mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 04:41:49 +00:00
d665afdbf3
Summary: **Context/Summary:** As revealed by heap profiling, allocation of `FileMetaData` for [newly created file added to a Version](https://github.com/facebook/rocksdb/pull/9924/files#diff-a6aa385940793f95a2c5b39cc670bd440c4547fa54fd44622f756382d5e47e43R774) can consume significant heap memory. This PR is to account that toward our global memory limit based on block cache capacity. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9924 Test Plan: - Previous `make check` verified there are only 2 places where the memory of the allocated `FileMetaData` can be released - New unit test `TEST_P(ChargeFileMetadataTestWithParam, Basic)` - db bench (CPU cost of `charge_file_metadata` in write and compact) - **write micros/op: -0.24%** : `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_file_metadata=1 (remove this option for pre-PR) -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 | egrep 'fillseq'` - **compact micros/op -0.87%** : `TEST_TMPDIR=/dev/shm/testdb ./db_bench -benchmarks=fillseq -db=$TEST_TMPDIR -charge_file_metadata=1 -disable_auto_compactions=1 -write_buffer_size=100000 -num=4000000 -numdistinct=1000 && ./db_bench -benchmarks=compact -db=$TEST_TMPDIR -use_existing_db=1 -charge_file_metadata=1 -disable_auto_compactions=1 | egrep 'compact'` table 1 - write #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 3.9711 | 0.264408 | 3.9914 | 0.254563 | 0.5111933721 20 | 3.83905 | 0.0664488 | 3.8251 | 0.0695456 | -0.3633711465 40 | 3.86625 | 0.136669 | 3.8867 | 0.143765 | 0.5289363078 80 | 3.87828 | 0.119007 | 3.86791 | 0.115674 | **-0.2673865734** 160 | 3.87677 | 0.162231 | 3.86739 | 0.16663 | **-0.2419539978** table 2 - compact #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 2,399,650.00 | 96,375.80 | 2,359,537.00 | 53,243.60 | -1.67 20 | 2,410,480.00 | 89,988.00 | 2,433,580.00 | 91,121.20 | 0.96 40 | 2.41E+06 | 121811 | 2.39E+06 | 131525 | **-0.96** 80 | 2.40E+06 | 134503 | 2.39E+06 | 108799 | **-0.78** - stress test: `python3 tools/db_crashtest.py blackbox --charge_file_metadata=1 --cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D36055583 Pulled By: hx235 fbshipit-source-id: b60eab94707103cb1322cf815f05810ef0232625
185 lines
6.6 KiB
C++
185 lines
6.6 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).
|
|
//
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
#include "cache/cache_reservation_manager.h"
|
|
|
|
#include <cassert>
|
|
#include <cstddef>
|
|
#include <cstring>
|
|
#include <memory>
|
|
|
|
#include "cache/cache_entry_roles.h"
|
|
#include "rocksdb/cache.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/status.h"
|
|
#include "table/block_based/reader_common.h"
|
|
#include "util/coding.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
template <CacheEntryRole R>
|
|
CacheReservationManagerImpl<R>::CacheReservationHandle::CacheReservationHandle(
|
|
std::size_t incremental_memory_used,
|
|
std::shared_ptr<CacheReservationManagerImpl> cache_res_mgr)
|
|
: incremental_memory_used_(incremental_memory_used) {
|
|
assert(cache_res_mgr);
|
|
cache_res_mgr_ = cache_res_mgr;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
CacheReservationManagerImpl<
|
|
R>::CacheReservationHandle::~CacheReservationHandle() {
|
|
Status s = cache_res_mgr_->ReleaseCacheReservation(incremental_memory_used_);
|
|
s.PermitUncheckedError();
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
CacheReservationManagerImpl<R>::CacheReservationManagerImpl(
|
|
std::shared_ptr<Cache> cache, bool delayed_decrease)
|
|
: delayed_decrease_(delayed_decrease),
|
|
cache_allocated_size_(0),
|
|
memory_used_(0) {
|
|
assert(cache != nullptr);
|
|
cache_ = cache;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
CacheReservationManagerImpl<R>::~CacheReservationManagerImpl() {
|
|
for (auto* handle : dummy_handles_) {
|
|
cache_->Release(handle, true);
|
|
}
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Status CacheReservationManagerImpl<R>::UpdateCacheReservation(
|
|
std::size_t new_mem_used) {
|
|
memory_used_ = new_mem_used;
|
|
std::size_t cur_cache_allocated_size =
|
|
cache_allocated_size_.load(std::memory_order_relaxed);
|
|
if (new_mem_used == cur_cache_allocated_size) {
|
|
return Status::OK();
|
|
} else if (new_mem_used > cur_cache_allocated_size) {
|
|
Status s = IncreaseCacheReservation(new_mem_used);
|
|
return s;
|
|
} else {
|
|
// In delayed decrease mode, we don't decrease cache reservation
|
|
// untill the memory usage is less than 3/4 of what we reserve
|
|
// in the cache.
