Revision 499ebb3ab5ea4207950fc95acf102b8f58add1c5 authored by Maysam Yabandeh on 24 June 2017, 21:06:43 UTC, committed by Facebook Github Bot on 24 June 2017, 21:11:29 UTC
Summary:
Throughput: 46k tps in our sysbench settings (filling the details later)

The idea is to have the simplest change that gives us a reasonable boost
in 2PC throughput.

Major design changes:
1. The WAL file internal buffer is not flushed after each write. Instead
it is flushed before critical operations (WAL copy via fs) or when
FlushWAL is called by MySQL. Flushing the WAL buffer is also protected
via mutex_.
2. Use two sequence numbers: last seq, and last seq for write. Last seq
is the last visible sequence number for reads. Last seq for write is the
next sequence number that should be used to write to WAL/memtable. This
allows to have a memtable write be in parallel to WAL writes.
3. BatchGroup is not used for writes. This means that we can have
parallel writers which changes a major assumption in the code base. To
accommodate for that i) allow only 1 WriteImpl that intends to write to
memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes
come via group commit phase which is serial anyway, ii) make all the
parts in the code base that assumed to be the only writer (via
EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are
protected via a stat_mutex_.

Note: the first commit has the approach figured out but is not clean.
Submitting the PR anyway to get the early feedback on the approach. If
we are ok with the approach I will go ahead with this updates:
0) Rebase with Yi's pipelining changes
1) Currently batching is disabled by default to make sure that it will be
consistent with all unit tests. Will make this optional via a config.
2) A couple of unit tests are disabled. They need to be updated with the
serial commit of 2PC taken into account.
3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires
releasing mutex_ beforehand (the same way EnterUnbatched does). This
needs to be cleaned up.
Closes https://github.com/facebook/rocksdb/pull/2345

Differential Revision: D5210732

Pulled By: maysamyabandeh

fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
1 parent 0ac4afb
Raw File
coding.h
//  Copyright (c) 2011-present, 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.
//  This source code is also licensed under the GPLv2 license found in the
//  COPYING file in the root directory of this source tree.
//
// 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"

// Some processors does not allow unaligned access to memory
#if defined(__sparc)
  #define PLATFORM_UNALIGNED_ACCESS_NOT_ALLOWED
#endif

namespace rocksdb {

// The maximum length of a varint in bytes for 64-bit.
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 PutVarint32Varint32(std::string* dst, uint32_t value1,
                                uint32_t value2);
extern void PutVarint32Varint32Varint32(std::string* dst, uint32_t value1,
                                        uint32_t value2, uint32_t value3);
extern void PutVarint64(std::string* dst, uint64_t value);
extern void PutVarint64Varint64(std::string* dst, uint64_t value1,
                                uint64_t value2);
extern void PutVarint32Varint64(std::string* dst, uint32_t value1,
                                uint64_t value2);
extern void PutVarint32Varint32Varint64(std::string* dst, uint32_t value1,
                                        uint32_t value2, uint64_t value3);
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 GetFixed64(Slice* input, uint64_t* value);
extern bool GetFixed32(Slice* input, uint32_t* 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);
}

// -- Implementation of the functions declared above
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;
  }
}

// Pull the last 8 bits and cast it to a character
inline void PutFixed32(std::string* dst, uint32_t value) {
  if (port::kLittleEndian) {
    dst->append(const_cast<const char*>(reinterpret_cast<char*>(&value)),
      sizeof(value));
  } else {
    char buf[sizeof(value)];
    EncodeFixed32(buf, value);
    dst->append(buf, sizeof(buf));
  }
}

inline void PutFixed64(std::string* dst, uint64_t value) {
  if (port::kLittleEndian) {
    dst->append(const_cast<const char*>(reinterpret_cast<char*>(&value)),
      sizeof(value));
  } else {
    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, static_cast<size_t>(ptr - buf));
}

inline void PutVarint32Varint32(std::string* dst, uint32_t v1, uint32_t v2) {
  char buf[10];
  char* ptr = EncodeVarint32(buf, v1);
  ptr = EncodeVarint32(ptr, v2);
  dst->append(buf, static_cast<size_t>(ptr - buf));
}

