mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +00:00
57997ddaaf
Summary: This PR implements a coroutine version of batched MultiGet in order to concurrently read from multiple SST files in a level using async IO, thus reducing the latency of the MultiGet. The API from the user perspective is still synchronous and single threaded, with the RocksDB part of the processing happening in the context of the caller's thread. In Version::MultiGet, the decision is made whether to call synchronous or coroutine code. A good way to review this PR is to review the first 4 commits in order - de773b3, 70c2f70, 10b50e1, and 377a597 - before reviewing the rest. TODO: 1. Figure out how to build it in CircleCI (requires some dependencies to be installed) 2. Do some stress testing with coroutines enabled No regression in synchronous MultiGet between this branch and main - ``` ./db_bench -use_existing_db=true --db=/data/mysql/rocksdb/prefix_scan -benchmarks="readseq,multireadrandom" -key_size=32 -value_size=512 -num=5000000 -batch_size=64 -multiread_batched=true -use_direct_reads=false -duration=60 -ops_between_duration_checks=1 -readonly=true -adaptive_readahead=true -threads=16 -cache_size=10485760000 -async_io=false -multiread_stride=40000 -statistics ``` Branch - ```multireadrandom : 4.025 micros/op 3975111 ops/sec 60.001 seconds 238509056 operations; 2062.3 MB/s (14767808 of 14767808 found)``` Main - ```multireadrandom : 3.987 micros/op 4013216 ops/sec 60.001 seconds 240795392 operations; 2082.1 MB/s (15231040 of 15231040 found)``` More benchmarks in various scenarios are given below. The measurements were taken with ```async_io=false``` (no coroutines) and ```async_io=true``` (use coroutines). For an IO bound workload (with every key requiring an IO), the coroutines version shows a clear benefit, being ~2.6X faster. For CPU bound workloads, the coroutines version has ~6-15% higher CPU utilization, depending on how many keys overlap an SST file. 1. Single thread IO bound workload on remote storage with sparse MultiGet batch keys (~1 key overlap/file) - No coroutines - ```multireadrandom : 831.774 micros/op 1202 ops/sec 60.001 seconds 72136 operations; 0.6 MB/s (72136 of 72136 found)``` Using coroutines - ```multireadrandom : 318.742 micros/op 3137 ops/sec 60.003 seconds 188248 operations; 1.6 MB/s (188248 of 188248 found)``` 2. Single thread CPU bound workload (all data cached) with ~1 key overlap/file - No coroutines - ```multireadrandom : 4.127 micros/op 242322 ops/sec 60.000 seconds 14539384 operations; 125.7 MB/s (14539384 of 14539384 found)``` Using coroutines - ```multireadrandom : 4.741 micros/op 210935 ops/sec 60.000 seconds 12656176 operations; 109.4 MB/s (12656176 of 12656176 found)``` 3. Single thread CPU bound workload with ~2 key overlap/file - No coroutines - ```multireadrandom : 3.717 micros/op 269000 ops/sec 60.000 seconds 16140024 operations; 139.6 MB/s (16140024 of 16140024 found)``` Using coroutines - ```multireadrandom : 4.146 micros/op 241204 ops/sec 60.000 seconds 14472296 operations; 125.1 MB/s (14472296 of 14472296 found)``` 4. CPU bound multi-threaded (16 threads) with ~4 key overlap/file - No coroutines - ```multireadrandom : 4.534 micros/op 3528792 ops/sec 60.000 seconds 211728728 operations; 1830.7 MB/s (12737024 of 12737024 found) ``` Using coroutines - ```multireadrandom : 4.872 micros/op 3283812 ops/sec 60.000 seconds 197030096 operations; 1703.6 MB/s (12548032 of 12548032 found) ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9968 Reviewed By: akankshamahajan15 Differential Revision: D36348563 Pulled By: anand1976 fbshipit-source-id: c0ce85a505fd26ebfbb09786cbd7f25202038696
112 lines
4.4 KiB
C++
112 lines
4.4 KiB
C++
// Copyright (c) Meta Platforms, Inc. and its affiliates. 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).
|
|
|
|
#if defined(USE_COROUTINES)
|
|
#include "folly/experimental/coro/Coroutine.h"
|
|
#include "folly/experimental/coro/Task.h"
|
|
#endif
|
|
#include "rocksdb/rocksdb_namespace.h"
|
|
|
|
// This file has two sctions. The first section applies to all instances of
|
|
// header file inclusion and has an include guard. The second section is
|
|
// meant for multiple inclusions in the same source file, and is idempotent.
