mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 02:44:18 +00:00
2f41ecfe75
Summary: MyRocks currently sets `max_write_buffer_number_to_maintain` in order to maintain enough history for transaction conflict checking. The effectiveness of this approach depends on the size of memtables. When memtables are small, it may not keep enough history; when memtables are large, this may consume too much memory. We are proposing a new way to configure memtable list history: by limiting the memory usage of immutable memtables. The new option is `max_write_buffer_size_to_maintain` and it will take precedence over the old `max_write_buffer_number_to_maintain` if they are both set to non-zero values. The new option accounts for the total memory usage of flushed immutable memtables and mutable memtable. When the total usage exceeds the limit, RocksDB may start dropping immutable memtables (which is also called trimming history), starting from the oldest one. The semantics of the old option actually works both as an upper bound and lower bound. History trimming will start if number of immutable memtables exceeds the limit, but it will never go below (limit-1) due to history trimming. In order the mimic the behavior with the new option, history trimming will stop if dropping the next immutable memtable causes the total memory usage go below the size limit. For example, assuming the size limit is set to 64MB, and there are 3 immutable memtables with sizes of 20, 30, 30. Although the total memory usage is 80MB > 64MB, dropping the oldest memtable will reduce the memory usage to 60MB < 64MB, so in this case no memtable will be dropped. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5022 Differential Revision: D14394062 Pulled By: miasantreble fbshipit-source-id: 60457a509c6af89d0993f988c9b5c2aa9e45f5c5
91 lines
2.4 KiB
C++
91 lines
2.4 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).
|
|
|
|
#include "db/flush_scheduler.h"
|
|
|
|
#include <cassert>
|
|
|
|
#include "db/column_family.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
void FlushScheduler::ScheduleWork(ColumnFamilyData* cfd) {
|
|
#ifndef NDEBUG
|
|
{
|
|
std::lock_guard<std::mutex> lock(checking_mutex_);
|
|
assert(checking_set_.count(cfd) == 0);
|
|
checking_set_.insert(cfd);
|
|
}
|
|
#endif // NDEBUG
|
|
cfd->Ref();
|
|
// Suppress false positive clang analyzer warnings.
|
|
#ifndef __clang_analyzer__
|
|
Node* node = new Node{cfd, head_.load(std::memory_order_relaxed)};
|
|
while (!head_.compare_exchange_strong(
|
|
node->next, node, std::memory_order_relaxed, std::memory_order_relaxed)) {
|
|
// failing CAS updates the first param, so we are already set for
|
|
// retry. TakeNextColumnFamily won't happen until after another
|
|
// inter-thread synchronization, so we don't even need release
|
|
// semantics for this CAS
|
|
}
|
|
#endif // __clang_analyzer__
|
|
}
|
|
|
|
ColumnFamilyData* FlushScheduler::TakeNextColumnFamily() {
|
|
while (true) {
|
|
if (head_.load(std::memory_order_relaxed) == nullptr) {
|
|
return nullptr;
|
|
}
|
|
|
|
// dequeue the head
|
|
Node* node = head_.load(std::memory_order_relaxed);
|
|
head_.store(node->next, std::memory_order_relaxed);
|
|
ColumnFamilyData* cfd = node->column_family;
|
|
delete node;
|
|
|
|
#ifndef NDEBUG
|
|
{
|
|
std::lock_guard<std::mutex> lock(checking_mutex_);
|
|
auto iter = checking_set_.find(cfd);
|
|
assert(iter != checking_set_.end());
|
|
checking_set_.erase(iter);
|
|
}
|
|
#endif // NDEBUG
|
|
|
|
if (!cfd->IsDropped()) {
|
|
// success
|
|
return cfd;
|
|
}
|
|
|
|
// no longer relevant, retry
|
|
if (cfd->Unref()) {
|
|
delete cfd;
|
|
}
|
|
}
|
|
}
|
|
|
|
bool FlushScheduler::Empty() {
|
|
auto rv = head_.load(std::memory_order_relaxed) == nullptr;
|
|
#ifndef NDEBUG
|
|
std::lock_guard<std::mutex> lock(checking_mutex_);
|
|
// Empty is allowed to be called concurrnetly with ScheduleFlush. It would
|
|
// only miss the recent schedules.
|
|
assert((rv == checking_set_.empty()) || rv);
|
|
#endif // NDEBUG
|
|
return rv;
|
|
}
|
|
|
|
void FlushScheduler::Clear() {
|
|
ColumnFamilyData* cfd;
|
|
while ((cfd = TakeNextColumnFamily()) != nullptr) {
|
|
if (cfd->Unref()) {
|
|
delete cfd;
|
|
}
|
|
}
|
|
assert(head_.load(std::memory_order_relaxed) == nullptr);
|
|
}
|
|
|
|
} // namespace rocksdb
|