rocksdb/db/log_reader.cc

331 lines
9.9 KiB
C++

// 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.
#include "db/log_reader.h"
#include <stdio.h>
#include "rocksdb/env.h"
#include "util/coding.h"
#include "util/crc32c.h"
namespace rocksdb {
namespace log {
Reader::Reporter::~Reporter() {
}
Reader::Reader(unique_ptr<SequentialFile>&& file, Reporter* reporter,
bool checksum, uint64_t initial_offset)
: file_(std::move(file)),
reporter_(reporter),
checksum_(checksum),
backing_store_(new char[kBlockSize]),
buffer_(),
eof_(false),
read_error_(false),
eof_offset_(0),
last_record_offset_(0),
end_of_buffer_offset_(0),
initial_offset_(initial_offset) {
}
Reader::~Reader() {
delete[] backing_store_;
}
bool Reader::SkipToInitialBlock() {
size_t offset_in_block = initial_offset_ % kBlockSize;
uint64_t block_start_location = initial_offset_ - offset_in_block;
// Don't search a block if we'd be in the trailer
if (offset_in_block > kBlockSize - 6) {
offset_in_block = 0;
block_start_location += kBlockSize;
}
end_of_buffer_offset_ = block_start_location;
// Skip to start of first block that can contain the initial record
if (block_start_location > 0) {
Status skip_status = file_->Skip(block_start_location);
if (!skip_status.ok()) {
ReportDrop(block_start_location, skip_status);
return false;
}
}
return true;
}
bool Reader::ReadRecord(Slice* record, std::string* scratch) {
if (last_record_offset_ < initial_offset_) {
if (!SkipToInitialBlock()) {
return false;
}
}
scratch->clear();
record->clear();
bool in_fragmented_record = false;
// Record offset of the logical record that we're reading
// 0 is a dummy value to make compilers happy
uint64_t prospective_record_offset = 0;
Slice fragment;
while (true) {
uint64_t physical_record_offset = end_of_buffer_offset_ - buffer_.size();
const unsigned int record_type = ReadPhysicalRecord(&fragment);
switch (record_type) {
case kFullType:
if (in_fragmented_record) {
// Handle bug in earlier versions of log::Writer where
// it could emit an empty kFirstType record at the tail end
// of a block followed by a kFullType or kFirstType record
// at the beginning of the next block.
if (scratch->empty()) {
in_fragmented_record = false;
} else {
ReportCorruption(scratch->size(), "partial record without end(1)");
}
}
prospective_record_offset = physical_record_offset;
scratch->clear();
*record = fragment;
last_record_offset_ = prospective_record_offset;
return true;
case kFirstType:
if (in_fragmented_record) {
// Handle bug in earlier versions of log::Writer where
// it could emit an empty kFirstType record at the tail end
// of a block followed by a kFullType or kFirstType record
// at the beginning of the next block.
if (scratch->empty()) {
in_fragmented_record = false;
} else {
ReportCorruption(scratch->size(), "partial record without end(2)");
}
}
prospective_record_offset = physical_record_offset;
scratch->assign(fragment.data(), fragment.size());
in_fragmented_record = true;
break;
case kMiddleType:
if (!in_fragmented_record) {
ReportCorruption(fragment.size(),
"missing start of fragmented record(1)");
} else {
scratch->append(fragment.data(), fragment.size());
}
break;
case kLastType:
if (!in_fragmented_record) {
ReportCorruption(fragment.size(),
"missing start of fragmented record(2)");
} else {
scratch->append(fragment.data(), fragment.size());
*record = Slice(*scratch);
last_record_offset_ = prospective_record_offset;
return true;
}
break;
case kEof:
if (in_fragmented_record) {
ReportCorruption(scratch->size(), "partial record without end(3)");
scratch->clear();
}
return false;
case kBadRecord:
if (in_fragmented_record) {
ReportCorruption(scratch->size(), "error in middle of record");
in_fragmented_record = false;
scratch->clear();
}
break;
default: {
char buf[40];
snprintf(buf, sizeof(buf), "unknown record type %u", record_type);
ReportCorruption(
(fragment.size() + (in_fragmented_record ? scratch->size() : 0)),
buf);
in_fragmented_record = false;
scratch->clear();
break;
}
}
}
return false;
}
uint64_t Reader::LastRecordOffset() {
return last_record_offset_;
}
void Reader::UnmarkEOF() {
if (read_error_) {
return;
}
eof_ = false;
if (eof_offset_ == 0) {
return;
}
// If the EOF was in the middle of a block (a partial block was read) we have
// to read the rest of the block as ReadPhysicalRecord can only read full
// blocks and expects the file position indicator to be aligned to the start
// of a block.
