rocksdb/util/coding_lean.h

134 lines
4.2 KiB
C
Raw Permalink Normal View History

// Copyright (c) Facebook, Inc. and its affiliates. 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).
// Encoding independent of machine byte order:
// * Fixed-length numbers are encoded with least-significant byte first
// (little endian, native order on Intel and others)
//
// More functions in coding.h
#pragma once
#include <cstdint>
#include <cstring>
#include "port/port.h" // for port::kLittleEndian
namespace ROCKSDB_NAMESPACE {
// Lower-level versions of Put... that write directly into a character buffer
// REQUIRES: dst has enough space for the value being written
// -- Implementation of the functions declared above
inline void EncodeFixed16(char* buf, uint16_t value) {
if (port::kLittleEndian) {
memcpy(buf, &value, sizeof(value));
} else {
buf[0] = value & 0xff;
buf[1] = (value >> 8) & 0xff;
}
}
inline void EncodeFixed32(char* buf, uint32_t value) {
if (port::kLittleEndian) {
memcpy(buf, &value, sizeof(value));
} else {
buf[0] = value & 0xff;
buf[1] = (value >> 8) & 0xff;
buf[2] = (value >> 16) & 0xff;
buf[3] = (value >> 24) & 0xff;
}
}
inline void EncodeFixed64(char* buf, uint64_t value) {
if (port::kLittleEndian) {
memcpy(buf, &value, sizeof(value));
} else {
buf[0] = value & 0xff;
buf[1] = (value >> 8) & 0xff;
buf[2] = (value >> 16) & 0xff;
buf[3] = (value >> 24) & 0xff;
buf[4] = (value >> 32) & 0xff;
buf[5] = (value >> 40) & 0xff;
buf[6] = (value >> 48) & 0xff;
buf[7] = (value >> 56) & 0xff;
}
}
// Lower-level versions of Get... that read directly from a character buffer
// without any bounds checking.
inline uint16_t DecodeFixed16(const char* ptr) {
if (port::kLittleEndian) {
// Load the raw bytes
uint16_t result;
memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load
return result;
} else {
return ((static_cast<uint16_t>(static_cast<unsigned char>(ptr[0]))) |
(static_cast<uint16_t>(static_cast<unsigned char>(ptr[1])) << 8));
}
}
inline uint32_t DecodeFixed32(const char* ptr) {
if (port::kLittleEndian) {
// Load the raw bytes
uint32_t result;
memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load
return result;
} else {
return ((static_cast<uint32_t>(static_cast<unsigned char>(ptr[0]))) |
(static_cast<uint32_t>(static_cast<unsigned char>(ptr[1])) << 8) |
(static_cast<uint32_t>(static_cast<unsigned char>(ptr[2])) << 16) |
(static_cast<uint32_t>(static_cast<unsigned char>(ptr[3])) << 24));
}
}
inline uint64_t DecodeFixed64(const char* ptr) {
if (port::kLittleEndian) {
// Load the raw bytes
uint64_t result;
memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load
return result;
} else {
uint64_t lo = DecodeFixed32(ptr);
uint64_t hi = DecodeFixed32(ptr + 4);
return (hi << 32) | lo;
}
}
Refine Ribbon configuration, improve testing, add Homogeneous (#7879) Summary: This change only affects non-schema-critical aspects of the production candidate Ribbon filter. Specifically, it refines choice of internal configuration parameters based on inputs. The changes are minor enough that the schema tests in bloom_test, some of which depend on this, are unaffected. There are also some minor optimizations and refactorings. This would be a schema change for "smash" Ribbon, to fix some known issues with small filters, but "smash" Ribbon is not accessible in public APIs. Unit test CompactnessAndBacktrackAndFpRate updated to test small and medium-large filters. Run with --thoroughness=100 or so for much better detection power (not appropriate for continuous regression testing). Homogenous Ribbon: This change adds internally a Ribbon filter variant we call Homogeneous Ribbon, in collaboration with Stefan Walzer. The expected "result" value for every key is zero, instead of computed from a hash. Entropy for queries not to be false positives comes from free variables ("overhead") in the solution structure, which are populated pseudorandomly. Construction is slightly faster for not tracking result values, and never fails. Instead, FP rate can jump up whenever and whereever entries are packed too tightly. For small structures, we can choose overhead to make this FP rate jump unlikely, as seen in updated unit test CompactnessAndBacktrackAndFpRate. Unlike standard Ribbon, Homogeneous Ribbon seems to scale to arbitrary number of keys when accepting an FP rate penalty for small pockets of high FP rate in the