499ebb3ab5
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
200 lines
7.0 KiB
C++
200 lines
7.0 KiB
C++
// 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.
|
|
|
|
#include "db/db_impl_readonly.h"
|
|
|
|
#include "db/compacted_db_impl.h"
|
|
#include "db/db_impl.h"
|
|
#include "db/db_iter.h"
|
|
#include "db/merge_context.h"
|
|
#include "db/range_del_aggregator.h"
|
|
#include "monitoring/perf_context_imp.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
|
|
const std::string& dbname)
|
|
: DBImpl(db_options, dbname) {
|
|
ROCKS_LOG_INFO(immutable_db_options_.info_log,
|
|
"Opening the db in read only mode");
|
|
LogFlush(immutable_db_options_.info_log);
|
|
}
|
|
|
|
DBImplReadOnly::~DBImplReadOnly() {
|
|
}
|
|
|
|
// Implementations of the DB interface
|
|
Status DBImplReadOnly::Get(const ReadOptions& read_options,
|
|
ColumnFamilyHandle* column_family, const Slice& key,
|
|
PinnableSlice* pinnable_val) {
|
|
assert(pinnable_val != nullptr);
|
|
Status s;
|
|
SequenceNumber snapshot = versions_->LastSequence();
|
|
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
|
|
auto cfd = cfh->cfd();
|
|
SuperVersion* super_version = cfd->GetSuperVersion();
|
|
MergeContext merge_context;
|
|
RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
|
|
LookupKey lkey(key, snapshot);
|
|
if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
|
|
&range_del_agg, read_options)) {
|
|
pinnable_val->PinSelf();
|
|
} else {
|
|
PERF_TIMER_GUARD(get_from_output_files_time);
|
|
super_version->current->Get(read_options, lkey, pinnable_val, &s,
|
|
&merge_context, &range_del_agg);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
|
|
ColumnFamilyHandle* column_family) {
|
|
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
|
|
auto cfd = cfh->cfd();
|
|
SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
|
|
SequenceNumber latest_snapshot = versions_->LastSequence();
|
|
auto db_iter = NewArenaWrappedDbIterator(
|
|
env_, read_options, *cfd->ioptions(), cfd->user_comparator(),
|
|
(read_options.snapshot != nullptr
|
|
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
|
|
->number_
|
|
: latest_snapshot),
|
|
super_version->mutable_cf_options.max_sequential_skip_in_iterations,
|
|
super_version->version_number);
|
|
auto internal_iter =
|
|
NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
|
|
db_iter->GetRangeDelAggregator());
|
|
db_iter->SetIterUnderDBIter(internal_iter);
|
|
return db_iter;
|
|
}
|
|
|
|
Status DBImplReadOnly::NewIterators(
|
|
const ReadOptions& read_options,
|
|
const std::vector<ColumnFamilyHandle*>& column_families,
|
|
std::vector<Iterator*>* iterators) {
|
|
if (iterators == nullptr) {
|
|
return Status::InvalidArgument("iterators not allowed to be nullptr");
|
|
}
|
|
iterators->clear();
|
|
iterators->reserve(column_families.size());
|
|
SequenceNumber latest_snapshot = versions_->LastSequence();
|
|
|
|
for (auto cfh : column_families) {
|
|
auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
|
|
auto* sv = cfd->GetSuperVersion()->Ref();
|
|
auto* db_iter = NewArenaWrappedDbIterator(
|
|
env_, read_options, *cfd->ioptions(), cfd->user_comparator(),
|
|
(read_options.snapshot != nullptr
|
|
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
|
|
->number_
|
|
: latest_snapshot),
|
|
sv->mutable_cf_options.max_sequential_skip_in_iterations,
|
|
sv->version_number);
|
|
auto* internal_iter =
|
|
NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
|
|
db_iter->GetRangeDelAggregator());
|
|
db_iter->SetIterUnderDBIter(internal_iter);
|
|
iterators->push_back(db_iter);
|
|
}
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
|
|
DB** dbptr, bool error_if_log_file_exist) {
|
|
*dbptr = nullptr;
|
|
|
|
// Try to first open DB as fully compacted DB
|
|
Status s;
|
|
s = CompactedDBImpl::Open(options, dbname, dbptr);
|
|
if (s.ok()) {
|
|
return s;
|
|
}
|
|
|
|
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;
|
|
|
|
s = DB::OpenForReadOnly(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 DB::OpenForReadOnly(
|
|
const DBOptions& db_options, const std::string& dbname,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
|
|
bool error_if_log_file_exist) {
|
|
*dbptr = nullptr;
|
|
handles->clear();
|
|
|
|
DBImplReadOnly* impl = new DBImplReadOnly(db_options, dbname);
|
|
impl->mutex_.Lock();
|
|
Status s = impl->Recover(column_families, true /* read only */,
|
|
error_if_log_file_exist);
|
|
if (s.ok()) {
|
|
// set column family handles
|
|
for (auto cf : column_families) {
|
|
auto cfd =
|
|
impl->versions_->GetColumnFamilySet()->GetColumnFamily(cf.name);
|
|
if (cfd == nullptr) {
|
|
s = Status::InvalidArgument("Column family not found: ", cf.name);
|
|
break;
|
|
}
|
|
handles->push_back(new ColumnFamilyHandleImpl(cfd, impl, &impl->mutex_));
|
|
}
|
|
}
|
|
if (s.ok()) {
|
|
for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
|
|
delete cfd->InstallSuperVersion(new SuperVersion(), &impl->mutex_);
|
|
}
|
|
}
|
|
impl->mutex_.Unlock();
|
|
if (s.ok()) {
|
|
*dbptr = impl;
|
|
for (auto* h : *handles) {
|
|
impl->NewThreadStatusCfInfo(
|
|
reinterpret_cast<ColumnFamilyHandleImpl*>(h)->cfd());
|
|
}
|
|
} else {
|
|
for (auto h : *handles) {
|
|
delete h;
|
|
}
|
|
handles->clear();
|
|
delete impl;
|
|
}
|
|
return s;
|
|
}
|
|
|
|
#else // !ROCKSDB_LITE
|
|
|
|
Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
|
|
DB** dbptr, bool error_if_log_file_exist) {
|
|
return Status::NotSupported("Not supported in ROCKSDB_LITE.");
|
|
}
|
|
|
|
Status DB::OpenForReadOnly(
|
|
const DBOptions& db_options, const std::string& dbname,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
|
|
bool error_if_log_file_exist) {
|
|
return Status::NotSupported("Not supported in ROCKSDB_LITE.");
|
|
}
|
|
#endif // !ROCKSDB_LITE
|
|
|
|
} // namespace rocksdb
|