//
// consumed_bytes + buffer_size() + remaining == kBlockSize
size_t consumed_bytes = eof_offset_ - buffer_.size();
size_t remaining = kBlockSize - eof_offset_;
// backing_store_ is used to concatenate what is left in buffer_ and
// the remainder of the block. If buffer_ already uses backing_store_,
// we just append the new data.
if (buffer_.data() != backing_store_ + consumed_bytes) {
// Buffer_ does not use backing_store_ for storage.
// Copy what is left in buffer_ to backing_store.
memmove(backing_store_ + consumed_bytes, buffer_.data(), buffer_.size());
}
Slice read_buffer;
Status status = file_->Read(remaining, &read_buffer,
backing_store_ + eof_offset_);
size_t added = read_buffer.size();
end_of_buffer_offset_ += added;
if (!status.ok()) {
if (added > 0) {
ReportDrop(added, status);
}
read_error_ = true;
return;
}
if (read_buffer.data() != backing_store_ + eof_offset_) {
// Read did not write to backing_store_
memmove(backing_store_ + eof_offset_, read_buffer.data(),
read_buffer.size());
}
buffer_ = Slice(backing_store_ + consumed_bytes,
eof_offset_ + added - consumed_bytes);
if (added < remaining) {
eof_ = true;
eof_offset_ += added;
} else {
eof_offset_ = 0;
}
}
void Reader::ReportCorruption(size_t bytes, const char* reason) {
ReportDrop(bytes, Status::Corruption(reason));
}
void Reader::ReportDrop(size_t bytes, const Status& reason) {
if (reporter_ != nullptr &&
end_of_buffer_offset_ - buffer_.size() - bytes >= initial_offset_) {
reporter_->Corruption(bytes, reason);
}
}
unsigned int Reader::ReadPhysicalRecord(Slice* result) {
while (true) {
if (buffer_.size() < (size_t)kHeaderSize) {
if (!eof_ && !read_error_) {
// Last read was a full read, so this is a trailer to skip
buffer_.clear();
Status status = file_->Read(kBlockSize, &buffer_, backing_store_);
end_of_buffer_offset_ += buffer_.size();
if (!status.ok()) {
buffer_.clear();
ReportDrop(kBlockSize, status);
read_error_ = true;
return kEof;
} else if (buffer_.size() < (size_t)kBlockSize) {
eof_ = true;
eof_offset_ = buffer_.size();
}
continue;
} else if (buffer_.size() == 0) {
// End of file
return kEof;
} else {
size_t drop_size = buffer_.size();
buffer_.clear();
ReportCorruption(drop_size, "truncated record at end of file");
return kEof;
}
}
// Parse the header
const char* header = buffer_.data();
const uint32_t a = static_cast<uint32_t>(header[4]) & 0xff;
const uint32_t b = static_cast<uint32_t>(header[5]) & 0xff;
const unsigned int type = header[6];
const uint32_t length = a | (b << 8);
if (kHeaderSize + length > buffer_.size()) {
size_t drop_size = buffer_.size();
buffer_.clear();
ReportCorruption(drop_size, "bad record length");
return kBadRecord;
}
if (type == kZeroType && length == 0) {
// Skip zero length record without reporting any drops since
// such records are produced by the mmap based writing code in
// env_posix.cc that preallocates file regions.
buffer_.clear();
return kBadRecord;
}
// Check crc
if (checksum_) {
uint32_t expected_crc = crc32c::Unmask(DecodeFixed32(header));
uint32_t actual_crc = crc32c::Value(header + 6, 1 + length);
if (actual_crc != expected_crc) {
// Drop the rest of the buffer since "length" itself may have
// been corrupted and if we trust it, we could find some
// fragment of a real log record that just happens to look
// like a valid log record.
size_t drop_size = buffer_.size();
buffer_.clear();
ReportCorruption(drop_size, "checksum mismatch");
return kBadRecord;
}
}
buffer_.remove_prefix(kHeaderSize + length);
// Skip physical record that started before initial_offset_
if (end_of_buffer_offset_ - buffer_.size() - kHeaderSize - length <
initial_offset_) {
result->clear();
return kBadRecord;
}
*result = Slice(header + kHeaderSize, length);
return type;
}
}
} // namespace log
} // namespace rocksdb