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
#ifndef UTIL_CORO_UTILS_H_
|
|
#define UTIL_CORO_UTILS_H_
|
|
|
|
#if defined(USE_COROUTINES)
|
|
|
|
// The follwoing macros expand to regular and coroutine function
|
|
// declarations for a given function
|
|
#define DECLARE_SYNC_AND_ASYNC(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__); \
|
|
folly::coro::Task<__ret_type__> __func_name__##Coroutine(__VA_ARGS__);
|
|
|
|
#define DECLARE_SYNC_AND_ASYNC_OVERRIDE(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__) override; \
|
|
folly::coro::Task<__ret_type__> __func_name__##Coroutine(__VA_ARGS__) \
|
|
override;
|
|
|
|
#define DECLARE_SYNC_AND_ASYNC_CONST(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__) const; \
|
|
folly::coro::Task<__ret_type__> __func_name__##Coroutine(__VA_ARGS__) const;
|
|
|
|
constexpr bool using_coroutines() { return true; }
|
|
#else // !USE_COROUTINES
|
|
|
|
// The follwoing macros expand to a regular function declaration for a given
|
|
// function
|
|
#define DECLARE_SYNC_AND_ASYNC(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__);
|
|
|
|
#define DECLARE_SYNC_AND_ASYNC_OVERRIDE(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__) override;
|
|
|
|
#define DECLARE_SYNC_AND_ASYNC_CONST(__ret_type__, __func_name__, ...) \
|
|
__ret_type__ __func_name__(__VA_ARGS__) const;
|
|
|
|
constexpr bool using_coroutines() { return false; }
|
|
#endif // USE_COROUTINES
|
|
#endif // UTIL_CORO_UTILS_H_
|
|
|
|
// The following section of the file is meant to be included twice in a
|
|
// source file - once defining WITH_COROUTINES and once defining
|
|
// WITHOUT_COROUTINES
|
|
#undef DEFINE_SYNC_AND_ASYNC
|
|
#undef CO_AWAIT
|
|
#undef CO_RETURN
|
|
|
|
#if defined(WITH_COROUTINES) && defined(USE_COROUTINES)
|
|
|
|
// This macro should be used in the beginning of the function
|
|
// definition. The declaration should have been done using one of the
|
|
// DECLARE_SYNC_AND_ASYNC* macros. It expands to the return type and
|
|
// the function name with the Coroutine suffix. For example -
|
|
// DEFINE_SYNC_AND_ASYNC(int, foo)(bool bar) {}
|
|
// would expand to -
|
|
// folly::coro::Task<int> fooCoroutine(bool bar) {}
|
|
#define DEFINE_SYNC_AND_ASYNC(__ret_type__, __func_name__) \
|
|
folly::coro::Task<__ret_type__> __func_name__##Coroutine
|
|
|
|
// This macro should be used to call a function that might be a
|
|
// coroutine. It expands to the correct function name and prefixes
|
|
// the co_await operator if necessary. For example -
|
|
// s = CO_AWAIT(foo)(true);
|
|
// if the code is compiled WITH_COROUTINES, would expand to
|
|
// s = co_await fooCoroutine(true);
|
|
// if compiled WITHOUT_COROUTINES, would expand to
|
|
// s = foo(true);
|
|
#define CO_AWAIT(__func_name__) co_await __func_name__##Coroutine
|
|
|
|
#define CO_RETURN co_return
|
|
|
|
#elif defined(WITHOUT_COROUTINES)
|
|
|
|
// This macro should be used in the beginning of the function
|
|
// definition. The declaration should have been done using one of the
|
|
// DECLARE_SYNC_AND_ASYNC* macros. It expands to the return type and
|
|
// the function name without the Coroutine suffix. For example -
|
|
// DEFINE_SYNC_AND_ASYNC(int, foo)(bool bar) {}
|
|
// would expand to -
|
|
// int foo(bool bar) {}
|
|
#define DEFINE_SYNC_AND_ASYNC(__ret_type__, __func_name__) \
|
|
__ret_type__ __func_name__
|
|
|
|
// This macro should be used to call a function that might be a
|
|
// coroutine. It expands to the correct function name and prefixes
|
|
// the co_await operator if necessary. For example -
|
|
// s = CO_AWAIT(foo)(true);
|
|
// if the code is compiled WITH_COROUTINES, would expand to
|
|
// s = co_await fooCoroutine(true);
|
|
// if compiled WITHOUT_COROUTINES, would expand to
|
|
// s = foo(true);
|
|
#define CO_AWAIT(__func_name__) __func_name__
|
|
|
|
#define CO_RETURN return
|
|
|
|
#endif // DO_NOT_USE_COROUTINES
|
|
} // namespace ROCKSDB_NAMESPACE
|