Revision cadc1adffa447f02eb65bd848cf26c13142a74bb authored by sdong on 13 June 2014, 22:54:19 UTC, committed by sdong on 16 June 2014, 23:10:52 UTC
Summary:
We added multiple fields to FileMetaData recently and are planning to add more.
This refactoring separate the minimum information for accessing the file. This object is copyable (FileMetaData is not copyable since the ref counter). I hope this refactoring can enable further improvements:

(1) use it to design a more efficient data structure to speed up read queries.
(2) in the future, when we add information of storage level, we can easily do the encoding, instead of enlarge this structure, which might expand memory work set for file meta data.

The definition is same as current EncodedFileMetaData used in two level iterator, so now the logic in two level iterator is easier to understand.

Test Plan: make all check

Reviewers: haobo, igor, ljin

Reviewed By: ljin

Subscribers: leveldb, dhruba, yhchiang

Differential Revision: https://reviews.facebook.net/D18933
1 parent 4d913cf
Raw File
coding.h
//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
//  This source code is licensed under the BSD-style license found in the
//  LICENSE file in the root directory of this source tree. An additional grant
//  of patent rights can be found in the PATENTS file in the same directory.
//
// 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

#pragma once
#include <algorithm>
#include <stdint.h>
#include <string.h>
#include <string>

#include "rocksdb/write_batch.h"
#include "port/port.h"

namespace rocksdb {

// 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);
extern void PutLengthPrefixedSliceParts(std::string* dst,
                                        const SliceParts& slice_parts);

// 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);
// This function assumes data is well-formed.
extern Slice GetLengthPrefixedSlice(const char* data);

extern Slice GetSliceUntil(Slice* slice, char delimiter);

// 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);

// -- Implementation of the functions declared above
inline void EncodeFixed32(char* buf, uint32_t value) {
#if __BYTE_ORDER == __LITTLE_ENDIAN
  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;
#endif
}

inline void EncodeFixed64(char* buf, uint64_t value) {
#if __BYTE_ORDER == __LITTLE_ENDIAN
  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;
#endif
}

inline void PutFixed32(std::string* dst, uint32_t value) {
  char buf[sizeof(value)];
  EncodeFixed32(buf, value);
  dst->append(buf, sizeof(buf));
}

inline void PutFixed64(std::string* dst, uint64_t value) {
  char buf[sizeof(value)];
  EncodeFixed64(buf, value);
  dst->append(buf, sizeof(buf));
}

inline void PutVarint32(std::string* dst, uint32_t v) {
  char buf[5];
  char* ptr = EncodeVarint32(buf, v);
  dst->append(buf, ptr - buf);
}

inline char* EncodeVarint64(char* dst, uint64_t v) {
  static const unsigned int B = 128;
  unsigned char* ptr = reinterpret_cast<unsigned char*>(dst);
  while (v >= B) {
    *(ptr++) = (v & (B - 1)) | B;
    v >>= 7;
  }
  *(ptr++) = static_cast<unsigned char>(v);
  return reinterpret_cast<char*>(ptr);
}

inline void PutVarint64(std::string* dst, uint64_t v) {
  char buf[10];
  char* ptr = EncodeVarint64(buf, v);
  dst->append(buf, ptr - buf);
}

inline void PutLengthPrefixedSlice(std::string* dst, const Slice& value) {
  PutVarint32(dst, value.size());
  dst->append(value.data(), value.size());
}

inline void PutLengthPrefixedSliceParts(std::string* dst,
                                        const SliceParts& slice_parts) {
  uint32_t total_bytes = 0;
  for (int i = 0; i < slice_parts.num_parts; ++i) {
    total_bytes += slice_parts.parts[i].size();
  }
  PutVarint32(dst, total_bytes);
  for (int i = 0; i < slice_parts.num_parts; ++i) {
    dst->append(slice_parts.parts[i].data(), slice_parts.parts[i].size());
  }
}

inline int VarintLength(uint64_t v) {
  int len = 1;
  while (v >= 128) {
    v >>= 7;
    len++;
  }
  return len;
}

inline bool GetVarint32(Slice* input, uint32_t* value) {
  const char* p = input->data();
  const char* limit = p + input->size();
  const char* q = GetVarint32Ptr(p, limit, value);
  if (q == nullptr) {
    return false;
  } else {
    *input = Slice(q, limit - q);
    return true;
  }
}

inline bool GetVarint64(Slice* input, uint64_t* value) {
  const char* p = input->data();
  const char* limit = p + input->size();
  const char* q = GetVarint64Ptr(p, limit, value);
  if (q == nullptr) {
    return false;
  } else {
    *input = Slice(q, limit - q);
    return true;
  }
}

inline bool GetLengthPrefixedSlice(Slice* input, Slice* result) {
  uint32_t len = 0;
  if (GetVarint32(input, &len) && input->size() >= len) {
    *result = Slice(input->data(), len);
    input->remove_prefix(len);
    return true;
  } else {
    return false;
  }
}

inline Slice GetLengthPrefixedSlice(const char* data) {
  uint32_t len = 0;
  // +5: we assume "data" is not corrupted
  auto p = GetVarint32Ptr(data, data + 5 /* limit */, &len);
  return Slice(p, len);
}

inline Slice GetSliceUntil(Slice* slice, char delimiter) {
  uint32_t len = 0;
  for (len = 0; len < slice->size() && slice->data()[len] != delimiter; ++len) {
    // nothing
  }

  Slice ret(slice->data(), len);
  slice->remove_prefix(len + ((len < slice->size()) ? 1 : 0));
  return ret;
}

inline uint64_t BitStreamGetInt(const std::string* src, size_t offset,
                                uint32_t bits) {
  return BitStreamGetInt(src->data(), src->size(), offset, bits);
}

inline uint64_t BitStreamGetInt(const Slice* src, size_t offset,
                                uint32_t bits) {
  return BitStreamGetInt(src->data(), src->size(), offset, bits);
}

}  // namespace rocksdb
back to top