mirror of
https://github.com/facebook/rocksdb.git
synced 2026-07-07 14:47:40 +08:00
82085868e2
Summary: Add read-scoped block buffers for scan reads. Introduce an experimental read-scoped block buffer provider API, configured through ReadOptions::read_scoped_block_buffer_provider, so supported block-based table iterator scans and MultiScan data-block reads can use caller-provided read-scoped storage for final data-block contents. When configured, supported provider-backed scan data-block reads bypass the data-block cache while preserving normal index/filter block-cache behavior. Known-uncompressed reads can attach provider cleanup to provider-backed read buffers without copying. Compressed reads decompress directly into provider-backed output, while maybe-compressed reads that turn out to be uncompressed copy once into provider-backed final contents. mmap reads ignore the provider. Extend AlignedBuffer and RandomAccessFileReader direct-I/O paths to support external aligned allocations, then use that support for read-scoped iterator, async I/O, and MultiRead scratch buffers. Centralize read-scoped I/O policy, keep coalesced async reads safe when blocks are released before completion, and validate provider lease contracts. Add focused coverage for read-scoped ownership, compressed and uncompressed blocks, direct I/O, data-block cache bypass behavior, invalid provider leases, async release handling, and stress-test provider invariants. Add public API release notes for read-scoped block buffers. Bonus change: Fixed a flaky test in ReserveThread ## Testing - CI Pull Request resolved: https://github.com/facebook/rocksdb/pull/14806 Reviewed By: anand1976 Differential Revision: D106999951 Pulled By: xingbowang fbshipit-source-id: b1f23d4bab6318b6373ba2ca99a5c4d6a842dc5a
135 lines
5.5 KiB
C++
135 lines
5.5 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).
|
|
|
|
#pragma once
|
|
|
|
#include <cinttypes>
|
|
#include <memory>
|
|
|
|
#include "db/blob/blob_read_request.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "rocksdb/advanced_compression.h"
|
|
#include "rocksdb/compression_type.h"
|
|
#include "rocksdb/rocksdb_namespace.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class Status;
|
|
struct ImmutableOptions;
|
|
struct FileOptions;
|
|
class HistogramImpl;
|
|
struct ReadOptions;
|
|
class Slice;
|
|
class FilePrefetchBuffer;
|
|
class BlobContents;
|
|
class Statistics;
|
|
|
|
class BlobFileReader {
|
|
public:
|
|
static Status Create(const ImmutableOptions& immutable_options,
|
|
const ReadOptions& read_options,
|
|
const FileOptions& file_options,
|
|
uint32_t column_family_id,
|
|
HistogramImpl* blob_file_read_hist,
|
|
uint64_t blob_file_number,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
std::unique_ptr<BlobFileReader>* reader) {
|
|
return Create(immutable_options, read_options, file_options,
|
|
column_family_id, blob_file_read_hist, blob_file_number,
|
|
io_tracer, /*skip_footer_validation=*/false, reader);
|
|
}
|
|
|
|
// Allows opening in-flight direct-write blob files by optionally skipping
|
|
// footer validation.
|
|
static Status Create(
|
|
const ImmutableOptions& immutable_options,
|
|
const ReadOptions& read_options, const FileOptions& file_options,
|
|
uint32_t column_family_id, HistogramImpl* blob_file_read_hist,
|
|
uint64_t blob_file_number, const std::shared_ptr<IOTracer>& io_tracer,
|
|
bool skip_footer_validation, std::unique_ptr<BlobFileReader>* reader);
|
|
|
|
BlobFileReader(const BlobFileReader&) = delete;
|
|
BlobFileReader& operator=(const BlobFileReader&) = delete;
|
|
|
|
~BlobFileReader();
|
|
|
|
Status GetBlob(const ReadOptions& read_options, const Slice& user_key,
|
|
uint64_t offset, uint64_t value_size,
|
|
CompressionType compression_type,
|
|
FilePrefetchBuffer* prefetch_buffer,
|
|
MemoryAllocator* allocator,
|
|
std::unique_ptr<BlobContents>* result,
|
|
uint64_t* bytes_read) const;
|
|
|
|
// offsets must be sorted in ascending order by caller.
|
|
void MultiGetBlob(
|
|
const ReadOptions& read_options, MemoryAllocator* allocator,
|
|
autovector<std::pair<BlobReadRequest*, std::unique_ptr<BlobContents>>>&
|
|
blob_reqs,
|
|
uint64_t* bytes_read) const;
|
|
|
|
CompressionType GetCompressionType() const { return compression_type_; }
|
|
|
|
uint64_t GetFileSize() const { return file_size_; }
|
|
|
|
private:
|
|
// `has_footer` tracks whether offset validation should reserve footer space.
|
|
BlobFileReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
|
|
uint64_t file_size, CompressionType compression_type,
|
|
std::shared_ptr<Decompressor> decompressor, SystemClock* clock,
|
|
Statistics* statistics, bool has_footer);
|
|
|
|
// `skip_footer_size_check` is used for direct-write files that are still
|
|
// missing their footer at open time.
|
|
static Status OpenFile(const ImmutableOptions& immutable_options,
|
|
const FileOptions& file_opts,
|
|
HistogramImpl* blob_file_read_hist,
|
|
uint64_t blob_file_number,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
uint64_t* file_size,
|
|
std::unique_ptr<RandomAccessFileReader>* file_reader,
|
|
bool skip_footer_size_check);
|
|
|
|
static Status ReadHeader(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options,
|
|
uint32_t column_family_id, Statistics* statistics,
|
|
CompressionType* compression_type);
|
|
|
|
static Status ReadFooter(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options, uint64_t file_size,
|
|
Statistics* statistics);
|
|
|
|
using Buffer = std::unique_ptr<char[]>;
|
|
|
|
static Status ReadFromFile(const RandomAccessFileReader* file_reader,
|
|
const ReadOptions& read_options,
|
|
uint64_t read_offset, size_t read_size,
|
|
Statistics* statistics, Slice* slice, Buffer* buf,
|
|
AlignedBuffer* direct_io_buffer);
|
|
|
|
static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
|
|
uint64_t value_size);
|
|
|
|
static Status UncompressBlobIfNeeded(const Slice& value_slice,
|
|
CompressionType compression_type,
|
|
Decompressor* decompressor,
|
|
MemoryAllocator* allocator,
|
|
SystemClock* clock,
|
|
Statistics* statistics,
|
|
std::unique_ptr<BlobContents>* result);
|
|
|
|
std::unique_ptr<RandomAccessFileReader> file_reader_;
|
|
uint64_t file_size_;
|
|
CompressionType compression_type_;
|
|
std::shared_ptr<Decompressor> decompressor_;
|
|
SystemClock* clock_;
|
|
Statistics* statistics_;
|
|
// False when the reader was opened before the blob file footer was written.
|
|
bool has_footer_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|