inline void PutVarint32Varint32Varint32(std::string* dst, uint32_t v1,
                                        uint32_t v2, uint32_t v3) {
  char buf[15];
  char* ptr = EncodeVarint32(buf, v1);
  ptr = EncodeVarint32(ptr, v2);
  ptr = EncodeVarint32(ptr, v3);
  dst->append(buf, static_cast<size_t>(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, static_cast<size_t>(ptr - buf));
}

inline void PutVarint64Varint64(std::string* dst, uint64_t v1, uint64_t v2) {
  char buf[20];
  char* ptr = EncodeVarint64(buf, v1);
  ptr = EncodeVarint64(ptr, v2);
  dst->append(buf, static_cast<size_t>(ptr - buf));
}

inline void PutVarint32Varint64(std::string* dst, uint32_t v1, uint64_t v2) {
  char buf[15];
  char* ptr = EncodeVarint32(buf, v1);
  ptr = EncodeVarint64(ptr, v2);
  dst->append(buf, static_cast<size_t>(ptr - buf));
}

inline void PutVarint32Varint32Varint64(std::string* dst, uint32_t v1,
                                        uint32_t v2, uint64_t v3) {
  char buf[20];
  char* ptr = EncodeVarint32(buf, v1);
  ptr = EncodeVarint32(ptr, v2);
  ptr = EncodeVarint64(ptr, v3);
  dst->append(buf, static_cast<size_t>(ptr - buf));
}

inline void PutLengthPrefixedSlice(std::string* dst, const Slice& value) {
  PutVarint32(dst, static_cast<uint32_t>(value.size()));
  dst->append(value.data(), value.size());
}

inline void PutLengthPrefixedSliceParts(std::string* dst,
                                        const SliceParts& slice_parts) {
  size_t total_bytes = 0;
  for (int i = 0; i < slice_parts.num_parts; ++i) {
    total_bytes += slice_parts.parts[i].size();
  }
  PutVarint32(dst, static_cast<uint32_t>(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 GetFixed64(Slice* input, uint64_t* value) {
  if (input->size() < sizeof(uint64_t)) {
    return false;
  }
  *value = DecodeFixed64(input->data());
  input->remove_prefix(sizeof(uint64_t));
  return true;
}

inline bool GetFixed32(Slice* input, uint32_t* value) {
  if (input->size() < sizeof(uint32_t)) {
    return false;
  }
  *value = DecodeFixed32(input->data());
  input->remove_prefix(sizeof(uint32_t));
  return true;
}

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, static_cast<size_t>(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, static_cast<size_t>(limit - q));
    return true;
  }
}

// Provide an interface for platform independent endianness transformation
inline uint64_t EndianTransform(uint64_t input, size_t size) {
  char* pos = reinterpret_cast<char*>(&input);
  uint64_t ret_val = 0;
  for (size_t i = 0; i < size; ++i) {
    ret_val |= (static_cast<uint64_t>(static_cast<unsigned char>(pos[i]))
                << ((size - i - 1) << 3));
  }
  return ret_val;
}

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
  // unsigned char is 7 bits, uint32_t is 32 bits, need 5 unsigned char
  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;
}

template<class T>
#ifdef ROCKSDB_UBSAN_RUN
#if defined(__clang__)
__attribute__((__no_sanitize__("alignment")))
#elif defined(__GNUC__)
__attribute__((__no_sanitize_undefined__))
#endif
#endif
inline void PutUnaligned(T *memory, const T &value) {
#if defined(PLATFORM_UNALIGNED_ACCESS_NOT_ALLOWED)
  char *nonAlignedMemory = reinterpret_cast<char*>(memory);
  memcpy(nonAlignedMemory, reinterpret_cast<const char*>(&value), sizeof(T));
#else
  *memory = value;
#endif
}

template<class T>
#ifdef ROCKSDB_UBSAN_RUN
#if defined(__clang__)
__attribute__((__no_sanitize__("alignment")))
#elif defined(__GNUC__)
__attribute__((__no_sanitize_undefined__))
#endif
#endif
inline void GetUnaligned(const T *memory, T *value) {
#if defined(PLATFORM_UNALIGNED_ACCESS_NOT_ALLOWED)
  char *nonAlignedMemory = reinterpret_cast<char*>(value);
  memcpy(nonAlignedMemory, reinterpret_cast<const char*>(memory), sizeof(T));
#else
  *value = *memory;
#endif
}

}  // namespace rocksdb
back to top