74781a0c49
Summary: This patch adds three new MemTableRep's: UnsortedRep, PrefixHashRep, and VectorRep. UnsortedRep stores keys in an std::unordered_map of std::sets. When an iterator is requested, it dumps the keys into an std::set and iterates over that. VectorRep stores keys in an std::vector. When an iterator is requested, it creates a copy of the vector and sorts it using std::sort. The iterator accesses that new vector. PrefixHashRep stores keys in an unordered_map mapping prefixes to ordered sets. I also added one API change. I added a function MemTableRep::MarkImmutable. This function is called when the rep is added to the immutable list. It doesn't do anything yet, but it seems like that could be useful. In particular, for the vectorrep, it means we could elide the extra copy and just sort in place. The only reason I haven't done that yet is because the use of the ArenaAllocator complicates things (I can elaborate on this if needed). Test Plan: make -j32 check ./db_stress --memtablerep=vector ./db_stress --memtablerep=unsorted ./db_stress --memtablerep=prefixhash --prefix_size=10 Reviewers: dhruba, haobo, emayanke Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D12117
135 lines
5.3 KiB
C++
135 lines
5.3 KiB
C++
// Copyright (c) 2011 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.
|
|
//
|
|
// Endian-neutral encoding:
|
|
// * Fixed-length numbers are encoded with least-significant byte first
|
|
// * In addition we support variable length "varint" encoding
|
|
// * Strings are encoded prefixed by their length in varint format
|
|
|
|
#ifndef STORAGE_LEVELDB_UTIL_CODING_H_
|
|
#define STORAGE_LEVELDB_UTIL_CODING_H_
|
|
|
|
#include <stdint.h>
|
|
#include <string.h>
|
|
#include <string>
|
|
#include "port/port.h"
|
|
|
|
namespace leveldb {
|
|
|
|
// The maximum length of a varint in bytes for 32 and 64 bits respectively.
|
|
const unsigned int kMaxVarint32Length = 5;
|
|
const unsigned int kMaxVarint64Length = 10;
|
|
|
|
// Standard Put... routines append to a string
|
|
extern void PutFixed32(std::string* dst, uint32_t value);
|
|
extern void PutFixed64(std::string* dst, uint64_t value);
|
|
extern void PutVarint32(std::string* dst, uint32_t value);
|
|
extern void PutVarint64(std::string* dst, uint64_t value);
|
|
extern void PutLengthPrefixedSlice(std::string* dst, const Slice& value);
|
|
|
|
// Standard Get... routines parse a value from the beginning of a Slice
|
|
// and advance the slice past the parsed value.
|
|
extern bool GetVarint32(Slice* input, uint32_t* value);
|
|
extern bool GetVarint64(Slice* input, uint64_t* value);
|
|
extern bool GetLengthPrefixedSlice(Slice* input, Slice* result);
|
|
extern Slice GetLengthPrefixedSlice(const char* data);
|
|
|
|
// Pointer-based variants of GetVarint... These either store a value
|
|
// in *v and return a pointer just past the parsed value, or return
|
|
// nullptr on error. These routines only look at bytes in the range
|
|
// [p..limit-1]
|
|
extern const char* GetVarint32Ptr(const char* p,const char* limit, uint32_t* v);
|
|
extern const char* GetVarint64Ptr(const char* p,const char* limit, uint64_t* v);
|
|
|
|
// Returns the length of the varint32 or varint64 encoding of "v"
|
|
extern int VarintLength(uint64_t v);
|
|
|
|
// Lower-level versions of Put... that write directly into a character buffer
|
|
// REQUIRES: dst has enough space for the value being written
|
|
extern void EncodeFixed32(char* dst, uint32_t value);
|
|
extern void EncodeFixed64(char* dst, uint64_t value);
|
|
|
|
// Lower-level versions of Put... that write directly into a character buffer
|
|
// and return a pointer just past the last byte written.
|
|
// REQUIRES: dst has enough space for the value being written
|
|
extern char* EncodeVarint32(char* dst, uint32_t value);
|
|
extern char* EncodeVarint64(char* dst, uint64_t value);
|
|
|
|
// Lower-level versions of Get... that read directly from a character buffer
|
|
// without any bounds checking.
|
|
|
|
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;
|
|
}
|
|
}
|
|
|
|
// Internal routine for use by fallback path of GetVarint32Ptr
|
|
extern const char* GetVarint32PtrFallback(const char* p,
|
|
const char* limit,
|
|
uint32_t* value);
|
|
inline const char* GetVarint32Ptr(const char* p,
|
|
const char* limit,
|
|
uint32_t* value) {
|
|
if (p < limit) {
|
|
uint32_t result = *(reinterpret_cast<const unsigned char*>(p));
|
|
if ((result & 128) == 0) {
|
|
*value = result;
|
|
return p + 1;
|
|
}
|
|
}
|
|
return GetVarint32PtrFallback(p, limit, value);
|
|
}
|
|
|
|
// Writes an unsigned integer with bits number of bits with its least
|
|
// significant bit at offset.
|
|
// Bits are numbered from 0 to 7 in the first byte, 8 to 15 in the second and
|
|
// so on.
|
|
// value is truncated to the bits number of least significant bits.
|
|
// REQUIRES: (offset+bits+7)/8 <= dstlen
|
|
// REQUIRES: bits <= 64
|
|
extern void BitStreamPutInt(char* dst, size_t dstlen, size_t offset,
|
|
uint32_t bits, uint64_t value);
|
|
|
|
// Reads an unsigned integer with bits number of bits with its least
|
|
// significant bit at offset.
|
|
// Bits are numbered in the same way as ByteStreamPutInt().
|
|
// REQUIRES: (offset+bits+7)/8 <= srclen
|
|
// REQUIRES: bits <= 64
|
|
extern uint64_t BitStreamGetInt(const char* src, size_t srclen, size_t offset,
|
|
uint32_t bits);
|
|
|
|
// Convenience functions
|
|
extern void BitStreamPutInt(std::string* dst, size_t offset, uint32_t bits,
|
|
uint64_t value);
|
|
extern uint64_t BitStreamGetInt(const std::string* src, size_t offset,
|
|
uint32_t bits);
|
|
extern uint64_t BitStreamGetInt(const Slice* src, size_t offset,
|
|
uint32_t bits);
|
|
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_UTIL_CODING_H_
|