rocksdb/db/log_writer.cc
Hans Wennborg 36a5f8ed7f A number of fixes:
- Replace raw slice comparison with a call to user comparator.
  Added test for custom comparators.

- Fix end of namespace comments.

- Fixed bug in picking inputs for a level-0 compaction.

  When finding overlapping files, the covered range may expand
  as files are added to the input set.  We now correctly expand
  the range when this happens instead of continuing to use the
  old range.  For example, suppose L0 contains files with the
  following ranges:

      F1: a .. d
      F2:    c .. g
      F3:       f .. j

  and the initial compaction target is F3.  We used to search
  for range f..j which yielded {F2,F3}.  However we now expand
  the range as soon as another file is added.  In this case,
  when F2 is added, we expand the range to c..j and restart the
  search.  That picks up file F1 as well.

  This change fixes a bug related to deleted keys showing up
  incorrectly after a compaction as described in Issue 44.

(Sync with upstream @25072954)
2011-10-31 17:22:06 +00:00

104 lines
2.8 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.
#include "db/log_writer.h"
#include <stdint.h>
#include "leveldb/env.h"
#include "util/coding.h"
#include "util/crc32c.h"
namespace leveldb {
namespace log {
Writer::Writer(WritableFile* dest)
: dest_(dest),
block_offset_(0) {
for (int i = 0; i <= kMaxRecordType; i++) {
char t = static_cast<char>(i);
type_crc_[i] = crc32c::Value(&t, 1);
}
}
Writer::~Writer() {
}
Status Writer::AddRecord(const Slice& slice) {
const char* ptr = slice.data();
size_t left = slice.size();
// Fragment the record if necessary and emit it. Note that if slice
// is empty, we still want to iterate once to emit a single
// zero-length record
Status s;
bool begin = true;
do {
const int leftover = kBlockSize - block_offset_;
assert(leftover >= 0);
if (leftover < kHeaderSize) {
// Switch to a new block
if (leftover > 0) {
// Fill the trailer (literal below relies on kHeaderSize being 7)
assert(kHeaderSize == 7);
dest_->Append(Slice("\x00\x00\x00\x00\x00\x00", leftover));
}
block_offset_ = 0;
}
// Invariant: we never leave < kHeaderSize bytes in a block.
assert(kBlockSize - block_offset_ - kHeaderSize >= 0);
const size_t avail = kBlockSize - block_offset_ - kHeaderSize;
const size_t fragment_length = (left < avail) ? left : avail;
RecordType type;
const bool end = (left == fragment_length);
if (begin && end) {
type = kFullType;
} else if (begin) {
type = kFirstType;
} else if (end) {
type = kLastType;
} else {
type = kMiddleType;
}
s = EmitPhysicalRecord(type, ptr, fragment_length);
ptr += fragment_length;
left -= fragment_length;
begin = false;
} while (s.ok() && left > 0);
return s;
}
Status Writer::EmitPhysicalRecord(RecordType t, const char* ptr, size_t n) {
assert(n <= 0xffff); // Must fit in two bytes
assert(block_offset_ + kHeaderSize + n <= kBlockSize);
// Format the header
char buf[kHeaderSize];
buf[4] = static_cast<char>(n & 0xff);
buf[5] = static_cast<char>(n >> 8);
buf[6] = static_cast<char>(t);
// Compute the crc of the record type and the payload.
uint32_t crc = crc32c::Extend(type_crc_[t], ptr, n);
crc = crc32c::Mask(crc); // Adjust for storage
EncodeFixed32(buf, crc);
// Write the header and the payload
Status s = dest_->Append(Slice(buf, kHeaderSize));
if (s.ok()) {
s = dest_->Append(Slice(ptr, n));
if (s.ok()) {
s = dest_->Flush();
}
}
block_offset_ += kHeaderSize + n;
return s;
}
} // namespace log
} // namespace leveldb