mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-29 18:33:58 +00:00
babe56ddba
Summary: Users can set the priority for file reads associated with their operation by setting `ReadOptions::rate_limiter_priority` to something other than `Env::IO_TOTAL`. Rate limiting `VerifyChecksum()` and `VerifyFileChecksums()` is the motivation for this PR, so it also includes benchmarks and minor bug fixes to get that working. `RandomAccessFileReader::Read()` already had support for rate limiting compaction reads. I changed that rate limiting to be non-specific to compaction, but rather performed according to the passed in `Env::IOPriority`. Now the compaction read rate limiting is supported by setting `rate_limiter_priority = Env::IO_LOW` on its `ReadOptions`. There is no default value for the new `Env::IOPriority` parameter to `RandomAccessFileReader::Read()`. That means this PR goes through all callers (in some cases multiple layers up the call stack) to find a `ReadOptions` to provide the priority. There are TODOs for cases I believe it would be good to let user control the priority some day (e.g., file footer reads), and no TODO in cases I believe it doesn't matter (e.g., trace file reads). The API doc only lists the missing cases where a file read associated with a provided `ReadOptions` cannot be rate limited. For cases like file ingestion checksum calculation, there is no API to provide `ReadOptions` or `Env::IOPriority`, so I didn't count that as missing. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9424 Test Plan: - new unit tests - new benchmarks on ~50MB database with 1MB/s read rate limit and 100ms refill interval; verified with strace reads are chunked (at 0.1MB per chunk) and spaced roughly 100ms apart. - setup command: `./db_bench -benchmarks=fillrandom,compact -db=/tmp/testdb -target_file_size_base=1048576 -disable_auto_compactions=true -file_checksum=true` - benchmarks command: `strace -ttfe pread64 ./db_bench -benchmarks=verifychecksum,verifyfilechecksums -use_existing_db=true -db=/tmp/testdb -rate_limiter_bytes_per_sec=1048576 -rate_limit_bg_reads=1 -rate_limit_user_ops=true -file_checksum=true` - crash test using IO_USER priority on non-validation reads with https://github.com/facebook/rocksdb/issues/9567 reverted: `python3 tools/db_crashtest.py blackbox --max_key=1000000 --write_buffer_size=524288 --target_file_size_base=524288 --level_compaction_dynamic_level_bytes=true --duration=3600 --rate_limit_bg_reads=true --rate_limit_user_ops=true --rate_limiter_bytes_per_sec=10485760 --interval=10` Reviewed By: hx235 Differential Revision: D33747386 Pulled By: ajkr fbshipit-source-id: a2d985e97912fba8c54763798e04f006ccc56e0c
108 lines
4.1 KiB
C++
108 lines
4.1 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 "file/random_access_file_reader.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 PinnableSlice;
|
|
class Statistics;
|
|
|
|
class BlobFileReader {
|
|
public:
|
|
static Status Create(const ImmutableOptions& immutable_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);
|
|
|
|
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, PinnableSlice* value,
|
|
uint64_t* bytes_read) const;
|
|
|
|
// offsets must be sorted in ascending order by caller.
|
|
void MultiGetBlob(
|
|
const ReadOptions& read_options,
|
|
const autovector<std::reference_wrapper<const Slice>>& user_keys,
|
|
const autovector<uint64_t>& offsets,
|
|
const autovector<uint64_t>& value_sizes, autovector<Status*>& statuses,
|
|
autovector<PinnableSlice*>& values, uint64_t* bytes_read) const;
|
|
|
|
CompressionType GetCompressionType() const { return compression_type_; }
|
|
|
|
uint64_t GetFileSize() const { return file_size_; }
|
|
|
|
private:
|
|
BlobFileReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
|
|
uint64_t file_size, CompressionType compression_type,
|
|
SystemClock* clock, Statistics* statistics);
|
|
|
|
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);
|
|
|
|
static Status ReadHeader(const RandomAccessFileReader* file_reader,
|
|
uint32_t column_family_id, Statistics* statistics,
|
|
CompressionType* compression_type);
|
|
|
|
static Status ReadFooter(const RandomAccessFileReader* file_reader,
|
|
uint64_t file_size, Statistics* statistics);
|
|
|
|
using Buffer = std::unique_ptr<char[]>;
|
|
|
|
static Status ReadFromFile(const RandomAccessFileReader* file_reader,
|
|
uint64_t read_offset, size_t read_size,
|
|
Statistics* statistics, Slice* slice, Buffer* buf,
|
|
AlignedBuf* aligned_buf,
|
|
Env::IOPriority rate_limiter_priority);
|
|
|
|
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,
|
|
SystemClock* clock,
|
|
Statistics* statistics,
|
|
PinnableSlice* value);
|
|
|
|
static void SaveValue(const Slice& src, PinnableSlice* dst);
|
|
|
|
std::unique_ptr<RandomAccessFileReader> file_reader_;
|
|
uint64_t file_size_;
|
|
CompressionType compression_type_;
|
|
SystemClock* clock_;
|
|
Statistics* statistics_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|