Revision 499ebb3ab5ea4207950fc95acf102b8f58add1c5 authored by Maysam Yabandeh on 24 June 2017, 21:06:43 UTC, committed by Facebook Github Bot on 24 June 2017, 21:11:29 UTC
Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
1 parent 0ac4afb
db_impl_readonly.h
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
#pragma once
#ifndef ROCKSDB_LITE
#include "db/db_impl.h"
#include <vector>
#include <string>
namespace rocksdb {
class DBImplReadOnly : public DBImpl {
public:
DBImplReadOnly(const DBOptions& options, const std::string& dbname);
virtual ~DBImplReadOnly();
// Implementations of the DB interface
using DB::Get;
virtual Status Get(const ReadOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
PinnableSlice* value) override;
// TODO: Implement ReadOnly MultiGet?
using DBImpl::NewIterator;
virtual Iterator* NewIterator(const ReadOptions&,
ColumnFamilyHandle* column_family) override;
virtual Status NewIterators(
const ReadOptions& options,
const std::vector<ColumnFamilyHandle*>& column_families,
std::vector<Iterator*>* iterators) override;
using DBImpl::Put;
virtual Status Put(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
const Slice& value) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::Merge;
virtual Status Merge(const WriteOptions& options,
ColumnFamilyHandle* column_family, const Slice& key,
const Slice& value) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::Delete;
virtual Status Delete(const WriteOptions& options,
ColumnFamilyHandle* column_family,
const Slice& key) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::SingleDelete;
virtual Status SingleDelete(const WriteOptions& options,
ColumnFamilyHandle* column_family,
const Slice& key) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
virtual Status Write(const WriteOptions& options,
WriteBatch* updates) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::CompactRange;
virtual Status CompactRange(const CompactRangeOptions& options,
ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::CompactFiles;
virtual Status CompactFiles(
const CompactionOptions& compact_options,
ColumnFamilyHandle* column_family,
const std::vector<std::string>& input_file_names,
const int output_level, const int output_path_id = -1) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
virtual Status DisableFileDeletions() override {
return Status::NotSupported("Not supported operation in read only mode.");
}
virtual Status EnableFileDeletions(bool force) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
virtual Status GetLiveFiles(std::vector<std::string>&,
uint64_t* manifest_file_size,
bool flush_memtable = true) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::Flush;
virtual Status Flush(const FlushOptions& options,
ColumnFamilyHandle* column_family) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DBImpl::SyncWAL;
virtual Status SyncWAL() override {
return Status::NotSupported("Not supported operation in read only mode.");
}
using DB::IngestExternalFile;
virtual Status IngestExternalFile(
ColumnFamilyHandle* column_family,
const std::vector<std::string>& external_files,
const IngestExternalFileOptions& ingestion_options) override {
return Status::NotSupported("Not supported operation in read only mode.");
}
private:
friend class DB;
// No copying allowed
DBImplReadOnly(const DBImplReadOnly&);
void operator=(const DBImplReadOnly&);
};
}
#endif // !ROCKSDB_LITE
Computing file changes ...
