|
|
|
// 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 "utilities/transactions/optimistic_transaction_db_impl.h"
|
|
|
|
|
|
|
|
#include <string>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "db/db_impl/db_impl.h"
|
|
|
|
#include "rocksdb/db.h"
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "rocksdb/utilities/optimistic_transaction_db.h"
|
|
|
|
#include "utilities/transactions/optimistic_transaction.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
Pessimistic Transactions
Summary:
Initial implementation of Pessimistic Transactions. This diff contains the api changes discussed in D38913. This diff is pretty large, so let me know if people would prefer to meet up to discuss it.
MyRocks folks: please take a look at the API in include/rocksdb/utilities/transaction[_db].h and let me know if you have any issues.
Also, you'll notice a couple of TODOs in the implementation of RollbackToSavePoint(). After chatting with Siying, I'm going to send out a separate diff for an alternate implementation of this feature that implements the rollback inside of WriteBatch/WriteBatchWithIndex. We can then decide which route is preferable.
Next, I'm planning on doing some perf testing and then integrating this diff into MongoRocks for further testing.
Test Plan: Unit tests, db_bench parallel testing.
Reviewers: igor, rven, sdong, yhchiang, yoshinorim
Reviewed By: sdong
Subscribers: hermanlee4, maykov, spetrunia, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D40869
10 years ago
|
|
|
Transaction* OptimisticTransactionDBImpl::BeginTransaction(
|
|
|
|
const WriteOptions& write_options,
|
|
|
|
const OptimisticTransactionOptions& txn_options, Transaction* old_txn) {
|
|
|
|
if (old_txn != nullptr) {
|
|
|
|
ReinitializeTransaction(old_txn, write_options, txn_options);
|
|
|
|
return old_txn;
|
|
|
|
} else {
|
|
|
|
return new OptimisticTransaction(this, write_options, txn_options);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
std::unique_lock<std::mutex> OptimisticTransactionDBImpl::LockBucket(
|
|
|
|
size_t idx) {
|
|
|
|
assert(idx < bucketed_locks_.size());
|
|
|
|
return std::unique_lock<std::mutex>(*bucketed_locks_[idx]);
|
|
|
|
}
|
|
|
|
|
|
|
|
Status OptimisticTransactionDB::Open(const Options& options,
|
|
|
|
const std::string& dbname,
|
|
|
|
OptimisticTransactionDB** dbptr) {
|
|
|
|
DBOptions db_options(options);
|
|
|
|
ColumnFamilyOptions cf_options(options);
|
|
|
|
std::vector<ColumnFamilyDescriptor> column_families;
|
|
|
|
column_families.push_back(
|
|
|
|
ColumnFamilyDescriptor(kDefaultColumnFamilyName, cf_options));
|
|
|
|
std::vector<ColumnFamilyHandle*> handles;
|
|
|
|
Status s = Open(db_options, dbname, column_families, &handles, dbptr);
|
|
|
|
if (s.ok()) {
|
|
|
|
assert(handles.size() == 1);
|
|
|
|
// i can delete the handle since DBImpl is always holding a reference to
|
|
|
|
// default column family
|
|
|
|
delete handles[0];
|
|
|
|
}
|
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status OptimisticTransactionDB::Open(
|
|
|
|
const DBOptions& db_options, const std::string& dbname,
|
|
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
|
|
std::vector<ColumnFamilyHandle*>* handles,
|
|
|
|
OptimisticTransactionDB** dbptr) {
|
|
|
|
return OptimisticTransactionDB::Open(db_options,
|
|
|
|
OptimisticTransactionDBOptions(), dbname,
|
|
|
|
column_families, handles, dbptr);
|
|
|
|
}
|
|
|
|
|
|
|
|
Status OptimisticTransactionDB::Open(
|
|
|
|
const DBOptions& db_options,
|
|
|
|
const OptimisticTransactionDBOptions& occ_options,
|
|
|
|
const std::string& dbname,
|
|
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
|
|
std::vector<ColumnFamilyHandle*>* handles,
|
|
|
|
OptimisticTransactionDB** dbptr) {
|
|
|
|
Status s;
|
|
|
|
DB* db;
|
|
|
|
|
|
|
|
std::vector<ColumnFamilyDescriptor> column_families_copy = column_families;
|
|
|
|
|
|
|
|
// Enable MemTable History if not already enabled
|
|
|
|
for (auto& column_family : column_families_copy) {
|
|
|
|
ColumnFamilyOptions* options = &column_family.options;
|
|
|
|
|
Refactor trimming logic for immutable memtables (#5022)
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
5 years ago
|
|
|
if (options->max_write_buffer_size_to_maintain == 0 &&
|
|
|
|
options->max_write_buffer_number_to_maintain == 0) {
|
|
|
|
// Setting to -1 will set the History size to
|
|
|
|
// max_write_buffer_number * write_buffer_size.
|
|
|
|
options->max_write_buffer_size_to_maintain = -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
s = DB::Open(db_options, dbname, column_families_copy, handles, &db);
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
*dbptr = new OptimisticTransactionDBImpl(db, occ_options);
|
|
|
|
}
|
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
void OptimisticTransactionDBImpl::ReinitializeTransaction(
|
|
|
|
Transaction* txn, const WriteOptions& write_options,
|
|
|
|
const OptimisticTransactionOptions& txn_options) {
|
|
|
|
assert(dynamic_cast<OptimisticTransaction*>(txn) != nullptr);
|
|
|
|
auto txn_impl = reinterpret_cast<OptimisticTransaction*>(txn);
|
|
|
|
|
|
|
|
txn_impl->Reinitialize(this, write_options, txn_options);
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|