structure. For example, 64-bit ribbon with 8 solution columns and 10% allocated space overhead for slots seems to achieve about 10.5% space overhead vs. information-theoretic minimum based on its observed FP rate with expected pockets of degradation. (FP rate is close to 1/256.) If targeting a higher FP rate with fewer solution columns, Homogeneous Ribbon can be even more space efficient, because the penalty from degradation is relatively smaller. If targeting a lower FP rate, Homogeneous Ribbon is less space efficient, as more allocated overhead is needed to keep the FP rate impact of degradation relatively under control. The new OptimizeHomogAtScale tool in ribbon_test helps to find these optimal allocation overheads for different numbers of solution columns. And Ribbon widths, with 128-bit Ribbon apparently cutting space overheads in half vs. 64-bit. Other misc item specifics: * Ribbon APIs in util/ribbon_config.h now provide configuration data for not just 5% construction failure rate (95% success), but also 50% and 0.1%. * Note that the Ribbon structure does not exhibit "threshold" behavior as standard Xor filter does, so there is a roughly fixed space penalty to cut construction failure rate in half. Thus, there isn't really an "almost sure" setting. * Although we can extrapolate settings for large filters, we don't have a good formula for configuring smaller filters (< 2^17 slots or so), and efforts to summarize with a formula have failed. Thus, small data is hard-coded from updated FindOccupancy tool. * Enhances ApproximateNumEntries for public API Ribbon using more precise data (new API GetNumToAdd), thus a more accurate but not perfect reversal of CalculateSpace. (bloom_test updated to expect the greater precision) * Move EndianSwapValue from coding.h to coding_lean.h to keep Ribbon code easily transferable from RocksDB * Add some missing 'const' to member functions * Small optimization to 128-bit BitParity * Small refactoring of BandingStorage in ribbon_alg.h to support Homogeneous Ribbon * CompactnessAndBacktrackAndFpRate now has an "expand" test: on construction failure, a possible alternative to re-seeding hash functions is simply to increase the number of slots (allocated space overhead) and try again with essentially the same hash values. (Start locations will be different roundings of the same scaled hash values--because fastrange not mod.) This seems to be as effective or more effective than re-seeding, as long as we increase the number of slots (m) by roughly m += m/w where w is the Ribbon width. This way, there is effectively an expansion by one slot for each ribbon-width window in the banding. (This approach assumes that getting "bad data" from your hash function is as unlikely as it naturally should be, e.g. no adversary.) * 32-bit and 16-bit Ribbon configurations are added to ribbon_test for understanding their behavior, e.g. with FindOccupancy. They are not considered useful at this time and not tested with CompactnessAndBacktrackAndFpRate. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7879 Test Plan: unit test updates included Reviewed By: jay-zhuang Differential Revision: D26371245 Pulled By: pdillinger fbshipit-source-id: da6600d90a3785b99ad17a88b2a3027710b4ea3a
2021-02-26 17:48:55 +01:00
// Swaps between big and little endian. Can be used to in combination
// with the little-endian encoding/decoding functions to encode/decode
// big endian.
template <typename T>
inline T EndianSwapValue(T v) {
static_assert(std::is_integral<T>::value, "non-integral type");
#ifdef _MSC_VER
if (sizeof(T) == 2) {
return static_cast<T>(_byteswap_ushort(static_cast<uint16_t>(v)));
} else if (sizeof(T) == 4) {
return static_cast<T>(_byteswap_ulong(static_cast<uint32_t>(v)));
} else if (sizeof(T) == 8) {
return static_cast<T>(_byteswap_uint64(static_cast<uint64_t>(v)));
}
#else
if (sizeof(T) == 2) {
return static_cast<T>(__builtin_bswap16(static_cast<uint16_t>(v)));
} else if (sizeof(T) == 4) {
return static_cast<T>(__builtin_bswap32(static_cast<uint32_t>(v)));
} else if (sizeof(T) == 8) {
return static_cast<T>(__builtin_bswap64(static_cast<uint64_t>(v)));
}
#endif
// Recognized by clang as bswap, but not by gcc :(
T ret_val = 0;
for (size_t i = 0; i < sizeof(T); ++i) {
ret_val |= ((v >> (8 * i)) & 0xff) << (8 * (sizeof(T) - 1 - i));
}
return ret_val;
}
} // namespace ROCKSDB_NAMESPACE