressedLength.
|
|
size_t outlen = ZSTD_compressBound(length);
|
|
if (ZSTD_isError(outlen)) {
|
|
return false;
|
|
}
|
|
output->resize(outlen);
|
|
ZSTD_CCtx* ctx = ZSTD_createCCtx();
|
|
outlen = ZSTD_compress2(ctx, &(*output)[0], output->size(), input, length);
|
|
ZSTD_freeCCtx(ctx);
|
|
if (ZSTD_isError(outlen)) {
|
|
return false;
|
|
}
|
|
output->resize(outlen);
|
|
return true;
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)output;
|
|
return false;
|
|
#endif // HAVE_ZSTD
|
|
}
|
|
|
|
inline bool Zstd_GetUncompressedLength(const char* input, size_t length,
|
|
size_t* result) {
|
|
#if HAVE_ZSTD
|
|
size_t size = ZSTD_getFrameContentSize(input, length);
|
|
if (size == 0) return false;
|
|
*result = size;
|
|
return true;
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)result;
|
|
return false;
|
|
#endif // HAVE_ZSTD
|
|
}
|
|
|
|
inline bool Zstd_Uncompress(const char* input, size_t length, char* output) {
|
|
#if HAVE_ZSTD
|
|
size_t outlen;
|
|
if (!Zstd_GetUncompressedLength(input, length, &outlen)) {
|
|
return false;
|
|
}
|
|
ZSTD_DCtx* ctx = ZSTD_createDCtx();
|
|
outlen = ZSTD_decompressDCtx(ctx, output, outlen, input, length);
|
|
ZSTD_freeDCtx(ctx);
|
|
if (ZSTD_isError(outlen)) {
|
|
return false;
|
|
}
|
|
return true;
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)input;
|
|
(void)length;
|
|
(void)output;
|
|
return false;
|
|
#endif // HAVE_ZSTD
|
|
}
|
|
|
|
inline bool GetHeapProfile(void (*func)(void*, const char*, int), void* arg) {
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)func;
|
|
(void)arg;
|
|
return false;
|
|
}
|
|
|
|
inline uint32_t AcceleratedCRC32C(uint32_t crc, const char* buf, size_t size) {
|
|
#if HAVE_CRC32C
|
|
return ::crc32c::Extend(crc, reinterpret_cast<const uint8_t*>(buf), size);
|
|
#else
|
|
// Silence compiler warnings about unused arguments.
|
|
(void)crc;
|
|
(void)buf;
|
|
(void)size;
|
|
return 0;
|
|
#endif // HAVE_CRC32C
|
|
}
|
|
|
|
} // namespace port
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_PORT_PORT_STDCXX_H_
|