rocksdb/util/cast_util.h
Peter Dillinger 17bc27741f Improve memory efficiency of many OptimisticTransactionDBs (#11439)
Summary:
Currently it's easy to use a ton of memory with many small OptimisticTransactionDB instances, because each one by default allocates a million mutexes (40 bytes each on my compiler) for validating transactions. It even puts a lot of pressure on the allocator by allocating each one individually!

In this change:
* Create a new object and option that enables sharing these buckets of mutexes between instances. This is generally good for load balancing potential contention as various DBs become hotter or colder with txn writes. About the only cases where this sharing wouldn't make sense (e.g. each DB usually written by one thread) are cases that would be better off with OccValidationPolicy::kValidateSerial which doesn't use the buckets anyway.
* Allocate the mutexes in a contiguous array, for efficiency
* Add an option to ensure the mutexes are cache-aligned. In several other places we use cache-aligned mutexes but OptimisticTransactionDB historically does not. It should be a space-time trade-off the user can choose.
* Provide some visibility into the memory used by the mutex buckets with an ApproximateMemoryUsage() function (also used in unit testing)
* Share code with other users of "striped" mutexes, appropriate refactoring for customization & efficiency (e.g. using FastRange instead of modulus)

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11439

Test Plan: unit tests added. Ran sized-up versions of stress test in unit test, including a before-and-after performance test showing no consistent difference. (NOTE: OptimisticTransactionDB not currently covered by db_stress!)

Reviewed By: ltamasi

Differential Revision: D45796393

Pulled By: pdillinger

fbshipit-source-id: ae2b3a26ad91ceeec15debcdc63ff48df6736a54
2023-05-24 11:57:15 -07:00

57 lines
2.1 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 <memory>
#include <type_traits>
#include "rocksdb/rocksdb_namespace.h"
namespace ROCKSDB_NAMESPACE {
// The helper function to assert the move from dynamic_cast<> to
// static_cast<> is correct. This function is to deal with legacy code.
// It is not recommended to add new code to issue class casting. The preferred
// solution is to implement the functionality without a need of casting.
template <class DestClass, class SrcClass>
inline DestClass* static_cast_with_check(SrcClass* x) {
DestClass* ret = static_cast<DestClass*>(x);
#ifdef ROCKSDB_USE_RTTI
assert(ret == dynamic_cast<DestClass*>(x));
#endif
return ret;
}
template <class DestClass, class SrcClass>
inline std::shared_ptr<DestClass> static_cast_with_check(
std::shared_ptr<SrcClass>&& x) {
#if defined(ROCKSDB_USE_RTTI) && !defined(NDEBUG)
auto orig_raw = x.get();
#endif
auto ret = std::static_pointer_cast<DestClass>(std::move(x));
#if defined(ROCKSDB_USE_RTTI) && !defined(NDEBUG)
assert(ret.get() == dynamic_cast<DestClass*>(orig_raw));
#endif
return ret;
}
// A wrapper around static_cast for lossless conversion between integral
// types, including enum types. For example, this can be used for converting
// between signed/unsigned or enum type and underlying type without fear of
// stripping away data, now or in the future.
template <typename To, typename From>
inline To lossless_cast(From x) {
using FromValue = typename std::remove_reference<From>::type;
static_assert(
std::is_integral<FromValue>::value || std::is_enum<FromValue>::value,
"Only works on integral types");
static_assert(std::is_integral<To>::value || std::is_enum<To>::value,
"Only works on integral types");
static_assert(sizeof(To) >= sizeof(FromValue), "Must be lossless");
return static_cast<To>(x);
}
} // namespace ROCKSDB_NAMESPACE