1
0
mirror of https://github.com/facebook/rocksdb.git synced 2026-10-23 08:09:02 +03:00
Files
rocksdb/db/blob/blob_log_sequential_reader.cc
Josh Kang aeebcbded4 Add coroutine external table reads (#15291)
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/15291

Add experimental coroutine interfaces for implementing asynchronous basic and full `ExternalTableReader`s. Implementations opt in through `CoroExternalTableReaderBase<Mode>` by providing `GetCoroutine()` and may override `MultiGetCoroutine()`; the default implementation runs the individual Get operations concurrently. The external-table adapter uses these APIs when supported and otherwise retains the existing synchronous behavior.

As a smaller supporting fix, Single Get coroutine reads using non-mmap, non-direct I/O on a kFSBuffer-capable `FileSystem` now use `FSRandomAccessFile::SubmitReadAsync()` instead of falling back to synchronous `Read()`.

Reviewed By: xingbowang

Differential Revision: D122187491

fbshipit-source-id: 217e2953756938bbd3f30358a997a7ca3ed5543e
2026-10-01 09:28:24 -07:00

134 lines
4.0 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
#include "db/blob/blob_log_sequential_reader.h"
#include "file/random_access_file_reader.h"
#include "monitoring/statistics_impl.h"
#include "util/stop_watch.h"
namespace ROCKSDB_NAMESPACE {
BlobLogSequentialReader::BlobLogSequentialReader(
std::unique_ptr<RandomAccessFileReader>&& file_reader, SystemClock* clock,
Statistics* statistics)
: file_(std::move(file_reader)),
clock_(clock),
statistics_(statistics),
next_byte_(0) {}
BlobLogSequentialReader::~BlobLogSequentialReader() = default;
Status BlobLogSequentialReader::ReadSlice(uint64_t size, Slice* slice,
char* buf) {
assert(slice);
assert(file_);
StopWatch read_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
// TODO: rate limit `BlobLogSequentialReader` reads (it appears unused?)
Status s = file_->Read(next_byte_, static_cast<size_t>(size), IOOptions(),
slice, buf, nullptr);
next_byte_ += size;
if (!s.ok()) {
return s;
}
RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_READ, slice->size());
if (slice->size() != size) {
return Status::Corruption("EOF reached while reading record");
}
return s;
}
Status BlobLogSequentialReader::ReadHeader(BlobLogHeader* header) {
assert(header);
assert(next_byte_ == 0);
static_assert(BlobLogHeader::kSize <= sizeof(header_buf_),
"Buffer is smaller than BlobLogHeader::kSize");
Status s = ReadSlice(BlobLogHeader::kSize, &buffer_, header_buf_);
if (!s.ok()) {
return s;
}
if (buffer_.size() != BlobLogHeader::kSize) {
return Status::Corruption("EOF reached before file header");
}
return header->DecodeFrom(buffer_);
}
Status BlobLogSequentialReader::ReadRecord(BlobLogRecord* record,
ReadLevel level,
uint64_t* blob_offset) {
assert(record);
static_assert(BlobLogRecord::kHeaderSize <= sizeof(header_buf_),
"Buffer is smaller than BlobLogRecord::kHeaderSize");
Status s = ReadSlice(BlobLogRecord::kHeaderSize, &buffer_, header_buf_);
if (!s.ok()) {
return s;
}
if (buffer_.size() != BlobLogRecord::kHeaderSize) {
return Status::Corruption("EOF reached before record header");
}
s = record->DecodeHeaderFrom(buffer_);
if (!s.ok()) {
return s;
}
uint64_t kb_size = record->key_size + record->value_size;
if (blob_offset != nullptr) {
*blob_offset = next_byte_ + record->key_size;
}
switch (level) {
case kReadHeader:
next_byte_ += kb_size;
break;
case kReadHeaderKey:
record->key_buf.reset(new char[record->key_size]);
s = ReadSlice(record->key_size, &record->key, record->key_buf.get());
next_byte_ += record->value_size;
break;
case kReadHeaderKeyBlob:
record->key_buf.reset(new char[record->key_size]);
s = ReadSlice(record->key_size, &record->key, record->key_buf.get());
if (s.ok()) {
record->value_buf.reset(new char[record->value_size]);
s = ReadSlice(record->value_size, &record->value,
record->value_buf.get());
}
if (s.ok()) {
s = record->CheckBlobCRC();
}
break;
}
return s;
}
Status BlobLogSequentialReader::ReadFooter(BlobLogFooter* footer) {
assert(footer);
static_assert(BlobLogFooter::kSize <= sizeof(header_buf_),
"Buffer is smaller than BlobLogFooter::kSize");
Status s = ReadSlice(BlobLogFooter::kSize, &buffer_, header_buf_);
if (!s.ok()) {
return s;
}
if (buffer_.size() != BlobLogFooter::kSize) {
return Status::Corruption("EOF reached before file footer");
}
return footer->DecodeFrom(buffer_);
}
} // namespace ROCKSDB_NAMESPACE