|
|
// We do this because
|
|
// (1) Dummy entry insertion is expensive in block cache
|
|
// (2) Delayed releasing previously inserted dummy entries can save such
|
|
// expensive dummy entry insertion on memory increase in the near future,
|
|
// which is likely to happen when the memory usage is greater than or equal
|
|
// to 3/4 of what we reserve
|
|
if (delayed_decrease_ && new_mem_used >= cur_cache_allocated_size / 4 * 3) {
|
|
return Status::OK();
|
|
} else {
|
|
Status s = DecreaseCacheReservation(new_mem_used);
|
|
return s;
|
|
}
|
|
}
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Status CacheReservationManagerImpl<R>::MakeCacheReservation(
|
|
std::size_t incremental_memory_used,
|
|
std::unique_ptr<CacheReservationManager::CacheReservationHandle>* handle) {
|
|
assert(handle);
|
|
Status s =
|
|
UpdateCacheReservation(GetTotalMemoryUsed() + incremental_memory_used);
|
|
(*handle).reset(new CacheReservationManagerImpl::CacheReservationHandle(
|
|
incremental_memory_used,
|
|
std::enable_shared_from_this<
|
|
CacheReservationManagerImpl<R>>::shared_from_this()));
|
|
return s;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Status CacheReservationManagerImpl<R>::ReleaseCacheReservation(
|
|
std::size_t incremental_memory_used) {
|
|
assert(GetTotalMemoryUsed() >= incremental_memory_used);
|
|
std::size_t updated_total_mem_used =
|
|
GetTotalMemoryUsed() - incremental_memory_used;
|
|
Status s = UpdateCacheReservation(updated_total_mem_used);
|
|
return s;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Status CacheReservationManagerImpl<R>::IncreaseCacheReservation(
|
|
std::size_t new_mem_used) {
|
|
Status return_status = Status::OK();
|
|
while (new_mem_used > cache_allocated_size_.load(std::memory_order_relaxed)) {
|
|
Cache::Handle* handle = nullptr;
|
|
return_status = cache_->Insert(GetNextCacheKey(), nullptr, kSizeDummyEntry,
|
|
GetNoopDeleterForRole<R>(), &handle);
|
|
|
|
if (return_status != Status::OK()) {
|
|
return return_status;
|
|
}
|
|
|
|
dummy_handles_.push_back(handle);
|
|
cache_allocated_size_ += kSizeDummyEntry;
|
|
}
|
|
return return_status;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Status CacheReservationManagerImpl<R>::DecreaseCacheReservation(
|
|
std::size_t new_mem_used) {
|
|
Status return_status = Status::OK();
|
|
|
|
// Decrease to the smallest multiple of kSizeDummyEntry that is greater than
|
|
// or equal to new_mem_used We do addition instead of new_mem_used <=
|
|
// cache_allocated_size_.load(std::memory_order_relaxed) - kSizeDummyEntry to
|
|
// avoid underflow of size_t when cache_allocated_size_ = 0
|
|
while (new_mem_used + kSizeDummyEntry <=
|
|
cache_allocated_size_.load(std::memory_order_relaxed)) {
|
|
assert(!dummy_handles_.empty());
|
|
auto* handle = dummy_handles_.back();
|
|
cache_->Release(handle, true);
|
|
dummy_handles_.pop_back();
|
|
cache_allocated_size_ -= kSizeDummyEntry;
|
|
}
|
|
return return_status;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
std::size_t CacheReservationManagerImpl<R>::GetTotalReservedCacheSize() {
|
|
return cache_allocated_size_.load(std::memory_order_relaxed);
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
std::size_t CacheReservationManagerImpl<R>::GetTotalMemoryUsed() {
|
|
return memory_used_;
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Slice CacheReservationManagerImpl<R>::GetNextCacheKey() {
|
|
// Calling this function will have the side-effect of changing the
|
|
// underlying cache_key_ that is shared among other keys generated from this
|
|
// fucntion. Therefore please make sure the previous keys are saved/copied
|
|
// before calling this function.
|
|
cache_key_ = CacheKey::CreateUniqueForCacheLifetime(cache_.get());
|
|
return cache_key_.AsSlice();
|
|
}
|
|
|
|
template <CacheEntryRole R>
|
|
Cache::DeleterFn CacheReservationManagerImpl<R>::TEST_GetNoopDeleterForRole() {
|
|
return GetNoopDeleterForRole<R>();
|
|
}
|
|
|
|
template class CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>;
|
|
template class CacheReservationManagerImpl<
|
|
CacheEntryRole::kCompressionDictionaryBuildingBuffer>;
|
|
template class CacheReservationManagerImpl<CacheEntryRole::kFilterConstruction>;
|
|
template class CacheReservationManagerImpl<CacheEntryRole::kMisc>;
|
|
template class CacheReservationManagerImpl<CacheEntryRole::kWriteBuffer>;
|
|
template class CacheReservationManagerImpl<CacheEntryRole::kFileMetadata>;
|
|
} // namespace ROCKSDB_NAMESPACE
|